minerals

Review
A Review of Mineral Prospectivity Mapping Using
Deep Learning
Kang Sun 1,2 , Yansi Chen 1,2, * , Guoshuai Geng 1,2 , Zongyue Lu 1,2 , Wei Zhang 1,2 , Zhihong Song 1,2 ,
Jiyun Guan 3 , Yang Zhao 4 and Zhaonian Zhang 5

1 Center for Geophysical Survey, China Geological Survey, Langfang 065000, China;
sunkang@[Link] (K.S.); hnsmxggs@[Link] (G.G.); luzongyue@[Link] (Z.L.);
zhangweicugb@[Link] (W.Z.); songzhihong2018@[Link] (Z.S.)
2 Technology Innovation Center for Earth Near Surface Detection, China Geological Survey,
Langfang 065000, China
3 Kunming Natural Resources Comprehensive Survey Center, China Geological Survey,
Kunming 650100, China; guanjiyun@[Link]
4 Langfang Comprehensive Survey Center of Natural Resources, China Geological Survey,
Langfang 065000, China; zhaoyang02@[Link]
5 School of the Earth Sciences and Resources, China University of Geosciences, Beijing 100083, China;
zhangzhaonian1996@[Link]
* Correspondence: chenyansi@[Link]

Abstract: Mineral resources are of great significance in the development of the national economy.
Prospecting and forecasting are the key to ensure the security of mineral resources supply, promote
economic development, and maintain social stability. The methods for prospecting prediction
have evolved from qualitative to quantitative prediction, from empirical research to mathematical
analysis. In recent years, deep learning algorithms have gradually entered the attention of geologists
due to their robust learning and simulation ability in the application of prospecting prediction.
Deep learning algorithms can effectively analyze and predict data, which have great significance
in improving the efficiency and accuracy of mineral exploration. However, there are not many
specific examples of their application in mineral exploration prediction, and researchers have not
yet conducted a comprehensive discussion on the advantages, disadvantages, and accuracy of deep
learning algorithms in mineral prospectivity mapping applications. This paper reviews and discusses
Citation: Sun, K.; Chen, Y.; Geng, G.;
the application of deep learning in prospecting prediction, highlighting the challenges faced by deep
Lu, Z.; Zhang, W.; Song, Z.; Guan, J.;
learning in the application of prospecting prediction in data preprocessing, data enhancement, system
Zhao, Y.; Zhang, Z. A Review of
parameter adjustment, and accuracy evaluation, and puts forward specific suggestions for research in
Mineral Prospectivity Mapping Using
Deep Learning. Minerals 2024, 14,
these aspects. The purpose of this paper is to provide a reference for the application of deep learning
1021. [Link] to researchers and practitioners in the field of prospecting prediction.
min14101021
Keywords: mineral prospectivity mapping; deep learning; data enhancement method
Academic Editor: Behnam Sadeghi

Received: 3 September 2024

Revised: 9 October 2024
Accepted: 9 October 2024 1. Introduction
Published: 10 October 2024
Mineral resources are the cornerstone of modern social and economic development
and are of great significance at the level of national strategic security. With the deepening of
mineral exploitation and the gradual formation of world trade barriers, the deep prospect-
Copyright: © 2024 by the authors.
ing prediction and exploration of strategic and pillar minerals have gradually become the
Licensee MDPI, Basel, Switzerland. focus of attention of various countries and government agencies. As a technical means of
This article is an open access article comprehensive utilization of geological, geophysical, geochemical, and other multi-source
distributed under the terms and information, mineral prediction mapping can effectively identify areas with mineral re-
conditions of the Creative Commons source potential, so as to guide exploration activities, improve exploration efficiency, and
Attribution (CC BY) license (https:// reduce costs.
[Link]/licenses/by/ The formation of the deposit is a long and complex process, which is influenced
4.0/). by many factors. The basic geological information of the study area, such as geological

Minerals 2024, 14, 1021. [Link] [Link]

Minerals 2024, 14, 1021 2 of 35

structure background, lithology characteristics, mineral types, alteration characteristics of

surrounding rock, geophysical and geochemical anomalies, and prospecting engineering
data, are the basis of prospecting and prediction research. The prediction of mineral re-
sources is supported by the theory of geological mineralization, and the comprehensive
analysis of the mineral geological data accumulated in geological survey is carried out to
summarize the metallogenic law and extract the metallogenic information, delineate the
prospecting potential area, and predict the amount of resources [1,2]. Early prospecting
prediction is mainly the prediction of the prospecting potential area or even target area, that
is, metallogenic prediction, which mainly relies on metallogenic theory, the metallogenic
system, comprehensive analysis of geological experience, and field geological survey to
carry out qualitative evaluation. Since the purpose of geological work is to pursue the
quantity and economic value of resources, the quantitative prediction method estimates
the quantity, value, and origin of undiscovered mineral resources by showing the eco-
nomic feasibility related to mineral resources, so the quantitative prospecting prediction
becomes inevitable.
In 1976, the International Union of Earth Sciences put forward the standard quanti-
tative method of resource prediction, and then with the wide application of geographic
information systems, quantitative prediction began to develop in the direction of math-
ematical geology. Quantitative evaluation based on mathematical statistical models can
process the data of complex statistical distribution characteristics, and can also explore
the potential nonlinear relationship between large-scale high-dimensional mineralization
information and ore deposits [3–5]. The model methods mainly include two types: one is a
knowledge-driven model, which relies on subjective expert understanding, and combines
experience with actual survey data to synthesize information and delineate prospective
areas, which is suitable for areas with insufficient exploration data (Table 1) [6–9]. The
American scholar Singer put forward the “three-part” metallogenic prediction method in
1993, emphasizing the comprehensive analysis of geologists’ subjective experience and
mining area geological exploration data [10]. Zhao Pengda put forward three prediction
theories of similarity analogy, difference seeking, and quantitative combined ore control in
1983 [11]. The second is the data-driven model [5–7,9], which is heavy on correlation and
light on causation, and is suitable for further exploration in areas where there is already
sufficient exploration data. Without considering the subjective factors brought by ore-
forming theory and the ore-forming system, a mathematical model is established to predict
mineral resources according to the relationship between various factors. The method of
metallogenic prediction based on a knowledge-driven metallogenic model has great advan-
tages in shallow surface and low geological exploration environments. However, with the
large-scale exploitation of the earth’s shallow minerals, the exploration of hidden and deep
deposits has gradually become the mainstream, the geological information has become
extremely complex due to the influence of factors such as mixing, compounding, covering,
and superposition [12], and the limitations of knowledge-driven methods have gradually
emerged. Common prospecting prediction model algorithms mainly include statistical
analysis methods such as the evidence weight method [13–15], information content method
and regression analysis [16,17], traditional machine learning algorithms such as the sup-
port vector machine [6,18–22] and random forest [5,22–25], and deep learning algorithms
represented by artificial neural networks, which provide an important theoretical basis for
metallogenic prediction. Through the data-driven model, we can obtain the apparent or
even hidden mineralization characteristics related to the formation of mineral resources
from massive data, determine the deep relationship between ore-forming elements and
mineralization, and help to optimize the existing ore-forming theory and prospecting tech-
nology. However, when dealing with complex geological data, the traditional method has
some problems, such as the limitation of the data dimension, difficulty in feature selection,
and low prediction accuracy. Therefore, further improving the accuracy and practicability
of metallogenic prediction has become one of the difficulties in metallogenic prediction.
In this context, deep learning, as a new technical means, has gradually attracted attention
Minerals 2024, 14, 1021 3 of 35

because of its ability to deal with complex relationships and nonlinear representation of
high-dimensional data.

Table 1. Comparison of several common metallogenic prediction methods.

Model Types Different Category Key Features

“three-part” metallogenic delineate geologically feasible areas for prospecting; standard grade
prediction tonnage model; metallogenic prospect area
knowledge-driven
model similarity analogy, difference similar geological environments have similar mineralization series and
seeking, and quantitative deposits; geological anomalies leading to mineral deposits; geological
combined ore control condition combination controls mineral deposits
combined with geological mineralization; graded weight of evidence; the
evidence weight metallogenic prediction factors correspond to the metallogenic
conditions by evidence weight method
quantitative extraction of ore-controlling factors; a posteriori probability
regression analysis
is calculated to evaluate the metallogenic potential
data-driven model the important factors which can correctly predict the ore deposit are
support vector machine
automatically selected from many metallogenic factors
construct multiple decision trees and synthesize their outputs; dealing
random forest
with the complexity and uncertainty of mineral geological information
ability to process large amounts of geological data; automatic feature
deep learning algorithms
extraction; excavate abnormal and potential deposits

Deep learning is characterized by continuous hierarchical representation learning and

it can handle nonlinear representations of complex relationships [26,27]. Unlike traditional
statistical methods, it does not require specific data distribution or independence assump-
tions, nor does it require in-depth study of deposit genesis or pre-analysis of geological
feature correlations [22,28]. By mining the high-dimensional abstract features of various
geological information, deep learning improves the comprehensive utilization rate of geo-
science big data, makes the prediction results more intuitive and objective, and has great
potential for processing nonlinear and high-dimensional earth science data [4,9,29]. There-
fore, deep learning is a set of popular techniques for metallogenic prediction. At present,
the algorithms used in the field of prospecting prediction mainly include the convolutional
neural network, recurrent neural network, deep autoencoder, adversarial neural network,
etc., which have been widely used in the fields of image and speech recognition. Among
them, convolutional neural networks are the most widely used, including LeNet, AlexNet,
VggNet, GoogleNet, ResNet, and other structures. The initial use of deep learning is for
image recognition, and the data type of the remote sensing image is an image. Therefore,
the remote sensing image has natural advantages as a data type of deep learning prospect-
ing. In addition, geochemical data is one of the most widely used data types for deep
learning. Xiong et al. [30] and Zuo et al. [31] successfully identified mineral-related geo-
chemical anomalies by applying deep autoencoders to regional chemical data. Li et al. [32],
Liu et al. [33,34], and Zheng et al. [35], respectively, used convolutional neural networks to
make prospecting predictions in the study area and achieved good results. The application
of deep learning algorithms in mineral prediction has made remarkable progress and
achievements. Although there are still challenges in using point data to capture complex
mineralization anomalies with spatial structure and high model complexity [36,37], its ad-
vantages in processing complex geological data and improving prediction accuracy make it
an important direction for future mineral prediction research and application. According to
previous studies, deep learning algorithms have been applied to various types of minerals
such as Au, Fe, Cu, W-Sn, Pb-Zn, REE, etc., with good effect, and their future application
prospects are very wide.
This paper aims to systematically review and summarize the latest research progress
and application of deep learning in metallogenic prediction. And no one has ever concretely
Minerals 2024, 14, 1021 4 of 35

summarized the advantages and possible limitations of deep learning compared to other
methods in mineral prospectivity mapping practice. By reviewing the current research
results, methods, and cases, the application prospects and existing problems of deep
learning technology in this field are discussed, helping researchers to understand the
current research hotspots and future development direction, and providing references for
research and application in related fields. The article’s structure is as follows. The first
section mainly introduces the data types and data formats used by deep learning in the
application of prospecting; the second section mainly introduces the main types of deep
learning algorithm models; the third section introduces several application examples of
deep learning in geological prospecting; the fourth section systematically summarizes the
outstanding problems and future development trends of deep learning in the application
of prospecting; and the fifth section concludes.

2. Data Foundation
2.1. Data Types
The types of data required for mineral prediction mapping mainly include geological
data, geophysical data, geochemical data, remote sensing data, and so on. These data types
play a crucial role in mineral prediction mapping and can help scientists and geological
experts better understand and predict the location and type of mineral deposits. Geological
data are the basis for mineral prospecting prediction, including information on petrology,
mineralogy, ore deposit geology, and ore-forming structures. These data help determine
geological structures and rock types, extract key geological information related to min-
eralization, delineate geological units as a basis for regional analogies, and thereby infer
potential mineral deposit locations. Geophysical data are obtained by measuring changes
in the Earth’s physical fields, such as gravity, magnetic force, and seismic wave data. These
data can reveal differences in the density and elasticity of underground materials, pro-
viding a comprehensive assessment of the Earth’s physical field within a selected area,
and thus helping to locate mineral deposits. Geochemical data are obtained by analyzing
the chemical compositions of soil, water, and rocks. Abnormal concentrations of specific
elements and compounds may indicate the presence of mineral deposits, and the anomaly
zones are delineated through the integration of various types of geochemical data within
the study area. Remote sensing data use satellite and aerial photography technology to
obtain information about surface features, helping to identify surface cover and vegetation
patterns, as well as alteration information related to mineralization, and delineate areas
with key information for mineralization. MPM involves combining all the data anomalies
to make mineral prospecting predictions within the study area.
The quality of the data we use has a significant impact on the results of our mineral
prospecting predictions. Therefore, when selecting data, we should pay attention to the
following issues:
(1) Accuracy of data. The accuracy of data directly affects the credibility of data analysis
and decision-making. If there are errors or biases in the data, it may lead to incorrect
decision-making and analysis results.
(2) Integrity of data. Collecting more complete data can lead to more accurate mineral
deposit prediction, such as specific information about known mineral deposits.
(3) Accuracy of data. In geological work, geological mapping, geophysical prospecting,
geochemical prospecting, and remote sensing are all carried out at a certain scale. In
practical work, the higher the precision and resolution, the more beneficial it is for
predicting results.
(4) The timeliness of data. As the times change and people’s perceptions evolve, some
data may become outdated, so we need to regularly filter the data we collect.
Minerals 2024, 14, 1021 5 of 35

2.2. Geological Database

2.2.1. Strata and Magmatic Rocks
Strata are closely related to ore deposits, and many ore deposits are formed in specific
strata or stratigraphic combinations. The role of strata in the ore-forming process is as
follows: (1) the migration channel of ore-forming fluid; (2) enrichment sites of ore-forming
materials. In strata-controlled skarn deposits, ore-forming materials are deposited in the
weak zone of strata, and the occurrence of ore bodies is often the same as that of strata. For
example, the widely distributed strata-controlled skarn deposits, such as Dongguashan and
Shizishan in Anhui Province, China, are preserved in the Silurian–Triassic strata, and the
occurrence of ore bodies is controlled by strata [38,39]. The formation of some ore deposits
is due to material exchange between strata and magmatic rocks, and ore-forming materials
are enriched. At this time, strata closely related to ore-forming formations are also the
characteristics that need to be paid attention to in prospecting and prediction. For example,
the formation of the famous Huangshan magmatic copper–nickel sulfide deposit in the
Central Asian orogenic belt is closely related to the Carboniferous and Jurassic strata [40,41].
For the sedimentary deposit, the strata are the ore-forming material itself, such as limestone,
gypsum rock, and so on. The main geological information includes the mineralizing strata,
ore-forming strata, controlling strata, rock texture and dip, mineral composition, geological
age, distribution of igneous rocks, types of intrusive rocks, distribution of granite, control
of mineralization by intrusive bodies, and so on. One of the limitations of geological data is
that geological bodies are oriented in a certain way, and predicting in plain view is affected
by the distribution of surface geological bodies.
Magmatic activity is closely related to the formation of ore deposits, and magmas
provide the heat and some ore-forming materials needed for mineralization. Most mag-
matic deposits are directly related to magmatic rocks, such as the Bushveld magmatic
Cu-Ni-PGE sulfide deposit in South Africa [42] and the Jinchuan Cu-Ni sulfide deposit
in Gansu Province, China [43]. Their mineral sources and occurrence beds are located
in magmatic rocks. Hydrothermal deposits are generally formed near the contact zone
between magma and surrounding rock, such as the world-famous Cerro Verde super-large
porphyry copper–molybdenum deposit in Peru [44] and the Mactung skarn schetungstate
deposit in Canada [45].

2.2.2. Geological Structure

Geological structure is the most important ore-controlling factor at all scales from
molecular to lithosphere [46]. The formation of mineral deposits is usually closely related to
the tectonic framework, and the known large deposits in the world are often controlled by
regional tectonic structures. The fluid flow and mineralization of the hydrothermal system
are mainly controlled by the fault zone framework and its permeability structure [47].
From the perspective of the relationship between ore deposits and the tectonic environ-
ment, the distribution and occurrence of ore deposits and ore bodies usually have the
following characteristics:
• Metallogenic magma and fluid often migrate along geological weak surfaces (fault
plane, fold plane, shear zone, etc.);
• The structural plane (fault plane, fold plane, shear zone, etc.) is the main channel of
heat source and the main place where heat exchange occurs;
• The repeated sliding of faults drives rapid changes in fluid pressure, velocity, and
stress. When the induced fluid channel growth destroys the dynamic balance of the
fluid system, the resulting rapid fluid depressor becomes the key driving factor for
metal precipitation and mineralization [47];
• Metallogenic material precipitation often occurs in the weak structural plane and near
the contact zone between the weak plane and the surrounding rock.
The location of ore deposits is often controlled by structural features. For example, the
occurrence of the Withnell gold deposit in Australia is mainly controlled by the Mallina
shear zone [48], and the formation of the Jiaodong gold deposit is mainly controlled by
Minerals 2024, 14, 1021 6 of 35

regional faults such as the Jiaojia Fault and Zhaoping Fault, which are formed in the
extensional tectonic background [49].
The structure plays an important role in the formation of the deposit. With the increase
in the distance from the tectonic plane, the fluidity of the fluid decreases, the heat loss
increases, and the formation of the deposit becomes difficult. Therefore, the structure
plays an important role in controlling and guiding the mineralization process, and the
study of the structural characteristics is of great significance for prospecting and prediction.
Structural information typically includes mineralizing structures, host structures, structures
controlled by faults, folds, deep-seated faults, and so on. Like geological data, the defect of
structural data is that structural surfaces have dips, and predicting in plain view is affected
by the distribution of structures on the ground.

