AI-Based Crop Management System
Author
Bavasabareesh N, Dhanush R, Dharanivel B.R, Gokul Kumar V, Dr. Manikandan R. P. S
Abstract
Farmers must make several interdependent decisions every season, such as which crop to grow, how much yield to expect, whether a crop is diseased and when to irrigate, and these are usually made without data-driven support. This paper presents an AI-Based Crop Management System, a full-stack web application that brings four decision-support modules together behind one REST interface. A Random Forest classifier recommends the most suitable crop out of 22 crops from soil nutrients (N, P, K), temperature, humidity, pH and rainfall, and reached an accuracy of about 99.5% on a held-out test set. A Random Forest regressor estimates harvest yield in tons from crop type, area, rainfall and temperature. A leaf disease module combines a cloud vision model with an offline colour-space computer vision engine that screens leaf images for powdery mildew, rust, blight, chlorosis and healthy tissue. A rule-based irrigation advisor converts soil moisture, temperature, humidity and rain forecast into an irrigate or skip decision with a water volume, and live weather is obtained from the Open-Meteo service. The backend is built with Flask and scikit-learn, and the frontend uses plain HTML, CSS and JavaScript, so the system runs on a modest machine without a GPU. The results show that an integrated and lightweight tool can give farmers fast and understandable guidance.
Keywords
Crop recommendation, Yield prediction, Plant disease detection, Smart irrigation, Random Forest, Flask
Full Text:
References
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70-90.
Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
Ingle, A. (2020). Crop recommendation dataset. Kaggle.
Zippenfenig, P. (2023). Open-Meteo.com weather API. Zenodo.
Grinberg, M. (2018). Flask web development: Developing web applications with Python (2nd ed.). O'Reilly Media.