Monthly Rainfall Forecasting in Pesisir Selatan Regency Using the Autoregressive Integrated Moving Average (ARIMA) Model

Abstrak

Rainfall is a climate variable that Plays a vital role in agricultural planning and water resources management, and hydrometeorological disaster mitigation. Therefore, a forecasting method capable of adequately describing the temporal patterns of rainfall data is required. This study aims to forecast monthly rainfall in Pesisir Selatan Regency using the ARIMA method. The dataset employed in this study consists of monthly rainfall records covering the period from 2015 to 2024. The analysis stages include missing data imputation, Box–Cox transformation, stationarity testing was conducted using the ADF test, followed by model identification based on the ACF and PACF plots, parameter estimation, and model evaluation based on the Akaike Information Criterion (AIC), residual diagnostic tests, and forecasting accuracy using MAPE. The results show that the ARIMA(0,1,1) model is the best model, as indicated by the lowest AIC value and residuals that satisfy the white noise assumption. The forecasting accuracy evaluation yields a MAPE value of 55.05%, indicating that the model’s ability to capture monthly rainfall variability is still limited. Rainfall forecasting for the period January to December 2025 produces relatively constant forecast values, reflecting the limitations of the ARIMA(0,1,1) model in representing seasonal variations. Therefore, this model is more suitable as a baseline approach for rainfall forecasting in Pesisir Selatan Regency. Future studies are recommended to apply models that incorporate seasonal components or external variables to improve forecasting accuracy.