A

MINI PROJECT REPORT ON

CROP AND FERTILIZER RECOMMENDATION SYSTEM
Submitted in Partial Fulfillment of the Requirements for
The Award of Degree
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE & ENGINEERING
(DATA SCIENCE)
BY
[Link] (22C31A6705)
MUBASHIR HUSSAIN SHARIEF (22C31A6744)
[Link] (22C31A6736)
[Link] (22C31A6715)

UNDER THE GUIDANCE

OF

Dr. M. Sridhar
Associate Professor, Department of CSE (DS & IOT)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING (DS & IOT)

BALAJI INSTITUTE OF TECHNOLOGY AND SCIENCE
Accredited by NBA (UG-CE, ECE, ME, CSE, EEE Programs) & NAAC A+ Grade
(Affiliated to JNTU Hyderabad and Approved by the AICTE, New Delhi)
NARSAMPET, WARANGAL – 506331

i
 BALAJI INSTITUTE OF TECHNOLOGY &
SCIENCE
Accredited by NBA (UG-CE, ECE, ME, CSE Programs) & NAAC A+ Grade
(Affiliated by JNTU Hyderabad and Approved by the AICTE, New Delhi)
NARSAMPET, WARANGAL – 506331
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
(DATA SCIENCE)

CERTIFICATE

This is to certify that A. DEVARAJ (22C31A6705), MUBASHIR HUSSAIN SHARIEF

(22C31A6744), L. BALAJI (22C31A6736) and D. RAHUL (22C31A6715) of B. Tech III–II
Sem have satisfactorily completed the Mini Project entitled ―CROP AND FERTILIZER
RECOMMENDATION SYSTEM‖, as part of the curriculum in Computer Science
Engineering during the academic year 2024-2025.

Internal Guide Head of Department

Dr. M. Sridhar Dr. M. Sridhar

Head & Associate Professor Head & Associate Professor

External Examiner

i
 ACKNOWLEDGEMENT

We would like to express our sincere gratitude to our HoD & Guide, Dr. M. Sridhar
whose knowledge and guidance have motivated us to achieve goals. We never thought
possible. He has consistently been a source of motivation, encouragement and inspiration.
The time we have spent working under his supervision has truly been a pleasure.

We heartily thank to our Principal Dr. V. S. Hariharan for giving this great
opportunity and his support to complete our project.

We would to appreciate the guidance given by project coordinator as well as the

panels especially in our project presentation that has improved our presentation skills by their
comment and tips.

We thank all our senior faculty members for their effort, guidance and help during our
course. Thanks to programmers and non - teaching staff of CSD Department of our college.

Finally Special thanks to our parents for their support and encouragement throughout
our life and this course. Thanks to all my friends and well-wishers for their constant support.

[Link] (22C31A6705)
MUBASHIR HUSSAIN SHARIEF (22C31A6744)
[Link] (22C31A6736)
[Link] (22C31A6715)

ii
 ABSTRACT
The growing global population has intensified the demand for increased
agricultural productivity and sustainability. Traditional farming practices often rely on
general assumptions about crop selection and fertilizer application, which can lead to
inefficient resource utilization and reduced crop yields. In this context, technological
innovations such as machine learning offer immense potential to revolutionize agriculture
by enabling data-driven decision-making. This project, titled "Crop and Fertilizer
Recommendation System Using Machine Learning", is developed with the objective
of assisting farmers in making intelligent decisions regarding suitable crop cultivation
and fertilizer usage based on their specific soil and environmental conditions.

The system leverages a variety of machine learning algorithms to analyze critical

parameters including nitrogen (N), phosphorus (P), and potassium (K) levels, soil pH,
humidity, temperature, and rainfall. These parameters are collected through sensor
modules or user inputs, and the data is processed and trained on curated agricultural
datasets. The machine learning model is capable of recommending the most suitable crop
for a given piece of land and also suggests optimal fertilizers to enhance productivity
while maintaining soil health.

