Agriculture is entering a new era—where data, intelligence, and innovation are redefining how food is produced, managed, and sustained. Data-Driven Intelligence: Deep Learning and Machine Learning in Agriculture takes readers on an engaging journey through the rapidly evolving world of artificial intelligence, presenting cutting-edge statistical, machine learning, and deep learning techniques tailored to agricultural challenges. From crop yield prediction, rainfall forecasting, and pest surveillance to image-based disease diagnosis and precision decision-making, the book demonstrates how advanced analytics can transform agricultural research and practice. Featuring expert contributions from renowned scientists and academicians, each chapter blends fundamental concepts with practical applications, enabling readers to understand not only how these models work but also when and why to use them. An essential resource for students, researchers, data scientists, extension professionals, and policymakers, this book empowers readers to harness the power of AI for building productive, climate-resilient, and sustainable agricultural systems in the digital age.
Dr. Mrinmoy Ray is currently serving as a Senior Scientist at the ICAR–Indian Agricultural Research Institute (IARI), New Delhi, India. He previously served as a Scientist in the Division of Forecasting and Agricultural Systems Modelling at the ICAR–Indian Agricultural Statistics Research Institute (IASRI), New Delhi, where he made significant contributions to research in statistical modelling and agricultural systems forecasting. Over the course of his career, he has published more than 100 research papers in reputed national and international journals. He has also developed several R packages to advance research and applications in his field. In recognition of his contributions, he was conferred the prestigious Jawaharlal Nehru Award in 2018 by ICAR, India. His current research interests include statistical modelling, technology forecasting and machine learning.
Dr. Amrender Kumar is a Principal Scientist (Agricultural Statistics) and Incharge at the Agricultural Knowledge Management Unit (AKMU) of ICAR-Indian Agricultural Research Institute, New Delhi, India. He obtained his Ph.D. in Statistics from Maharshi Dayanand University, Rohtak in 2012 and completed his M.Sc. in Agricultural Statistics from Indian Agricultural Research Institute, New Delhi in 1997. Dr. Kumar has extensive experience in statistical and ecological modelling, data mining, artificial intelligence-based techniques, and technology foresight. He began his career as a Scientist at ICAR-Indian Agricultural Statistics Research Institute in 1999, later joined IARI as a Senior Scientist in 2013, and has significantly to agricultural research with more than 100 peer-reviewed publications and several book chapters. He has also been actively involved in teaching, training, and research supervision at the Post- Graduate School of IARI since 2003, delivering courses on econometrics, forecasting techniques, statistical modelling, optimization techniques, and multi-variate analysis. Dr. Kumar has led and collaborated on numerous national and international research projects related to crop forecasting, pest and disease modelling, climate change impacts, and digital knowledge management in agriculture. He is also a recipient of several recognitions including the ICAR Junior Research Fellowship and qualification in the ICAR-NET for Lecturership.
Dr. Rajeev Ranjan Kumar is a Researcher in Agricultural Statistics and Informatics, dedicated to improving farming systems through AI and machine learning at ICAR-Indian Agricultural Statistics Research Institute, New Delhi. He has developed advanced hybrid time series models, including decomposition-based LSTM and Transformer-based architectures, for forecasting crop yields and prices under climate uncertainty. His AI-based price forecasting tools support in securing better market prices and reducing risks. He has developed over 15 R software packages with 100,000+ downloads and more than 60 research papers. Dr. Kumar has received the Young Scientist Award (2020) and Best Thesis Award (2021) from SSDAT. He has delivered expert lectures, promoted R-based statistical learning, and was awarded a travel grant by IAAE for an international presentation. His work fosters sustainable agriculture, addressing price instability, climate risks, and enhancing farmer livelihoods.
