AgriPredict: An Integrated Machine Learning Framework for Crop Price Forecasting and Leaf Disease Identification

Abstract

Agriculture remains the backbone of the Indian economy, yet farmers continue to face significant challenges including unpredictable crop prices, rampant plant diseases, and limited access to timely decision-support tools. This paper presents AgriPredict, an integrated machine learning framework designed to assist farmers and village officials (Talathis) through two primary modules: crop price forecasting and leaf disease identification with treatment recommendations. The crop price forecasting module leverages machine learning regression models trained on historical market data, weather patterns, and regional crop information to predict future prices, enabling farmers to plan sales strategies effectively. The disease identification module employs Convolutional Neural Networks (CNNs) to classify leaf diseases from uploaded images and recommends appropriate pesticide treatments, facilitating early intervention and reduced crop loss. The platform further integrates real-time weather forecasts and links to government agricultural schemes, providing a holistic decision-support environment. Experimental evaluation demonstrates high accuracy in both price forecasting and disease classification tasks. The system is designed with a user-friendly web interface accessible to users with limited technical exper-tise. AgriPredict contributes toward bridging the technological gap in Indian agriculture, promoting data-driven decisions that improve crop yield, reduce financial losses, and enhance overall agricultural productivity.

Introduction

The text presents AgriPredict, an AI-based integrated agricultural platform designed to support farmers with crop price forecasting, plant disease detection, weather updates, and government scheme access within a single system.

Agriculture in India and other developing countries faces major challenges such as price volatility, plant diseases, and lack of timely information, which often force farmers to rely on intuition rather than data. While machine learning and deep learning techniques (such as ARIMA, Random Forest, LSTM, and CNNs like VGG16 and ResNet) have been successfully used for price prediction and disease detection separately, most existing solutions are fragmented and do not combine these services into one unified platform.

To address this gap, the proposed AgriPredict system integrates multiple components:

• Crop price forecasting module using ML models (Random Forest and LSTM) trained on historical prices, weather, crop type, and regional data.
• Leaf disease detection module using CNNs (transfer learning with ResNet/VGG16) trained on the PlantVillage dataset for identifying plant diseases and recommending treatments.
• Weather integration using external APIs like OpenWeatherMap.
• Government scheme access for farmer support.
• Role-based web platform for Farmers and Talathis (local officials), allowing data entry, forecasting, and advisory services.

The system architecture includes a frontend interface, backend Flask API, machine learning models layer, database storage, and external API integration. It uses datasets from AGMARKNET and PlantVillage, and is deployed as a web application with real-time inference capabilities.

Experimental results show strong performance:

• Disease detection CNN achieved about 96.4% accuracy
• Price forecasting performed best with Random Forest (MAE ~142.3) and LSTM (~158.9 MAE), outperforming traditional methods like ARIMA.

Overall, AgriPredict aims to empower farmers with data-driven decision-making, improve productivity, reduce losses, and provide an accessible, unified agricultural intelligence system.

Conclusion

This paper presented AgriPredict, an integrated machine learning framework for smart agricultural advisory combining crop price forecasting and leaf disease identification with treatment recommendations. The system addresses critical gaps in existing agricultural technology by unifying multiple decision-support functionalities within a single, user-friendly interface. The crop price forecasting module, leveraging Random Forest regression with weather and regional feature integra-tion, achieves an MAE of 142.3 INR — the best among evaluated models. The CNN-based leaf disease identification module demonstrates 96.4% accuracy across multiple disease categories and maps predictions to actionable treatment rec-ommendations. Experimental results confirm that the integrated framework outperforms standalone approaches by providing contextual, localized, and holistic agricultural guidance. The Talathi com-munity data contribution mechanism, real-time weather in-tegration, and government scheme access further distinguish AgriPredict as a comprehensive agricultural decision-support platform. Future work will focus on mobile application development, IoT sensor integration, expanded crop and disease cover-age, multilingual support, and cloud scalability to extend the framework’s reach and impact across diverse agricultural communities.

References

[1] K. Ghosh and M. Kumar, “Crop Price Prediction Using Machine Learning Algorithm,” IJSRCSEIT, vol. 6, no. 2, pp. 50–54, Mar. 2023. [2] J. Zhang, H. Wang, and X. Li, “Plant Disease Detection Using Con-volutional Neural Networks System,” Proc. IEEE ICIP, pp. 201–205, 2022. [3] A. Singh, R. Pandey, and S. Sharma, “A Predictive Analytics Approach for Sustainable Agriculture,” Computers and Electronics in Agriculture, vol. 183, pp. 106–119, 2021. [4] P. Patil and S. Deshmukh, “Towards Smart Farming: Crop Disease Detection and Price Prediction Using AI,” Proc. IEEE ICAIS, pp. 312–317, 2022. [5] M. Sharma and R. Verma, “Impact of Weather Data on Crop Price and Yield Prediction Models,” IEEE Access, vol. 10, pp. 65234–65245, 2022. [6] S. Mohanty, D. P. Hughes, and M. Salathe´, “Deep Learning for Plant Disease Detection,” Frontiers in Plant Science, vol. 11, pp. 1–11, 2020. [7] D. P. Hughes and M. Salathe´, “An Open Access Repository of Images on Plant Health to Enable Mobile Disease Diagnostics,” arXiv preprint arXiv:1511.08060, 2015. [8] L. Chen, Y. Zhang, and X. Zhao, “Transfer Learning for Plant Disease Detection with Limited Data,” Proc. IEEE CVPRW, pp. 98–105, 2021. [9] N. Gupta, R. Kumar, and M. Agrawal, “Integrate IoT and AI for Smart Agriculture: A Case Study on Crop Yield and Price Prediction,” IEEE Internet of Things Journal, vol. 9, no. 12, pp. 9870–9882, 2022. [10] R. K. Sharma, S. Jain, and T. Patel, “A Comprehensive Survey on Weather Impact on Crop Yield and Price Prediction,” IEEE Access, vol. 10, pp. 45123–45139, 2022. [11] K. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine Learning in Agriculture: A Review,” Sensors, vol. 18, no. 8, p. 2674, 2018. [12] K. R. Thakur, P. K. Singh, and A. Kumar, “Machine Learning Models for Agricultural Price Forecasting,” Proc. IEEE ICCCNT, pp. 1–6, 2021. [13] S. S. Sastry, P. S. N. Rao, and A. M. Manjula, “Application of CNN for Plant Leaf Disease Prediction,” IJACSA, vol. 10, no. 4, pp. 205–210, 2019. [14] J. Kamilaris and F. X. Prenafeta-Boldu´, “Deep Learning in Agriculture: A Survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [15] M. K. Bhan, V. Tyagi, and S. Rajput, “Crop Price Prediction using Machine Learning Algorithms,” IJSRCSEIT, vol. 6, no. 2, pp. 50–54, 2020.

Copyright

Copyright © 2026 Prof. R. S. Pore, Ganesh Shihire, Amol Waghmode, Mayur Gutal, Amit Jadhav. 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.