Research

Fabrication and investigation of agricultural monitoring system

with IoT & AI
P. Indira1 · I. Sheik Arafat1,2 · R. Karthikeyan3 · Shitharth Selvarajan4,6 · Praveen Kumar Balachandran5

Received: 1 June 2023 / Accepted: 16 October 2023

© The Author(s) 2023  OPEN

Abstract
Artificial intelligence (AI) can be used in a variety of fields and has the potential to alter how we currently view farming.
Due to its emphasis on effectiveness and usability artificial intelligence has the largest impact on agriculture of all indus-
tries. We highlight the automation-supporting technologies such as Artificial Intelligence (AI), Machine Learning, and
Long-Range (LoRa) technology which provides data integrity and protection. We also offer a structure for smart farming
that depends on the location of data processing after a comprehensive investigation of numerous designs. As part of
our future study we have divided the unresolved difficulties in smart agriculture into two categories such as networking
issues and technology issues. Artificial Intelligence and Machine Learning are examples of technologies whereas the
Moderate Resolution Imaging Spectroradiometer satellite and LoRa are used for all network-related jobs. The goal of the
research is to deploy a network of sensors throughout agricultural fields to gather real-time information on a variety of
environmental factors including temperature, humidity, soil moisture and nutrient levels. The seamless data transmission
and communication made possible by these sensors’ integration with Internet of Things technologies. With the use of AI
techniques and algorithms the gathered data is examined. The technology may offer practical insights and suggestions
for improving agricultural practices because the AI models are trained to spot patterns, correlations, and anomalies in
the data. We are also focusing on indoor farming by supplying Ultra Violet radiation and artificial lighting in accordance
with plant growth. When a pest assault is detected using AI and LoRa even in poor or no network coverage area and
notifies the farmer’s mobile in any part of the world. The irrigation system is put to the test with various plants at various
humidity and temperature levels in both dry and typical situations. To keep the water content in those specific regions
soil moisture sensors are used.

Keywords AI · LoRa · IoT · Sensors · MODIS satellite

* Shitharth Selvarajan, [email protected]; P. Indira, [email protected]; I. Sheik Arafat, [email protected];

R. Karthikeyan, [email protected]; Praveen Kumar Balachandran, [email protected] | 1Department of Physics,
Gnanamani College of Technology, Namakkal, Tamil Nadu, India. 2Department of ECE, Vel Tech Rangarajan Dr. Sagunthala R&D Institute
of Science and Technology, Chennai, Tamil Nadu, India. 3Department of CSE (AI&ML), Vardhaman College of Engineering, Hyderabad,
India. 4Department of CSE, Kebri Dehar University, Kebri Dehar, Somali, Ethiopia. 5Present Address: Department of EEE, Vardhaman
College of Engineering, Hyderabad, TS 501218, India. 6School of Built Environment, Engineering and Computing, Leeds Beckett University,
LS1 3HE Leeds, U.K..

SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

Vol.:(0123456789)
Research SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

1 Introduction the seven bands of MODIS satellite images of the land

surfaces in order to show changes in rainfall at the sub-
The present world population will increase to 8 billion basin level.
people in 2023. Rapid population growth according to The only way that water is used in agriculture today is
the United Nation (UN) makes it more difficult to eradi- for irrigation. This proportion may increase as a result of
cate poverty, end hunger and malnutrition, and broaden increased food consumption and population growth. Thus,
access to healthcare and educational opportunities [1]. one of the problems facing the planet is water scarcity.
The UN Food and Agriculture Organisation predicts that Day by day the most efficient plant monitoring systems
the global food supply would need to increase by 70% currently in use make use of plant optical and infrared
by 2050 as a result of decreasing agricultural lands and imaging. Everyone needs water including humans, ani-
the depletion of limited natural resources [2]. As a result mals, and plants. It is a fundamental necessity of human
there is a pressing need to raise farm productivity. Due being. Water waste is the key problem in the majority of
to a lack of natural resources such as fresh water and agriculture. By applying various water-saving strategies
cultivated land as well as trends in declining agricultural this can be reduced to a minimum. There are many strate-
yields for several key commodities the issue has gotten gies to stop or minimise water waste. Water is trickled onto
worse. Another obstacle is the agricultural workforce’s the plant’s roots using drip irrigation which is the most
changing organisational structure. effective method of irrigation [5]. A sprinkler system is an
There seem to be astonishing numbers for the Indian irrigation-based system that makes use of tubes-mounted
agricultural industry. With a Gross Value Addition of guns, sprays, or sprinklers.
US Dollar 265.51 billion it supports the livelihood of Abiotic and biotic constraints are two categories of
58% of Indians. Despite employing around 58% of the environmental limitations that have an impact on crop
working force directly and indirectly, this industry only production. Actually these aspects are more obvious due
provides about 15.87% of the nation’s Gross Domestic to climate change brought on by global warming [6]. Abi-
product (GDP) [3]. The topic of agricultural productivity otic stresses modify a plant’s morphology, physiology,
is brought up as a result. Agricultural Value Added per biochemistry, and molecular structure which negatively
Worker is the indicator that is most frequently used to affects its growth and productivity. Climate and soil char-
gauge agricultural output. China, India, Indonesia and acteristics (soil components, physicochemical, pH, and
other impoverished or emerging countries with large biological features) (drought, flood, cold, heat stress, etc.)
populations have the lowest agricultural value added are examples of abiotic constraints. On the other hand
per worker. biotic variables include weeds, vertebrate pests, patho-
India has the lowest agricultural value added per gens, beneficial species (pollinators, decomposers, and
worker among the top 20 economies. Water is essential natural enemies), and anthropogenic evolution. To address
to life for all creatures including plants and animals. It all the environmental issues that are lowering crop yields
is a fundamental necessity of every human being. The and maintaining food security, trans- and multidisciplinary
only way that water is used in agriculture in India today research is required.
is for irrigation. This proportion may increase as a result Numerous factors present a severe risk that will lower
of increased food consumption and population growth. productivity if farms are not adequately monitored and
So a problem that affects most agriculture is a lack of maintained. Three categories biological, environmental,
water. By applying various water-saving strategies this and technological can be used to categorise these vari-
can be reduced to a minimum. There are many strategies ables [7]. Due to the need to increase crop production
to stop or minimise water waste. and the increasing use of farming practises like irriga-
Tamil Nadu’s quick development and industrialisa- tion, extensive inorganic fertiliser application, and syn-
tion is responsible for the state’s excessive water usage. thetic chemical weed and insect control, more land has
The primary factor influencing the rapid deployment of been converted to agriculture [8]. These operations have
ground water irrigation is the ongoing change in Tamil decreased the quality of the soil, the water, exacerbated
Nadu’s yearly rainfall pattern. The main objective of this soil erosion, contaminated groundwater and the quality of
work is to use groundwater irrigation to decrease the the food. In an effort to enhance yields on current farms
negative effects of water scarcity on crop productivity while reducing the environmental effect of agriculture this
in order to sustain agriculture in Tamil Nadu through- has prompted programmes for sustainable development
out the year. This investigation looks at temporal vari- [9–13].
ations in irrigated areas between 2000 and 2014 [4]. Today wireless sensor networks play a huge role in
We use spectral matching methods to map and classify agriculture. These systems among others include those
that use Radio Frequency Identification (RFID) based

