TELANGANA RICE CROP YIELD PREDICTION USING MACHINE LEARNING

Accurate rice yield prediction is essential for effective agricultural planning and resource management inTelangana. This study applies machine learning techniques to develop a predictive model using key agroclimatic and fertilizer consumption attributes, including district code, year, rice cultivation area, productionvolume, temperature variations, precipitation, annual rainfall, and nitrogen, phosphate, and potash consumption.Multiple models, including Linear Regression, Lasso Regression, and Decision Tree, were evaluated, withLinear Regression achieving the highest accuracy (0.889 score). Data preprocessing, such as feature selectionand standardization, was implemented to enhance model performance.This machine learning-based approach provides a reliable and interpretable solution for crop yield forecasting,assisting farmers and policymakers in making data-driven agricultural decisions. The model can be integratedinto a web-based application for real-time predictions, contributing to improved food security and resourceallocatio