The accurate prediction of crop yield is paramount for effective agricultural planning, resource allocation, and risk management. In this study, we employed advanced fuzzy logic techniques to optimize crop yield forecasting models. Through the integration of fuzzy inference systems, fuzzy clustering, and fuzzy time series analysis, we aimed to enhance the accuracy, interpretability, and robustness of existing forecasting models. Evaluation metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared were employed to assess the accuracy of the models. The results revealed promising performance, with the fuzzy logic models demonstrating improved accuracy in predicting crop yield across different time periods. Our findings underscore the potential of fuzzy logic techniques in enhancing crop yield forecasting accuracy and provide valuable insights for stakeholders in agricultural decision-making.

MAE, RMSE, R- squared, crop yield