Vol:.(1234567890)
SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1 Research

traceability systems, continuously monitor the environ- type of irrigation-based system that employ sprinklers,
ment and preserve agricultural accuracy. For the auto- sprays or guns mounted on tubes. The tubes carry water
mated irrigation system to transmit the sensor data for and some of the ends include sprinklers to apply water
the soil moisture content, temperature, and humidity to where it is needed. The sprinkler won’t activate until the
the remote area, a wireless modem using LoRa is essen- temperature and humidity sensor in the root zone sur-
tial. Wireless sensor networks are used to remotely moni- passes the threshold value. The rotary system is the best
tor humidity and temperature information on a regular irrigation technique for large regions. The rotary system
or irregular basis utilising General Packet Radio Service uses mechanically driven sprinklers that travel in a round
(GPRS) based systems. motion due to its 100-foot range. As a result the device
The aforementioned information allows us to frame the sprinkles over time in a larger area while using less water.
proposal’s objective as For the purpose of watering cotton crops, infrared ther-
Fabrication of monitoring device with AI analyzation of mometers are utilised to measure the temperature of the
Drought Monitoring and forecasting by Normalized Differ- remote canopy [19]. A temperature threshold is upheld
ence Vegetation Index (NDVI) time series data from MODIS during this process. When the canopy temperature rises
Satellite. above a certain threshold the mechanism activates. The
The contributions of the study are as follows majority of irrigation systems are automated rather than
manual in order to maximise cotton production and water
• NDVI time series data from MODIS Satellite along with usage. An alternative parameter to calculate agricultural
Micro climate Analysis for adapting the new cropping irrigation requirements is plant Evapotranspiration (ET).
pattern. When two terms are combined as in evaporation and plant
• Implementation of irrigation depends on age of crops transpiration the result is called ET. Evaporation is the
and Micro climate using AI vaporisation of water from soil, water bodies and canopy
• To monitor crop growth leaf colour changes, pest interception [20] into the atmosphere. Water vaporises
control, nutrients deficiency by Spectrogram images from stems, flowers, and leaves during the process of tran-
adopting AI. spiration. Water reductions of up to 42% are possible with
• Also provide Fertilizer calculator to have a realistic esti- ET-based systems [21]. Due to uses like vehicle monitoring
mate of the quality of fertilizer needed for our crop and and robot control, Wireless Sensor Network (WSN) nodes
area. have grown in popularity in recent years. IRIS nodes built
• To proposed LoRa Technology transmit all sensors data on TINY OS are used to measure the soil moisture content
from farm field to control unit without Global System of paddy fields [15]. The most popular method for measur-
for Mobile communication (GSM) technology and any ing the data in irrigation fields is the ZigBee transmission
other Internet facilities. of data from end devices. However the distance between
the two nodes is only 10 to 100 m when these devices
are used. As a result the majority of applications transport
2 Literature review data to faraway locations using GPRS-based technologies
[17]. ZigBee-based transmission is used in the agricul-
Currently irrigation is the only usage of water in agricul- tural sector to collect data from numerous sensor nodes.
ture. Increased food demand and population expansion In today’s world wireless sensor networks are essential to
could cause this percentage to increase. Therefore a global agriculture and the food industry. These systems among
issue is the lack of water [14]. Utilising plant optical and others, include those that use RFID-based traceability sys-
infrared pictures the most effective plant monitoring sys- tems, continuously monitor the environment and uphold
tems are being implemented daily [15]. Every human, ani- agricultural precision [16].A wireless modem using GSM/
mal and plant needs water to survive. Every human being GPRS is called the SIM900A. It is crucial for the automated
has a basic need for it. Water waste is the main issue in irrigation system to communicate the values from the soil
the majority of agriculture. Utilising various water saving moisture [12] content sensor as well as the temperature,
techniques can help to lessen this [16]. There are numer- humidity and other sensor data to the remote area. The AT
ous ways to prevent or reduce water waste. The first one commands can be used to do this. The microcontroller unit
is the ditch irrigation system, in which rows of seeds are and GSM/GPRS modem are interfaced [12]. Wireless sen-
placed in ditches that have been dug out. For the passage sor networks are used for remote monitoring using GPRS-
from the main ditch to the canals there are tubes resem- based systems to continuously or sporadically monitor
bling syphon tubes. The most effective technique of irriga- temperature and humidity data in industry and even in
tion is drip irrigation which involves pouring water onto agricultural [18].Various models and limitations of existing
the plant’s roots [17, 18]. Sprinkler systems are another systems are discussed in the Table 1.