Key Words: Agricultural Decision Support System, Crop Recommendation, Fertilizer

Recommendation, Machine Learning in Agriculture

iii
 TABLE OF CONTENTS

CONTENT PAGE NO.

i
CERTIFICATE

AKCNOWLEDGEMENT ii

ABSTRACT iii

TABLE OF CONTENTS iv

1 Introduction

1.1) Problem Statement 1

1.2) Objective 2

1.3) Proposed Solution 2

1.4) Motivation 3

2 Literature Survey 4

3 System Development 6

3.1) System Architecture 7 6

3.2) Introduction To Machine Learning 9 7

3.3) Approaches 11 8

3.4) Dataset 11 8

3.5) Data Preprocessing & Model Building 14 11

3.6) Algorithms Of Machine Learning 19 12

3.7) Tools And Libraries Used 22 16

4 Performance Analysis 30 19

iv
4.1) About The Data 19

4.2) Accuracy Comparison Between Different Algorithms 19

4.3) Accuracy Comparison Of Algorithms 24

4.4) Output 25

5 Conclusion 26

5.1) Future Scope 26

References 28

v
 1 INTRODUCTION
As we know snice the humans have started practicing or doing agriculture activities
―Agriculture‖ has become the most important activity for humans. In today’s era or
world agriculture is not only for surviving it’s also play huge part or role in economy of
any country. Agriculture plays vital role in India’s economy and in human future too. In
India it also provides large portion of employment for Indians. As a result, with passage
of time the need for production has been accumulated exponentially. thus, on
manufacture in mass amount individuals are exploitation technology in associate degree
extremely wrong method.
With the improvement of the technologies day by day there is creation of hybrid
varieties day by day. In comparison with naturally created crop these hybrid varieties
don’t offer or provide essential contents. Depending more on unnatural techniques may
lead to soil acidification and crust. These types of activities all lead up to environmental
pollution. These types of activities (unnatural activities) are for avoiding or reducing
losses. However, once the farmer or producer get or grasp the correct data on the crop
yield, it will help the farmer in avoiding or reducing the loss
Around the globe India is the second largest country in terms of population. Many
people are dependent on agriculture, but the sector lacks efficiency and technology
especially in our country. By bridging the gap between traditional agriculture and data
science, effective crop cultivation can be achieved. It is important to have a good
production of crops. The crop yield is directly influenced by the factors such as soil type,
composition of soil, seed quality, lack of technical facilities etc.
In India agriculture plays important role in economic sector and also plays the most
important role in global development. A lot more than 60% of the country's land is used
for agriculture to meet the needs of 1.3 billion people. So, adopting new technologies for
agriculture plays important role. This is going to lead our country's farmers to make a
profit. Crop prediction and fertilizer prediction in most part of part India is done on by
farmers will prefer previous or neighboring crops or most prone to the surrounding
region only because of their land and do not have sufficient information about the content
of soil like phosphorus, potassium, nitrogen.

1.1) Problem statement

Most of the Indians have farming as their occupation. Farmers plant the same crop over

1
and over again without trying new varieties and randomly fertilize without knowing the
amount and content that is missing. Therefore, it directly affects crop yield and acidifies
the soil result in reducing soil fertility.
We are designing the system using machine learning to help farmers in crop and
fertilizer prediction. Right crop will be recommended for a specific soil and also keeping
in mind of climatic boundaries. Also, the system provides information about the
fertilizer, the seeds needed for planting.
With the help of our system farmers can try to grow or cultivate different varieties with right

technique, which will help farmers in maximizing their profit.

1.2) Objective
• Recommend crops that should be planted by farmers based on several criteria and
help them make an informed decision before planting.
• Recommend the most suitable fertilizer, based on the same criteria.
• In this project, we are launching a website where the following applications
are made:
• Crop recommendations, fertilizer recommendations, respectively.
• In the crop recommendation app, the user can provide soil data on his side and
the app will predict which crop the user should grow.
• With the fertilizer application, the user can enter soil data and the type of crop
they are planting, and the application will predict what the soil is lacking.

