<![CDATA[Rainfall is one of the most variable and difficult-to-predict climate factors, especially in tropical regions like Indonesia. This uncertainty can significantly impact various sectors such as agriculture, forestry, and disaster mitigation. This study aims to develop a rainfall prediction model based on polynomial regression using historical weather data from Southeast Sulawesi. The dataset includes average temperature, average humidity, and sunlight duration, obtained from BMKG and processed using linear interpolation to handle missing values. Polynomial regression was chosen due to its ability to capture non-linear relationships between weather variables and rainfall. Model evaluation using Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) resulted in values of 41.84, 4.67 and 4.85, respectively, indicating relatively low prediction error. Therefore, polynomial regression proves to be an effective, accurate, and computationally efficient method for short-term rainfall forecasting.]]>
Copyrights © 2025