Vol.:(0123456789)
Research SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

The main objective of this article is to develop an auto-

The internet that the action requires human inter-

matic watering system using AI and sensors linked to a

action requires human intervention to be car-

IoT networks that are based on mobile devices

incompatible with the proposed framework

Unable to implement in locations with low or

Ongoing connection to the internet that the
and Intelligent Transportation Systems are
microcontroller. This study made use of the DHT11 sensor
for temperature and humidity as well as the VH400 sen-
sor for soil moisture. These sensors are interfaced with the

non-existent internet connectivity

Unable to discern the soil’s quality
microcontroller unit which was buried beneath the root
zone of the plant. Sending an SMS to a mobile phone of a
Unsuitable for mixed farming

vention to be carried out

remote owner is the main goal of using a microcontroller.
SMS messages are delivered using the SIM900A module
which is coupled to the microcontroller unit. The irriga-
tion system is put to the test with various plants at various
humidity and temperature levels in both dry and typical
Limitations

ried out
situations. To keep the water content in those specific
regions soil moisture sensors are used. All results acquired
under wet and normal conditions have been shown to be
logical.
Utilising agriculture profiles to create irrigation

Model for an Automatic Agricultural Field Analy- Keep an eye on the soil’s moisture content and
Predict the presence of late blight in tomatoes
better data delivery performance in agricul-
lower the ratio of energy consumption with
An IoT-based WSN architecture with high energy To provide a wise choice for data routing and

If a farm is dry without a human presence,

2.1 LoRa technology

A LoRa-enabled architecture for precise irrigation and

monitoring has been demonstrated [28] with each sen-
Agriculture is being driven by digital innovation A rise in agricultural output

sor node being able to connect to another LoRa-enabled

schedules for their farms

receiver and create a communication channel. A low-

power operating method called LoRa allows for trans-
mission and reception over a vast communication range.
provide water
look for pests
and potatoes

Despite the fact that LoRa technology makes it simple

tural areas

to transfer sensor data from farm fields to a control unit.

Purpose

Field-installed sensors gather information about things

like soil moisture, temperature, and humidity. These sen-
sors broadcast the data in discrete packets using low-
through a control system incorporating node

Using a machine learning approach based on

efficiency and security for smart agriculture

power, long-range wireless technology called LoRa.

artificial neural networks, a sensor network
Sushanth and Sujatha [24] IoT, WSN, and cloud-based smart agriculture

The packets are sent by LoRa-capable sensors to LoRa

gateways placed around the farm. Gateways accept the
packets and use the LoRaWAN (LoRa Wide Area Network)
protocol to send them to a central control unit.
sis and Monitoring System

The control unit gathers and analyses the incoming

data to produce actionable insights. Real-time updates
on crop conditions may be included in this data, enabling
knowledgeable decisions on pest management, fertilisa-
applications

tion, and irrigation.

NodeMCU
sensors

system
Model

2.2 Challenges of AI
Table 1  Comparison of existing systems

Although implementing AI in the agricultural sector faces

Muangprathub et al. [22]

significant obstacles it is a logical step towards smart agri-

culture for efficient, cost-effective, and sustainable farm-
Haseeb et al. [23]

Vanaja et al. [27]

ing. The agricultural sector and the field of AI research

Araby et al. [25]

Kajol et al. [26]

are not connected. Therefore AI researchers are not well-

versed in the issues that farmers confront, and farmers are
Sr. No. Author

also not well-versed in the AI technologies that are cur-

rently available. It will take more interdisciplinary coop-
eration to find a solution to this dual issue. The use of AI
in agriculture is still in its early stages, hence there aren’t
3

6
1

Vol:.(1234567890)
SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1 Research

any established norms or regulations. As a result there deploy certain AI algorithms. In remote, rural areas with
are several legal questions surrounding smartt farming. no higher speed mobile networks but where agriculture
Because the majority of AI-IoT solutions were cloud-based is the main industry, edge AI has the potential to trans-
until recently, farmers were reluctant to adopt AI methods form the game. The potential for intelligent agriculture is
due to worries about cyber attacks, data security, and pri- increased. Convolution Neural Networks (CNN) were used
vacy. A new IoT option called "Edge AI" has emerged to in [29] to compress sensor image data at the edge layer
address this problem. Edge AI handles sensor data locally before transmitting the compressed data to the fog layer
and offers better data protection and privacy as well as using LoRa technology.
reduced latency and cost. Another challenge for AI in
agriculture is a lack of data. AI is a data-driven technol-
ogy. The absence of pertinent data makes it difficult to 3 System architecture

The three layers of the proposed system architecture are

depicted in Fig. 1. Layer 1: A farming device The founda-
tion layer of the smart farm architecture is called layer.
It consists of numerous components, including sensors
which are dispersed across the agricultural ground. These
devices also known as distributed source nodes, are simply
LoRa wireless sensor networks. They recognise the physi-
cal parameters continuously collect data in real-time and
send it to the gateway node at the following layer. The data
received by several sensors and cameras in various smart
agriculture applications is shown in Fig. 2. For instance
data is gathered by on Unmanned Aerial Vehicle (UAV)
sensors and cameras in a field of rice and relayed to the
edge where subsurface soil sensors process it.
Layer-2: The Edge Computing Layer is included in Layer
2. There are several edge nodes in this. Depending on the
Fig. 1  System architecture particular smart agriculture system, different nodes may

Fig. 2  Product over view

Vol.:(0123456789)
Research SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

be present. Here, layer-1 data is processed, filtered and monsoon was the subject of our investigation. We focused
encrypted. Due of resource constraints at the edge layer our research on the monsoon season (kharif season) from
the prognostic and solution components were previously May to December because all the agricultural activities are
completed at the following layer. Trained machine learn- done during this season and image analysis also carried
ing models can perform prognostics and provide sugges- out for that season.
tions at this layer, nevertheless thanks to recent hardware
advancements and initiatives for AI at the edge. However if 4.3 Spectral matching techniques for identifying
the task requires a lot of resources or is not time-sensitive, changes in irrigated area using NDVI
prognosis and inference can both be done in the following
layer. For instance the ESP8266 for integrating smart agri- The NDVI, which is a combination of near infrared and red
cultural components to manage environmental conditions bands, is frequently used to discern vegetation conditions
[25] and the ESP32 for smart irrigation [26]. such as density and vigour. NDVI values range from − 1
Layer-3: The third or uppermost layer in the bottom-up to + 1, with higher values indicating more vigorous vegeta-
design of the smart agriculture system is cloud comput- tion and lower values indicating less vigorous vegetation.
ing. This virtual layer is often located in data centres and is The total area irrigated from 2000–2001 to 2014–2015 and
accessible via the Internet from any location in the world the annual irrigated area differ significantly. The change in
[27]. Massive amounts of data generated by cameras or the irrigated area was discovered using spectral matching
sensors in agricultural farms are required. techniques. The highest mean NDVI value in Tamil Nadu
was 0.79 during the kharif season. From this result along
with the micro climate analysis (Temperature, Air quality
4 Data index and Humidity) suggest the right crop for the season.