2.3. Geophysical Data

Geophysics is a comprehensive discipline that uses gravity exploration, magnetic
exploration, electrical and electromagnetic exploration, seismic exploration, radioactive
exploration, aerial geophysical exploration, and other methods to detect and analyze
the material inside the Earth. Geophysical exploration provides detailed information of
underground structure and material distribution, helps researchers to understand the
deep dynamic process of mineralization and the crustal structure that determines the
spatial distribution of ore deposits, reveals the spatial distribution of ore-forming and
ore-controlling geological elements, and provides necessary intrinsic information for deep
prospecting. The comprehensive application of a variety of geophysical methods provides
a choice of method for the deep exploration of polymetallic deposits, and also plays a
great role in the “transparency” of deep prospecting [50]. The geophysical method plays a
particularly important role in the prospecting prediction of covered areas.
The theoretical basis of electrical exploration is the controlled factors of the electrical
properties of rock (ore) or geological bodies, their action rules and IP effect [51], and the
data types mainly include the numerical information of electrical conductivity and the
dielectric property. When using resistivity data, it is necessary to select the resistivity
interpretation chart with appropriate depth to reduce the error caused by the quality of the
data itself. Magnetotelluric measurements of the resistivity of underground rocks can help
identify conductive rock bands that may have mineralized prospects, and can also provide
information about the depth and shape of conductive bands, but the magnetotelluric
method is limited by itself, which may cause interference in the process of signal acquisition
and processing. In addition, the electromagnetic method depends on natural field sources,
whose strength and stability may affect the accuracy of data. The gravity data layer can
provide valuable information about changes in rock density under a particular area, and
can also provide information about the depth and thickness of the overlying sedimentary
cover, and areas with thin sedimentary layers are more likely to have exposed rock units,
which makes rock detection and sampling easier [52]. The aeromagnetic anomaly is usually
regarded as one of the signs of mineralization, and it is necessary to process the raw data
by the magnetic anomaly pole method to eliminate the dipolarity of the magnetic anomaly.
Spectral gamma rays in aerial geophysical methods, due to their fast coverage and low unit
area survey cost, can infer the concealed mineral and structural features related to mineral
deposits, thus standing out from other geophysical methods [53,54].
The Victoria deposit in Sudbury, Canada was discovered by the inversion of various
geophysical methods, despite decades of traditional geological work failing to uncover
it [55]. Due to its location in the plains covered area, the syenite-type magnetite deposit
discovered in recent years in the Qihe–Yucheng area of Shandong Province was also
delimited by geophysical prospecting profiles, including magnetic prospecting and gravity
prospecting, based on the abnormalities in the results of geophysical prospecting profile
inversion [56]. Gold Potentiality Mapping of the Atalla Area and its environs in Egypt was
established by the geological work combined with spectral gamma-ray data [53].
Minerals 2024, 14, 1021 7 of 35

In summary, geophysical exploration plays an irreplaceable role in ore prospecting.

Through reasonable selection and comprehensive application of different geophysical explo-
ration methods, the underground ore body can be effectively identified and located, and the
efficiency and success rate of ore prospecting can be improved. The study and application
of geophysical data is of great significance to modern mineral resources exploration.

2.4. Geochemical Data

Geochemical data is the most common type of data used by researchers in geological
survey and prospecting prediction. In the study of geological bodies and mineral resources,
geochemical background and anomaly play a key role. The distribution map of geochem-
ical data reflects the superposition field of geological bodies and mineral resources with
different properties and grades [4,57].
Geochemical point data collected from stream sediments, lake sediments, soils, and
rocks are important for discovering undiscovered deposits and monitoring environmental
change [58]. In addition, geoelectrochemical survey is an unconventional comprehensive
prospecting method to obtain geochemical information by geophysical means, which has
a high application prospect in prospecting, especially in covering areas combined with
other geological data [59–62]. In traditional research, the application of geochemical data
is often based on the causal relationship between known mineralization and geochemical
characteristics. However, due to the changes in geochemical data caused by water–rock
reaction, weathering and denudation, and crustal movement, researchers may overlook the
key role of some geochemical anomalies in mineralization [31,33].
In the 20th century, American geologists conducted geochemical surveys in the Carlin
area of Nevada and found high anomaly zones of Au, As, Hg, Sb, and Ti, thus discovering
and defining Carlin-type gold deposits [63]. The Hadamengou gold deposit in China was
located by Au anomaly based on the geochemical survey of the 1:100,000 gold deposit area
in Inner Mongolia, and the resources exceeded 100 tons [64].
In addition, in many areas with a high research degree, traditional logging data
and geochemical logging data are abundant, these data can also be applied to geological-
geophysical and geochemical exploration data according to their data types, and these data
are also of great significance in data analysis [65,66]. However, it should also be noted that
there are certain limitations to the earth chemical data from the data collection to the data
processing and interpretation.

2.5. Remote Sensing Image Data

The appearance of remote sensing satellite technology makes the “space-air-ground”
integrated monitoring become a reality, and provides a strong support for the exploration
of mineral resources. Remote sensing images are widely used in the field of geological
exploration for their convenience, speed, and economy. As a member of big data, remote
sensing images are more and more applied in the prospecting work of the majority of
scholars. Remote sensing satellites can provide a wide range of high-resolution image
data. Through multispectral and hyperspectral imaging technology, spectral information
of different bands can be captured, which helps to identify the mineral composition and
characteristics of the surface; and especially important, remote sensing can efficiently and
accurately detect altered minerals related to the hydrothermal process that formed the de-
posit [67,68]. In remote sensing data, spectral characteristics related to electronic vibration of
different minerals are different, which brings convenience to mineral identification [69,70].
In addition, remote sensing satellites can regularly acquire image data of the same area,
making dynamic monitoring possible. Compared to other data, remote sensing data can
accurately identify mineralization anomalies, cover hard-to-reach areas, reduce costs, and
improve efficiency.
Minerals 2024, 14, 1021 8 of 35

The formation of mineral deposits is often accompanied by various forms of hydrother-

mal alteration, including magnetite alteration, pyritization, sericitization, sulphidization,
carbonatization, chloritization, and so on. In practical applications of using remote sensing
techniques for mineral deposit prediction, the extraction of hydrothermal alteration, espe-
cially OH-bearing minerals and iron oxides, is the most mainstream application method.
Ali et al. [71] used ASTER, Advanced land imager, Landsat8, and Sentinel 2 datasets to iden-
tify hydrothermal alteration and delineate mineral prospecting areas in the eastern desert
region of Egypt, which showed good consistency with the aeromagnetic, radiometric, and
geochemical data. The Olympic Dam gold–copper–uranium deposit in Australia has not
been well explored by geological and geophysical exploration methods, but great progress
has been made after analyzing and comparing regional geological characteristics and geo-
physical data with remote sensing images. The mineralized area exceeds 20 km2 and the
proved ore amount reaches 2 billion tons [72]. Dazhuyuan bauxite in the north Guizhou
region is an important bauxite-producing area in China. Researchers used Landsat-8 and
ASTER image data to analyze ground vegetation, rock strata distribution, rock types, and
other information, which became an important means of bauxite exploration [73,74].
When using remote sensing data, in addition to paying attention to the resolution
of the data, it is also important to choose data with less environmental interference, and
it should be noted that the choice of information extraction method can lead to vastly
different analysis results.

3. Deep Learning Technology

Deep learning refers to machine learning based on deep neural network models and
methods, represented by an artificial neural network, and it can effectively identify the
features and data types that have invisible associations with mineralization in mineral
prediction, making up for the shortcomings of general machine learning algorithms [4]. The
artificial neural network is an algorithmic mathematical model that mimics the behavior
characteristics of biological neural networks to process complex data input with distributed
and parallel information [75], and defines the variables in the network and their topological
relationships in a structured way [34]. With the continuous development of deep learning,
more and more deep learning algorithms are applied in prospecting prediction, which has
become a hotspot and frontier of research. This paper uses “mineral prospectivity mapping”
as the topic in the Web of Science (WOS) database, obtains 260 journal articles, uses “deep
learning” and “mineral prospectivity mapping” as the topic in the WOS database, and
obtains 90 journal literature, respectively. There was a total of 27 journal articles on the
topic of “Deep learning prospecting and prediction” in the CNKI database. The time range
of the literature was from 1 January 2000 to 1 April 2024, and the retrieval time was 15 April
2024. The retrieved data were downloaded in the full description format with references
for subsequent processing.
All the literature was imported into Citespace software 6.3 for analysis, and the
results are shown in Figure 1. From the results of the Chinese literature analysis, the most
important keywords mainly include “deep learning”, “machine learning”, “geochemistry”,
etc. From the timeline, “machine learning” and “unsupervised learning” have always
been the hot content of research, and geochemical data is a commonly used data type.
In terms of the English literature, “machine learning”, “mineral province”, and “deep
learning” are the main keywords, focusing on the application of deep learning algorithms
in prospecting and prediction, and taking into account the comparison with traditional
machine learning algorithms and the mining of geological data types. The following
introduces the algorithms which are widely used in prospecting prediction and which have
made some research progress.
Minerals 2024, 14, 1021 9 of 36

Minerals 2024, 14, 1021 introduces the algorithms which are widely used in prospecting prediction and which
9 of 35
have made some research progress.

(a) (b)

(c) (d)
Figure 1. 1.
Figure High-frequency
High-frequencykeyword
keywordco-occurrence
co-occurrenceand
and timeline
timeline chart of main
chart of mainkeywords
keywordsininCNKI
CNKIand
and WOS (made by Citespace): (a) High-frequency keywords co-occurrence in CNKI; (b) The time-
WOS (made by Citespace): (a) High-frequency keywords co-occurrence in CNKI; (b) The timeline
line chart of main keywords in CNKI; (c) High-frequency keywords co-occurrence in WOS; (d) The
chart of main keywords in CNKI; (c) High-frequency keywords co-occurrence in WOS; (d) The
timeline chart of main keywords in WOS.
timeline chart of main keywords in WOS.
[Link].
Deep
DeepAutoencoder
Autoencoder
AnAn autoencoder
autoencoder (AE)
(AE)is is
ananunsupervised
unsupervised feature
featurelearning
learningnetwork
network that utilizes
that a a
utilizes
backpropagation algorithm so that the target output value equals the input
backpropagation algorithm so that the target output value equals the input value. The value. The
autoencoder
autoencoder consists of an
consists ofinput layer,layer,
an input a hidden layer,layer,
a hidden and anandoutput layer. After
an output [Link]
inputthe
layer
inputis input,
layer isthe datathe
input, aredata
compressed and encoded
are compressed in the hidden
and encoded layer to
in the hidden enhance
layer the
to enhance
characteristics of the data,
the characteristics of theand then
data, anddecoded [30,76]; the
then decoded encoding
[30,76]; Formula (1)
the encoding and decod-
Formula (1) and
ingdecoding
FormulaFormula
(2), respectively, are
(2), respectively, are
𝑍 = φ Weθx (1)
Z = φ(Weθx) (1)

X=
X =W
WDZZ==WWφ Weθx
D φ(Weθx)
(2)(2)
where
where x represents
x represents thethe
training
trainingdata (including
data (including bias), WeWe
bias), represents
represents thethe
encoder,
encoder, φ repre-
φ repre-
sents the activation function, and Z represents the output value. W
sents the activation function, and Z represents the output value. WD represents thethe D represents de-
decoder,
coder, which translates the output value to the input value. Since the
which translates the output value to the input value. Since the input data and output input data and out-
putvalues
values of of
thethe autoencoder
autoencoder model
model unitunit follow
follow the basic
the basic logiclogic of a single
of a single real neuron
real neuron [77], the
[77], the decoding
decoding operation
operation processprocess
function function is an identity
is an identity functionfunction
to obtain tothe
obtain
output thevalue
output and
value
the and the encoded
encoded input value.
input value.
TheTheDeep
Deep Belief Network
Belief Network (DBN)
(DBN) was
wasproposed
proposed byby
Hinton
Hinton in in
2006.
[Link] is
It aisprobabilistic
a probabilistic
generation model composed of stacked constrained Boltzmann
generation model composed of stacked constrained Boltzmann sets. By training sets. By training the
the weights
weights
between between neurons,
neurons, the whole
the whole neural neural
networknetwork can generate
can generate training
training datadata according
according to the
to the maximum
maximum probability
probability [30,78,79].
[30,78,79]. TheThedeepdeep autoencoder
autoencoder (DAE)
(DAE) is developed
is developed on deep
on deep belief
belief networks.
networks. First,First, a model
a model is trained
is trained to learntothe
learn the pattern
pattern distribution
distribution of the the
of the sample, sample,
sample
is reconstructed by minimizing the difference between the output value and the input value,
and then the sample with a high reconstruction error is identified as an anomaly.
Minerals 2024, 14, 1021 10 of 35

The autoencoder can train samples without difference, reduce the extraction of irrele-
vant feature information, and it has a good effect on data dimensionality reduction [4,80].
Since the autoencoder has a high reconstruction error for abnormal samples and a low
reconstruction error for background samples, it has good applicability in processing geo-
physical, geochemical, and remote sensing data and can quickly identify data anomalies.
According to the metallogenic law and prospecting practice, the formation and discov-
ery of the deposit are small probability events. Anomalies in the data associated with
mineralization often belong to low-probability samples, which have little contribution to
the autoencoder, so their coding and reconstruction will be poor and have relatively high
reconstruction errors [29,30,81]. We can use these data with large reconstruction errors to
identify outliers in ore prospecting and prediction.

3.2. Generative Adversarial Network

As a deep generative model, the generative adversarial network (GAN) model is
composed of a generative network and a discriminant network. The generative network
generates samples close to real samples by learning the distribution of data. The discrimi-
nant network is used to evaluate whether the samples are from real samples or generated
samples. The two neural network models continue to perform the binary minimax game
until the antagonism between the two networks reaches a Nash equilibrium, often used
for processing complex, high-dimensional data [82]. Compared with the traditional au-
toencoder framework, the discriminator added by the generative adversarial network
framework has the function of regulating feedback and guiding the generator [29]. For the
basic framework of generating adversarial networks, the formula is

L(D) = E[logD(x)] + E[log(1 − D( G (z))) ] (3)

L(G) = E[log(D( G (z))) ] (4)

Formula (3) is the discriminator loss function, Formula (4) is the generator loss function,
x represents the real data, z represents the noise, G stands for generative model, D stands
for discriminant model, and G(z) represents the output of an input noise after generating
the network; the generator’s goal is to generate data very close to the real data, that is,
D(G(z)) as close as possible to 1.
In the process of deep learning, the finiteness and unbalance of geological exploration
data often lead to large model errors or strong overfitting characteristics. Using the genera-
tive adversarial network to enhance data processing is very suitable to solve the problem
of the small number of positive samples of geological data. When processing data with
unbalanced positive and negative samples, generative adversarial networks can capture
complex patterns and dependencies in the original geological data to generate high-quality
sample data [52,83,84]. Farahbakhsh et al. [84] used the generated adversarial network
to generate high-quality samples that closely mimic the distribution of underlying data
to increase the number of positive samples in the model, effectively solving the problem
of unbalanced training data caused by insufficient positive samples in geological data.
Wu et al. [52] used conditional generation adversarial networks to add appropriate labels
to the initial random noise, generate synthetic samples similar to the original geological
data, adjust the distribution of positive and negative samples, and improve the quality of
data. The data set model enhanced by the generated adversarial network shows better
robustness, the accuracy of the training set and the test set reaches a high level, and the
model has better anti-overfitting ability.
The image generated by the generative adversarial network is clearer in the course of
training, but it is prone to modal collapse and gradient disappearance [80]. The generative
adversarial network also lacks an effective reasoning mechanism, and its data are often
difficult to perform an abstract reasoning process with. Some studies have used the
correlation between the generative adversarial network and deep autoencoder to train
its reasoning ability [85]. Therefore, when predecessors used the generative adversarial
Minerals 2024, 14, 1021 11 of 35

network for prospecting prediction, they often used its super ability to generate sample
sets for data enhancement operations, and the subsequent prospecting prediction modeling
process used other deep learning algorithms. Therefore, when predecessors used the
generative adversarial network to make prospecting predictions, they often used its super-
strong sample generation ability to enhance the data, and the generated data had better
consistency with the original data. On this basis, the researchers combined it with other
deep learning methods to make prospecting predictions.