Dr. Anirban Mukherjee is a distinguished Senior Scientist at ICAR–Research Complex for Eastern Region (ICAR-RCER), Patna, with over a decade of experience in agricultural research, data analytics, and statistical modelling. Since joining ICAR in July 2013, he has increasingly focused on integrating advanced quantitative tools with agricultural systems research, contributing to evidence-based decision making and policy formulation. Dr. Mukherjee possesses a strong academic foundation, with specialization in extension systems during his M.Sc., and Doctoral research on Farmer Producer Companies (FPCs). Over time, his work has evolved toward the application of statistical and computational modelling approaches to understand complex socio-ecological and agricultural systems. He is currently involved in a ICAR-NASF-funded project centered on technology simulation and modelling, where he applies advanced methodologies, such as Agent-Based Modelling (ABM) and System Dynamics Modelling (SDM) to analyze farmer behaviour, technology adoption, and system-level interactions. His expertise also spans multi-variate statistics, structural equation modelling, and impact assessment using tools, such as SPSS, AMOS, and JASP. Dr. Mukherjee has made significant contributions to research methodology, including the development of indices, knowledge test batteries, and standardized scales. He has authored over 150 scholarly publications, including research papers, book chapters, and technical articles. His contributions have been recognized through prestigious awards, such as the Young Scientist Award (2016 and 2017) and the Jawaharlal Nehru Award (2020) for Outstanding Doctoral Research in Social Sciences. As an Editor of a book on statistical modelling, Dr. Mukherjee brings a strong commitment to analytical rigor, methodological innovation, and interdisciplinary integration. His editorial perspective emphasizes the application of advanced modelling techniques to address real-world agricultural and socio-economic challenges, fostering data-driven insights and sustainable development.
1. Which Model to Use? Navigating Modelling Tools for Agricultural Stakeholders..........................................................................1 Anirban Mukherjee, Pankaj Suman, Kumari Shubha and Mrinmoy Ray
2. Introduction to Statistical Modelling in Agriculture.............................15 Chiranjit Mazumder, Pankaj Das and Samir Barman and Pradip Basak
3. Classification Tree Models for Better Decision-Making in Agriculture................................................................................................35 Ramasubramanian V., Abin George and Mrinmoy Ray
4. Support Vector Machines (SVM) for Crop Yield Forecasting..............57 Pankaj Das, Samir Barman, Chiranjit Mazumder and Tanuj Misra
5. Logistic Regression with Application to Crop Yield Prediction...........75 N.M. Alam, Sourav Ghosh, Debarati Datta, S.P. Mazumdar, Shamna A., Sabyasachi Mitra and Gouranga Kar
6. Applications of Machine Learning Models in Modern Agricultural Systems................................................................................93 Rohan Kumar Raman, Anirban Mukherjee, Mrinmoy Ray, Pankaj Suman, Ujjwal Kumar, Abhay Kumar, D.K. Singh and Ashutosh Upadhayaya
7. XGBoost Model for High-Dimensional Agricultural Data.................109 Sharanbasappa D. Madival, Ritwika Das, Dwijesh Chandra Mishra and Girish Kumar Jha
8. Predictive Modelling of Indian Rainfall Through Self-Attention Powered Transformer Deep Learning Architecture............................119 G.H. Harish Nayak, Md. Wasi Alam, Ashalatha K.V., G Avinash, Mrinmoy Ray, Rajeev Ranjan Kumar, B. Samuel Naik and Sujith Arokia Swamy B
9. Random Forest for Pest and Disease Forewarning.............................145 Pradip Basak, Prahlad Sarkar, Shyamal Kheroar, Subhradip Roy, Mrinmoy Ray, Chiranjit Majumder and Litan Das
10. Overview of Deep Learning in Agriculture..........................................161 Md Ashraful Haque, Harsh Sachan, Shalini Kumari, Chandan Kumar Deb, Shashi Dahiya, Alka Arora and Sudeep Marwaha
11. Gated Recurrent Unit (GRU): An Advanced Recurrent Neural Network for Agricultural Time Series Data............................177 C.K. Nihala Asees and Prity Kumari
12. Long Short-Term Memory (LSTM) Networks and Its Application in Agriculture.....................................................................193 Ronit Jaiswal, Rajeev Ranjan Kumar, Geetika Malik, Javid Iqbal Mir and Kapil Choudhary
13. Recurrent Neural Network for Time Series Forecasting in Agriculture..............................................................................................287 Sujith Arokia Swamy B., Raj Shekar M, G.H. Harish Nayak and G. Avinash
14. Advances in YOLO-Based Deep Learning for Fast Detection of Pests and Disease Symptoms in Crops..............................................307 Chandan Kumar Deb, Md. Ashraful Haque, Akash Bharti, Sourav Chakrabarty, Harsh Sachan, Shalini Kumari, Madhurima Das, Alka Arora and Sudeep Marwaha
15. Convolutional Neural Networks (CNN) for Agricultural Image Classification................................................................................327 Yashavanth B.S., Sayantani Karmakar and A. Dhandapani
Appendix...................................................................................................345