1.3) Proposed solution

In the system, we propose testing of multiple algorithms and by reading the
classification report we compare the algorithms and select the best one.
It should find accuracy for the given datasets, test database accuracy, precision and recall
by comparing algorithms.
The following steps will be there in process:
• Defining the problem

• Preparing the data

• Comparing algorithms

• Finding best algorithm

2
 1.4) Motivation
Farming is a major Indian occupation. About 70% of small and medium enterprises are
based on agriculture. So, to improve farming many farmers have started using new
technologies and methods. In this case the concept of identifying crop suitability and
yield based on various production factors can increase crop quality and yield, thereby
increasing economic growth and profitability.
For agriculture to continue to grow, many farmers have begun to use the latest technology
and methods. However, there is a huge gap in knowledge about crop production and how
it can affect farm profitability.
Choosing a crop to plant is one of the biggest challenges farmers faces in growing crops.
There are several factors involved. By recommending the most suitable crops and
promoting the right crop fertilizer, a crop recommendation system can help farmers
choose the right crop yield crop.

3
 2 LITERATURE SURVEY
Recommendation system for crop and fertilizer are present in market and also many
are on developing stage which consider various factors such as climate condition at the
time of plantation, rainfall, humidity or soil contents. Many research has been done in
this field and following are some of the research and paper that has been carried out in
this field.
The article ―Prediction of crop yield and fertilizer recommendation using machine
learning algorithms ―[1] concludes that the prediction of crop for all intents and
purposes yield based on location and proper implementation of algorithms have
essentially proved that the pretty much higher crop actually, kind-of yield can generally
particularly be achieved, which definitely is quite significant, or so they generally
thought. From above work I particularly conclude that for soil classification Random
Forest is definitely good with accuracy of 86.35% compared to Support Vector Machine,
which definitely really is quite significant, or so they for the most part thought.
For crop essentially yield prediction Support Vector Machine generally specifically
is particularly very good with accuracy 99.47% mostly compare to fairly kind of Random
Forest algorithm in a for all intents and purposes major way, sort of contrary to popular
belief. The work can basically literally be extended particularly further to mostly for the
most part add following functionality, particularly contrary to popular belief. Mobile
application can essentially be kind of for the most part build to generally particularly
help farmers by uploading image of farms. Crop diseases detection using image
processing in which user get pesticides based on disease images, which generally is quite
significant. Implement actually fairly Smart Irrigation System for farms to for all intents
and purposes mostly get pretty sort of much kind of higher yield, or so they kind of for all
intents and purposes thought.

Paper introduced [2] by Rakesh Kumar, M.P. Singh, Prabhat Kumar and J.P. Singh
proposed utilization of seven AI procedures i.e., ANN, SVM, KNN, Decision Tree,
Random Forest, GBDT and Regularized Gradient Forest for crop determination. The
framework is intended to recover every one of the harvests planted and season of
developing at a specific season. Yield pace of each harvest is gotten and the harvests
giving better returns are chosen. The framework likewise proposes an arrangement of
harvests to be planted to get the more significant returns

4
 Leo Brieman [3], is gaining practical experience in the precision and strength and
connection of arbitrary woods calculation. Arbitrary woods calculation makes choice
trees on various information tests and afterward foresee the information from every
subset and afterward by casting a ballot offers better the response for the framework.
Irregular Forest utilized the stowing strategy to prepare the information. To support the
exactness, the arbitrariness infused needs to limit the connection ρ while keeping up with
strength.

5
 3 SYSTEM DEVELOPMENT
3.1) System architecture

Figure 1: System Architecture

Figure 2: Crop Recommendation

6
3.2) Introduction to Machine Learning

―Machine learning is part of Artificial intelligent. Machine studying’s purpose is to

recognize the shape of facts and in shape it into models that humans can apprehend and
utilize.‖
―Machine Learning’s a subfield of pc technology that differs from conventional
computational strategies. In classical computer science, an algorithm is a set of certain
instructions that are explicitly used by a computer to compute or solve a problem.
Machine studying, however, permits computer systems to study from records inputs after
which use statistical analysis to provide outputs which can be within a given variety.
Machine getting to know makes it simpler for computer systems to develop fashions
from pattern records and automate choice- making techniques based totally on facts
inputs as a result.‖
―Machine gaining knowledge of is a swiftly changing place. As a result, whether or
not operating with system getting to know approach reanalyzing the impact of system
studying techniques, there are a few elements to do not forget.‖

Methods of Machine Learning

In machine gaining knowledge of, obligations are regularly divided into large
[Link] classifications are based totally on how data is acquired and the way the
system responds to it.
Two of the maximum widely used gadget getting to know methods are unsupervised
mastering, which gives the algorithm without a labelled information so as for it to find
structure inside its input statistics, and supervised mastering, which trains algorithms
primarily based on example input and output facts that is labelled via humans. Let's take
a deeper study each of those strategies.