4.1 Satellite data 4.4 Crop management

The seven bands of MODIS are used to measure surface Crop management is the process of evaluating the socio-
reflectance. Blue wavelengths between 459 and 479 nm, logical, ecological and economic factors that play a sig-
green between 545 and 565 nm, red between 620 and nificant role in the choice, growing and selling of crops.
670 nm, near-infrared between 841 and 875 nm, and Cropping patterns are influenced by crop growth, the
short-wave infrared between 1628 and 2155 nm, are used availability of water resources, labour, insurance, and
to examine vegetation and land surfaces. For monitor- environmental conditions using MODIS satellite and AI.
ing the vegetation at a continental scale [30] using the Cropping patterns might change according to ecological
Terra platform’s MODIS 500-m resolution and 8-day sur- variables. For instance traditional crops like paddy agri-
face reflectance. Scientific Data Set documentation for culture, which require extensive water resources, cannot
MOD09A1 [31] is given. The study also included secondary be supported in places with diminishing water supplies
data in addition to the original data set, which came from and groundwater tables. Crop choice is also influenced by
MODIS time-series data as shown in Fig. 3a the agricultural product’s market as well as the export and
import regulations of other nations.
4.2 River basins and their irrigated area
4.5 Soil monitoring
There are 40,000 tanks, 1 million wells, and 61 large res-
ervoirs that rely extensively (17.5 BCM) on surface water. In the overall farming process, soil moisture is crucial. Dur-
Surface irrigation is not as important as ground water irri- ing the course of a plant’s growth, it is in charge of pho-
gation (15. 3 BCM). Table 2 provides information on the tosynthesis, respiration, transpiration and the transfer of
basin’s irrigation condition for 39 years, from 1976 to 2014, minerals [30]. In making decisions for farms, soil monitor-
together with 54 years’ worth of rainfall data, from 1961 to ing is crucial. Cropping patterns are influenced by a num-
2014 shown in Fig. 3b also. At the sub-national level, which ber of variables, including soil salinity, pests, precipitation,
is similar to a state, county or district, statistics on the total pH, and humidity. These elements support the evaluation
amount of irrigated agriculture and irrigated area of the of soil health. Field-based sensors track the temperature
country were gathered. The Department of Economics and and humidity of the soil, and the cloud receives through
Statistics of the Tamil Nadu government provided data on LoRa Transmitter and the process the data. Farmers will
irrigated areas. Daily rainfall data from 2000 to 2014 were be informed about a variety of issues, and planting pat-
collected from the India Meteorological Department’s terns are evaluated and chosen depending on salinity
(IMD) Hydro Met Division website at http://i​ md.g ​ ov.i​ n. The content, soil nutrient level, humidity, and temperature. A

Vol:.(1234567890)
SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1 Research

Fig. 3  a Rainfall fluctuations over time in different irrigated agricultural areas in Tamil Nadu. b Tamil Nadu agricultural land classification, by
source, with major river basins

wide range of topics will be discussed with farmers, and classified as either soil moisture sensor-based or weather-
planting patterns will be considered and selected based based. A controller controls the irrigation in weather-
on factors like salinity content, soil nutrient level, humid- based irrigation systems, which collect temperature and
ity, and temperature. Water is essential for photosynthesis, rainfall data from a nearby small weather station. In irriga-
regulates temperature, and transports food and nutrients tion systems using soil moisture sensors, sensors buried
for plant growth, making soil moisture a crucial element in in tree grass provide precise measurements of the soil’s
plant growth. Humidity controls the food supply and tran- moisture content. In order to irrigate the field with this
spiration rate for ideal plant growth. A humidity of 50% sort of irrigation, precise humidity and air temperature
to 60% is ideal for the growth of vegetable plants [32]. To measurements, weather monitoring, and cropping pat-
ensure the best possible use of water resources, soil mois- terns are all necessary with AI. Sprinkler actuators and
ture sensors are inserted into plant roots and analyse soil data are delivered to the cloud together [35]. The data
moisture level measurements [33, 34]. from the soil moisture sensor determine the irrigation
schedule for each farm area. Maximum crop growth and
4.6 Smart irrigation 100% water utilisation efficiency are guaranteed by micro
level analysis, scheduling, and effective actuation [36].
Smart irrigation is the practise of enhancing the quality From a mobile application built for smart phones, farmers
and quantity of production while making the most use of can monitor and may control the irrigation system. This
available water resources. By giving the plants the right irrigation system is based on information collected from
amount of water, it saves water. Irrigation systems can be field-installed temperature, humidity, soil moisture, and

Vol.:(0123456789)
Research SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

Table 2  Characteristics of the major river basins

Basin id Basin name Catchment area (ha) Average annual Number of tanks Average tank and
rainfall (mm) canal irrigated area

1 Chennai Basin 558,385 1130 1304 133,033

2 Palar River Basin 1,067,737 940 661 202,507
3 Varahanadhi River Basin 469,630 1250 131 80,755
4 Ponnaiyar River Basin 1,217,599 920 1133 161,364
5 Paravanar River Basin 76,000 NA 2 130,095
6 Vellar Basin 727,472 980 386 742,220
7 Cauvery River Basin 4,709,572 930 NA 120,042
8 Agniyar River Basin 638,190 910 346 110,143
9 PambarKottakarai year 417,625 880 160 117,251
10 Vaigai River Basin 775,164 900 521 92,306
11 Gundar River Basin 419,091 770 526 77,505
12 Vaippar Basin 606,359 800 151 16,319
13 Kallar River Basin 146,385 600 15 74,035
14 Thamirabarani River 576,010 1110 NA 25,108
15 Nambiyar River Basin 153,800 950 559 24,681
16 Kodayar River Basin 212,790 1720 2 48,208
17 P.A.P. Basin 320,285 610 NA 12,770