3.3. Convolutional Neural Network

The convolutional neural network (CNN) is a deep feedforward artificial neural
network classification method in machine learning, which adopts the idea of the local
receptive field, and time or space subsampling, and has the characteristics of translation
invariance and shared weight structure, which significantly reduce the number of free
parameters in the network. The advantage of the convolutional neural network is that it
cannot only learn the overall features of the data, but also learn the local features of the data,
and these local features also have a certain correlation. By extracting the features of the
deposit data layer by layer, the correlation between mineralization factors and the deposit
can be obtained [4,86]. The convolutional neural network is based on images, and the
multi-source geological data and remote sensing data used in prospecting prediction can be
easily unified into the image format, which provides basic conditions for the convolutional
neural website in prospecting prediction [87].
A basic convolutional neural network structure generally includes an input layer,
convolutional layer, pooling layer, fully connected layer, and output layer. The input
layer takes the original meshed data as the input data. Since the input layer data are not
processed, and the hidden layer part cannot be manually intervened, the convolutional
neural network avoids the influence that may be brought by the subjective cognition of
researchers and their own limitations [34,76,86,88]. Pooling is to compress and converge
the data features completed by convolution, reduce the calculation amount, and extract the
main features of the data [89]. Two pooling methods are generally selected: average pooling
and maximum pooling [86]. Average pooling has relatively low hardware requirements,
can reduce the convolutional layer to obtain data redundancy, and retains the diversity
of geological features as much as possible. Maximum pooling can highlight the most
significant features, reduce the complexity of calculation, and enhance the robustness of
the model [9,90]. In the fully connected layer, every node is connected with all the nodes
of the previous layer, and the features extracted from the convolutional layer and pooling
layer are integrated to achieve feature mapping and classification at the end of the network.
The essence of the fully connected layer is a backpropagation neural network [86,88,91].
The general process of the convolutional neural network for prospecting prediction
includes the following: data collection and collation—generation of training set, verification
set, test set—model construction—training and validation—determination of prospecting
prediction region. Since there are many kinds of geological data, convolutional neural
networks can fully mine the deep relationships between different kinds of data, which
brings great help to the full utilization of data. Therefore, the convolutional neural network
is widely used in geological prospecting and prediction.

3.4. Recurrent Neural Network

In the field of deep learning, recurrent neural networks (RNNs) with recurrent con-
nections are capable of processing variable length sequence inputs, modeling sequence
data for sequence recognition and prediction, storing information using cyclic iterative
functions, and capturing contextual information well. To realize transient dependency
learning, the research object is mainly sequence data, such as text, time series data, etc. [92].
The recurrent neural network consists of an input layer, hidden layer, and output layer.
In the process of use, people find it difficult to establish long-term dependency, so pre-
decessors have designed more complex activation functions to solve this problem. The
 learning, the research object is mainly sequence data, such as text, time series data, etc.
[92]. The recurrent neural network consists of an input layer, hidden layer, and output
layer. In the process of use, people find it difficult to establish long-term dependency, so
Minerals 2024, 14, 1021 12 of 35
predecessors have designed more complex activation functions to solve this problem. The
most important methods include Long Short-Term Memory (LSTM) (Figure 2) and Gated
Recurrent Unit (GRU) [93–95]. LSTM is specifically designed for analyzing sequence data,
mostitsimportant
and main ideamethods include
is to make Long Short-Term
predictions Memoryconnected
through cyclically (LSTM) (Figure
memory 2) and Gated
units and
Recurrent Unit (GRU) [93–95]. LSTM is specifically designed for analyzing sequence data,
three key gate units in each memory block (i.e., forgetting gate, input gate, and output
and its main idea is to make predictions through cyclically connected memory units and
gate). Gates are a way to selectively retain or forget information through activation func-
three key gate units in each memory block (i.e., forgetting gate, input gate, and output gate).
tions [96]. GRUs have gated units that regulate the flow of information within the unit,
Gates are a way to selectively retain or forget information through activation functions [96].
but do not have separate storage units, showing better performance on smaller data sets
GRUs have gated units that regulate the flow of information within the unit, but do not
[97].
have separate storage units, showing better performance on smaller data sets [97].

Figure 2.
Figure 2. AA basic
basic LSTM
LSTM block
block [98].
[98]. ft,
ft, it,
it, and
and Ot
Ot are
are outputs
outputs of
of the
the forget
forgetgate,
gate,the
theinput
inputgate,
gate,and
andthe
output gate, respectively, at time step t. C − 1 and Ct correspond to the cell state
the output gate, respectively, at time step t.t Ct − 1 and Ct correspond to the cell state of the time of the time t and
t
∼
and
timetime
t − 1. Ct represents
t −C1.t represents thethe fresh
fresh information
information brought
brought intime
in at at time
stepstep t. σL
t. σL andand
σRσRareare used
used as as
the
the activation
activation function.
function. + represents
+ represents addition.
addition. × represents
× represents multiply.
multiply.

Recurrent
Recurrent neural
neural networks
networks focus
focus on
on learning
learning the
the interaction
interaction between
between variables
variables that
that
interact
interact with
with each
each other
other andand have
have the
the potential
potential to
to integrate
integrate highly
highly correlated
correlated geological
geological
features
features for
for prospecting
prospecting prediction.
prediction. LSTM
LSTM isis capable
capable of
of capturing
capturing contextual
contextual information
information
within
within sequences,
sequences, which
which complements
complements the the limitations
limitations ofof the
the CNN
CNN inin context
context sequence
sequence
modeling
modeling and is the first choice for interpreting geochemical elements related
is the first choice for interpreting geochemical elements related to genesis to genesis
[99].
[99].
This This advantage
advantage of recurrent
of the the recurrent neural
neural network
network plays
plays a very
a very important
important role
role in in
thethe use
use of
text-based
of text-based geological
geologicaldata,
data,which
whichcan canintegrate
integratethe
theoriginal
original data
data and extract important
important
information related
information related toto mineralization.
mineralization.

4. Application
4. Applicationof ofDeep
DeepLearning
LearningininMineral
Mineral Prospectivity
Prospectivity Mapping
Mapping
4.1. Application of DAE
4.1. Application of DAE
The deep autoencoder encodes the input data, and the decoder reconstructs the output
The deep autoencoder encodes the input data, and the decoder reconstructs the out-
from the encoding. Because the small probability sample has little contribution to the
put from the encoding. Because the small probability sample has little contribution to the
autoencoder and a high reconstruction error, it has a good advantage in the identification
autoencoder and a high reconstruction error, it has a good advantage in the identification
of geochemical anomalies.
of geochemical anomalies.
Xiong et al. [30] used the deep autoencoder algorithm to identify geochemical anomaly
Xiong et al. [30] used the deep autoencoder algorithm to identify geochemical anom-
data. Firstly, the deep autoencoder network was constructed, the improved unsupervised
aly data. Firstly, the deep autoencoder network was constructed, the improved unsuper-
building module (Continuous Restricted Boltzmann Machine) was selected as the basis
vised building module (Continuous Restricted Boltzmann Machine) was selected as the
of the deep autoencoder, and the initial weights were pre-trained. Attempts were made
basis of the deep autoencoder, and the initial weights were pre-trained. Attempts were
to find and enhance correlations between visible and hidden cell values, creating neural
made to find
networks. Theand enhancedescent
gradient correlations between
technique was visible
used toand hidden
adjust cell values,
the network in creating
order to
neural networks. The gradient descent technique was used to adjust the network
minimize reconstruction errors. Secondly, data preprocessing was carried out, the drainagein order
to minimize
sediment reconstruction
geochemical errors.
data in Secondly,
the study data selected
area were preprocessing was data,
as the basic carried
theout, the
closure
problem of the basic data was processed by using isometric logarithmic transformation,
and the measured values were normalized to the range [0, 1]. Then the model was trained
and the parameters were adjusted. Finally, the identification of geochemical data anomalies
was carried out. Xiong et al. [30] believe that when applying the deep autoencoder, it is
necessary to focus on the setting of learning rate and iteration number, as well as the size
 drainage sediment geochemical data in the study area were selected as the basic data, the
closure problem of the basic data was processed by using isometric logarithmic transfor-
mation, and the measured values were normalized to the range [0,1]. Then the model was
trained and the parameters were adjusted. Finally, the identification of geochemical data
Minerals 2024, 14, 1021 anomalies was carried out. Xiong et al. [30] believe that when applying the deep autoen- 13 of 35
coder, it is necessary to focus on the setting of learning rate and iteration number, as well
as the size of the hidden layer of the geochemical data. When the reconstruction error is
minimal
of and stable,
the hidden thethe
layer of autoencoder
geochemical network and itsthe
data. When corresponding
reconstructionparameters are opti-
error is minimal
malstable,
and for thethe
modeling of geochemical
autoencoder network and samples. The results show
its corresponding that theare
parameters geochemical
optimal forhigh
the
modeling
anomaly areaof geochemical
accounts forsamples.
2.4% of theThe results
total area show that the
and 31.5% geochemical
of the total known high
ironanomaly
deposits
area accounts
(Figure 3). Theformedium
2.4% of the total area
anomaly and
area 31.5% offor
accounts the34.1%
total known iron deposits
of the total area and(Figure
68.4% 3).
of
The medium anomaly area accounts for 34.1% of the total area and 68.4% of the
the known iron reserves. Compared with the recognition results of the constrained Boltz- known iron
reserves. Compared
mann machine, with the
the results recognition
of the results of have
deep autoencoder the constrained Boltzmann
similar spatial machine,
distribution char-
the results ofwhich
acteristics, the deep autoencoder
proves that the have
deep similar spatialhas
autoencoder distribution characteristics,
a good ability which
in geochemical
proves
anomaly that the deep autoencoder has a good ability in geochemical anomaly recognition.
recognition.

Figure 3.3. Spatial

Figure Spatial relationship
relationship between
between geochemical
geochemical anomaly
anomaly maps
maps obtained
obtained by
by DAE
DAE and
and iron
iron ore
ore
deposit locations (modified from [30]).
deposit locations (modified from [30]).

Thedeep
The deepautoencoder
autoencoderplays
playsananimportant
importantrole roleininidentifying
identifyinganomalies,
anomalies,but butthe
thetype
type
of
ofanomaly
anomalydata dataassociated
associatedwith
withprospecting
prospecting prediction
prediction requires researchers
requires researchers to analyze the
to analyze
geological evolution process, that is, the judgment of expert experience
the geological evolution process, that is, the judgment of expert experience is needed as is needed as the
basis for data
the basis adoption.
for data When
adoption. When thethe
autoencoder
autoencoder is is
used
usedforformetallogenic
metallogenicprediction,
prediction,the the
abnormal
abnormalregions
regionsare
areoften
oftenextracted
extractedincorrectly
incorrectlyduedueto tothe
thehigh
high noise
noise of
of the
the original
original data,
data,
so
sosome
somemethods
methodsneedneedtotobe
be used
used toto suppress
suppress the the noise
noise andand reconstruct
reconstruct the
the error.
error. Research
Research
showed
showedthatthatincreasing
increasingthe
thenumber
numberof ofhidden
hiddenunits
unitsin inthe
thedeep
deepautoencoder
autoencodernetwork
networkcan can
effectively reduce the error between the input data and the generated output
effectively reduce the error between the input data and the generated output value, but value, but this
method will greatly
this method increase
will greatly the risk
increase theofrisk
overfitting of the of
of overfitting model [81], so[81],
the model we need
so wetoneed
adjustto
the parameters repeatedly when using
adjust the parameters repeatedly when using [Link].

4.2.
4.2. Application
Application of
of CNN
CNN
The convolutional neural network is the most widely used deep learning algorithm in
The convolutional neural network is the most widely used deep learning algorithm
mineral prospectivity mapping at present, including LeNet, AlexNet, VggNet, GoogleNet,
in mineral prospectivity mapping at present, including LeNet, AlexNet, VggNet, Goog-
ResNet, U-Net, and other structural types. The main difference between types lies in the
leNet, ResNet, U-Net, and other structural types. The main difference between types lies
structure and depth of the network (Figure 4). The LeNet structure is relatively simple, and
in the structure and depth of the network (Figure 4). The LeNet structure is relatively
people usually choose the Sigmond function or Tanh function as the activation function.
simple, and people usually choose the Sigmond function or Tanh function as the activation
Liu et al. [33] applied the convolutional neural network based on LeNet to mine the cou-
function. Liu et al. [33] applied the convolutional neural network based on LeNet to mine
pling correlation between the distribution characteristics of elements and the underground
placement space of the ore body, and the accuracy rate reached 93%. Xu et al. [100] used
the CNN of the LeNet structure to effectively learn the relationship between geological,
geophysical, and geochemical data and deposit distribution locations, and the results
showed that 90% of known gold deposits were distributed in prospective areas, accounting
for only 15% of the studied area. During training, temporarily dropping certain units in
the neural network from the network according to a certain probability is Dropout. The
AlexNet structure is deeper than the LeNet structure, uses the ReLu function as an acti-
 [100] used the CNN of the LeNet structure to effectively learn the relationship between
geological, geophysical, and geochemical data and deposit distribution locations, and the
results showed that 90% of known gold deposits were distributed in prospective areas,
accounting for only 15% of the studied area. During training, temporarily dropping cer-
Minerals 2024, 14, 1021 tain units in the neural network from the network according to a certain probability is
14 of 35
Dropout. The AlexNet structure is deeper than the LeNet structure, uses the ReLu func-
tion as an activation function to reduce gradient disappearance [101], and performs data
enhancement
vation function during training,
to reduce adding
gradient Dropout to suppress
disappearance [101], andoverfitting.
performs data Li et enhancement
al. [102] used
the
during training, adding Dropout to suppress overfitting. Li et al. [102] used thegeochemical
CNN of the AlexNet structure to learn the internal relationship between CNN of the
data,
AlexNet sedimentary
structure tostrata,
learn structure,
the internalwater system,between
relationship and other geologicaldata,
geochemical information
sedimentary and
the location of ore occurrence, and delineated the metallogenic prospect
strata, structure, water system, and other geological information and the location of ore area, and the ver-
ification
occurrence, accuracy rate was 86.21%.
and delineated Li et al. [103]
the metallogenic predicted
prospect sedimentary
area, and manganese
the verification accuracyore
prospecting
rate was 86.21%. in theLiSongtao–Huayuan
et al. [103] predicted areasedimentary
based on themanganese
AlexNet network, and obtained
ore prospecting in thea
classification model based on the CNN, with an accuracy of 88.89%.
Songtao–Huayuan area based on the AlexNet network, and obtained a classification model VggNet [9,104] has a
simple structure and reduces the number of weights by stacking
based on the CNN, with an accuracy of 88.89%. VggNet [9,104] has a simple structure multiple 3 × 3 convolu-
tion cores instead
and reduces of largeofconvolution
the number weights by cores.
stacking It also uses ReLU
multiple as the activation
3 × 3 convolution coresfunction
instead
after the fully connected layer to suppress overfitting, which
of large convolution cores. It also uses ReLU as the activation function after the fullyis highly applicable. The
GoogleNet
connected layer structure, designed
to suppress by the Google
overfitting, whichteam in 2014,
is highly can extract
applicable. Thefeatures
GoogleNet from dif-
struc-
ferent convolution
ture, designed by thekernels
Googleofteamfeature images
in 2014, canin parallel,
extract enriching
features the information
from different convolutioncon-
tained
kernelsinofmulti-scale
feature images featurein maps. Multi-source
parallel, enriching the geological data provide
information contained theinbasis for fea-
multi-scale
tures to integrate feature information with the GoogleNet structure,
feature maps. Multi-source geological data provide the basis for features to integrate making this method
more
feature suitable
informationfor prospecting and prediction
with the GoogleNet [87,105].
structure, ResNet
making thiswas
methodproposed
more by He et for
suitable al.
[106] in 2016,
prospecting andaiming to introduce
prediction [87,105].a ResNet
deep residual learning
was proposed byframework to solve
He et al. [106] in 2016,theaiming
prob-
lem of training
to introduce a deepaccuracy
residual degradation by adding
learning framework to residual
solve the structure.
problem ofResNet
trainingartificially
accuracy
makes certainbylayers
degradation adding of the neural
residual networkResNet
structure. skip theartificially
connections of the
makes next layer
certain layersofofneu-the
neuralconnecting
rons, network skip the the connections
layers separately,ofweakening
the next layer the of neurons,
strong connecting
connections the layers
between each
separately,
layer. weakeninginput
By combining the strong connections
and output, ResNet between eachalleviates
effectively layer. By thecombining input and
loss of geo-infor-
output, ResNet effectively alleviates the loss of geo-information
mation caused by convolution operations, and also plays a positive role in solving the caused by convolution
operations,
problem of and also plays
gradient a positive role
disappearance in solvinginthe
or explosion problem
deep of gradient
networks disappearance
[107,108]. U-Net is a
or explosionupdated
completely in deep convolutional
networks [107,108].
neural U-Net
network is awith
completely updated convolutional
an encoder–decoder structure.
neural
The network
encoder with an
extracts encoder–decoder
features structure. The
through convolution, encoder
pooling, extracts
etc., features through
and gradually reduces
convolution, pooling, etc., and gradually reduces the input
the input dimension. According to the data provided by the encoder, the decoder can dimension. According to the
re-
data provided by the encoder, the decoder can repair the detailed
pair the detailed features to improve the accuracy. Its advantage are that the required features to improve the
[Link]
training Its advantage
are smaller,are thethat the is
result required trainingand
more accurate, dataitare
hassmaller, the result
an advantage is more
in the pro-
accurate, and it has an advantage
cessing of small-scale data [109–111]. in the processing of small-scale data [109–111].

Figure 4. CCN structures for mineral prospectivity modeling (modified from [9,87,107]): (a) Different
CCN structures for mineral prospectivity modeling: a) LeNet, b) AlexNet, c) VggNet, d) GoogleNet;
e) ResNet-50; (b) A basic structure for convolution; (c) the detailed process for “Inception” in
GoogleNet; (d) the detailed process for “Identity Block” in ResNet-50.

The Nanling area is one of the most important non-ferrous metal metallogenic belts in
China, and tungsten tin is the dominant mineral. There are several world-class tungsten tin
deposits in this area, such as the Xihuashan tungsten deposit, Dachang Tin deposit, and
 ent CCN structures for mineral prospectivity modeling: a) LeNet, b) AlexNet, c) VggNet, d) Goog-
leNet; e) ResNet-50; (b) A basic structure for convolution; (c) the detailed process for “Inception” in
GoogleNet; (d) the detailed process for “Identity Block” in ResNet-50.

