Evaluation of the XGBoost Model for Rainfall Prediction and Classification Using BMKG Data and OpenWeather API

Indonesia, situated between two continents and two oceans, experiences significant climate variability, with rainfall patterns shaped by geographical and topographical factors, as well as phenomena like the El Niño Southern Oscillation (ENSO). Accurate rainfall forecasting plays a critical role in disaster mitigation, agricultural planning, and water resource management. This study focuses on developing a rainfall prediction and classification model using the Extreme Gradient Boosting (XGBoost) algorithm. The model leverages historical rainfall data from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG) and real-time data from the OpenWeather API. The output includes rainfall trend graphs and classification of rainfall intensity into categories such as light, moderate, or heavy. Model performance is assessed through metrics like accuracy, precision, RMS (Root Mean Square), and RMSE (Root Mean Square Error). This research highlights the integration of historical and real-time data for weather forecasting and demonstrates the application of advanced machine learning techniques like XGBoost to build robust and precise prediction models. The findings are expected to offer practical insights for disaster risk reduction, agricultural strategy planning, and effective water resource management.