See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/385097323

ARTIFICIAL INTELLIGENCE IN AGRICULTURE

Chapter · October 2024

CITATIONS READS

0 200

2 authors:

Janaki Dasarathan Hemavarshini M P

Tamil Nadu Agricultural University Tamil Nadu Agricultural University
31 PUBLICATIONS 38 CITATIONS 8 PUBLICATIONS 3 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Hemavarshini M P on 21 October 2024.

The user has requested enhancement of the downloaded file.

 Advances
in
Agriculture Sciences
Volume - 42

Chief Editor
Dr. R.K. Naresh
Professor, Department of Agronomy, College of Agriculture, Sardar
Vallabhbhai Patel Univ. of Agri & Tech, Meerut, Uttar Pradesh, India

®
AkiNik Publications
New Delhi
Published By: AkiNik Publications

AkiNik Publications
169, C-11, Sector - 3,
Rohini, Delhi-110085, India
Toll Free (India) – 18001234070
Phone No.: 9711224068, 9911215212
Website: www.akinik.com
Email: [email protected]

Chief Editor: Dr. R.K. Naresh

The author/publisher has attempted to trace and acknowledge the materials

reproduced in this publication and apologize if permission and
acknowledgements to publish in this form have not been given. If any material
has not been acknowledged please write and let us know so that we may rectify
it.

The responsibility for facts stated, opinion expressed or conclusions reached

and plagiarism, if any, in this book is entirely that of the author. So, the views
and research findings provided in this publication are those of the author/s
only. The Editor & Publishers are in no way responsible for its contents.

© AkiNik Publications TM
Publication Year: 2023
Pages: 154
ISBN: 978-93-5570-646-1
Book DOI: https://doi.org/10.22271/ed.book.2175
Price: ` 764/-

Registration Details
➢ Printing Press License No.: F.1 (A-4) press 2016
➢ Trade Mark Registered Under
• Class 16 (Regd. No.: 5070429)
• Class 35 (Regd. No.: 5070426)
• Class 41 (Regd. No.: 5070427)
• Class 42 (Regd. No.: 5070428)
 Contents

Chapters Page No.

1. Extraction and Analysis of Pesticides Residue in Vegetables 01-14
(Nirali Patel and Mayuri C. Rathod)

2. What is Weed, Classification, Characteristics and Different

Methods of Weed Management 15-28
(Utkarsh Singh, Ashish Kumar Verma, Pradeep Kumar, Shivam Kaushik,
Ashish Kumar and Ajay Maurya)

3. Establishment of Agro-Meteorological Observatory and their

Importance in Agriculture 29-38
(Devi Lal and Ram Niwas)

4. Biostimulants for Sustainable Crop Production 39-65

(T. Sunil Kumar, R. Sai Mithra and V.N. Shiyal)

5. Paradigm of Climate Change Impacts on Food Safety and

Security 67-89
(Shubham, Shivani Chand, Shilpa Kaushal, Arushi Kapoor and Uday Sharma)

6. Insect Pest Management in Organic Farming: An Indian

Perspective 91-105
(Mayuri Baruah, Rituraj Saikia and Sanjib Ranjan Borah)

7. Artificial Intelligence in Agriculture 107-120

(D Janaki, MP Hemavarshini, R Poorniammal and R Chitra)

8. Gene Regulation for Disease Resistance in Field Crops 121-141

(K. Amarnath and K. Madhavilatha)

9. Conservation Agriculture: A Sustainable Pathway 143-154

(Dr. Pawan Kumar, Satender Kumar and Dr. Sonia Rani)
 Chapter - 7
Artificial Intelligence in Agriculture
D Janaki, MP Hemavarshini, R Poorniammal and R Chitra