ultrasonic sensors [37]. Farmers can execute actuation by weather, optimise supply chains, manage irrigation sys-
turning on the irrigation pumps to water the farm using tems, manage pesticide and fertiliser use, and control
a user-friendly mobile application that is built for smart weeds. Researchers are using fuzzy logic, other AI/ML tech-
phones and connected to the cloud for analysis. niques like classification and logistic regression, as well as
Neuro-Fuzzy logic, to improve agricultural decision-mak-
4.7 Plant growth monitoring ing, predictive analytics, and mobile expert systems [48].
Real-time monitoring of the environment in agricul-
The key step after selecting a crop is crop cultivation. tural areas is made possible by integrating sensors with
Modern technology is available to farmers and sensors a microcontroller unit. The system can identify the pres-
installed in the field monitor plant growth. For instance, ence of pests or unusual variables linked to pest attacks
ultrasonic sensors. For instance, to track the presence of by deploying sensors like temperature, humidity and pest-
insects and pests that hinder plant growth, ultrasonic sen- specific sensors. Early identification is made possible by
sors are deployed in the field. When pests are found, high this allowing farmers to act right away and minimise any
frequency sound waves are produced to eliminate them, crop damage.
and the farmer is also made aware of their presence for The system may analyse sensor data and detect cer-
additional assistance [31]. tain pest species or patterns linked to pest infestations by
incorporating AI algorithms. The accuracy of pest identi-
fication can be increased over time by using AI models
5 Methodology and implementation that have been taught to detect pests. The manual effort
needed for pest monitoring is decreased thanks to this
Applied Machine Learning and Artificial Intelligence automated identification procedure which also provides
Machine intelligence that resembles human intelligence prompt and precise detection.
is known as artificial intelligence. Many industries, includ- By utilizing LoRa the system can transmit data even in
ing e-commerce and marketing [38], human resources areas with poor or no network coverage. This is particularly
[39], computer vision [40], multimedia forensics [41, 42], valuable in rural or remote agricultural locations where
healthcare [43], social media [44, 45], gaming [46, 47] and traditional network connectivity may be limited. The agri-
agriculture have showed great potential as a result of cultural system can transmit pest detection data via LoRa
advancements in AI and ML. In agriculture, artificial intel- to a central server or cloud platform.
ligence (AI) is used to improve productivity, crop yield, Using LoRa technology alerts can be sent to the
and profitability as well as to track livestock, monitor the farmer’s mobile device as soon as the system detects

Vol:.(1234567890)
SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1 Research

and identifies a pest attack. These notices may contain 5.2 Features

details on the individual pest the intensity of the attack
and suggested pest control measures. This makes it pos- • Pest Detection: Detects pests through Keras-RetinaNet
sible for farmers to act quickly and protect their crops object detection model. (As explained above)
no matter where they are. Farmers can keep informed • Pest affect Density: The amount of pests found in each
and make informed decisions wherever they are thanks image is counted by the model. It serves as a criterion to
to remote accessibility via mobile alerts. determine how much damage has already been done
According to the Indian Council of Agricultural and provides an estimate of how many pests are present
Research, pests lose between 30 and 35 percent of on a leaf.
India’s annual agricultural yield. By applying cutting
edge AI solutions to this issue there is a tremendous The sensors and AI will begin to function according to the
possibility to raise our yield. Early pest detection allows power supply given to the Arduino board in the proposed
for the use of appropriate and less-excessive pesticides approach. A soil moisture sensor coupled to a microcon-
to protect the crop, increasing crop output. troller unit delivers the corresponding readings on a periodic
Three steps make up the Process Flow module: Data basis, and the DHT11 sensor detects the temperature and
gathering, Keras-RetinaNet-based pest detection and humidity in the crop roots on the other end. An air index
Pest attack density detection as shown in Fig. 4 sensor is also used to determine the air index. The microcon-
troller unit’s primary goal is to get the data values sent by the
sensors and ESP32, which was configured to save the data
5.1 Training the model in the cloud. These values are shown on the LCD screen by
the data that is delivered to the microcontroller. For timely
We utilised a Keras-RetinaNet model to identify pest irrigation, which supplies the necessary amount of water to
photos because deep learning for visual identification the receptive crops according to the stages, a Direct Cur-
is becoming increasingly successful. rent (DC) Pump and a Microcontroller are employed. If the
Arduino is turned on and all the sensors are controlled by
• Keras-RetinaNet With ResNet + FPN as the backbone for Arduino, then all of the aforementioned sensors will start
feature extraction and two task-specific subnetworks working at once. The Raspberry PI, AI, and camera that are
for classification and bounding box regression, Keras- housed in the other portion of the gadget are utilised to
RetinaNet, developed by Facebook AI Research (FAIR), detect both pest and disease attacks. The farmer is informed
achieves state-of-the-art performance and outper- if the camera detects the insect attack. We also offer a fer-
forms Faster RCNN, the well-known two-stage detector tiliser calculator to help you determine how much fertiliser
[49]. is necessary for each crop in order to control insect attacks.
• Recent studies have shown that adopting pre-trained Therefore, farmers may apply the proper amount of fertilis-
networks and applying them to other datasets signifi- ers to the crops using our fertiliser calculator. We now offer
cantly improves performance compared to develop- a mobile application that allows you to examine real-time
ing new models from scratch. This was made possible farm data in addition to the fertiliser calculator feature. Our
by the models’ capacity to discover general features mobile application pulls data from the cloud and displays it
applicable to a variety of computer vision tasks. On in accordance with what farmers are asking for.
the COCO dataset, we used a pre-trained model with Micro climate analysis, harnessed through AI algorithms,
a ResNet50 backbone, and we trained it using our offers a data-driven approach to optimize crop selection.
own data. To train our model, we utilised the weights Through continuous monitoring of temperature, air quality
“resnet50_coco_best_v2.1.0.h5”. We have tested a num- index, and humidity, AI employs decision trees algorithm
ber of models throughout the course of this project to correlate environmental variables with crop preferences.
and updated them as we discovered models that per- For instance, decision trees analyze historical and real-time
formed better. data to identify temperature thresholds where specific
crops flourish, ensuring ideal growing conditions. Air qual-
ity insights guide choices, as AI recognizes crops resilient to

Fig. 4  AI process flow for pest

detection Determine Send Alert
Data set Pest detecon using
pest Aack through
collecon Keras-RetinaNet
density Mobile app

