Ensemble-Based Machine Learning for Improving Local Weather Prediction Accuracy in Batam, Indonesia

Abstract

Accurate short-term rainfall prediction in tropical microclimates such as Batam remains challenging due to strong local atmospheric variability and the limited generalization capability of single-model classifiers. This study proposes an ensemble-based framework that integrates Naïve Bayes, C4.5, and Random Forest through a majority-voting mechanism for multi-class hourly rainfall prediction. The experiments were conducted using multi-year hourly meteorological data collected for Batam City from an open-source weather archive, covering key atmospheric variables and exhibiting an imbalanced rainfall-class distribution. Model performance was evaluated using ten-fold cross-validation with accuracy, precision, recall, and F1-score metrics. The proposed ensemble achieved an accuracy of 84.74%, consistently outperforming the corresponding base classifiers. The model demonstrated strong predictive capability for dominant rainfall classes (TidakHujan and HujanRingan), while reduced performance was observed for HujanSedang and HujanBerat due to class imbalance, a well-documented challenge in tropical rainfall modeling. Overall, the results indicate that combining probabilistic and tree-based learners yields a more stable and reliable prediction framework for localized tropical weather. This work contributes a practical and reproducible ensemble approach tailored to microclimate conditions, offering a foundation for improved data-driven rainfall forecasting in similar high-variability