AgroPredictX: Machine Learning for Precision Farming

Abstract

Agriculture is the primary source of livelihood for a massive population in India, particularly in states like Maharashtra. However, farmers face mounting challenges including unpredictable climate conditions, soil degradation, and increasing instances of crop diseases. To combat these issues, this research proposes an AI-Powered Crop Yield Prediction and Agricultural Diagnostic System that integrates Machine Learning and Computer Vision technologies into a unified platform. The system utilizes a Random Forest regression model to predict crop yield based on rainfall, temperature, soil nutrients (NPK), crop type, and seasonal data, achieving a high predictive accuracy of 91.64%. Furthermore, a Convolutional Neural Network (CNN) model is incorporated for early plant disease detection and treatment recommendation. The system is designed with a multi-layered architecture accessible via web and mobile interfaces, providing farmers with actionable insights to optimize resource management and agricultural productivity.

Introduction

Agriculture, especially in countries like India, faces major challenges such as climate variability, soil degradation, pests, and crop diseases, which reduce productivity and increase risks for farmers. Traditional decision-making methods are often unreliable under changing environmental conditions.

The proposed AI-Powered Crop Yield Prediction and Agricultural Diagnostic System addresses these issues by integrating machine learning and computer vision into a unified platform. It uses a Random Forest model to predict crop yield based on factors like rainfall, temperature, soil nutrients, and season, and a CNN model to detect plant diseases from leaf images.

The system follows a multi-layer architecture with a React web interface and Android app for user interaction, a Node.js backend for processing, a Python-based ML engine for predictions, and MongoDB for data storage. It also includes a Behaviour Analysis Module that studies historical data to improve prediction accuracy, identify disease patterns, and provide personalized crop recommendations.

The methodology involves data collection, preprocessing, model training, and system integration, ensuring accurate and efficient results. Overall, the system enhances agricultural decision-making, improves productivity, reduces risks, and promotes sustainable, data-driven farming practices.

Conclusion

The research demonstrates the immense potential of AI in transforming traditional agriculture into a data-driven enterprise. The 91.64% accuracy of the Random Forest model and the effective CNN-based disease detection provide a comprehensive decision-support system. Future enhancements will integrate real-time weather analytics and expand geographic coverage.

References

[1] B. S. Pawar, “Digital Health Empowerment in Rural Areas,” Journal of Community Health, vol. 49, no. 2, pp. 312–325, 2024. [2] V. S. Kulkarni, “Women’s Preventive Healthcare Frameworks,” Global Health Action, vol. 15, no. 1, p. 2039211, 2022. [3] S. Mohanty, D. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, p. 1419, 2016. [4] K. P. Ferentinos, “Deep Learning Models for Plant Disease Detection and Diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. [5] N. Ramesh and D. Vydeki, “Recognition and Classification of Paddy Leaf Diseases Using Optimized Deep Neural Network with IoT,” Information Processing in Agriculture, vol. 7, no. 4, pp. 1–12, 2020. [6] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep Learning in Agriculture: A Survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [7] J. Jeong, A. Resop, N. Mueller, D. Fleisher, and others, “Random Forests for Global and Regional Crop Yield Predictions,” PLoS ONE, vol. 11, no. 6, e0156571, 2016. [8] T. K. Ho, “Random Decision Forests,” Proceedings of the Third International Conference on Document Analysis and Recognition, pp. 278–282, 1995. [9] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, Cambridge, Massachusetts, 2016. [10] J. Schmidhuber, “Deep Learning in Neural Networks: An Overview,” Neural Networks, vol. 61, pp. 85–117, 2015.

Copyright

Copyright © 2026 Gaykar Sanika Bipin, Dumbre Gauri Santosh, Hadawale Akshada Dattatray, Prof. Nawale S. K.. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.