Vol.:(0123456789)
Research SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

pollutants or sensitive to air composition changes. Humid- receives the data from the LoRa receiver and displays the
ity data guides water-intensive crop selection in suitable information in the LCD screen.
conditions. Additionally, AI can perform clustering analy- For timely irrigation, which supplies the necessary
sis, grouping areas with similar micro climates, enabling amount of water to the receptive crops according to the
regional-specific crop recommendations. AI’s adaptive learn- stages, a DC Pump and a Microcontroller are employed. If
ing capabilities fine-tune crop recommendations over time, the Arduino is turned on and all the sensors are controlled
enhancing accuracy with each season’s data. by Arduino, then all of the aforementioned sensors will
start working at once. The Raspberry PI, AI and camera that
are located in the other portion of the gadget are utilised
5.3 Implementing a fertilizer calculator with AI
to detect both insect and disease attacks. The farmer is
involves several steps
informed if the camera detects the insect attack. We also
offer a fertiliser calculator to help you determine how
1. Collect data on crop types, soil characteristics, growth
much fertiliser is necessary for each crop in order to con-
stages, and historical pest incidents.
trol pest attacks. So, according to our fertilizer calculator
2. Apply regression algorithms to analyze this data, cor-
farmers can feed the correct quantity of fertilizers to the
relating nutrient levels with pest occurrences.
crops. Along with fertilizer calculator facility we also pro-
3. Train the AI model using historical data to predict
vide Mobile Application to view the live data of the farm.
optimal nutrient requirements based on crop and soil
Our mobile application retrieves data from the cloud
conditions. Incorporate real-time data such as weather
and shows it in accordance with what farmers are asking
forecasts and pest population trends to dynamically
for (multilingual). Google Firebase, where the database
adjust recommendations.
is located and the web server is hosted on Apache Web
4. Create a user-friendly Mobile App interface where
Server, receives the data. Figures 5, 6, 7, 8, 9, 10 and 11
farmers input crop details and receive AI-generated
display the entire prototype output screenshot of Mobile
fertiliser suggestions. Integrate data from IoT devices
Application.
and sensors for accurate, up-to-date information.
5. Regularly update and refine the AI model with new
data to improve accuracy.
7 Conclusion

Technology advancements and the meteoric expansion of

6 Results ICT have transformed traditional agriculture into a smart,
intelligent, automated agriculture. Smart agriculture
Framework of proposed work is variety of environmental reduces its carbon footprint by implementing sustainable,
factors including temperature, humidity, soil moisture and green farming, limiting the use of pesticides and fertilis-
nutrient is defined. Next, select and fabricate the necessary ers, and increasing the use of natural resources. As was
hardware components, including sensors and IoT devices. already said, smart agriculture has various challenges. To
Then, set up data collection and management, ensuring get around these challenges, both new and old technolo-
secure storage and preprocessing. Develop AI models gies must be used.
for real-time analysis and visualization of data, enabling
actionable insights for farmers.
According to the suggested algorithm as depicted
in Fig. 2, the sensors will start operating in accordance
with the power supply provided to the Arduino board.
The microcontroller unit and the soil moisture sensor are
both interfaced, and the microcontroller unit periodically
receives the corresponding readings from the soil mois-
ture sensor. Along with the temperature and humidity
of the microenvironment detected by the temperature
sensor, the air index is also monitored using an air index
sensor and NDVI time series data from MODIS Satellite for
adapting the new cropping pattern. The main objective
of the microcontroller unit is to receive the data values
transmitted by the sensors and the LoRa transmitter, which
is set up to save the data in the cloud. The microcontroller Fig. 5  Output of micro climate analysis humidity

Vol:.(1234567890)
SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1 Research

Fig. 10  Output of soil nutrients—phosperous value

Fig. 6  Output of micro climate analysis temperature

Fig. 11  Output of pest attack identification

Fig. 7  Output of micro climate analysis air quality

the sensor data exceeds a predetermined threshold value,
the microcontroller unit continuously examines the sensor
data using AI and sends an alarm SMS to the mobile phone
of an owner who is in a faraway place.
The relevant data obtained from measuring the DHT11
sensor’s varied readings in a range of climatic conditions
are used to determine the threshold value. By employ-
ing WSN nodes like LoRa for data transmission and data-
base systems for local data storage, this system can be
improved. Technology advancements and the meteoric
Fig. 8  Output of soil nutrients—nitrogen value emergence of AI have transformed traditional agriculture
into a smart, intelligent, automated agriculture. Smart agri-
culture reduces its carbon footprint by implementing sus-
tainable, green farming, limiting the use of pesticides and
fertilisers, and increasing the use of natural resources. The
agricultural industry will soon include Agriculture 5.0 [48].
By doing this, the system’s sustainability will be preserved
as yields rise. Both industrialised and developing countries
will follow a similar trend. From an economic and environ-
mental standpoint, humanity will embrace efficient food
production and delivery more than ever [50].
Future work of the work should prioritize sensor tech-
Fig. 9  Output of soil nutrients—potassium value nology advancements, enhancing AI models for preci-
sion agriculture, optimizing energy efficiency, expanding
user-friendly interfaces, promoting scalability and cost-
In this work, cloud-based AI models for smart agricul- efficiency. These efforts will contribute to more accurate
ture are used. The use of advanced microcontrollers in data collection, better decision-making for farmers, sus-
hardware has expedited the shift in computing paradigm. tainable IoT implementations, improved accessibility, and
Giving IoT devices intelligence is the most recent develop- wider adoption of this technology, ultimately fostering
ment. LoRa technology enables network accessibility. If increased agricultural productivity and sustainability.

