<![CDATA[Batam is a strategic coastal region located along an international shipping route, characterized by a tropical climate with high rainfall intensity. These conditions substantially affect key sectors such as transportation and tourism, underscoring the need for accurate climatological predictions. This study develops simple and multiple linear regression models for monthly rainfall, incorporating air temperature and relative humidity as predictor variables. The dataset comprises observations recorded at the BMKG Hang Nadim Meteorological Station for the period 2000–2024. Model performance was evaluated by comparing predicted values with observed data for 2024 using the Root Mean Square Error (RMSE) and the Pearson correlation coefficient ( ). The results show that the multiple linear regression model provides the highest predictive accuracy, with an RMSE of approximately mm and a correlation coefficient of . Among the single-predictor models, relative humidity performed better than temperature, achieving an RMSE of mm ( ) compared with mm ( ). These findings indicate that the integration of temperature and relative humidity predictors is more effective for monthly rainfall prediction, based on the analysis of a 25-year climatological dataset from a tropical maritime region such as Batam. This improvement in rainfall prediction supports more robust climate adaptation and disaster mitigation strategies in Batam.]]>
Copyrights © 2026