Abstract
Artificial Intelligence (AI) is one of the key area of studies in computer
science. AI has excessive importance in agriculture wherein about 30.7% of
the sector population is depending on 2781 million hectares of agricultural
land. The major issues in agriculture are crop tracking, soil health, pest and
disease infestation, insufficient utility of chemical substances, fallacious
drainage and irrigation, weed manage, yield prediction, and so on.
(Gouravmoy Bannerjee et al., 2018). To get a good crop, the fertile land with
good enough fertilizer. Right dose of fertilizer can help plants to produce
right yields and quantities, to fulfill the desires of a global population with
increasing number of rising in need of food. (Marianah Masrie et al., 2017).
Acquiring excessive-resolution aerial pix from Unmanned Aerial vehicle
(UAV) can assist growers to evaluate soil conditions, crop growth and
provide beneficial records approximately plant fitness. It create excessive-
resolution area maps, and spray an appropriate amount of liquid in actual
time for even insurance presents the opportunity for patch spraying and
correct website online-particular control. (Nadia Delavarpour et al., 2021).
Agricultural robots are developed for many agricultural activities like crop
cultivation, planting, weedicide spraying, pruning and harvesting. (Arad et
al., 2019). Artificial Intelligence in agriculture support the farmers to
automate their farming to precise cultivation for better usage of fewer
operation with good crop yield.
Keywords: Artificial intelligence, weed manage, agriculture, weedicide
spraying, pruning and harvesting
Introduction
Agricultural operations provide an essential supply of livelihood,
increase GDP, serve as a source of national commerce, lessen
unemployment, offer raw substances for other sectors and assist the
economy grow overall. With the arena's populace developing exponentially,

Page | 109
it's more crucial than ever to think again agricultural strategies to give you
new methods to preserve and enhance agricultural hobby. Other technical
breakthroughs, along with large statistical analysis, robotics, the net of
factors, the provision of low-fee sensors and cameras, drone etc. or even
wide net connectivity on geographically separated fields and this will enable
the adoption of AI into agriculture (Eli-Chukwu, 2019). AI is having a vast
influence throughout all industries. Every field is trying to automate
particular professions through the usage of shrewd technology. Agriculture
and farming are many of the global's oldest and maximum important
vocations. It's far very considerable in the financial area. By 2050, the
population is expected to reach greater than nine billion, so we need to
increase agricultural production as much as 70% to meet demand. As an end
result, we need to take a more strategic approach to boost output. (Jiali Zha,
2020)
Definition
The definition of artificial intelligence has changed over the years due to
rapid development, and there is no single definition even today. Artificial
intelligence is the simulation of human intelligence processes by machines,
especially computer systems. It is related to the similar task of using
computers to understand human intelligence.
Importance of artificial intelligence
Synthetic Intelligence (AI) is a paradigm shift in how we see farming
these days. AI-powered answers will no longer handiest permit farmers to do
more with less, however it's going to assist farmers to achieve greater yield,
as in keeping with the growing utilization of high-tech machineries in well-
known lifestyles, along with training, hospitals and even governance.
Agriculture is the maximum reverberated of all, as artificial intelligence is
targeted on easiness and clever running. Agricultural fields need to be more
desirable with AI at low expenses and clean processing. Through artificial
Intelligence numerous agriculture problems are controlled in a brief interval
of time. In artificial intelligence, numerous techniques like enhance
harvesting and introduce indoor farming for a better production charge of
crops.
Types of artificial intelligence
Narrow AI
A narrow AI is a type of AI that is capable of performing a specific task
or one task with intelligence. Narrow AI cannot go beyond its domain or

Page | 110
boundaries because it is only trained for a specific project. It is the goal-
oriented version of AI designed to better perform a single task for examples
include chess, buying guides on e-commerce websites, self-driving cars,
speech and image recognition
General artificial intelligence
It is referred to as strong AI. Some key trends of strong AI include
perceptual tasks, such as vision and language processing, along with
cognitive tasks, such as processing, contextual understanding and thinking.
It's the kind of artificial intelligence we see in movies, just like robots. AGI
is a device with widely known intelligence that, much like a character, can
explore that intelligence to solve any problem. Introducing a device with
human-level intelligence that can be used for any challenge.
AI Application in crop and soil monitoring
The satisfactory of vegetation extensively depends on the type of soil
and nutrients of the soil. However with the growing change of deforestation,
the soil first-rate is degrading daily, and it's far hard to decide it.AI is
efficiently used to monitor soil health and offer records which includes
moisture level, pH degree and nutritional deficiencies in the soil. With the
help of AI, we minimized the problems like soil-borne pathogens and
pollutants.AI is an efficient way to identify possible defects and nutrient
deficiencies in the soil. It is an effective way to perceive feasible defects and
nutrient deficiencies in the soil. It's far identified through snap shots captured
through the digicam.AI may be used to make soil maps, which help to reveal
soil characteristics for future planning and prediction of soil nutrient status
and management to be adopted in the future for better yield.
In this research, photo processing and synthetic neural community was
used to effectively detect the pH of soil and nutrients using Soil Testing Kit
(STK) and Rapid Soil Testing (RST) of Bureau of Soils and Water
Management. The use of artificial neural network is to accelerate the
performance of image processing with accurate result.
The program that determines the six nutrients (Nitrogen, Phosphorus,
Potassium, Zinc, Calcium, and Magnesium) and pH level of the soil through
photo processing and the use of synthetic neural community became
effective with the use of MATLAB. Ten soil samples randomly selected with
varying nutrient content were used for the assessment of this system. The
samples had been manually tested and as compared to the STK. This was
synchronized with manual interpretation of soil testing and this system.
(Puno et al., 2017)