Vol.:(0123456789)
Research SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1

on agro-ecology and sustainable agricultural systems. Univer-

sity of California, Santa Cruz, pp 1–14
Author contributions Data curation, I.S.A and R.K.K and P.K.B.; Formal 10. Godfray HCJ, Beddington JR, Crute IR, Haddad L, Lawrence D,
analysis, S.S. and P.I; Funding acquisition, P.I and P.K.B.; Methodology, Muir JF et al (2010) Food security: the challenge of feeding 9
I.S.A. and S.S.; Project administration, P.K.B.; Resources, I.S.A, and P.I. billion people. Science 327:812–818. https://​doi.​org/​10.​1126/​
; Supervision, S.S.; Writing–original draft, R.K.K and P.I. All authors scien​ce.​11853​83
have read and agreed to the published version of the manuscript. 11. Foley JA, Ramankutty N, Brauman KA, Cassidy ES, Gerber JS,
Johnston M et al (2011) Solutions for a cultivated planet. Nature
478:337–342. https://​doi.​org/​10.​1038/​natur​e10452
Funding The authors have not disclosed any funding. 12. Mueller ND, Gerber JS, Johnston M, Ray DK, Ramankutty N, Foley
JA (2012) Closing yield gaps through nutrient and water man-
Declarations agement. Nature 490:254–257. https://​doi.​org/​10.​1038/​natur​
e11420
Conflict of interest The authors have not disclosed any competing 13. Wang C-H (2014) Farming methods effects on the soil fertil-
interests. ity and crop productionn under a rice—vegetables cropping
sequences. J Plant Nutr 37:1498–1513. https://​doi.​org/​10.​1080/​
Open Access This article is licensed under a Creative Commons Attri- 01904​167.​2014.​881876
bution 4.0 International License, which permits use, sharing, adap- 14. Lin J, Yu W, Zhang N, Yang X, Zhang H, Zhao W (2017) A sur-
tation, distribution and reproduction in any medium or format, as vey on Internet of Things: architecture enabling technologies
long as you give appropriate credit to the original author(s) and the security and privacy and applications. IEEE Internet Things J
source, provide a link to the Creative Commons licence, and indicate 4(5):1125–1142
if changes were made. The images or other third party material in this 15. Hi X, An X, Zhao Q, Liu H, Xia L, Sun X et al (2019) State-of-the-art
article are included in the article’s Creative Commons licence, unless Internet of Things in protected agriculture. Sensors 19(8):1833
indicated otherwise in a credit line to the material. If material is not 16. Elijah O, Rahman TA, Orikumhi I, Leow CY, Hindia MN (2018)
included in the article’s Creative Commons licence and your intended An overview of Internet of Things (IoT) and data analytics in
use is not permitted by statutory regulation or exceeds the permitted agriculture: benefits and challenges. IEEE Internet Things J
use, you will need to obtain permission directly from the copyright 5(5):3758–3773
holder. To view a copy of this licence, visit http://​creat​iveco​mmons.​ 17. Tzounis A, Katsoulas N, Bartzanas T, Kittas C (2017) Internet of
org/​licen​ses/​by/4.​0/. Things in agriculture recent advances and future challenges.
Biosyst Eng 164:31–48
18. Vågen T-G, Winowiecki LA, Tondoh JE, Desta LT, Gumbricht T
(2016) Mapping of soil properties and land degradation risk in
Africa using MODIS reflectance. Geoderma 263:216–225
References 19. Khoa TA, Man MM, Nguyen T-Y, Nguyen VD, Nam NH (2019)
Smart agriculture using IoT multi-sensors: a novel watering
management system. J Sens Actuator Netw 8(3):45
1. World Health Organization (2019) The state of food security and 20. Biswas SB, Iqbal MT (2018) Solar water pumping system con-
nutrition in the world: safeguarding against economic slow- trol using a low cost ESP32 microcontroller. In: Proceedings of
downs and downturns. FAO, Rome IEEE Canadian conference on electrical & computer engineering
2. Wunderlich SM, Martinez NM (2018) Conserving natural (CCECE). IEEE, pp 1–5
resources through food loss reduction: production and con- 21. Gupta M, Abdelsalam M, Khorsandroo S, Mittal S (2020) Security
sumption stages of the food supply chain. Int Soil Water Conserv and privacy in smart farming: challenges and opportunities. IEEE
Res 6:331–339 Access 8:34564–34584. https://​doi.​org/​10.​1109/​ACCESS.​2020.​
3. Press Information Bureau Government of India Ministry of 29751​42
Finance 31-January-2022 “Despite COVID-19 shock agriculture 22. Muangprathub J, Boonnam N, Kajornkasirat S, Lekbangpong
sector grows at 3.9% in 2021–22 and 3.6% in 2020–21 N, Wanichsombat A, Nillaor P (2019) IoT and agriculture data
4. Gumma MK, Kajisa K, Mohammed IA, Whitbread AM, Nelson analysis for smart farm. Comput Electron Agric 156:467–474
A, Rala A, Palanisami K (2015) Temporal change in land use 23. Haseeb K, Ud Din I, Almogren A, Islam N (2020) An energy effi-
by irrigation source in Tamil Nadu and management implica- cient and secure IoT-based WSN framework: an application to
tions. Environ Monit Assess 187:4155. https://​doi.​org/​10.​1007/​ smart agriculture. Sensors 20(7):2081
s10661-​014-​4155-1 24. Sushanth G, Sujatha S (2018) IOT based smart agriculture sys-
5. Reynolds TW, Waddington SR, Anderson CL, Chew A, True Z, Cul- tem. In: 2018 International conference on wireless communica-
len A (2015) Environmental impacts and constraints associated tions, signal processing and networking (WiSPNET). IEEE, pp 1–4
with the production of major food crops in Sub-Saharan Africa 25. Araby AA, Abd Elhameed MM, Magdy NM, Abdelaal N, Abd Allah
and South Asia. Food Secur 7:795–822 YT, Darweesh MS, Fahim MA, Mostafa H (2019) Smart IoT moni-
6. Rajendranath UNVP, Hency VB (2015) Implementation of an toring system for agriculture with predictive analysis. In 2019
automated irrigation system smart irrigation system. In: IEEE 8th international conference on modern circuits and systems
sponsored 2nd international conference on innovations in infor- technologies (MOCAST). IEEE, pp 1–4
mation, embedded and communication systems 26. Kajol R, Kashyap AK (2018) Automated agricultural field analy-
7. Metclfe DS, Elkins DM (1980) Crop production: principles and sis and monitoring system using IoT. Int J Inf Eng Electron Bus
practices. Macmillan Publishing Co., Inc., New York 10(2):17
8. Oldfield EE, Bradford MA, Wood SA (2019) Global meta-analysis 27. Vanaja KJ, Suresh A, Srilatha S, Kumar KV, Bharath M (2018) IOT
of the relationship between soil, organic matter and crop yields. based agriculture system using node MCU. Int Res J Eng Technol
Soil 5:15–32. https://​doi.​org/​10.​5194/​soil-5-​15-​2019 5(3):3025–3028
9. Allen P, Van Dusen D (1988) Sustainable agriculture: choosing 28. Swain M, Zimon D, Singh R, Hashmi MF, Rashid M, Hakak S
the future. In: Appen P, Van Dusen D (eds) Global perspectives (2021) LoRa-LBO: an experimental analysis of LoRa link budget

