Agriculture plays a vital role in economic development and food security. Accurate crop yield prediction is important for farmers and policymakers to improve productivity and reduce financial risks. Traditional crop yield estimation methods mainly depend on manual calculations and farmer experience, which are often time-consuming and less accurate. This project proposes an AI-Driven Crop Yield Prediction System using Machine Learning techniques to predict crop yield before harvesting. The system uses Linear Regression as a baseline model and Random Forest Regressor to improve prediction accuracy by handling complex agricultural data. Historical agricultural and environmental data such as crop type, rainfall, temperature, soil type, and cultivation area are collected and preprocessed for model training. The system is developed using Python, Flask, and Scikit- learn to provide a simple and user-friendly web interface. The proposed system helps farmers make data-driven decisions, optimize resource usage, and improve agricultural planning. It also supports smart agriculture practices by providing fast and reliable crop yield predictions. Future enhancements include weather API integration, mobile application support, and crop price prediction for better agricultural management.
The study presents an AI-Driven Crop Yield Prediction System developed using Machine Learning techniques and open-source technologies to provide accurate and reliable crop yield predictions. The system helps farmers and agricultural planners make data-driven decisions by analyzing important agricultural and environmental parameters such as rainfall, temperature, pesticide usage, crop type, and cultivation area.
The proposed system integrates Machine Learning models such as Random Forest Regressor, Gradient Boosting, and XGBoost to improve prediction accuracy and reduce manual estimation errors. By preprocessing historical agricultural datasets and training predictive models, the system generates reliable crop yield forecasts that support smart agriculture practices.
The lightweight and efficient architecture allows the system to operate smoothly on standard computers using Python, Flask, and Scikit-learn without requiring expensive infrastructure. The web-based interface also makes the application simple and accessible for farmers and users.
Future enhancements may include real-time weather API integration, multilingual support, IoT sensor connectivity, satellite-based crop monitoring, mobile application deployment, and advanced agricultural analytics. The project demonstrates how Artificial Intelligence and Machine Learning can provide effective, affordable, and scalable solutions for modern agriculture and sustainable farming practices.
References
[1]P. Agiwal and R. Gupta, “Advances in Crop Yield Prediction: From Traditional to Machine Learning Models,” in 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), 2025, pp. 189–194, doi:
10.1109/IC3ECSBHI63591.2025.10990698. [2]T. M. Geethajali, P. B, P. K. M, P. Gowda C. M, and Priyanka, “Agroinsights Chatbot: AI- Driven Precision Farming For Optimal Yields, Crop Selection, And Disease-Free Harvests,” in 2024 IEEE North Karnataka Subsection Flagship International Conference (NKCon), 2024, doi: 10.1109/NKCon62728.2024.10774802. [3]S. Kumar, V. Gupta, V. Partap, and A. Kumar, “Crop Yield Prediction for Smart Farming,” in 2025 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI), 2025,
pp. 610–615, doi: 10.1109/ICCSAI64074.2025.11064531.
[4]M. Goel and M. Pandey, “Crop Yield Prediction using AI: A Review,” in 2024 2nd International Conference on Disruptive Technologies (ICDT), 2024, pp. 1547–1549, doi: 10.1109/ICDT61202.2024.10489432. [5]J. Ranjani, V. K. G. Kalaiselvi, A. Sheela, D.
S. Deepika, and G. Janaki, “Crop Yield Prediction Using Machine Learning Algorithm,” in 2021 4th International Conference on Computing and Communications Technologies (ICCCT), 2021, pp. 611–613, doi:
10.1109/ICCCT53315.2021.9711853.
How to Cite This Paper
S.V.S.K.Harathi, M.Sravanthi, M.Chandana , Mr.C.Ramachandran (2026). AI-Driven Crop Yield Prediction System. International Journal of Computer Techniques, 13(3). ISSN: 2394-2231.
