Comparison Of Machine Learning Algorithms For Rice Production Prediction

Rice production forecasting plays an important role in supporting future agricultural planning, food supply management, and food security. Accurate yield prediction allows governments and farmers to estimate production outcomes and develop appropriate strategies to maintain stable food availability.This study addresses this gap by comparing four regression-based machine learning models: Random Forest, XGBoost, Support Vector Regression (SVR), and Artificial Neural Network (ANN). All models were trained and tested using the same dataset to ensure a fair evaluation. Model performance was measured using the coefficient of determination (R²). The results show that Random Forest achieved the best performance (R² = 0.963), followed by XGBoost (R² = 0.959). In contrast, SVR (R² = -0.064) and ANN (R² = -2.417) performed poorly, indicating limited predictive capability. Overall, these findings suggest that ensemble-based methods, particularly Random Forest and XGBoost, are more reliable and effective for rice production forecasting compared to SVR and ANN.