Supervised
In this learning machine learning model is provide with dataset having inputs as well as
their correct outputs too. Or we can say that labelled datasets are provided to algorithms
in machine learning model for training (guided training). Applications of supervised
learning speech recognition, spam detection, bioinformatic etc.

7
Unsupervised
In this learning labelled datasets is not provided. It tries to find pattern between the data
in the datasets. In this type of learning involvement of human or human supervision is
required less compared to the supervised learning. It can manage or handle unstructured
data and unlabeled data more easily. Though, it make easier to analyzing, finding pattern
in complex data.

3.3) Approaches
As a field, the information gadget is closely associated with computer knowledge, so
having a mathematical legacy helps you to better see and apply machine management
techniques.
For those who have never studied mathematics before, the definition of relatability
and regression, the two most commonly used methods of assessing the correlation
between quantitative statistics, is a good place to start. The relationship of degree of
communication between unstructured or independent variables to each other. Reversal is
used to look for the correlation between a single supported variable and a neutral one at
its basic level. Because they can be used for fixed variable predictions while neutral
variables are understood, retrospective facts provide predictive capabilities.

3.4) Dataset
We have considered 2 datasets. One helps recommendation of crops, and second dataset
helps in prediction or recommendation of fertilizer
Dataset for crop recommendation
As we all know that good crop production or good yield of crop depends on various
factor, in this dataset we are provided with various factors that is involved in production
of crop. With the help of this data set crop recommendation model can be created.

Dataset for crop recommendation have following data fields

a) N: tells about the ratio of nitrogen

b) P: tells about the ratio of Phosphorous

c) K: tells about the ratio of Potassium

d) Temperature: in Celsius

e) Humidity: relative humidity in %

8
 f) Ph: tells either soil is acidic or basic

g) Rainfall: in mm

Figure 3: data set for crop prediction

Dataset for fertilizer recommendation

Only finding right crop to grow is not enough for good yield or good yield production we must
also find what fertilizer must be used for crop care.

Dataset for fertilizer recommendation have following data fields

a) N: tells about the ratio of nitrogen

b) P: tells about the ratio of Phosphorous

9
c) K: tells about the ratio of Potassium

d) Ph

e) soil moisture

f) crop

Figure 4: dataset for fertilizer prediction

10
3.5) Data Preprocessing
Data is collected from various sources therefore it may contain many missing values or
raw data which is collected is processed in a manner so that it can be easily process in
different tasks like in machine learning model, data science tasks.

Model Building
Model building is a process to create a mathematical model which will help in predicting
or calculating the outcomes in future based on data collected in the past.
E.g.-

A retail wants to know the default behavior of its credit card customers. They want to
predict the probability of default for each customer in next three months.
Probability of default would lie between 0 and 1.
Assume every customer has a 10% default rate.
Probability of default for each customer in next 3 months=0.1

It moves the probability towards one of the extremes based on attributes of past
information. A customer with volatile income is more likely (closer to) to default.
A customer with healthy credit history for last years has low chances of default (closer to
0).
Steps in Model
Building Algorithm
Selection Training
Model Prediction
Scoring

11
Algorithm Selection

Example

Have dependent variable?

Yes
No

Supervised Unsupervised
Learning Learning

Is dependent
variable
continuous?
Yes No

Regression Classification

Figure 5: Algorithm Selection

E.g.- Predict the customer will buy product or not.
3.6) Algorithms of machine learning
Logistic
Regression
Decision Tree
Random
Forest

Training Model
It is a process to learn relationship / correlation between independent and dependent
variables. We use dependent variable of train data set to predict/estimate. Dataset
Train Past data (known dependent variable). Used to train model. Test Future data

12
(unknown dependent variable) Used to score.
We apply training learning to test data set for prediction/estimation.

