CROP YIELD PRODUCTION PREDICTION USING MACHINE LEARNING

Abstract

Agriculture plays a vital role in the economic development of a nation, yet many
agricultural sectors still face challenges due to limited adoption of advanced
technologies and inefficient resource management. These issues often lead to reduced
crop productivity, directly impacting the agricultural economy. Accurate prediction of
crop yield can help farmers and policymakers make informed decisions to improve
productivity and optimize resource utilization.
This project presents a machine learning-based approach for crop yield production
prediction using historical agricultural data. The system analyzes various input
parameters such as district name, season, year, and crop type to estimate crop yield.
Data preprocessing techniques, including cleaning, normalization, and feature
selection, are applied to enhance the quality of the dataset and improve model
performance.
Multiple machine learning regression algorithms are implemented and compared to
identify the most accurate model for yield prediction. Performance evaluation is
carried out using metrics such as Mean Absolute Error (MAE) and R²-score. The
system is capable of predicting the yield for a specific crop based on given inputs, as
well as estimating yields for multiple crops under different conditions