Page | 111
 Soil fertility in determining the health of soil, as it indicates the extent to
which why soil is capable of supporting plant life. Soil fertility is measured
by the amount of macro-and micronutrients, water, pH, EC etc. Most farmers
go for the blanket recommendation of fertilizers for the crops. However,
adding fertilizers in the right amount is of great importance since excess or
deficit dose of fertilizers will affect the soil quality as well as the yield. The
soil nutrients content determined by manual method and as well as
quantified by sensors. An automatic machine for the controlled addition of
fertilizers has been developed for balanced dertilization.
The device determines NPK nutrients in the soil with AI and estimates
the fertilizers to be applied. The time taken for determining the soil testing
by chemical methods in the laboratory will be more than a week whereas in
the proposed machine the results are obtained within half-hour. The results
received from the soil check are fed to sensors and the outcomes are
analyzed with the use of a microcontroller which takes few seconds.
(Amurtha et al., 2016)
Optical transducer is evolved to measure and to find the presence of
Nitrogen (N), Phosphorus (P) and Potassium (K) of soil. Such transducer
decide the extra contents of those nutrients are to be introduced to the soil to
boom soil fertility. The N, P and K value are determined by way of
absorption light of every nutrient. The optical transducer, LEDs and
photodiode with Arduino microcontroller as an opportunity approach of
determination of the deficiency N, P or K within the soil. This project can
lessen the problems in determining the amount of nutrients in soil. It also
reduce the undesired use of fertilizers to be applied to the soil. (Marianah
Masrie et al., 2017)
The sensors are used for identification and mapping of salt-affected
regions. For mapping of salt affected areas it is related to the spectral
behaviour of salt types, spatial distribution of salts at the terrain floor,
temporal modifications on salinity, interference of crops and spectral
confusion with other terrain surfaces. (Metternicht and Zinck, 2003)
Many elements interfere with soil reflectance like tillage practices, crop
residue, row orientation and soil moisture. Therefore, the usage of
multispectral imagery is excellent tool for farms having uniform tillage and
moisture conditions at the time of photograph acquisition. The soil property
of interest need to show cast a spectral image for example, soil with higher
sand content material tend to have a better reflectance in the visible and NIR
part of the spectrum. (E.M. Barnes, M. G. Baker, 2000)

Page | 112
 Synthetic neural networks are an effective method of modelling both
quantitative and qualitative descriptions of soil. The outcomes help to give
the accurate quantity of clay, silt and natural carbon present in the soil.
(Levine, 1995)
The identification of nutrient deficiencies is achieved with the aid of the
convolutional neural network is displayed in the system. The sensors like
soil moisture, humidity, temperature, pH is taken into consideration for
figuring out the amount of fertilizer. The machine can routinely fertilize the
field with the aid of sprinkling mechanism. (Amirtha T et al., 2020)
AI Application in weed management
One of the challenging problem in crop cultivation is weed control,
weeds compete with crop plants for resources like water, nutrients, and
daylight. For weed management, we use the chemical weedicide, it has a
doubtlessly poor effect on public health and extra use can pollute the
environment. Use of computer visualization, robotics, and machine studying
AI practices had been designed to lessen the usage of herbicides through
unique and suitable management of weeds. With AI sensors, weed can be
detected effortlessly, and it additionally detects weed affected regions. The
herbicides may be precisely sprayed to lessen the use of herbicides and also
saves time and crop. AI helps to locate and discriminate harmful weed
bloom in the crop fields.
The studies presented a collaborative human-robot framework for
precise spraying of grape cluster objectives. A test to assess the factors of the
collaborative human-robotic framework, operating in sync turned into
designed, implemented and evaluated. The test proves the feasibility of
human-robot collaboration for the complex venture of focused spraying. The
collaborative spraying machine reduces the quantity of sprayed chemicals by
50%, which has both monetary and environmental influences. (Berenstein et
al., 2017)
AI in disease detection
The chief threat to the worldwide economic system, environment,
clients, and farmers can be caused by plant diseases.AI help to discover the
disease and offer the applicable remedy. With this, they could easily
diagnose diseases with right method and on time. It can save the life of plant
and farmer's time.
The numerous meteorological information like temperature, relative
humidity, leaf wetness, duration and wind velocity are used for the early