Minerals 2024, 14, 1021 The Nanling area is one of the most important non-ferrous metal metallogenic 15 belts
of 35
in China, and tungsten tin is the dominant mineral. There are several world-class tungsten
tin deposits in this area, such as the Xihuashan tungsten deposit, Dachang Tin deposit,
and Shizhuyuan
Shizhuyuan tungsten
tungsten deposit
deposit [112].[112].
Li et Li
al. et [Link]
[36] [36] made
use ofuse of multivariate
multivariate data indata
theinarea
the
area and adopted the convolutional neural network model to
and adopted the convolutional neural network model to make prospecting predictions. make prospecting predic-
tions.
The The selected
selected dataincluded
data layers layers included the following:
the following: granite and granite
fault;and
localfault; localanomaly
gravity gravity
anomaly closely related to W-Sn ore mineralization; distribution of
closely related to W-Sn ore mineralization; distribution of W, Sn, Bi, Be, Pb, Ag, Mo, and W, Sn, Bi, Be, Pb, Ag,
Mo,geochemical
Zn and Zn geochemical
elements. elements.
The bufferThe zone buffer zone was according
was delimited delimited to according to the
the distance of dis-
the
tance ofand
granite thefault,
granite and fault,and
respectively, respectively,
the buffer zoneand the
mapbuffer zone mapThe
was generated. wasgeophysical
generated. and The
geophysical data
geochemical and geochemical
were mappeddata were mapped
according to inverse according
distance to inverseDue
weights. distance weights.
to insufficient
Due to insufficient training samples of geological data, the researchers
training samples of geological data, the researchers used sliding windows and random used sliding win-
dows and random zero noise
zero noise for data enhancement. for data enhancement.
Sincethere
Since thereare
aremany
many channels
channels in the
in the geological
geological datadata
layer,layer, the traditional
the traditional convolu-
convolutional
tional neural
neural network network is complicated
is complicated to calculate
to calculate and itand it iseasy
is not not to
easy to automatically
automatically extract
extract key
key channel
channel information.
information. A feature
A feature of the
of the human
human visual
visual systemisistotoselectively
system selectivelyfocus
focus onon
highlighted parts of the
highlighted the entire
entire scene
scenetotobetter
bettercapture
capturethe thevisual
visualstructure.
structure. Therefore,
Therefore, re-
searchers add
researchers addananattention
attention mechanism
mechanism based
basedon the characteristics
on the characteristicsof theof human
the human eye after
eye
after the convolutional
the convolutional layer layer to obtain
to obtain the channel
the channel attention
attention graph,graph,
whichwhich
enhances enhances the
the repre-
representation
sentation of key of features
key features
and and weakens
weakens the performance
the performance of channels
of channels withwith
low low weight
weight val-
values.
ues. Its Its network
network structure
structure is shown
is shown in in Figure
Figure 5. 5.

Figure5.5. ATT-CNN
Figure ATT-CNNstructure
structurefor
formineral
mineralprospectivity
prospectivitymodeling
modeling(modified
(modifiedfrom [36]).
from[36]).

Combined with the

Combined with thedata
dataenhancement
enhancementmethod, method, thethe researchers
researchers built
built fourfour models
models sep-
separately: a sliding
arately: a sliding window
window CNN
CNN model,a arandom
model, randomzerozeronoise
noiseCNN
CNN model,
model, anan attention-
attention-
adding
adding mechanism
mechanism CNN CNN (ATT-CNN)
(ATT-CNN) modelmodel using
using aa sliding
sliding window,
window, and and ananATT-CNN
ATT-CNN
model
model using a random zero noise; a receiver operating characteristic curve (ROC) and
using a random zero noise; a receiver operating characteristic curve (ROC) and an
an
area under ROC curve (AUC) were used to evaluate the accuracy of the
area under ROC curve (AUC) were used to evaluate the accuracy of the prediction model. prediction model.
The
Theexperimental
experimentalresults(Figure
results(Figure6)6)show
showthat
thatthe
theAUC
AUCvalue
valueofof the
the ATT-CNN
ATT-CNNmodel modelusing
using
the
the sliding window is the highest (0.987), followed by the ATT-CNN model using random
sliding window is the highest (0.987), followed by the ATT-CNN model using random
zero
zeronoise
noise(0.971),
(0.971),the
theCNN
CNNmodel
modelusing
usingthethesliding
slidingwindow
window(0.970),
(0.970),andand the
the CNN
CNN model
model
using random zero noise (0.964). This shows that the performance of
using random zero noise (0.964). This shows that the performance of the convolutional the convolutional
neural
neural network
network model
model hashas been
been improved
improved after
after the
the addition
addition ofof the
the attention
attention mechanism,
mechanism,
and the recognition ability of important data layers has been enhanced, which provides a
and the recognition ability of important data layers has been enhanced, which provides a
good example for prospecting prediction in other areas.
good example for prospecting prediction in other areas.
The following problems should also be paid attention to when using the convolutional
neural network for prospecting prediction modeling: the size of the grid, the size of the
convolutional kernel, the number of layers, the learning rate, and the number of iterations.
The smaller grid can make better use of the existing data and make the calculation more
accurate, but it will lead to excessive calculation. If the grid is too large, it cannot effectively
use all the data, resulting in reduced accuracy [102]. Zuo [58] studied the size of the
output unit and proved that different grid sizes have certain effects on the concentration
distribution of geochemical anomalies and the texture structure of different geochemical
types. Complex neural networks do not necessarily improve the accuracy of the model.
Sun et al. [22] found that in artificial neural networks, the mean squared error of the model
does not decrease significantly with the increase in the number of neurons. The learning
Minerals 2024, 14, 1021 16 of 35

rate will affect the convergence rate of the model. If the learning rate is too small, the
convergence speed will be fast, and if the learning rate is too large, it is difficult to reach
the extreme point [9]. In practical application, it is necessary to consider the density and
cartographic scale of different types of data samples, and carry out continuous debugging
Minerals 2024, 14, 1021 16 of 36
to select the appropriate mesh size, convolutional kernel size, neural network layer number,
learning rate, and other parameters.

Figure 6.
Figure 6. MPM
MPM of
of W-Sn ore obtained
W-Sn ore obtained by
by using
using sliding
sliding window
window ATT-CNN
ATT-CNN (modified
(modified from
from[36]).
[36]).

The following
4.3. Application of RNN problems should also be paid attention to when using the convolu-
tionalThe
neural network
recurrent for prospecting
neural network hasprediction
the ability modeling:
to integratethe highly
size of the grid, thegeologi-
correlated size of
the features,
cal convolutional
is very kernel,
friendly theto
number of layers,
geological data inthegeological
learning rate, and the and
prospecting number of iter-
prediction,
ations.
and hasThe smaller
a good grid can make
application betterinuse
prospect of the existing
research areas with dataabundant
and makegeological
the calculation
data.
more accurate, but it will lead to excessive calculation. If
Wang et al. [96] made use of geological, geochemical, and geophysical data in the the grid is too large, it cannot
study
effectively
area use
to carry out allweight
the data, resulting
function in reduced
analysis based on accuracy [102]. Zuo
the singularity [58] studied
of deposit the size
location, and
of theaoutput
built long and unitshort
and proved
term memorythat different
network grid sizesfor
model havethecertain
evidenceeffects on the
layer. Theconcen-
results
tration distribution
showed that all known of geochemical
deposits fell in anomalies and the texture
the high prospect area, and structure
10% of theof different
prospect geo-
area
chemical types.
accounted for more Complex
than 90% neural networks
of the iron oredo not necessarily
deposits. improve
By combining the accuracy
LSTM with the of the
CNN,
[Link]
Wang et al.
al. [99] [22] found
focused on the that in artificial
inherent featureneural networks,ofthe
representation mean squared
adjacent samples error
and theof
the model does not decrease significantly with the increase in the
contextual association information learning of geochemical variables, and captured 96% of number of neurons. The
learning
the graniterate
in will
15%affectof thethe convergence
study rate ofathe
area, providing new model. If the
idea for thelearning rate isoftoo
identification small,
regional
geological features
the convergence and will
speed contributing
be fast, andto the mineral
if the prospectivity
learning rate is toomapping
large, it of areas with
is difficult to
insufficient mapping.
reach the extreme point [9]. In practical application, it is necessary to consider the density
The Baguio District
and cartographic scale ofofdifferent
the Philippines
types ofisdata
one samples,
of the most andimportant
carry outgold depositsde-
continuous in
the world,
bugging to with
selectproven gold reserves
the appropriate mesh ofsize,
moreconvolutional
than 800 tons,kerneland the gold
size, deposits
neural are
network
mainly volcanic
layer number, epithermal
learning deposits.
rate, and Yin et al. [97] used four types of geological data
other parameters.
within the region, such as NE faults, NW faults, Agno magmatite margins, and porphyry
intrusive contact
4.3. Application of zones,
RNN as data layers to build models, built buffers and converted grids
fromThethe four types
recurrent neural of geological
network data,
has and used nonlinear
the ability to integrate control
highly functions
correlatedof geological
geological
characteristics to assign artificial values to grids in all buffers.
features, is very friendly to geological data in geological prospecting and prediction, andThe data enhancement
method
has a goodwasapplication
used to generateprospect sufficient samples.
in research areas with abundant geological data. Wang et
al. [96] made use of geological, geochemical, and geophysical data in the study area to
carry out weight function analysis based on the singularity of deposit location, and built
a long and short term memory network model for the evidence layer. The results showed
that all known deposits fell in the high prospect area, and 10% of the prospect area ac-
counted for more than 90% of the iron ore deposits. By combining LSTM with the CNN,
Wang et al. [99] focused on the inherent feature representation of adjacent samples and
 the world, with proven gold reserves of more than 800 tons, and the gold deposits are
mainly volcanic epithermal deposits. Yin et al. [97] used four types of geological data
within the region, such as NE faults, NW faults, Agno magmatite margins, and porphyry
intrusive contact zones, as data layers to build models, built buffers and converted grids
Minerals 2024, 14, 1021 from the four types of geological data, and used nonlinear control functions of geological 17 of 35
characteristics to assign artificial values to grids in all buffers. The data enhancement
method was used to generate sufficient samples.
The GRU
The GRU model
model inin the
the recurrent
recurrent neural
neural network
networkwaswasselected
selectedtotobuild
buildthe
themodel,
model,
which includes a cyclic layer, a dense layer, and an activation layer. Its network structureis
which includes a cyclic layer, a dense layer, and an activation layer. Its network structure
is shown
shown in in Figure
Figure 7. 7.

Figure [Link]
Figure Datarepresentation
representationfor
forthe
the GRU
GRU model
model (modified
(modified fromfrom [97]
[97]): (a)):Basic
(a) Basic process
process of theofmodel;
the
model; (b) Inner structure of the hidden layer; (c) Inner structure of the GRU. The black arrows
(b) Inner structure of the hidden layer; (c) Inner structure of the GRU. The black arrows represent
represent normal flow and the red arrows represent recurrent connection.
normal flow and the red arrows represent recurrent connection.
When using
When using recurrent
recurrent neural
neural network
networkalgorithms,
algorithms,the theordering
orderingofofthe
theevidence
evidencelayers
layers
is critical to the accuracy and predictive power of the final model,
is critical to the accuracy and predictive power of the final model, and sinceand since the GRU can
the GRU
process sequence data through special cyclic states, 24 different input orders
can process sequence data through special cyclic states, 24 different input orders can can be se-be
lected for the four geological evidence layers to model. By analyzing the accuracy,
selected for the four geological evidence layers to model. By analyzing the accuracy, AUC AUC
value, Kappa
value, Kappa value,
value, Matthews
Matthews correlation
correlationcoefficient
coefficient(MCC),
(MCC),and
andrecall
recallrate
rateofof2424different
different
order models, the researchers determined the optimal evidence layer [Link]
order models, the researchers determined the optimal evidence layer ranking. Theresults
results
(Figure 8)
(Figure 8) show
show that
that the
the sequence
sequence beginning
beginningwith
withthe
theporphyry
porphyryintrusion
intrusioncontact
contactzone zonehas
has
better accuracy, while the sequence ending with the porphyry intrusion contact
better accuracy, while the sequence ending with the porphyry intrusion contact zone has zone has
Minerals 2024, 14, 1021 the worst
the worstaccuracy.
[Link] Inthe
themineral
mineralpotential
potentialmap,
map,thethe extremely
extremely high
high anomaly
anomaly areaarea con-
18 of 36
contains
tains 18 deposits, accounting for only 19.23% of the surface, showing
18 deposits, accounting for only 19.23% of the surface, showing good accuracy. good accuracy.

Figure 8.
Figure 8. Mineral
Mineral potential
potential analysis
analysis in
in Baguio
Baguioregion
regionbased
basedon
onGRU
GRUmodel
model(modified
(modifiedfrom
from[97]).
[97]).

experimental results
The experimental results show
show that
that the
theknown
knowngoldgolddeposits
depositsare
aremainly
mainlydistributed
distributedin
in the
the extremely
extremely high
high andand high
high occurrence
occurrence areas
areas after
after the the classification
classification of the
of the prospect
prospect map
map generated by the GRU by the quantile discontinuous method. The results
generated by the GRU by the quantile discontinuous method. The results of the success of the suc-
cess curve
rate rate curve evaluation
evaluation showshow
that that the GRU
the GRU method
method has has better
better prediction
prediction ability.
ability.

4.4. Application of GAN

Generative adversarial networks are well suited for enhancing geological data, as
they can effectively address the problem of having fewer positive samples. When dealing
with imbalanced datasets, generative adversarial networks (GANs) can capture the com-
Minerals 2024, 14, 1021 18 of 35

4.4. Application of GAN

Generative adversarial networks are well suited for enhancing geological data, as they
can effectively address the problem of having fewer positive samples. When dealing with
imbalanced datasets, generative adversarial networks (GANs) can capture the complex
patterns and dependencies present in the original geological data and generate high-
quality sample data. GANs can generate fake samples that follow the same population
distribution pattern as real samples. GANs have been successfully used in fields such as
image processing and earth science.
In the process of actual prospecting work, it is hard to obtain enough positive samples.
Jordão et al. [113] proposed a geological model for generating borehole samples, realizing
the automatic division of the ore body geological domain based on borehole data by GANs.
Li et al. [114] used GANs to enhance geochemical data from rare earth deposits in southwest
Jiang, China, and made quantitative measurements of the quality of the augmented data.
The test results show that GANs can extract advanced features of real samples and support
the synthesis of enhanced data from random inputs.
Guo et al. [115] used a hybrid deep learning method called the SMOTified GAN to
detect geochemical anomalies associated with mineralization, which uses SMOTE to gener-
ate positive samples, helping to improve the quality of GAN regenerated positive samples.
Firstly, a bagging algorithm was used as the integration construction technology and elm
as the base classifier as the infrastructure. Secondly, the SMOTified GAN oversampling
technique was used to oversample positive samples of geochemical exploration data. Fi-
nally, the generated data were used to determine the thresholds for the classification of
geochemical anomalies associated with polymetallic mineralization.
The results (Figure 9) show that the high-level anomaly of model recognition is
23.64%. Moreover, the geochemical anomalies associated with polymetallic mineralization
Minerals 2024, 14, 1021 19 of 36
in the three identified abnormal areas are highly consistent with the regional geological
characteristics and polymetallic metallogenic characteristics of the study area.

Figure 9.
Figure 9. Geochemical
Geochemical anomalies
anomalies associated
associated with
with polymetallic
polymetallicmineralization
mineralizationclassified
classifiedbybythe
the
SMOTified GAN (modified from [115]).
SMOTified GAN (modified from [115]).