Predictive Modelling
By using former data we forecast the future
using former data E.g.-
Past Horror Movies
Future Unwatched Horror Movies

Predicting stock price

movement Analyzing past stock
prices.

Analyzing similar stocks.

Future stock price
required.
Types
Supervised Learning:
It is a type of machine learning where a model is trained on labeled data—meaning
each input is paired with the correct output. the model learns by comparing its
predictions with the actual answers provided in the training data. Over time, it adjusts
itself to minimize errors and improve accuracy. The goal of supervised learning is to
make accurate predictions when given new, unseen data. For example, if a model is
trained to recognize handwritten digits, it will use what it learned to correctly identify
new numbers it hasn't seen before.

Unsupervised learning :
It is a branch of machine learning that deals with unlabeled data. Unlike supervised
learning, where the data is labeled with a specific category or outcome, unsupervised
learning algorithms are tasked with finding patterns and relationships within the data
without any prior knowledge of the data's meaning. Unsupervised machine learning
algorithms find hidden patterns and data without any human intervention, i.e., we don't
give output to our model. The training model has only input parameter values and
discovers the groups or patterns on its own.

13
 Clustering:
A clustering problem is where you want to discover the inherent groupings in the data,
such as grouping customers by purchasing behavior.
Association: An association rule learning problem is where you want to discover rules
that describe large portions of your data, such as people that buy X also tend to buy Y.

Stages of Predictive Modelling

i. Problem definition
ii. Hypothesis Generation
iii. Data Extraction/Collection
iv. Data Exploration and Transformation
v. Predictive Modelling
vi. Model Development/Implementation
 Logistic Regression
Logistic regression is a supervised learning classification algorithm used to predict the
probability of a target variable. The nature of target or dependent variable is
dichotomous, which means there would be only two possible classes.

Figure 6: Logistic Regression

14
• Naive Bayes
This algorithm thinks that the dataset features are all independent of each other.

Larger the dataset it works better. DAG (directed acyclic graph) is used for classification
in this or naïve bayes algorithm.

• Random forest
Random Forest has the ability to analyze crop growth related to the current climatic
conditions and biophysical change. Random forest algorithm creates decision trees on
different data samples and then predict the data from each subset and then by voting gives
better solution for the system. Random Forest uses the bagging method to train the data
which increases the accuracy of the result.

 Decision Tree
Decision tree is the most powerful and popular tool for classification and prediction. A
Decision tree is a flowchart like tree structure, where each internal node denotes a test on
an attribute, each branch represents an outcome of the test, and each leaf node (terminal
node) holds a class label.

 Support Vector Machine (SVM)

Support Vector Machine is a relatively simple Supervised Machine Learning Algorithm
used for classification and/or regression. It is more preferred for classification but is
sometimes very useful for regression as well. Basically, SVM finds a hyper-plane that
creates a boundary between the types of data. In 2-dimensional space, this hyper-
plane is nothing but a line. In SVM, we plot each data item in the dataset in an N-
dimensional space, where N is the number of features/attributes in the data. Next, find
the optimal hyperplane to separate the data. So, by this, you must have understood that
inherently, SVM can only perform binary classification (i.e., choose between two
classes).

15
 Figure 7 :Support vector machine

3.7) Tools and libraries

used Python:
For carrying out this project in the best possible manner, we decided on using
Python Language, which comes with several pre-built libraries (such as pandas, NumPy,
SciPy, and etc.) and is loaded with numerous features for implementing data science and
machine learning techniques which allowed us to design the model in the most efficient
manner possible. For building this project we utilized numerous python libraries for
executing different operations.
● Python - Python is a robust programming language with a wide range of
capabilities. Its broad features make working with targeted programs (including meta-
programming and meta- objects) simple. Python takes advantage of power typing as well
as the integration of reference computation and waste management waste collecting. It
also supports advanced word processing (late binding), which binds the way the words
change during the process.
Patches to fewer essential sections of C Python that can give a minor improvement
in performance at an obvious price are rejected by Python developers who try to prevent
premature execution. When speed is crucial, the Python program developer can use mod-
written modules in C-languages or Python, a timely compiler, to submit time-
sensitive jobs.