Page | 113
detection for opportunity of diseases in crops. Characterization of numerous
meteorological data in linguistic variable is logical to describe favourable
weather conditions. Fuzzy logic gives the opportunity to outline linguistic
variables offered professional device estimates the chance of incidence of
ailment within the plant. (Tilva et al., 2013)
IOT gadget is designed for early and accurate detection of diseases by
using the usage of machine learning and shows insecticides to protect the
crop from those diseases and decrease the guide disease detection efforts.
The usage of this gadget, farmers get the information of scheduling the
fertilizers, pesticides spraying, irrigation, etc. This may be beneficial to
farmers and to protect the vineyards from affecting the diseases. With the aid
of correct identification of sicknesses and offering accurate spraying and
irrigation time table, development within the great and amount of grapes is
achieved together (Patil et al., 2016).
The professional system that turned into advanced the usage of the if-
then regulations may be used for drawing conclusions on the issue of pests
and illnesses of plant. The machine has a mechanism of drawing conclusions
primarily based on understanding that has been saved in the understanding
base and interactive talk among customers and structures. This professional
device may be used by the person and useful for the person, especially in
which the presence of specialists hard to locate and a reference e book on
pests and plant illnesses are tough to acquire. The person can without
difficulty perform the system and achieve consequences quickly, based on
the recognized signs and symptoms of the plant without the want for direct
session with a consultant on pest and plant illnesses. (Dewanto Satrio and
Jonathan Lukas, 2014). For correct and a success cultivation of crops it's far
important to discover sicknesses accurately. Raspberry Pi based totally smart
self-reliant Farming robot with plant health indication the use of photograph
we can accurately discover and classify sicknesses on diverse vegetation
using all above strategies. (Prerana S. Doke, 2018)
The rice disease detection with the usage of IoT architecture with drone
was studied. This study proven that the use of rice disease detection machine
uses the HSV colour area, which can be used for disease segmentation. With
this system, we could detect the place on the leaf where the disease occurred,
and we will see the course for the first stage of early detection and
notification (Kitpo et al., 2018).
AI in pest management
Pests are the insects dwelling and developing in a place where not
desired and can damage to vegetation, human beings, structures, and

Page | 114
different creatures. This affects the plant growth and in turn affect the yield.
The use of AI answers to address this problem.
If pests are detected early, suitable measures may be taken to protect the
crop by using appropriate and reduced pesticide use, thereby boosting crop
yield. The companies involved in pest control use artificial Intelligence
programmed to develop the pest path plan to pest prediction.
With the assist of drone, the farmers can really visit all of the vegetation
and monitora and locate pests, diseases, dead soil, or abnormal degradation
of the plants. The farmer can acquire the data for any specific crop/ region
and therefore prevent the pest incidence.
Image processing plays an important role in the detection of pests. The
purpose of this pest identification is to find the pest is use of pan tilt digital
camera for taking crop leaves images without affecting the crop leaves by
way of using drone vehicle. (Divya, 2018)
Selvaraj et al., 2019 introduces a system with practical and relevant
answer for detecting the elegance and place of diseases in banana plant
which represents a prime similar distinction with different methods for plant
diseases type. The developed model become capable of discover the
difference between affected and good for specific banana disorder
identification.
AI in drone technology
To create 3D map of the field, its terrain, irrigation drainage and soil
variability ought to be evolved the use of the drone. This must be
accomplished before the crop cycle begins. Drones with high decision
cameras collect precision area photos. Chemical spraying and crop health
assessment prevails as one of the most important domains in agriculture to
provide drone-based totally solutions in coactions with pc imaginative
technology and AI. It also gives farmers precise statistics, permitting them to
make well-informed decisions about pesticide software, water necessities,
and soil fitness.
A low-value Weed Identity machine (WIS) the use of RGB photos taken
with the aid of drones as schooling data and making use of Convolutional
Neural Networks (CNN) to construct the identity version. The result of the
WIS may be used as a reference for agriculture researchers and also can be
used to tell farmers to take important decisions. (Liang et al., 2019)
The photos from UAV with Tetracam on-board may be a useful device
for detecting nitrogen deficiencies. Image procedure is simple may be geared