4.5. Application
4.5. Application of Mixed Algorithm
Algorithm
Deep learning
Deep learning has a strong ability
ability in
in data
data mining,
mining,and
anddifferent
differentdeep
deeplearning
learningalgo-
algo-
rithms have
rithms have slightly
slightly different
different capabilities
capabilities and
and focuses
focuses in
in practical
practicalapplications.
[Link]
Withthe
the
continuousdevelopment
continuous developmentofoftraditional
traditionalmachine
machinelearning
learningandand deep
deep learning
learning algorithms,
algorithms, the
the combination of different algorithms has become the main way for researchers to avoid
their own defects.
The deep autoencoder can be directly used for prospecting prediction. However,
since the noise of its own data is generally large, and the prediction results are easily af-
fected by noise, combining it with the convolutional neural network can help eliminate
the influence of noise. Zhang et al. [116] use the Convolutional Autoencoder (CAE) to learn
meaningful abstract representations of multi-source geographic information at different
Minerals 2024, 14, 1021 19 of 35

combination of different algorithms has become the main way for researchers to avoid their
own defects.
The deep autoencoder can be directly used for prospecting prediction. However,
since the noise of its own data is generally large, and the prediction results are easily
affected by noise, combining it with the convolutional neural network can help eliminate
the influence of noise. Zhang et al. [116] use the Convolutional Autoencoder (CAE) to learn
meaningful abstract representations of multi-source geographic information at different
scales, and determine the degree of influence of reconstruction errors of each data variable
by reducing the removal of evidence variables. The types of geological data that have a
greater influence on the reconstruction error are analyzed and the factors that have a greater
correlation with mineralization are determined. The core of the CAE is to combine the
convolutional operation with the autoencoder structure to form the convolutional encoder
and the convolutional decoder, so as to optimize the training results. The success rate curve
shows that the predicted potential mineralization area accounts for 23.8% of the study area
and contains 77.8% of known gold deposits.
Xie et al. [80] used the combination of the autoencoder and the GAN to conduct
metallogenic prediction in the Lhasa area, which not only ensured the stability of the
training process, but also ensured the clarity of the training results. The AUC value of the
model reached 0.95. The Convolutional neural network mixed the channel information
in the process of feature extraction. The combination of the CAE and CNN [29,116] can
remove the data types in the evidence layer that have little influence on the reconstruction
error, and determine the factors with greater correlation with mineralization. The prediction
accuracy AUC value can reach 0.863 and 0.908 in the two regions, respectively.
In order to solve the problem of the lack of labeled data in deep learning algorithms,
Li et al. [114] proposed a data enhancement method based on generative adversarial net-
works, used the enhanced data to carry out research on the convolutional neural network
Minerals 2024, 14, 1021 algorithm, and conducted prospecting prediction analysis on rare earth deposits in 20 south-
of 36

ern Jiangxi Province, China. The results (Figure 10) show that the GAN can learn the
internal structural features of real samples, and can synthesize enhanced data from random
inputs. The model training
inputs. training accuracy
accuracy reaches
reaches 99.7%,
99.7%,and
andthe
thevalidation
validationaccuracy
accuracyreaches
reaches
98.9%. The research also shows that
98.9%. that although
although“black
“blackbox”
box”isisaaproblem
problemthat
thatdeep
deeplearning
learning
cannot avoid,
cannot avoid, the analysis of
of prediction
predictionresults
resultscombined
combinedwith
withgeological
geologicaland
andgeochemical
geochemical
data can
data can show
show the reliability and accuracy
accuracy of
of deep
deep learning
learningalgorithm
algorithmapplication.
application.

Figure 10.
Figure 10. Regolith-hosted
Regolith-hostedREE
REEdeposits
depositsprospectivity
prospectivitymap
mapderived
derivedby
bythe
theGAN
GANand
andCNN
CNN(modified
(modi-
fied from [114]).
from [114]).

The combination of different algorithms will provide more ideas and methods for
mineral prospectivity mapping.

5. Discussion
5.1. Preprocessing of Geological Data
Minerals 2024, 14, 1021 20 of 35

The combination of different algorithms will provide more ideas and methods for
mineral prospectivity mapping.

5. Discussion
5.1. Preprocessing of Geological Data
Geological data are generally text data, geophysical and geochemical data are often
point data, and remote sensing data are image data. Different data types need to be
preprocessed in different ways when prospecting predictions are made. The uses of various
data types are shown in Table 2.

Table 2. Applications of different data types in MPM.

Data Type Application Examples

Strata and magmatic rocks Gao et al. [25], Li et al. [117], Li et al. [118], Li et al. [114], Xie et al. [80], Farahbakhsh et al. [84]
Li et al. [117], Li et al. [118], Yang et al. [87], Zhang et al. [116], Yang et al. [9], Yang et al. [4],
Geological structure
Wu et al. [52], Xie et al. [80], Farahbakhsh et al. [84]
Geophysical data Li et al. [117], Li et al. [36], Xie et al. [80], Farahbakhsh et al. [84]
Xiong et al. [30], Zuo et al. [31], Chen et al. [119], Zhang et al. [81], Li et al. [102], Li et al. [117],
Geochemical data Luo et al. [120], Yang et al. [87], Zhang et al. [29], Gao et al. [107], Yang et al. [9], Yang et al. [4],
Li et al. [37], Li et al. [114], Fu et al. [27], Wu et al. [52], Li et al. [36], Xie et al. [80],
Farahbakhsh et al. [84]
Remote sensing image data Zhao et al. [98], Zidan et al. [68], Fu et al. [27], Farahbakhsh et al. [84]

Geological data generally do not include digital information, and it is difficult for
machine learning algorithms to read these text data; geological data use generally two
types of methods. One is to select ore-controlling strata and magmatic rocks closely related
to mineralization as geological data sources, define different lithologies as different values,
and simply classify according to lithology; strata and magmatic rock data mostly adopt
this method. Zheng et al. [35] classify different strata according to 1, 2, 3. . . The unknown
geologic body is coded as 0, and the lithology value directly defined during grid training is
taken as the grid value. The other type is interpolated according to the distance between
strata, structures, and known deposits, the buffer distance is delimited according to the
distance size, and the distance value is used directly as the grid value. Researchers often
measure the impact of geological formations using the distance from the target location to
the structure, converting the data into a distance buffer map that retains distance, position,
and orientation information in an image that the machine can recognize. The types of buffer
distance graph mainly include the discrete buffer distance graph and continuous buffer
distance graph. In the discrete buffer distance graph, the same distance value is in the
same “step size” [117,121,122], which simplifies the distance information and makes the
calculation more convenient, but this method will reduce the accuracy of the construction
information expression. The continuous buffer distance graph uses the continuous value to
represent the distance between the target point and the structure, and the result is more
accurate and complete [9,22]. Xiong et al. [121], Sun et al. [22], and Yang et al. [9] used
the continuous buffer distance to measure the influence range of the geological structure,
which better preserved the detailed information of the geological structure in the image,
and improved the ability of deposit prediction. In addition, Sun et al. [22] also used the
distance between the magma intrusion contact site and the target location and the density
of regional faults as the evidence layer of geological characteristics to participate in the
modeling. Li et al. [102] used convolutional neural networks to explore the coupling
relationship between geological data such as strata, faults, and water systems in the study
area and the mining area. In addition, using a natural language model to process earth
science text has certain potential in mineral prospect modeling, and has been used in some
meaningful applications [123].
Minerals 2024, 14, 1021 21 of 35

It is worth noting that in the process of geological data application, most researchers
did not consider the comprehensive use of the relevant characteristics of the whole process
of deposit formation, such as source, transport, trap, sedimentation and enrichment, weath-
ering and denudation, etc., and the data types selected were relatively simple, which may
have a certain impact on the predicted results. Therefore, it is also necessary to strengthen
the exploration of the content, method, and form of geological data types used in deep
learning prospecting.
The interpolation of point data sets into raster plots is a common method in geochemi-
cal mapping, and the most common method is inverse distance weighted interpolation. The
inverse distance weighted interpolation method takes the distance between the interpola-
tion point and the sample point as the weighted average, and the closer to the interpolation
point, the higher the weight [27]. The data of geochemical discrete points can be interpo-
lated into the geochemical continuous concentration map, which has a good smoothing
effect on the original data. In the past, various univariate or multivariate geochemical sta-
tistical analysis methods were used to describe geochemical data and anomalies, requiring
normal or lognormal distribution of geochemical data; otherwise, geochemical anomalies
could not be correctly identified [81]. In fact, the formation of mineral deposits is a rare
event, and the basic requirement of normal or lognormal distribution of geochemical data
cannot be guaranteed. Traditional multivariate statistical methods often lose their function
when dealing with geochemical data under complex conditions, but deep learning algo-
rithms can learn the deep-level evidence information in the data without data processing.
Sometimes geochemical data are the composition of a certain substance, for example, H is a
part of H2 O, the content of H is correlated with H2 O, and the contribution of H to statistical
analysis is very likely to represent the contribution of H2 O to statistical analysis, which will
lead to closure problems in multivariate statistical analysis [124]. The researchers used the
method of isometric logarithmic ratio transformation to process the raw data.
In addition, geochemical data of rocks or mineral deposits, such as major trace ele-
ments, hydrogen and oxygen isotopes, Re-Os isotopes, U-Th-Pb isotopes, Sr-Nd isotopes,
etc., are not stable and representative of in situ data due to their sampling locations and
sampling principles different from grid sampling of ordinary geophysical and geochemical
data. Therefore, this type of data is generally not used. However, when part of the data
has in situ data characteristics and has a certain correlation with mineralization, it can be
selected as a feature of deep learning to participate in the calculation.
The geochemical data often come from or are close to the earth’s surface and may
not necessarily include key ore-controlling geological factors, which can lead to a poor
MPM result [125]. Li et al. [102] made use of the method of coupling geochemical data with
geological data, projected the information of geological data onto geochemical data, and
used deep learning to make better use of geochemical data for prospecting and prediction,
achieving good results and providing us with new ideas for using geological data.
Remote sensing data itself has the characteristics of multi-dimensional numbers, un-
even noise, and so on, which brings many problems to data processing. However, deep
learning can extract useful features from massive remote sensing data, and has great poten-
tial in mineral deposit classification and prospecting prospect prediction. The recognition of
remote sensing images related to mineralization mainly includes the recognition of a linear
ring structure and the recognition of surrounding rock alteration. Zidan et al. [68] used the
deep learning algorithm of the CNN to extract hydrothermal alteration regions related to
porphyry copper deposits based on ASTER images, and delineated the scope for further
determining the potential areas for prospecting. Sun et al. [22] used the iron oxide alteration
and mud alteration obtained from Landsat ETM+ images as evidence layers and other
geological data to conduct deep learning modeling and delineate the prospecting target
area, providing an important basis for further prospecting and exploration. Fu et al. [27]
used the CNN algorithm based on GF-5 remote sensing images, ASTER images, and geo-
chemical data to predict the mineral prospect area in the Duolong region of Tibet, and
used alteration minerals such as dolomite and kaolin, identified by the short-wave infrared
Minerals 2024, 14, 1021 22 of 35

band, as the evidence layer to construct the CNN model for prospecting prediction. The
results show that the alteration zone extracted from remote sensing images has good indi-
cation significance for prospecting prediction. Therefore, the processing of remote sensing
data mainly uses a variety of image processing techniques to extract geological structure
information and alteration information as data layers for deep learning modeling.
By summarizing the previous studies, we find that geochemical data, geological data,
and remote sensing data are widely used in prospecting prediction, the research methods
are increasing, and the varieties are becoming more and more abundant. As an impor-
tant means of prospecting and exploration, geophysical methods have more and more
diversified physical property types and data forms. As geophysical methods play an
increasingly important role in deep prospecting, geophysical data as the evidence layer
of deep learning algorithms can help improve the accuracy and generalization ability of
the model. Sun et al. [22] used gravity data, aeromagnetic exploration data, and resistivity
data in the Tongling area of Anhui Province, China to generate a magnetic anomaly pole
map, lithology density map, −800m resistivity interpretation map, and other geological
data as data layers. Based on the source, transport, and storage processes of mineralization,
the support vector machine, random forest, and machine learning algorithms were used to
model and analyze the ore prospecting prediction, the ore prospecting prediction in the
study area was evaluated, and the favorable metallogenic prediction area was delineated.
Wang et al. [96] used aeromagnetic data combined with regional granite mass, regional
major faults, and geochemical data to predict the iron ore prospecting potential in Fujian
Province, China, and the results showed the feasibility and reliability of prospecting predic-
tion by using aeromagnetic data. However, due to the multi-solution of geophysical data,
there are still some limitations in geological prospecting prediction, and the application
of geophysical data in deep learning prospecting is not extensive enough. The next step
is to combine geophysical data with geological data to improve the coupling ability of
geophysical data and ore deposits.

5.2. Improvement of Data Enhancement Method in Mineral Prospectivity Mapping

Machine learning for prospecting prediction is essentially a binary classification prob-
lem, and the result is to classify each area as promising or unpromising [18,22]. In areas
with few ore deposits or where no ore deposits have been found, there are not enough
data samples to reach the amount of data required by deep learning, and there is poor
extraction of ore-related features, poor generalization ability of the resulting model, and
even non-convergence of prediction results. Therefore, sufficient training samples are the
key to the success of the model. In order to ensure the robustness of the model, the positive
and negative samples in the sample set need to be relatively balanced. However, in reality
and prospecting practice, the samples with ore deposits are much larger than the samples
without ore deposits, resulting in the imbalance between positive and negative samples.
Due to the small number of geological data samples, it is an urgent problem to enhance
them in machine learning algorithms.
Data enhancement is the use of a series of methods to expand the amount of data to
overcome the lack of deep learning training samples. The traditional data enhancement
methods generally use inversion, distortion, rotation, clipping, and other deformation
operations to increase the number of samples, but in geological prospecting work, these
methods cannot increase the effective training samples, and may even make the final result
progress in the opposite direction. Therefore, researchers continue to develop more feasible
data enhancement methods in geological work, mainly including the sliding window,
clipping and patching, adding random noise, etc., and with the development of deep
learning, the CAE and GAN can also play an important role in data enhancement due to
their excellent data generation capabilities. Table 3 lists the application of different data
enhancement methods in prospecting prediction.
Minerals 2024, 14, 1021 23 of 35

Table 3. Application of different data enhancement methods.

Data Enhancement Application Examples

Sliding window Li et al. [37], Li et al. [36]
Adding random zero noise Li et al. [117], Yang et al. [4], Li et al. [36], Wu et al. [52]
Clipping and repairing Yang et al. [9]
Pixel-to-feature Zhang et al. [126]
Autoencoder Zhang et al. [116]

Sliding window is a commonly used data enhancement method. Core areas are
selected at each evidence layer in turn, a window smaller than the core area is used to
slide in the area for resampling, and then resampling results of each evidence layer are
combined. The generated window remains in the core area until the required number
of samples is generated. The advantage of sliding windows is that new data can carry
all the information in the original evidence layers and resampling. Wu et al. [52] use
sliding window technology to enhance data samples and solve the problem of scarcity and
imbalance of label data in deep learning environments.
Adding random zero noise is another processing method. By adding zero noise points
to the original evidence layer and combining the original evidence layer to achieve the
purpose of increasing data, this method can maintain the original geographical location,
correlation, and other relative information of the data, and can maintain the integrity of
the data and highlight the overall characteristics of the data. However, it is necessary to
consider the ratio of random zero noise when using it. Adding different ratios of zero noise
will make the generated sample data carry different characteristics. The purpose of adding
zero noise is to generate more samples to expand the data, and from the experience of
previous people, the random noise ratio is set between 5% and 10% for the best effect.
In addition, Brandmeier et al. [127] increased the number of training samples by
disturbing the location of the deposit and adding data points around the real deposit.
Yang et al. [9,87] used a clipping and repairing method to generate additional training
samples. This method not only ensured that the expanded sample data and the test
data had similar deposit indication characteristics and deposit location, but also ensured
that the expanded sample data and the test data had different combinations of multi-
source geographic information in different spatial locations, which has a good reference
significance. Zhang et al. [126] used the pixel-to-feature method to reassemble the pixels of
the sample to generate enough training samples.
With the development of deep learning algorithms, researchers use the GAN and other
algorithms based on sample data to generate more usable sample sets, which can retain
deeper features in the original samples. Wu et al. [52] add random noise to the original
data, combine corresponding label information from real samples to generate basic data,
and use the generated adversarial network for data enhancement, which is essentially a
comprehensive application of adding random noise and the GAN. Li et al. [114] also used
the GAN to enhance the geochemical data, which achieved good results.

5.3. Deep Learning in Mineral Prospectivity Mapping

Compared with traditional statistical analysis methods such as the evidence weight
method, information content method, regression analysis, support vector machine, random
forest, and other traditional machine learning algorithms, deep learning can directly extract
key features from the original data without the need for manual design or selection in
advance. By building multi-level neural networks, deep learning is able to capture nonlinear
relationships in data, so it has strong data fitting ability, which makes deep learning
achieve better results when solving complex problems. When the geological data are
comprehensively utilized, the number of channels is large, and the deep learning algorithm
can fully meet the practical application of prospecting prediction. Fu et al. [27] used remote
sensing images and geochemical data to make prospecting predictions of the Duolong
porphyry copper mine in Xizang, China. The AUC value of the CNN model was 0.982,
Minerals 2024, 14, 1021 24 of 35

which was better than that of random forest and the support vector machine (0.973 and
0.959, respectively). Wang et al. [96] conducted prospecting prediction in iron ore deposits
in Fujian, China. According to the success rate curve, the recurrent neural network and
logistic regression model accounted for more than 90% and 80% of iron ore deposits,
respectively, in 10% prospective areas, and the linear regression results were significantly
better. According to previous studies, deep learning algorithms have been applied to
various types of minerals such as Au, Fe, Cu, W-Sn, Pb-Zn, REE, etc., with good effect, and
their future application prospects are very wide.
In the field of mineral prospectivity mapping, the application of deep learning algo-
rithms is gradually increasing, which significantly improves the efficiency and accuracy
of mineral resource exploration. Different algorithms are suitable for different application
scenarios because of their unique advantages. For example, GANs are mainly used in
data enhancement, DAEs are used in data enhancement and denoising, RNNs are widely
used in text information extraction and time series data analysis, and CNNs are widely
used in geological image analysis and processing to identify mineralization features and
geological structures due to their excellent performance in image processing, providing an
important basis for prospecting prediction. Table 4 lists the application examples of deep
learning algorithms in prospecting prediction. In terms of data volume, compared with
traditional statistical analysis methods, deep learning has a very strong data processing
ability, and geological data processing of mineral deposits, mining areas, and regions can
be completed. The number of iterations, learning rate, and batch size of deep learning are
greatly affected by the quality of the original data. Due to the imbalance of positive and
negative samples, data noise, and other problems in the original data, it is often necessary
to conduct several iterations to stabilize the model. From the perspective of model accuracy
of deep learning, the AUC value is generally greater than 0.8, and in convolutional neural
networks, the AUC value can even reach more than 0.98, which is far more accurate than
traditional algorithms. It can be seen that deep learning algorithms have the ability to mine
deep features in complex data and hidden associations between data.

