<![CDATA[Global climate change is making weather conditions in Indonesia, particularly in Palembang City, increasingly difficult to predict. The unexpected high-intensity rainfall frequently triggers hydrometeorological disasters, leading to threats to human safety and substantial economic losses. Consequently, reliable rainfall forecasting systems are urgently needed to support early warning, disaster mitigation, and operational planning across critical sectors. This research aims to design an accurate rainfall forecasting model for Palembang City by applying the Multiple Attribute Hierarchical Fuzzy Logic System (HFLS) with quartile-based consequent calibration. The method integrates the strengths of both Sugeno and Mamdani fuzzy inference models within a hierarchical structure to manage data uncertainty more effectively and reduce rule complexity. Unlike conventional fuzzy rainfall models that rely on fixed rainfall intensity categories, this study introduces a quartile-based calibration of Sugeno consequent values derived from local rainfall data. The model is developed using daily meteorological variables such as temperature, humidity, sunshine duration, and wind characteristics, obtained from the BMKG station in Palembang. Two configurations of consequent values are tested, one using conventional rainfall intensity categories and the other using quartile-based local data distribution derived from empirical rainfall observations. The experimental results show that the quartile-based configuration significantly improves accuracy, achieving MAE of 12.26 mm and RMSE of 25.85 mm, outperforming the conventional configuration (with MAE of 18.89 mm and RMSE of 28.29 mm). These findings highlight the importance of integrating hierarchical fuzzy architecture with locally calibrated consequent values to enhance rainfall prediction performance in tropical regions characterized by highly skewed rainfall distributions.]]>