Page | 115
up in a short time. In this manner, the farmer can take decisions to provide
suitable management strategy on a site-specific and solve nitrogen
deficiencies in crop. (Aguera, 2011)

AI in robotics
Robotics is being extensively used in one-of-a-kind sectors, particularly
in manufacturing, to carry out complicated tasks. These days, different AI
groups are growing robots to be employed inside the agriculture quarter.
these AI robots are advanced in one of these way that they could perform a
couple of tasks in farming.AI robots also are trained in checking the
exceptional of vegetation, stumble on and controlling weeds, and harvesting
the crop with quicker speed in comparison to a human.
The massive variations between a modified and unmodified crop for
harvest in a single row planting with machine harvest was studied in sweeper
robot. The performance for the modified crop was to 61.0% rather than 29%
of the unmodified crop. This suggest the performance of the robot via
addressing occlusions and clusters of fruit. The harvest success was 61% for

Page | 116
the best crop conditions. This shows the importance of a success robotic
harvesting. (Boaz Arad et al., 2020)

The SWEEPER robot for harvesting sweet pepper

References
1. Agüera F, Carvajal F, Pérez M. Measuring sunflower nitrogen status
from an unmanned aerial vehicle-based system and an on the ground
device. International Archives of the Photogrammetry, Remote Sensing
and Spatial Information Sciences. 2011;38(1):C22.
2. Amirtha T, Gokulalakshmi T, Umamaheswari P, Rajasekar T. Machine
Learning Based Nutrient Deficiency Detection in Crops. International
Journal of Recent Technology and Engineering, 2020, 8(6).
3. Amrutha A, Lekha R, Sreedevi A. Automatic Soil Nutrient Detection
and Fertilizer Dispensary System, International Conference on Robotics:
Current Trends and Future Challenges (RCTFC), 2016.
4. Barnes EM, Baker MG. Multispectral data for mapping soil texture:
possibilities and limitations. Applied Engineering in Agriculture.
2000;16(6):731.
5. Berenstein Ron, Yael Edan. Human‐robot collaborative site‐specific
sprayer. Journal of Field Robotics. 201;34(8):1519-1530.
6. Boaz Arad, Jos Balendonck, Ruud Barth, Ohad Ben‐Shahar, Yael Edan,
Thomas Hellstrom, et al. Development of a sweet pepper harvesting
robot, Journal of Field Robotics, 2019, 1-13.
7. Dewanto, Satrio, Jonathan Lukas. Expert system for diagnosis pest and
disease in fruit plants. In EPJ Web of Conferences, EDP Sciences.
2014;68:000-24.

