Comparing Monthly Rainfall Prediction in West Sumatra Using SARIMA, ETS, LSTM, and XGBoosting Methods

<p><em>T</em><em>he West Sumatra Province, serving as the trading center on the island of Sumatra, and boasting various attractive tourist destinations, is not immune to incidents of high precipitation leading to hydro-meteorological disasters such as floods and landslides. Therefore, the accurate prediction of monthly rainfall is crucial to minimize the impacts of high precipitation. This research aims to determine the best method for predicting monthly rainfall using data from 1992 to 2022, which can adequately represent its climatological conditions.</em><em> The results indicate that the Extreme Gradient Boosting method outperforms the Seasonal Autoregressive Integrated Moving Average (SARIMA), Exponential Smoothing (ETS), and Long Short-Term Memory (LSTM) methods in West Sumatra Province, represented by three weather observation points from the BMKG (Climatology Station of West Sumatra, Maritime Meteorology Station of Teluk Bayur, and Minangkabau Meteorology Station). This method exhibits the lowest error values and the strongest correlation between predicted and actual data. This is evident from the Nash-Sutcliffe Efficiency (NSE) values, which are 0.188214535, 0.613823746, and 0.545734162 (unsatisfactory-satisfactory), as well as the obtained correlation values of 0.472103386, 0.795586268, and 0.743002591 (moderate-strong). However, this method is unable to perfectly capture outlier values. These outliers arise as a result of unusual conditions, such as natural disasters or climate changes, and atmospheric phenomena like El Niño-Southern Oscillation (ENSO) and Indian Ocean Dipole (IOD), leading to exceptionally high or low precipitation</em><em>.</em></p>