CROP YIELD PREDICTION USING MACHINE LEARNING

Abstract The rapid growth of agricultural data and the increasing need for sustainable farming practices have created a demand for intelligent decision-support systems. This paper presents a Smart Agriculture System that integrates ML, rule-based inference, and a web-based management platform to assist both farmers and administrators in making informed agricultural decisions. The system provides crop yield prediction, crop recommendation, and fertilizer suggestion, using a trained Random Forest model that achieved 99.15% accuracy on a curated dataset of crop samples. Additionally, fertilizer recommendations are generated using a rule-based expert module, ensuring reliable outputs even in cases of limited training data. The platform is built using Python and Flask for backend processing and MySQL for secure data storage, while the frontend is implemented with HTML, CSS, and JavaScript, delivering a responsive and user-friendly interface. Separate dashboards are provided for users and Administrators: farmers can access predictions, alerts, and feedback modules, whereas admins can monitor analytics, manage crops, view farmer history, and broadcast notifications. This unified system streamlines agricultural decision

Keywords: Smart Agriculture; Machine Learning; Crop Yield Prediction; Fertilizer Recommendation; Crop Recommendation; Precision Farming; Decision Support System; Artificial Intelligence (AI); Random Forest; Rule-Based System; Data Analytics; Web Application; Flask Framework; MySQL Database; Sustainable Agriculture; Agricultural Informatics; Predictive Modeling; Farmer Advisory System.