Page | 117
8. Divya, Bhuvaneswari. Detection of Pest from Paddy Crop Leaf Using
Image Processing Techniques. International Journal of Engineering
Research & Technology. 2018;7:7.
9. Gai, Jingyao, Lie Tang, Brian L. Steward. Automated crop plant
detection based on the fusion of color and depth images for robotic weed
control. Journal of Field Robotics. 2020;37(1):35-52.
10. Gouravmoy Bannerjee, Uditendu Sarkar, Swarup Das, Indrajit Ghosh.
Artificial Intelligence in Agriculture: A Literature Survey. International
Journal of Scientific Research in Computer Science Applications and
Management Studies, 2018. ISSN 2319 – 1953.
11. Jiali Zha, Artificial Intelligence in Agriculture, Journal of Physics:
Conference Series, 2020.
12. John Carlo Puno, Edwin Sybingco, Elmer dadios, Ira Valenzuela, Joel
cuello. Determination of Soil Nutrients and pH level using Image
Processing and Artificial Neural Network, IEEE, 2017.
13. Kitpo, Nuttakarn, Masahiro Inoue. Early rice disease detection and
position mapping system using drone and IoT architecture. In 2018 12th
South East Asian Technical University Consortium (SEATUC), IEEE.
2018;1:1-5.
14. Levine ER, Kimes DS, Sigillito VG. Classifying soil structure using
neural networks. Ecological modelling. 1996;92(1):101-108.
15. Liang, Wei-Che, You-Jei Yang, Chih-Min Chao. Low-cost weed
identification system using drones. In 2019 Seventh International
Symposium on Computing and Networking Workshops (CANDARW),
IEEE, 2019, pp. 260-263.
16. Marianah Masrie, Mohamad Syamim, Aizuddin Rosman, Rosidah Sam,
Zuriati Janin. Detection of Nitrogen, Phosphorus, and Potassium (NPK)
nutrients of soil using Optical Transducer, Proc. of the 4th IEEE
International Conference on Smart Instrumentation, Measurement and
Applications (ICSIMA), Malaysia, 2017.
17. McCarthy J, Minsky ML, Rochester N, Shannon CE. A Proposal for the
Dartmouth Summer. Research Project on Artificial Intelligence.
1955;27(4):12-12.
18. Megha P. Arakeri, Vijaya Kumar BP, Shubham Barsaiya, Sairam HV.
Computer Vision Based Robotic Weed Control System for Precision
Agriculture, Proc. of the 4th IEEE International Conference on Smart

Page | 118
 Instrumentation, Measurement and Applications (ICSIMA), Malaysia,
2017.
19. Metternicht, Graciela Isabel, Zinck JA. Remote sensing of soil salinity:
potentials and constraints. Remote sensing of Environment.
2003;85(1):1-20.
20. Nadia Delavarpour, Cengiz Koparan, John Nowatzki, Sreekala Bajwa,
Xin Sun. A Technical Study on UAV Characteristics for Precision
Agriculture Applications and Associated Practical Challenges. Remote
sensing, 2021.
21. Ngozi Clara Eli-Chukwu. Applications of Artificial Intelligence in
Agriculture: A Review, Engineering, Technology & Applied Science
Research. 2019;9(4):4377-4383.
22. Patil, Suyash S, Sandeep A. Thorat. Early detection of grapes diseases
using machine learning and IoT. In 2016 second international
conference on Cognitive Computing and Information Processing
(CCIP), pp. 1-5. IEEE
23. Prerana S. Doke, Mali SD. Raspberry Pi based Intelligent Autonomous
Farming Robot with plant health indication using Image Processing.
International Journal of Creative Research Thoughts. 2018;6:2.
24. Puno JC, Sybingco E, Dadios E, Valenzuela I, Cuello J. December.
Determination of soil nutrients and pH level using image processing and
artificial neural network. In 2017 IEEE 9th International Conference on
Humanoid, Nanotechnology, Information Technology, Communication
and Control, Environment and Management (HNICEM). IEEE,
2017, pp. 1-6.
25. Selvaraj, Michael Gomez, Alejandro Vergara, Henry Ruiz, Nancy
Safari, Sivalingam Elayabalan, et al. AI-powered banana diseases and
pest detection. Plant Methods. 2019;15(1):1-11.
26. Sudhir Rao Rupanagudi, Ranjani BS, Prathik Nagaraj, Varsha G Bhat,
Thippeswamy G. A Novel Cloud Computing based Smart Farming
System for Early Detection of Borer Insects in Tomatoes, International
Conference on Communication, Information & Computing Technology
(ICCICT), Mumbai, 2015.
27. Tilva, Vidita, Jignesh Patel, Chetan Bhatt. Weather based plant diseases
forecasting using fuzzy logic. In Nirma University International
Conference on Engineering (NUiCONE), IEEE, 2013, 1-5.

Page | 119
28. Wei-Che Liang, You-Jei Yang, Chih-Min Chao. Low-Cost Weed
Identification System Using Drones, Seventh International Symposium
on Computing and Networking Workshops, 2019.

Page | 120

View publication stats