Python is a Python interpreter that transforms Python scripts to C and uses the C-
1evel API to call the Python interpreter directly. Python's creators attempt to make the
language as fun to use as possible. Python's architecture supports Lisp culture in terms of
functionality. Filters, maps, and job reduction, as well as a list comprehension,

16
dictionaries, sets, and generator expressions, are all included. Two modules (itertools and
functools) in the standard library use realistic Haskell and Standard ML tools.

Why Use Python?

We're using Python because it works on a wide range of platforms. Python is a language
with no stages. Python is a as simple as English. Python have many libraries and has a
simple linguistic structure similar to English, whereas Java and C++ have complicated
codes. Python applications contain less lines than programs written in other languages.
That is why we choose Python for artificial intelligence, artificial consciousness, and
dealing with massive volumes of data. Python is an article-oriented programming
language. Classes, objects, polymorphism, exemplification, legacy, and reflection are all
concepts in Python.

NumPy library:
NumPy is a Python program library, which adds support for large, multi-dimensional
collections and matrices, as well as a large collection of mathematical functions
developed to work in these components.
The use of NumPy in Python is basically the same as that of MATLAB as they both
translate and allow customers to create projects faster as long as multiple tasks are
focused on clusters or networks rather than scales. Along with these critical ones, there
are several options:

Pandas’ library:
It is a software library in python to decrypt and analyze data. It provides data structures
and functions to manage number tables and time series. Free software released under a
three-phase BSD license. The term is taken from the term "panel data", an econometrics
term for data sets that incorporates visibility into many identical people.
Adding or modifying data engines by a robust community that allows different
applications to be integrated into data sets. High output of a combination of data and a
combination. Hierarchical indexing provides an accurate way of dealing with large-scale
data in a small data structure.

Matplotlib:
John Hunter and many others built a matplotlib Python library to create graphs, charts,
and high-quality statistics. The library can change very little information about
mathematics, and it is great. Some of the key concepts and activities in matplotlib are:

17
Picture
Every image is called an image, and every image is an axis. Drawing can be considered
as a way to draw multiple episodes.
Structure
Data is the first thing that a graph should be drawn. A keyword dictionary with keys and
values such as x and y values can be declared. Next, scatter (), bar (), and pie () can be
used to create a structure and a host of other functions.
Axis
Adjustments are possible using the number and axes obtained using the sub-sections ().
Uses a set () function to adjust x-axis and y-axis features.

Scikit learn:
The best Python Scikit-learn machine library. The SKlearn library contains many
practical machine learning tools and mathematical modeling methods, including division,
deceleration, integration and size reduction. Machine learning models used by SKlearn.
Scikit-Learn charges for tons of features and should not be used to read data or trick or
summarize it. Some of them are there to help you translate the spread.

Scikit-learn comes with many features. Some of them are here to help us explain
the spread:
• Supervised learning algorithms: Consider any professional reading algorithms you may
have studied and may be part of science. Starting with the standard line models, SVM,
decision trees are all in the science toolbox. One of the main reasons for the high level of
use of scientists is the proliferation of machine learning algorithms. I started using scikit,
and I would recommend young people to learn the scikit / machine. I will solve
supervised learning problems.
• Unchecked learning algorithms: There are also a wide variety of machine learning
algorithms ranging from compilation, feature analysis, key component analysis to
unchecked neural networks.
• Contrary verification: a variety of methods are used by SKlearn to ensure the accuracy
of the models followed with invisible details.
• Feature removal: Scientific learning to remove images and text elements.
• Datasets for different toys: This was useful when studying science. I have studied SAS
for different educational data sets. It helped them a lot to support when they read the new
library.

