<![CDATA[Food security vulnerability in Jember Regency, driven by rice production fluctuations due to extreme climate change and productive land depletion, necessitates accurate crop yield forecasting. Current prediction inaccuracies lead to significant inefficiencies in distributing essential agricultural resources, such as fertilizers and seeds, which threatens regional stability. This study aims to develop and optimize a robust machine learning-based prediction model by integrating dynamic climatic variables (temperature, humidity, wind speed) from API services with phenological data (planting area) to enhance forecasting precision. This study employs a Random Forest algorithm optimized through hyperparameter tuning and feature selection to identify critical predictors for harvest outcomes. The results demonstrate exceptional model performance with a quantitative R² score of 0.99, indicating a near-perfect correlation between predicted and actual yields. The analysis reveals a clear hierarchy where phenological features like “tanam bulan lalu” dominate, supported by substantial contributions from climatic factors. Furthermore, the model successfully identified two annual harvest peaks and highlighted a critical misalignment in current urea fertilizer distribution schedules. This research recommends a strategic shift toward predictive-based resource allocation to synchronize fertilizer timing with optimal planting cycles. This integrated approach provides a significant contribution to informatics-based precision agriculture by offering a data-driven tool for strategic decision-making and resource optimization.]]>