Vol:.(1234567890)
SN Applied Sciences (2023) 5:322 | https://doi.org/10.1007/s42452-023-05526-1 Research

optimization in custom build IoT test bed for agriculture 4.0. 41. Mitra A, Mohanty SP, Corcoran P, Kougianos E (2021) EasyDeep:
Agronomy 11:820 an IoT friendly robust detection method for GAN generated
29. Yao-lin Z, Gao-qiang Z, Lei Z, Jin X (2011) Design of wire- deepfake images in socialmedia. In: Proceedings of the 4th FIP
less multi-point temperature transmission system based on international Internet of Things (IoT) conference (IFIP-IoT)
nRF24l01. In: 2011 international conference on business man- 42. Mitra A, Mohanty SP, Corcoran P, Kougianos E (2021) iFace: a
agement and electronic information. IEEE. https://​doi.​org/​10.​ deepfake resilient digital identification framework for smart cit-
1109/​icbmei.​2011.​59203​75 ies. In: Proceedings of IEEE international symposium on smart
30. Thenkabail PS, Schull M, Turral H (2005) Ganges and Indus river electronic systems (iSES) (formerly iNiS), 2021, Accepted, In
basin land use/land cover (LULC) and irrigated area mapping Press. 36 everything you wanted to know about smart agricul-
using continuous streams of MODIS data. Remote Sens Environ ture A PREPRINT
95(3):317–341 43. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen
31. Vitali G, Francia M, Golfarelli M, Canavari M (2021) Crop man- H, Wang Y (2017) Artificial intelligence in healthcare: past, pre-
agement with the IoT: An interdisciplinary survey. Agronomy sent and future. Stroke Vasc Neurol 2(4):230–243
11(1):181. https://​doi.​org/​10.​3390/​agron​omy11​010181 44. Mitra A, Mohanty SP, Corcoran P, Kougianos E (2020) A novel
32. Balakrishna K, Nethravathi SN, Harshitha K (2016) Real-time soil machine learning based method for deepfake video detection
monitoring system for the application of agriculture. Int J Eng in social media. In: Proceedings of IEEE international symposium
Sci Comput 6(5):2016 on smart electronic systems (iSES) (formerly iNiS), pp 91–96.
33. Ma Z, Pan X (2012) Agricultural environment information col- https://​doi.​org/​10.​1109/​iSES5​0453.​2020.​00031
lection system based on wireless sensor network. In: 2012 IEEE 45. Mitra A, Mohanty SP, Corcoran P, Kougianos E (2021) A machine
global high tech congress on electronics, pp 24–28 learning based approach for deepfake detection in social media
34. Radha N, Swathika R (2021) A polyhouse: plant monitoring and through key video frame extraction. SN Comput Sci 2(2):98.
diseases detection using CNN. In: Proceedings of international https://​doi.​org/​10.​1007/​s42979-​021-​00495-x
conference on artificial intelligence and smart systems (ICAIS), 46. Palaus M, Marron EM, Viejo-Sobera R, Redolar-Ripoll D (2017)
pp 966–971. https://d ​ oi.o
​ rg/1​ 0.1
​ 109/I​ CAIS5
​ 0930.2 ​ 021.9
​ 39584 ​ 7 Neural basis of video gaming: a systematic review. Front Hum
35. Kanchana S (2018) IoT in agriculture: smart farming. Int J Sci Neurosci 11:248
Res Comput Sci Eng Inf Technol 3:181–184. https://​doi.​org/​10.​ 47. Skinner G, Walmsley T (2019) Artificial intelligence and deep
32628/​cseit​183856 learning in video games a brief review. In: Proceedings of IEEE
36. Nagothu SK (2016) Weather based smart watering system using 4th international conference on computer and communication
soil sensor and GSM. In: Proceedings of world conference on systems (ICCCS), pp 404–408. https://​doi.​org/​10.​1109/​CCOMS.​
futuristic trends in research and innovation for social welfare 2019.​88217​83
(startup conclave), pp 1–3. https://​doi.​org/​10.​1109/​START​UP.​ 48. Saiz-Rubio V, Rovira-Más F (2020) From smart farming towards
2016.​75839​91 agriculture 5.0: a review on crop data management. Agronomy
37. Ogidan OK, Afia KR (2019) Smart irrigation system with an 10(2):207
androidbased remote logging and control. In: Proceedings of 49. Rahutomo R, Perbangsa AS, Lie Y, Cenggoro TW, Pardamean
IEEE AFRICON. IEEE. https://d ​ oi.o
​ rg/1
​ 0.1​ 109/a​ frico
​ n4675 ​ 5.2
​ 019.​ B (2019) Artificial intelligence model implementation in web-
91339​53 based application for pineapple object counting. In: Interna-
38. Soni VD (2020) Emerging roles of artificial intelligence in ecom- tional conference on information management and technology
merce. Int J Trend Sci Res Dev 4(5):223–225 (ICIMTech), pp 19–21
39. Strohmeier S, Piazza F (2015) Artificial intelligence techniques 50. Fraser EDG, Campbell M (2019) Agriculture 5.0: reconciling pro-
in human resource management—a conceptual exploration. In: duction with planetary health. One Earth 1(3):278–280
Kahraman C, Onar SC (eds) Intelligent techniques in engineering
management. Springer, pp 149–172 Publisher’s Note Springer Nature remains neutral with regard to
40. Mitra A, Mohanty SP, Corcoran P, Kougianos E (2021) Detection jurisdictional claims in published maps and institutional affiliations.
of deep-morphed deepfake images to make robust automatic
facial recognition systems. In: Proceedings of the 19th OITS
international conference on information technology (OCIT)

Vol.:(0123456789)