Table 4. The practical application of different algorithms in mineral prospectivity mapping.

Algorithm Data Volume Epoch AUC Learning Rate Batch Size

6682 data [30] 100 [80] 0.9 [31] 0.001 [80] 16 [80]
9041 data [81] 200 [30,31,81] 0.85 [81]
DAE
36 data layers [119] 0.89 [116,119,128]
39 data layers [31,128] 0.8
5488 data [32] 40 [52] 0.95 [116] 0.01 [107,126] 12 [27]
7234 data [107] 50 [27] 0.97 [87] 0.0005 [36] 32 [107]
9041 data [116] 30 [36] 0.958 [9] 0.00001 [114] 64 [36]
9 data layers [116] 100 [116,120] 0.944 [126] 0.00005 [52] 128 [99,126]
CNN 11 data layers [9,36,87] 120 [107] 0.982 [27]
14 data layers [52] 500 [32] 0.987 [36]
17 data layers [27] 1000 [9,87]
21 data layers [102] 1200 [114]
39 data layers 2000 [114] data
5 data layers [120] 10 [117] 0.863 [29] 0.001 [80] 16 [80]
14 data layers [52] 40 [52] 0.0001 [29] 64 [117]
GAN 100 [29,80] 0.00001 [117] 128 [29]
2000 [114] 0.00005 [52]
13,740 data [99] 200 [96] 0.0001 [99] 1 [97]
RNN 50 bands [98] 600 [99] 0.0005 [98] 3 [96]
44 data layers [96] 1000 [97,98] 128 [99]

However, we should also note that deep learning algorithms have certain limitations,
specifically including the following questions:
Minerals 2024, 14, 1021 25 of 35

(1) The support for the algorithm by textual geological data. Deep learning algorithms
need to convert some text information into numerical information for computation. In
the application of geological information, the data can only be displayed, but a lot of
geological information will be discarded. For example, when applying fault data, the
distance between different positions and faults will be reflected, but different types of
faults will not be reflected, which is unreasonable in geological understanding. Natural
language processing (NLP) is a branch of computer science and artificial intelligence
that studies how computers understand, generate, and translate human language.
RNNs can process sequence data and are particularly effective for natural language
processing tasks, so the application of RNNs in geological data can be increased in
future research.
(2) The research on geological data enhancement methods. Data enhancement can enrich
data, but the large-scale use of data enhancement methods will increase the complex-
ity of training, sometimes resulting in some categories being “over-enhanced”, and
others being ignored, resulting in an imbalance between categories. Nowadays, many
scholars try to use the combination of transfer learning and deep learning for rock and
ore analysis and mineral prospecting prediction [108,129–131]. The robustness and
generalization ability of transfer learning are proved, the convergence speed of deep
learning is accelerated, and the learning efficiency of the prospecting prediction model
is enhanced. So, we believe that the use of transfer learning and the adversarial gener-
ation network in the future will greatly improve the reliability and logic of enhanced
data, which will greatly improve the accuracy of prospecting prediction.
(3) Avoidance and treatment of model overfitting. Overfitting often occurs when testing
with a small number of training sets, and will greatly affect the test results and the
performance of the model. The most direct way to improve the performance of
neural networks is to increase the number of parameters such as depth and network,
but this will make it easier for the updated network to reach the overfitting state,
especially when the number of positive samples, such as in prospecting prediction,
is limited. At present, in other fields, the methods to solve the overfitting of deep
learning models mainly include data preprocessing, simplifying the model structure,
adding regularization terms, adding Dropout layers, and adjusting model parameters.
In mineral prospectivity mapping, the application of Dropout layers has achieved
good results. Krizhevsky et al. [101] solve the overfitting problem by increasing the
number and size of layers while using the method of Dropout. Li et al. [117] believe
that increasing the number of layers and parameters will increase the computational
amount of learning, and adding Dropout can reduce the training time during the
training process with a large amount of data. Moreover, from the application point of
view [90], after using Dropout, the hidden neurons no longer depend on the existence
of other hidden neurons, and the co-adaptability with other neurons decreases, which
has a good effect on solving the overfitting problem. In the next research process, the
diversity of data can be increased in the data preprocessing process, and the learning
rate, batch size, and other parameters in the model can be adjusted in time.
(4) Adjustment of parameters of the model. In some research examples, we can see that
researchers often need to constantly try to modify various parameters, such as the
learning rate, the epoch, the batch size, and so on, according to the size of data or the
quality of data to obtain better prediction results. This is because the deep learning
model needs to optimize the performance of the model by adjusting parameters
during the training process, so that it can better fit the training data and generalize to
the unseen data. Therefore, we may need to continue to strengthen the self-adaptive
research of the model, so that the model can automatically adjust parameters according
to the original data and the target.
(5) The choice of backbone architecture and the effectiveness of different deep learning
algorithms. Convolutional neural network is the most widely used deep learning
algorithm in mineral prospectivity mapping at present, including LeNet, AlexNet,
Minerals 2024, 14, 1021 26 of 35

VggNet, GoogleNet, ResNet, U-Net and other structural types. The most common
methods of recurrent neural networks include Long Short-Term Memory (LSTM) and
Gated Recurrent Unit (GRU). We need to choose the backbone architecture and deep
learning algorithms according to the actual situation.
(6) The explanation of the model “black box” mechanism. The “black box” mechanism
of deep learning cannot know about the drivers of underlying phenomena and pro-
cesses [125], so the interpretability of model outputs, the relationship between data
input and output, and the internal operation mechanism need further study. At
present, the Google DeepMind team is exploring the “black box” mechanism in deep
learning from the perspective of cognitive psychology [132], but there is still a long
way to go. To enhance the explainability of deep learning, Fu et al. [27] used the
SHAP library in Python to explain the individual output results of deep learning. The
results showed that the different types of data selected for distinguishing between
the presence and absence of minerals in the study area are of significantly different
importance. Many scholars have found that the predictive results of deep learning are
not as good as those of SVM or random forest algorithms in some cases, and a major
reason for this is the type of data used [4,22].

5.4. Accuracy Evaluation Method in Mineral Prospectivity Mapping

Accuracy is the proportion of samples with correct prediction in all samples [36],
and accuracy can directly reflect the proportion of correct classification; the calculation of
accuracy is very simple. However, in the process of mineral prospectivity mapping, the
number of samples with ore is often small, and the accuracy rate will lose its significance
due to the extreme imbalance of positive and negative data. Therefore, other evaluation
methods are often used in the prediction and evaluation of prospecting.
The recall rate represents the proportion of positive samples predicted correctly in
all positive samples, and precision represents the proportion of positive samples with
correct prediction and all samples with correct prediction. Generally, the recall rate and
precision are combined, and the harmonic mean of the recall rate and precision (F1 value)
is used for comprehensive evaluation. The recall rate and precision index are suitable for
the binary classification index, and it is a binary classification calculation model that we
need to determine whether there is an ore deposit in prospecting prediction, so the recall
rate and precision index are suitable for prospecting prediction and evaluation.

TP
R= (5)
TP + FN
TP
P= (6)
TP + FP
2PR
F1 = (7)
P+R
R represents the recall rate, P represents the precision, TP represents the number of
actual true predictions that are true, FN represents the number of actual true predictions
that are false, FP represents the number of actual false predictions that are true, and F1
represents the harmonic mean of the recall rate and precision.
Accuracy function and loss function can also be used to evaluate the accuracy of deep
learning. A better effect needs a smaller loss function and a higher accuracy [35]. Generally,
the receiver operating characteristic curve (ROC) and Area Under the Curve (AUC) are
used for accuracy evaluation.
TP
TPR = (8)
TP + FN
FP
FPR = (9)
FP + TN
Minerals 2024, 14, 1021 27 of 35

TPR represents the true rate, FPR represents the false positive rate, and TN represents
the number of predictions that are false and actually false. It can be seen from the formula
that TPR is the same as the recall rate.
The vertical coordinate of the ROC curve is the true rate, and the horizontal coordinate
is the false positive rate. The TPR is the probability of being judged to be true in the true
sample, and the FPR is the probability of being misjudged to be true in the false sample.
The advantage of the ROC curve is that in the evaluation process, it is not necessary to add
a number as the judgment value of the evaluation, and the accuracy level of the prediction
results can be analyzed only according to the below-line area.
The Kappa coefficient is the proportion of correct classification after the removal of
accidental coincidence probability, and the calculation formula of the Kappa coefficient is

Po − Pe
kappa = (10)
1 − Pe
Po is the accuracy of prediction, that is, the consistency of model prediction results and
actual classification results. Pe is accidental consistency, that is, the consistency between
two variables (in this case, the classification result and the validation sample); even if the
two variables are completely independent, it will not be 0, and there are still cases where
chance causes the two variables to be consistent. Using the Kappa coefficient to evaluate
the reliability of prospecting prediction models can often increase the difference between
different models and make the advantages of models more prominent.
The predicted area curve composed of the prediction rate and area rate is another
method of accuracy evaluation. The intersection point of the two curves of deposit pro-
portion and occupied area proportion is taken as the evaluation standard. When the
intersection point of the two curves is closer to the top position, it means that more deposits
are contained in fewer areas, indicating that the prediction effect is more ideal [4,87,133,134].
In mineral prediction, researchers often use the success rate curve to evaluate the
accuracy of the prospecting prediction model with the success rate of known deposit
prediction, in which different slopes represent different ore-forming potentials, and the
steeper the slope, the more deposits are captured in smaller areas [4,135]. The higher the
success rate and the more deposits captured in a smaller area, the higher the accuracy of
the model and the better the prediction effect.
The accuracy rate is the proportion of correctly classified samples in the total samples,
it is easy to understand and explain, and in the case of a relatively balanced number
of positive and negative samples, accuracy can better reflect the overall performance of
the model. However, when the number of positive and negative samples is unbalanced,
the accuracy will be biased towards the majority class, which may lead to insufficient
recognition ability for the minority class. The accuracy rate cannot reflect the ability of the
model to recognize positive and negative samples alone, so it is necessary to evaluate the
performance of the model in combination with other indicators. The recall rate measures
how many truly positive samples the model is able to identify and is very sensitive to
unbalanced data sets. However, the recall rate may ignore the ability to identify negative
samples, and in the binary classification problem, different thresholds will lead to different
recall rates, so it is necessary to choose the appropriate threshold according to the specific
situation. The PR curve (precision rate–recall curve) is used to evaluate the performance
of the model in a specific category, especially a few categories [96]. It has recall as the
horizontal axis and precision as the vertical axis. The recall rate represents the proportion
of all positive samples that are correctly judged to be positive; the accuracy rate represents
the percentage of all samples judged to be positive that are actually positive. The PR
curve has higher sensitivity when dealing with unbalanced data sets, so it has a good
application prospect for accuracy evaluation in mineral prospectivity mapping. The ROC
curve is mainly used to evaluate the performance of classification models, especially in
binary classification problems, which can provide for the performance of models under
different thresholds. The Kappa coefficient is mainly used to evaluate the model accuracy
Minerals 2024, 14, 1021 28 of 35

of multiple classification problems, especially when the consistency between evaluators

is more common. Success rate curves can be used to show how the model performs at
different thresholds, providing more detail. Nowadays, ROC and AUC, the predicted
area curve, and success rate curve are widely used, respectively, in prospecting prediction
activities (Table 5).

Table 5. Application of different accuracy evaluation methods in MPM.

Accuracy Evaluation Method Application Examples

Brandmeier et al. [127], Yang et al. [9], Yang et al. [4], Li et al. [37], Yin et al. [97],
Accuracy
Li et al. [114], Fu et al. [27]
Sun et al. [22], Chen et al. [128], Li et al. [102], Yin et al. [97], Wang et al. [96], Yang et al. [9],
Recall rate, Precision, and F1
Yang et al. [4], Gao et al. [107], Li et al. [36], Zidan et al. [68], Wu et al. [52]
Gao et al. [25], Zuo et al. [31], Xiong et al. [122], Chen et al. [119], Chen et al. [128],
Zhang et al. [81], Chen et al. [119], Chen et al. [128], Sun et al. [22], Zhang et al. [29],
ROC and AUC Luo et al. [120], Luo et al. [120], Zhang et al. [116], Gao et al. [107], Yin et al. [97], Yang et al. [9],
Yang et al. [4], Yang et al. [4], Nathwani et al. [136], Li et al. [36], Xie et al. [80], Fu et al. [27],
Wang et al. [99]
Rodriguez-Galiano et al. [135], Gao et al. [25], Sun et al. [22], Shirmard et al. [67], Yang et al. [4],
Kappa
Yin et al. [97], Yang et al. [9], Li et al. [36], Wu et al. [52]
Xiong et al. [122], Sun et al. [22], Shirmard et al. [67], Zhang et al. [29], Yang et al. [9],
Predicted area curve
Yang et al. [4], Li et al. [36]
Zuo et al. [137], Zuo et al. [138], Rodriguez-Galiano et al. [135], Gao et al. [25], Xu et al. [100],
Success rate curve
Li et al. [118], Wang et al. [96], Yin et al. [97], Yang et al. [4], Yang et al. [9], Wang et al. [99]

At the same time, the confusion matrix, mean squared error series, and Brier score
are often applied to deep learning tasks. The confusion matrix is a specific table used to
visualize the performance of an algorithm, showing how the actual class compares to the
predicted class. The overall performance of the model can be assessed by size; the larger the
value on the diagonal, the better. But the confusion matrix may not work well for extremely
unbalanced data sets, as the performance of a few classes may be overshadowed by the
performance of the many classes. Therefore, it is necessary to use this method carefully
when making prospecting predictions. Mean squared error (MSE), Root mean squared error
(RMSE), and Mean absolute error (MAE) are used to measure the difference between the
predicted value and the actual value. The smaller the MSE and RMSE, the more accurate
the model prediction, while MAE directly reflects the average level of prediction error.
MSE is very sensitive to large deviations between predicted and actual values. Since the
errors are squared, larger errors will be penalized more severely, which helps the model
better capture and reduce these large errors. MSE, RMSE, and MAE are very sensitive to
small probability metallogenic events, but they are widely used in regression problems,
reflecting the overall error level of numerical prediction, so these evaluation methods can
be used carefully in future studies about mineral prospectivity mapping. The Brier score
is the mean square error of the difference between the forecast probability and the actual
result, and is often used to evaluate the degree of calibration and accuracy of probabilistic
models; the closer to 0 the prediction is, the better the prediction is. The Brier score is
sensitive to the change in predicted value near 0 or 1, which has a good application space
in deep learning prospecting prediction. Prediction accuracy evaluation methods are
varied. In practical application, in order to avoid various curves that may exist in a single
accuracy evaluation method, several different accuracy evaluation methods can be used to
comprehensively judge the reliability of the model. In the future, we also need to continue
to try to apply various other accuracy assessment methods to deep learning in mineral
prospectivity mapping.
Minerals 2024, 14, 1021 29 of 35

In addition, we need to consider the influencing factors of accuracy evaluation. By

summarizing the previous research process, we believe that the accuracy of the results is
mainly affected by the following reasons:
(1) Type and accuracy of data. The correlation between the data and the ore deposit and
the number of data types affects the prediction accuracy. Yang et al. [9] selected three
kinds of geological data and eight kinds of geochemical prospecting factors, for a total
of 11 predictive variables, to predict gold deposits in Fengxian County in China by
the CNN, and the training accuracy was 1.00. Liu et al. [33] only selected Pb in the
geochemical element to predict lead–zinc ore deposits in Anhui, China, and a training
accuracy of 0.93 was obtained. The accuracy of the data affects the prediction accuracy
all the same. Li et al. [117] selected 1:200,000 geochemical data to use for mineral
prospectivity mapping in the southwestern Fujian Province, China, and the accuracy
was 0.95. Using 1:50,000 stream sediment geochemical survey data, Fu et al. [27]
predicted the deposit with an accuracy of 0.993. The study of Zuo [58] shows that the
size of different scales has a slight influence on metallogenic prediction.
(2) The number and distribution of known deposits. It is clear that the number of known
mineral sites in the study area determines the prediction results. More importantly, due
to the spatial heterogeneity of the deposit itself, the spatial distribution characteristics
of known deposits also affect the prediction results. Therefore, collecting more com-
prehensive ore deposits in the study area will be helpful for prospecting prediction.
(3) Types of algorithms. The metallogenic systems and processes under different re-
gional frameworks are discrepant, so we should select the data type according to the
characteristics of the study area to be used for metallogenic prediction, then select
targeted deep learning algorithms according to different data characteristics. Luo
et al. [120] efficiently extracted anomalies from geochemical data using the GAN, and
the corresponding AUC was 0.893. Wang et al. [96] used a Long Short-Term Memory
network to extract and integrate the deep-level geological prospecting information
among the weighted evidence layers, and almost all known iron ore deposits de-
veloped in delineated high prospective areas. We believe that the selection of deep
learning algorithms should rely on the comprehensive consideration of data types and
regional characteristics.
Therefore, when applying deep learning to mineral prospecting mapping, we should
first collect data comprehensively and accurately to ensure that the type of data is compre-
hensive and the accuracy is reliable, and then carefully consider the selection of data and
the application of methods according to the distribution characteristics of known deposits.