18
 4 PERFORMANCE ANALYSIS

4.1) About the data

The data used in this project is made by enlarging and consolidating India’s publicly
available data sets such as weather, soil, etc. This data is simple compared to very few
factors but useful as opposed to complex factors that affect crop yields.
The data are rich in Nitrogen, Phosphorus, Potassium, and soil PH. Also, it contains
humidity, temperature and rainfall required for a particular plant.

4.2) Accuracy Comparison between different algorithms:

• Logistic regression
On applying it on dataset it gives accuracy of 95.22%.

Figure 8: accuracy in logistic regression

19
• Naive Bayes
On applying it on dataset it gives accuracy of 99.09%.

Figure 9: accuracy in gaussian naïve bayes

20
• Random Forest
On applying it on dataset it gives accuracy of 99.09%.

Figure 10: accuracy in random forest

21
• Decision tree
On applying it on dataset it gives accuracy of 90%.

Figure 11: accuracy in Decision tree

22
• SVM: (Support vector machine)
On applying it on dataset it gives accuracy of 97.95%.

Figure 12: accuracy in support vector machine

23
4.3) Accuracy Comparison of Algorithms

Figure 13: Accuracy Comparison of Algorithms

24
4.4) Output:
Crop Recommended

Figure 14: Crop Recommended

Fertilizer Recommended

Figure 15: Fertilizer Recommended

25
 5 CONCLUSIONS
In this project we try to get best crop and fertilizer recommendation with the help of
machine learning. For the calculation of accuracy many machine learning techniques
were imposed or used. Numerous algorithms were used on datasets to get the best output
which leads to best crop and fertilizer recommendation for particular soil of particular
region.
This system will help farmers to visualize crop yields based on that climatic and
subsistence boundaries
Using this farmer can decide whether to plant that crop or to look for another crop if
yield forecasts are incorrect.
This tool can help the farmer to make the best decisions when it comes to growing
something harvest. It may also predict the negative effects of the plant.
Currently our farmers use outdated technology or not use effectively, so there can be an
opportunity of the wrong choice of cultivated crops that will reduce the profit by
production.
To reduce these types of loss we try to create a farmer-friendly system, which will help in
predicting which crop is best for a specific soil and this project will give the
recommendation about the fertilizer needed by the soil for cultivation, seeds needed for
cultivation, expectations yield and market price. Thus, this enables farmers to make the
right choice in choosing a crop farming so that the agricultural sector can develop with
new ideas

5.1) Future Scope

For the upcoming updates in this project we can use deep learning techniques for plant
diseases prediction with the help of images and we can also implement IOT techniques
for getting contents of soil directly from the fields.
Future Work on this can add many options such as:
• Diagnosis and prevention of plant diseases, predicting plant species.
• Current Market Conditions and analysis for information on crop market
rates, production costs, fertilizer.
• Government options for knowing new government programs related to
borrowing, fertilizer, and harvesting.
• The mobile app can be developed to assist farmers with uploading farm photos.

26
• Plant Disease Detection is used to process images where the user finds
pesticides based on their pictures of diseases.

27
 REFERENCES
1. Bondre, D. A., & Mahagaonkar, S. (2019). PREDICTION OF CROP YIELD
AND FERTILIZER RECOMMENDATION USING MACHINE LEARNING
ALGORITHMS. International Journal of Engineering Applied Science and
Technology,
04(05), 371–376. [Link]

2. R. Kumar, M. P. Singh, P. Kumar and J. P. Singh, "Crop Selection Method to

maximize crop yield rate using machine learning technique," 2015 International
Conference on Smart Technologies and Management for Computing,
Communication, Controls, Energy and Materials (ICSTM), 2015, pp. 138-145, doi:
10.1109/ICSTM.2015.7225403.

3. Leo Brieman, ―Random Forests‖, 2001

4. Priya, P., Muthaiah, U., Balamurugan, M.‖Predicting Yield of the Crop Using
Machine Learning Algorithm‖,2015

5. Mishra, S., Mishra, D., Santra, G. H.,―Applications of machine learning

techniques in agricultural crop production‖,2016

6. Ramesh Medar,Vijay S, Shweta, ―Crop Yield Prediction using Machine

Learning Techniques‖, 2019

28