<![CDATA[Rice production prediction is a crucial aspect in agricultural planning and food security. This study compares the performance of four regression algorithms in predicting rice production based on agronomic and climatological variables. The algorithms used are Random Forest Regression, XGBoost Regression, Support Vector Regression (SVR), and Artificial Neural Network (ANN). The evaluation results showed that Random Forest performed best with an R² of 0.963, followed by XGBoost with an R² of 0.959, indicating that these two models were able to explain more than 95% of the data variation. In contrast, SVR performed poorly with an R² of -0.064, while ANN had the worst result with an R² of -2.417, indicating the model's unsuitability for the dataset used. Thus, it can be concluded that Random Forest and XGBoost are the best options for rice production prediction, while SVR and ANN require further optimization to be used effectively in this context.]]>
Copyrights © 2025