6. Conclusions
As a new data-driven model, deep learning algorithms can directly extract key features
from the original data by building multi-layer neural networks, which can capture nonlinear
relationships and demonstrate powerful data fitting capabilities. At present, they are
widely used in geological prospecting and prediction, and applied to a certain extent in
various ore deposits, with good results and optimistic prospects for future application.
Compared with traditional prospecting prediction, deep learning algorithms have obvious
advantages, and different types of deep learning algorithms, including the DAE, CNN,
RNN, GAN, etc., have enhanced the development of prospecting prediction methods to
varying degrees, and are of great significance to mineral development. Integrated methods
currently used in exploration projects, such as integrated geophysical inversion methods
and joint optimization methods, can also be integrated with deep learning in mineral
prospectivity mapping in the future.
Multivariate geological data, data enhancement, and deep learning algorithms are
three important components of deep learning-based mineral prospectivity mapping. How-
ever, at present, there are some challenges in mineral prospectivity mapping using deep
learning, mainly including the poor quality of geological basic data, the applicability of data
Minerals 2024, 14, 1021 30 of 35

enhancement methods, the interpretability of deep learning algorithms, and the selection
of prediction accuracy evaluation methods.
The application of deep learning in prospecting prediction is very effective, the
prospect is objective, and it can provide new ideas for future prospecting. The main re-
search directions of future deep learning in mineral prospectivity mapping are the category
extension and processing method of geological data, the further study of data enhancement
methods, and the comprehensive application of deep learning algorithms to give full play
to their respective advantages. Solving these problems will help deep learning make greater
progress in the field of mineral prospectivity mapping.

Author Contributions: Conceptualization, Y.C., G.G. and K.S.; formal analysis, K.S., Y.Z. and
Z.L.; writing—original draft preparation, K.S.; writing—review and editing, K.S., Y.C. and W.Z.;
supervision, J.G., Z.S., Z.L. and Z.Z. All authors have read and agreed to the published version of
the manuscript.
Funding: This research was funded by the Program of China Geological Survey (project numbers
DD20243184, DD20230591, DD20243187).
Conflicts of Interest: The authors declare no conflicts of interest.

References
1. Zhang, S. Multi-Geoinformation Integration for Mineral Prospectivity Mapping in the Hezuo-Meiwu District, Gansu Province.
Ph.D. Thesis, China University of Geoscience, Beijing, China, 2022.
2. Zhao, P. Quantitative mineral prediction and deep mineral. Earth Sci. Front. 2007, 14, 001–010.
3. Xiao, K.; Ding, J.; Liu, R. The Discussion of Three-part Form of Non-fuel Mineral Resource Assessment. Geol. Rev. 2006, 52,
793–798. [CrossRef]
4. Yang, N.; Zhang, Z.; Yang, J.; Hong, Z. Mineral Prospectivity Prediction by Integration of Convolutional Autoencoder Network
and Random Forest. Nat. Resour. Res. 2022, 31, 1103–1119. [CrossRef]
5. Carranza, E.J.M.; Laborte, A.G. Data-driven predictive mapping of gold prospectivity, Baguio district, Philippines: Application of
Random Forests algorithm. Ore Geol. Rev. 2015, 71, 777–787. [CrossRef]
6. Carranza, E.J.M. Geocomputation of mineral exploration targets. Comput. Geosci. 2011, 37, 1907–1916. [CrossRef]
7. Porwal, A.; Carranza, E.J.M. Introduction to the Special Issue: GIS-based mineral potential modelling and geological data analyses
for mineral exploration. Ore Geol. Rev. 2015, 71, 477–483. [CrossRef]
8. Zhang, D. Spatially Weighted Technology for Logistic Regression and Its Application in Mineral Prospective Mapping.
Ph.D. Thesis, China University of Geoscience, Wuhan, China, 2015.
9. Yang, N.; Zhang, Z.; Yang, J.; Hong, Z. Applications of data augmentation in mineral prospectivity prediction based on
convolutional neural networks. Comput. Geosci. 2022, 161, 105075. [CrossRef]
10. Singer, D.A. Basic concepts in three-part quantitative assessments of undiscovered mineral resources. Nonrenew. Resour. 1993, 2,
69–81. [CrossRef]
11. Zhao, P.; Hu, J.; Li, Z. The theory and practices of statistical prediction for mineral deposits. Earth Sci.- J. Wuhan Coll. Geol. 1983, 4,
107–121.
12. Cheng, Q. Ideas and methods for mineral resources integrated prediction in covered areas. Earth Sci.- J. Wuhan Coll. Geol. 2012, 37,
1109–1125.
13. Agterberg, F.P.; Cheng, Q. Conditional Independence Test for Weights-of-Evidence Modeling. Nat. Resour. Res. 2002, 11, 249–255.
[CrossRef]
14. Cheng, Q. BoostWofE: A New Sequential Weights of Evidence Model Reducing the Effect of Conditional Dependency. Math.
Geosci. 2015, 47, 591–621. [CrossRef]
15. Chen, S. Research of Multiple Geoscience Information Prospecting Prediction in Xikuangshan Antimony Ore Field. Ph.D. Thesis,
China University of Geoscience, Beijing, China, 2012.
16. Li, X.; Yuan, F.; Zhang, M.; Jia, C.; Jowitt, S.; Ord, A.; Zheng, T.; Hu, X.; Li, Y. Three-dimensional mineral prospectivity modeling
for targeting of concealed mineralization within the Zhonggu iron orefield, Ningwu Basin, China. Ore Geol. Rev. 2015, 71, 633–654.
[CrossRef]
17. Porwal, A.; González-Álvarez, I.; Markwitz, V.; McCuaig, T.C.; Mamuse, A. Weights-of-evidence and logistic regression modeling
of magmatic nickel sulfide prospectivity in the Yilgarn Craton, Western Australia. Ore Geol. Rev. 2010, 38, 184–196. [CrossRef]
18. Zuo, R.; Carranza, E.J.M. Support vector machine: A tool for mapping mineral prospectivity. Comput. Geosci. 2011, 37, 1967–1975.
[CrossRef]
19. Shabankareh, M.; Hezarkhani, A. Application of support vector machines for copper potential mapping in Kerman region, Iran.
J. Afr. Earth Sci. 2017, 128, 116–126. [CrossRef]
Minerals 2024, 14, 1021 31 of 35

20. Chen, Y.; Wu, W. Application of one-class support vector machine to quickly identify multivariate anomalies from geochemical
exploration data. Geochem. Explor. Environ. Anal. 2017, 17, 231–238. [CrossRef]
21. Chen, Y.; Wu, W. Mapping mineral prospectivity by using one-class support vector machine to identify multivariate geological
anomalies from digital geological survey data. Aust. J. Earth Sci. 2017, 64, 639–651. [CrossRef]
22. Sun, T.; Chen, F.; Zhong, L.; Liu, W.; Wang, Y. GIS-based mineral prospectivity mapping using machine learning methods: A case
study from Tongling ore district, eastern China. Ore Geol. Rev. 2019, 109, 26–49. [CrossRef]
23. Carranza, E.J.M.; Laborte, A.G. Random forest predictive modeling of mineral prospectivity with small number of prospects and
data with missing values in Abra (Philippines). Comput. Geosci. 2015, 74, 60–70. [CrossRef]
24. Wang, Z.; Zuo, R.; Dong, Y. Mapping geochemical anomalies through integrating random forest and metric learning methods.
Nat. Resour. Res. 2019, 28, 1285–1298. [CrossRef]
25. Gao, Y.; Zhang, Z.; Xiong, Y.; Zuo, R. Mapping mineral prospectivity for Cu polymetallic mineralization in southwest Fujian
Province, China. Ore Geol. Rev. 2016, 75, 16–28. [CrossRef]
26. Zhang, F.M.A. Research on Deep Learning Extraction Method in Open Mining Area Based on Multi-Source Remote Sensing Images; Anhui
University: Hefei, China, 2020.
27. Fu, Y.; Cheng, Q.; Jing, L.; Ye, B.; Fu, H. Mineral Prospectivity Mapping of Porphyry Copper Deposits Based on Remote Sensing
Imagery and Geochemical Data in the Duolong Ore District, Tibet. Remote Sens. 2023, 15, 439. [CrossRef]
28. Feng, J.; Zhang, Q.; Luo, J. Deeply mining the intrinsic value of geodata to improve the accuracy of predicting by quantitatively
optimizing method for prospecting target areas. Earth Sci. Front. 2022, 29, 403–411. [CrossRef]
29. Zhang, C.; Zuo, R. Recognition of multivariate geochemical anomalies associated with mineralization using an improved
generative adversarial network. Ore Geol. Rev. 2021, 136, 104264. [CrossRef]
30. Xiong, Y.; Zuo, R. Recognition of geochemical anomalies using a deep autoencoder network. Comput. Geosci. 2016, 86, 75–82.
[CrossRef]
31. Zuo, R.; Xiong, Y. Big Data Analytics of Identifying Geochemical Anomalies Supported by Machine Learning Methods. Nat.
Resour. Res. 2018, 27, 5–13. [CrossRef]
32. Shi, L.; Jianping, C.; Jie, X. Prospecting Information Extraction by Text Mining Based on Convolutional Neural Networks–A Case
Study of the Lala Copper Deposit, China. IEEE Access 2018, 6, 52286–52297. [CrossRef]
33. Liu, Y.; Zhu, L.; Zhou, Y. Application of Convolutional Neural Network in prospecting prediction of ore deposits: Taking the
Zhaojikou Pb-Zn ore deposit in Anhui Province as a case. Acta Petrol. Sin. 2018, 34, 3217–3224.
34. Liu, Y. Experimental research on big data mining and intelligent prediction of prospecting target area—Application of convolu-
tional neural network model. Geotecton. Metallog. 2020, 44, 192–202.
35. Zheng, X.; Zhang, M.; Ren, W. Application of convolution neural networks in gold exploration and prediction in Shandong
Province. Geophys. Geochem. Explor. 2023, 47, 1433–1440.
36. Li, Q.; Chen, G.; Luo, L. Mineral prospectivity mapping using attention-based convolutional neural network. Ore Geol. Rev. 2023,
156, 105381. [CrossRef]
37. Li, Y.-S.; Chai, S.-L. Soil geochemical prospecting prediction method based on deep convolutional neural networks-Taking Daqiao
Gold Deposit in Gansu Province, China as an example. China Geol. 2022, 5, 71–83.
38. Du, Y.; Cao, Y.; Huo, D.; Li, D.; Gao, Z. Petrology and geochemistry of Silurian-Triassic sedimentary rocks in the Tongling area;
Constraints on the genesis of stratabound skarn deposits. Earth Sci. Front. 2014, 21, 228–239.
39. Ling, Q.; LIU, C. REE behavior during formation of st ra ta-bound skarn and related deposit: A case study of Dongguashan ska
rn deposit in Anh ui province, China. Acta Petrol. Sin. 2003, 19, 192–200.
40. Deng, Y.; Song, X.; Jie, W.; Yuan, F.; Zhao, Z.; Wei, S.; Zhu, J.; Kang, J.; Wang, K.; Liang, Q.; et al. Determination of sedimentary
ages of strata in the Huangshan-Jingerquan mineralization belt and its geological significance. Acta Geol. Sin. 2021, 95, 362–376.
[CrossRef]
41. Xue, S.; Wang, Q.; Tang, D.; Mao, Y.; Yao, Z. Contamination mechanism of magmatic Ni-Cu sulfide deposits in orogenic belts:
Examples from Permian Ni-Cu deposits in Tianshan-Beishan. Miner. Depos. 2022, 41, 1–20.
42. Grobler, D.F.; Brits, J.A.N.; Maier, W.D.; Crossingham, A. Litho- and chemostratigraphy of the Flatreef PGE deposit, northern
Bushveld Complex. Miner. Depos. 2019, 54, 3–28. [CrossRef]
43. Li, L.-J.; Li, D.-X.; Mao, X.-C.; Liu, Z.-K.; Lai, J.-Q.; Su, Z.; Ai, Q.-X.; Wang, Y.-Q. Evolution of magmatic sulfide of the giant
Jinchuan Ni-Cu deposit, NW China: Insights from chalcophile elements in base metal sulfide minerals. Ore Geol. Rev. 2023,
158, 105497. [CrossRef]
44. Mukasa, S.B.; Vidal, C.C.E.; Injoque-Espinoza, J. Lead isotope-bearing on the metallogenesis of sulfide ore deposits in central and
southern Peru. Econ. Geol. 1990, 85, 1438–1446. [CrossRef]
45. Elongo, V.; Lecumberri-Sanchez, P.; Legros, H.; Falck, H.; Adlakha, E.E.; Roy-Garand, A. Paragenetic constraints on the Cantung,
Mactung and Lened tungsten skarn deposits, Canada: Implications for grade distribution. Ore Geol. Rev. 2020, 125, 103677.
[CrossRef]
46. Ord, A.; Hobbs, B.E.; Lester, D.R. The mechanics of hydrothermal systems: I. Ore systems as chemical reactors. Ore Geol. Rev.
2012, 49, 1–44. [CrossRef]
Minerals 2024, 14, 1021 32 of 35

47. Yang, L.; Yang, W.; Zhang, L.; Gao, X.; Shen, S.; Wang, S.; Xu, H.; Jia, X.; Deng, J. Developing structural control models for
hydrothermal metallogenic systems: Theoretical and methodological principles and applications. Earth Sci. Front. 2024, 31,
239–266.
48. Liu, Z. Ore-controlling structure of Withnell gold deposit, Pilbara Craton, Australia. J. Geol. 2021, 45, 154–160. [CrossRef]
49. Song, M.; Wang, B.; Song, Y.; Li, J.; Zheng, J.; Li, S.; Fan, J.; Yang, Z.; He, C.; Gao, M.; et al. Spatial coupling relationship between
faults and gold deposits in the Jiaodong ore concentration area and the effect of thermal doming-extension on mineralisation. Ore
Geol. Rev. 2023, 153, 105277. [CrossRef]
50. Lv, Q.; Dong, S.; Tang, J.; Shi, D.; Chang, Y. Multi-scale and integrated geophysical data revealing mineral systems and exploring
for mineral deposits at depth: A synthesis from SinoProbe-03. Chin. J. Geophys. 2015, 58, 4319–4343. [CrossRef]
51. Zhang, S.; Wang, Q.; Luo, Y. An overview on the development of the electrical prospecting method in China. Acta Geophys. Sin.
1994, 37, 408–424.
52. Wu, Y.; Liu, B.; Gao, Y.; Li, C.; Tang, R.; Kong, Y.; Xie, M.; Li, K.; Dan, S.; Qi, K.; et al. Mineral prospecting mapping with
conditional generative adversarial network augmented data. Ore Geol. Rev. 2023, 163, 105787. [CrossRef]
53. Shebl, A.; Abdellatif, M.; Elkhateeb, S.O.; Csámer, Á. Multisource Data Analysis for Gold Potentiality Mapping of Atalla Area
and Its Environs, Central Eastern Desert, Egypt. Minerals 2021, 11, 641. [CrossRef]
54. Shebl, A.; Abdellatif, M.; Hissen, M.; Ibrahim Abdelaziz, M.; Csámer, Á. Lithological mapping enhancement by integrating
Sentinel 2 and gamma-ray data utilizing support vector machine: A case study from Egypt. Int. J. Appl. Earth Obs. Geoinf. 2021,
105, 102619. [CrossRef]
55. Spicer, B. Geophysical signature of the Victoria property, vectoring toward deep mineralization in the Sudbury Basin. Interpret. A
J. Subsurf. Charact. 2016, 4, T281–T290. [CrossRef]
56. Wang, R.; Hao, X.; Hu, L.; Chen, H.; Liu, H.; Chen, F.; Yu, L.; Liu, W.; Fang, L.; Kang, Y. Discovery of skarn iron-rich deposit based
on gravity and magnetic data in the Qihe-Yucheng, Shandong Province: Enlightenment to prospecting of the superdeep coverage
area. Geol. China 2023, 50, 331–346.
57. Wang, S. The new development of theory and method of synthetic information mineral resources prognosis. Geol. Bull. China
2010, 29, 1399–1403.
58. Zuo, R. Exploring the effects of cell size in geochemical mapping. J. Geochem. Explor. 2012, 112, 357–367. [CrossRef]
59. Luo, X.; Yang, X. Study and prospecting prediction of hidden deposits by geoelectrochemical survey. Geol. Explor. 1989, 54, 43–51.
60. Liu, Y.; Luo, X.; Liu, P.; Zheng, C.; Liu, G.; Song, B.; Song, G. Application of geo-electrochemical integration technology to search
for concealed Pb-Zn ore in the Geluqiduishan mining area and its periphery, Inner Mongolia. Geol. Explor. 2018, 54, 1001–1012.
[CrossRef]
61. Yue, D.; Liu, P.; Liao, X.; Chen, J.; Li, J.; Yang, Q.; Yang, X. Research and application of AMT and geo-electrochemical measurements
in deep prospecting of the Murong lithium deposit in Yajiang, western Sichuan Province. Geol. Explor. 2023, 59, 760–773.
62. Yang, Q.; Luo, X.; Yue, D.; Liu, P.; Gao, W.; Wen, M.; Liao, X.; Li, J.; Liang, M.; Liu, Y. Intelligent prospecting method based on
probabilistic neural network: Taking the Murong lithium deposit in Yajiang County of Sichuan Province as an example. Geol.
Explor. 2023, 59, 985–999.
63. Henry, C.D.; John, D.A.; Leonardson, R.W.; McIntosh, W.C.; Heizler, M.T.; Colgan, J.P.; Watts, K.E. Timing of Rhyolite Intrusion
and Carlin-Type Gold Mineralization at the Cortez Hills Carlin-Type Deposit, Nevada, USA. Econ. Geol. 2023, 118, 57–91.
[CrossRef]
64. Yang, B.; Li, C.; Bo, H.; Hou, X.; Su, P.; Fan, S. Geochemical characteristics and genesis of Changhangou crystalline graphite
deposit in Hadamengou area, Inner Mongolia. Miner. Depos. 2023, 42, 444–462. [CrossRef]
65. Min, X.; Pengbo, Q.; Fengwei, Z. Research and application of logging lithology identification for igneous reservoirs based on
deep learning. J. Appl. Geophys. 2020, 173, 103929. [CrossRef]
66. Liu, J.-J.; Liu, J.-C. Integrating deep learning and logging data analytics for lithofacies classification and 3D modeling of tight
sandstone reservoirs. Geosci. Front. 2022, 13, 101311. [CrossRef]
67. Shirmard, H.; Farahbakhsh, E.; Beiranvand Pour, A.; Muslim, A.M.; Müller, R.D.; Chandra, R. Integration of Selective Dimension-
ality Reduction Techniques for Mineral Exploration Using ASTER Satellite Data. Remote Sens. 2020, 12, 1261. [CrossRef]
68. Zidan, U.; Desouky, H.A.E.; Gaber, M.M.; Abdelsamea, M.M. From Pixels to Deposits: Porphyry Mineralization With Multispectral
Convolutional Neural Networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 9474–9486. [CrossRef]
69. Hunt, G.R.; Ashley, R.P. Spectra of altered rocks in the visible and near infrared. Econ. Geol. 1979, 74, 1613–1629. [CrossRef]
70. Shirmard, H.; Farahbakhsh, E.; Müller, R.D.; Chandra, R. A review of machine learning in processing remote sensing data for
mineral exploration. Remote Sens. Environ. 2022, 268, 112750. [CrossRef]
71. Shebl, A.; Abdellatif, M.; Badawi, M.; Dawoud, M.; Fahil, A.S.; Csámer, Á. Towards better delineation of hydrothermal alterations
via multi-sensor remote sensing and airborne geophysical data. Sci. Rep. 2023, 13, 7406. [CrossRef]
72. Haynes, D. The Olympic Dam ore deposit discovery—A personal view. SEG Newsl. 2006, 66, 1–15. [CrossRef]
73. Guo, J.; Zhu, G.; Zou, L.; Wang, R.; Han, Y.; Wang, W.; Xiang, A. Remote sensing geological survey of bauxite deposits in
Dazhuyuan-Longxing area of north Guizhou. Miner. Resour. Geol. 2016, 30, 117–121.
74. Xiao, L. Lithologic and mineral information extraction for bauxite deposits exploration using ASTER data in the Wuchuan-
Zheng’an-Daozhen area, northern Guizhou province, China. J. Mines Met. Fuels 2018, 66, 280–286.
Minerals 2024, 14, 1021 33 of 35

75. van Gerven, M.; Bohte, S. Editorial: Artificial Neural Networks as Models of Neural Information Processing. Front. Comput.
Neurosci. 2017, 11, 114. [CrossRef] [PubMed]
76. Jiao, L.; Yang, S.; Liu, F.; Wang, S.; Feng, Z. Seventy years beyond neural networks: Retrospect and prospect. Chin. J. Comput.
2016, 39, 1697–1716.
77. Majumdar, A. Graph structured autoencoder. Neural Netw. 2018, 106, 271–280. [CrossRef]
78. Hinton, G.E.; Osindero, S.; Teh, Y.-W. A Fast Learning Algorithm for Deep Belief Nets. Neural Comput. 2006, 18, 1527–1554.
[CrossRef]
79. Hinton, G.E.; Salakhutdinov, R.R. Reducing the dimensionality of data with neural networks. Dep. Comput. Sci. Univ. Tor. 2006,
313, 504–507. [CrossRef] [PubMed]
80. Xie, M.; Liu, B.; Wang, L.; Li, C.; Kong, Y.; Tang, R. Auto encoder generative adversarial networks—Based mineral prospectivity
mapping in Lhasa area, Tibet. J. Geochem. Explor. 2023, 255, 107326. [CrossRef]
81. Zhang, S.; Xiao, K.; Carranza, E.J.M.; Yang, F.; Zhao, Z. Integration of auto-encoder network with density-based spatial clustering
for geochemical anomaly detection for mineral exploration. Comput. Geosci. 2019, 130, 43–56. [CrossRef]
82. Vincent Dumoulin, I.B.; Poole, B.; Lamb, A.; Arjovsky, M.; Mastropietro, O.; Courville, A. Adversarially Learned Inference. arXiv
2016, arXiv:1606.00704.
83. Chen, Y.; Wang, Y.; Kirschen, D.; Zhang, B. Model-Free Renewable Scenario Generation Using Generative Adversarial Networks.
IEEE Trans. Power Syst. 2018, 33, 3265–3275. [CrossRef]
84. Farahbakhsh, E.; Maughan, J.; Müller, R.D. Prospectivity modelling of critical mineral deposits using a generative adversarial
network with oversampling and positive-unlabelled bagging. Ore Geol. Rev. 2023, 162, 105665. [CrossRef]
85. Anders Boesen Lindbo, L.; Søren Kaae, S.; Larochelle, H.; Winther, O. Autoencoding beyond pixels using a learned similarity
metric. In Proceedings of the International Conference on Machine Learning, New York City, New York, USA, 19–24 June 2016;
pp. 1558–1566.
86. Liu, W.; Liang, X.; Qu, H. Learning performance of convolutional neural networks with different pooling models. J. Image Graph.
2016, 21, 1178–1190. [CrossRef]
87. Yang, N.; Zhang, Z.; Yang, J.; Hong, Z.; Shi, J. A Convolutional Neural Network of GoogLeNet Applied in Mineral Prospectivity
Prediction Based on Multi-source Geoinformation. Nat. Resour. Res. 2021, 30, 3905–3923. [CrossRef]
88. Li, Z.; Xue, L.; Ran, X.; Li, Y.; Dong, G.; Li, Y.; Dai, J. Intelligent prospect prediction method based on convolutional neural
network: A case study of copper deposits in Longshoushan Area, Gansu Province. J. Jilin Univ. (Earth Sci. Ed.) 2022, 52, 418–433.
89. Sankar, M.; Batri, K.; Parvathi, R. Earliest diabetic retinopathy classification using deep convolution neural networks. Int. J. Adv.
Eng. Technol. 2016, 10, M9.
90. Li, J.; Yuan, Z.; Li, Z.; Ren, A.; Ding, C.; Draper, J.; Nazarian, S.; Qiu, Q.; Yuan, B.; Wang, Y. Normalization and dropout for
stochastic computing-based deep convolutional neural networks. Integration 2019, 65, 395–403. [CrossRef]
91. Wu, H.; Zhao, J. Deep convolutional neural network model based chemical process fault diagnosis. Comput. Chem. Eng. 2018, 115,
185–197. [CrossRef]
92. Chung, J.; Gulcehre, C.; Cho, K.; Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv
2014, arXiv:1412.3555.
93. Bengio, Y.; Simard, P.; Frasconi, P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw.
1994, 5, 157–166. [CrossRef]
94. Van Houdt, G.; Mosquera, C.; Nápoles, G. A review on the long short-term memory model. Artif. Intell. Rev. 2020, 53, 5929–5955.
[CrossRef]
95. Cho, K.; Van Merriënboer, B.; Bahdanau, D.; Bengio, Y. On the properties of neural machine translation: Encoder-decoder
approaches. arXiv 2014, arXiv:1409.1259.
96. Wang, Z.; Zuo, R. Mineral prospectivity mapping using a joint singularity-based weighting method and long short-term memory
network. Comput. Geosci. 2022, 158, 104974. [CrossRef]
97. Yin, B.; Zuo, R.; Xiong, Y. Mineral Prospectivity Mapping via Gated Recurrent Unit Model. Nat. Resour. Res. 2022, 31, 2065–2079.
[CrossRef]
98. Huijie Zhao, K.D.; Li, N.; Wang, Z.; Wei, W. Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory
(LSTM) for Mineral Identification Using Hyperspectral Imagery. Sensors 2020, 20, 6854. [CrossRef]
99. Wang, Z.; Li, T.; Zuo, R. Leucogranite mapping via convolutional recurrent neural networks and geochemical survey data in the
Himalayan orogen. Geosci. Front. 2024, 15, 181–192. [CrossRef]
100. Xu, Y.; Li, Z.; Xie, Z.; Cai, H.; Niu, P.; Liu, H. Mineral prospectivity mapping by deep learning method in Yawan-Daqiao area,
Gansu. Ore Geol. Rev. 2021, 138, 104316. [CrossRef]
101. Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. Commun. ACM 2017,
60, 84–90. [CrossRef]
102. Li, S.; Chen, J.; Xiang, J. Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional
geological big data. Neural Comput. Appl. 2020, 32, 2037–2053. [CrossRef]
103. Li, S.; Chen, J.; Xiang, J.; Zhang, Z.; Zhang, Y. Two-dimensional prospecting prediction based on AlexNet network: A case study
of sedimentary Mn deposits in Songtao-Huayuan area. Geol. Bull. China 2019, 38, 2022–2032.
104. Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556.
Minerals 2024, 14, 1021 34 of 35

105. Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with
convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA,
USA, 7–12 June 2015; Volume 7, pp. 1–9. [CrossRef]
106. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778.
107. Gao, L.; Huang, Y.; Zhang, X.; Liu, Q.; Chen, Z. Prediction of Prospecting Target Based on ResNet Convolutional Neural Network.
Appl. Sci. 2022, 12, 11433. [CrossRef]
108. Boiger, R.; Churakov, S.V.; Ballester Llagaria, I.; Kosakowski, G.; Wüst, R.; Prasianakis, N.I. Direct mineral content prediction
from drill core images via transfer learning. Swiss J. Geosci. 2024, 117, 8. [CrossRef]
109. Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of
the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich,
Germany, 5–9 October 2015; Proceedings, Part III 18; pp. 234–241.
110. Liu, C.; Wang, W.; Tang, J.; Wang, Q.; Zheng, K.; Sun, Y.; Zhang, J.; Gan, F.; Cao, B. A deep-learning-based mineral prospectivity
modeling framework and workflow in prediction of porphyry–epithermal mineralization in the Duolong ore District, Tibet.
Ore Geol. Rev. 2023, 157, 105419. [CrossRef]
111. Mou, N.; Carranza, E.J.; Wang, G.; Sun, X. A Framework for Data-Driven Mineral Prospectivity Mapping with Interpretable
Machine Learning and Modulated Predictive Modeling. Nat. Resour. Res. 2023, 32, 2439–2462. [CrossRef]
112. Wang, D.; Huang, F.; Wang, Y.; He, H.; Li, X.; Liu, X.; Sheng, J.; Liang, T. Regional metallogeny of Tungsten-tin-polymetallic
deposits in Nanling region, South China. Ore Geol. Rev. 2020, 120, 103305. [CrossRef]
113. Jordão, H.; Azevedo, L.; Sousa, A.J.; Soares, A. Generative adversarial network applied to ore type modeling in complex geological
environments. Math. Geosci. 2022, 54, 1165–1182. [CrossRef]
114. Li, T.; Zuo, R.; Zhao, X.; Zhao, K. Mapping prospectivity for regolith-hosted REE deposits via convolutional neural network with
generative adversarial network augmented data. Ore Geol. Rev. 2022, 142, 104693. [CrossRef]
115. Guo, M.; Chen, Y. A SMOTified-GAN-augmented bagging ensemble model of extreme learning machines for detecting geochemi-
cal anomalies associated with mineralization. Geochemistry 2024, 126156. [CrossRef]
116. Zhang, S.; Carranza, E.J.M.; Wei, H.; Xiao, K.; Yang, F.; Xiang, J.; Zhang, S.; Xu, Y. Data-driven mineral prospectivity mapping by
joint application of unsupervised convolutional auto-encoder network and supervised convolutional neural network. Nat. Resour.
Res. 2021, 30, 1011–1031. [CrossRef]
117. Li, T.; Zuo, R.; Xiong, Y.; Peng, Y. Random-Drop Data Augmentation of Deep Convolutional Neural Network for Mineral
Prospectivity Mapping. Nat. Resour. Res. 2020, 30, 27–38. [CrossRef]
118. Li, S.; Chen, J.; Liu, C.; Wang, Y. Mineral Prospectivity Prediction via Convolutional Neural Networks Based on Geological Big
Data. J. Earth Sci. 2021, 32, 327–347. [CrossRef]
119. Chen, L.; Guan, Q.; Feng, B.; Yue, H.; Wang, J.; Zhang, F. A multi-convolutional autoencoder approach to multivariate geochemical
anomaly recognition. Minerals 2019, 9, 270. [CrossRef]
120. Luo, Z.; Zuo, R.; Xiong, Y.; Wang, X. Detection of geochemical anomalies related to mineralization using the GANomaly network.
Appl. Geochem. 2021, 131, 105043. [CrossRef]
121. Xiong, Y.; Zuo, R.; Carranza, E.J.M. Mapping mineral prospectivity through big data analytics and a deep learning algorithm.
Ore Geol. Rev. 2018, 102, 811–817. [CrossRef]
122. Xiong, Y.; Zuo, R. GIS-based rare events logistic regression for mineral prospectivity mapping. Comput. Geosci. 2018, 111, 18–25.
[CrossRef]
123. Atalay, F. Estimation of Fe Grade at an Ore Deposit Using Extreme Gradient Boosting Trees (XGBoost). Min. Metall. Explor. 2024,
41, 2119–2128. [CrossRef]
124. Filzmoser, P.; Garrett, R.G.; Reimann, C. Multivariate outlier detection in exploration geochemistry. Comput. Geosci. 2005, 31,
579–587. [CrossRef]
125. Hronsky, J.M.A.; Kreuzer, O.P. Applying spatial prospectivity mapping to exploration targeting: Fundamental practical issues
and suggested solutions for the future. Ore Geol. Rev. 2019, 107, 647–653. [CrossRef]
126. Zhang, C.; Zuo, R.; Xiong, Y. Detection of the multivariate geochemical anomalies associated with mineralization using a deep
convolutional neural network and a pixel-pair feature method. Appl. Geochem. 2021, 130, 104994. [CrossRef]
127. Brandmeier, M.; Cabrera Zamora, I.G.; Nykänen, V.; Middleton, M. Boosting for Mineral Prospectivity Modeling: A New GIS
Toolbox. Nat. Resour. Res. 2019, 29, 71–88. [CrossRef]
128. Chen, L.; Guan, Q.; Xiong, Y.; Liang, J.; Wang, Y.; Xu, Y. A Spatially Constrained Multi-Autoencoder approach for multivariate
geochemical anomaly recognition. Comput. Geosci. 2019, 125, 43–54. [CrossRef]
129. Li, S.; Liu, C.; Chen, J. Mineral Prospecting Prediction via Transfer Learning Based on Geological Big Data: A Case Study of
Huayuan, Hunan, China. Minerals 2023, 13, 504. [CrossRef]
130. Mantilla-Dulcey, A.; Goyes-Peñafiel, P.; Baez-Rodríguez, R.; Khurama, S. Porphyry-type mineral prospectivity mapping with
imbalanced data via prior geological transfer learning. Gondwana Res. 2024, 136, 236–250. [CrossRef]
131. Wu, B.; Li, X.; Yuan, F.; Li, H.; Zhang, M. Transfer learning and siamese neural network based identification of geochemical
anomalies for mineral exploration: A case study from the CuAu deposit in the NW Junggar area of northern Xinjiang Province,
China. J. Geochem. Explor. 2022, 232, 106904. [CrossRef]
Minerals 2024, 14, 1021 35 of 35

132. Ritter, S.; Barrett, D.G.T.; Santoro, A.; Botvinick, M.M. Cognitive psychology for deep neural networks: A shape bias case study.
Int. Conf. Mach. Learn. 2017, 2940–2949.
133. Yousefi, M.; Carranza, E. Prediction–area (P–A) plot and C–A fractal analysis to classify and evaluate evidential maps for mineral
prospectivity modeling. Comput. Geosci. 2015, 79, 69–81. [CrossRef]
134. Roshanravan, B.; Aghajani, H.; Yousefi, M.; Kreuzer, O. An Improved Prediction-Area Plot for Prospectivity Analysis of Mineral
Deposits. Nat. Resour. Res. 2019, 28, 1089–1105. [CrossRef]
135. Rodriguez-Galiano, V.; Sanchez-Castillo, M.; Chica-Olmo, M.; Chica-Rivas, M. Machine learning predictive models for mineral
prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol. Rev.
2015, 71, 804–818. [CrossRef]
136. Nathwani, C.L.; Wilkinson, J.J.; Brownscombe, W.; John, C.M. Mineral Texture Classification Using Deep Convolutional Neural
Networks: An Application to Zircons From Porphyry Copper Deposits. J. Geophys. Res. Solid Earth 2023, 128, e2022JB025933.
[CrossRef]
137. Zuo, R.; Cheng, Q.; Agterberg, F.P. Application of a hybrid method combining multilevel fuzzy comprehensive evaluation with
asymmetric fuzzy relation analysis to mapping prospectivity. Ore Geol. Rev. 2009, 35, 101–108. [CrossRef]
138. Zuo, R.; Zhang, Z.; Zhang, D.; Carranza, E.J.M.; Wang, H. Evaluation of uncertainty in mineral prospectivity mapping due to
missing evidence: A case study with skarn-type Fe deposits in Southwestern Fujian Province, China. Ore Geol. Rev. 2015, 71,
502–515. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.