West Kalimantan is highly vulnerable to meteorological drought driven by global climate variability, particularly El Niño–Southern Oscillation (ENSO). This study aims to estimate the Standardized Precipitation Index (SPI) using a Random Forest (RF) model and to analyze the spatio-temporal patterns of meteorological drought across West Kalimantan. Monthly ERA5 reanalysis precipitation data (resolution ±0.25°) for 1995–2024 were used as the primary dataset; the model was trained on 1995–2018 data and tested on 2019–2024 data. Model performance was evaluated using the coefficient of determination (R2) and Root Mean Square Error (RMSE). The RF model achieved R2 = 0.997 and RMSE = 0.052 during training, and R2 = 0.968 and RMSE = 0.176 during testing, demonstrating excellent generalization capability. Spatial analysis of four representative El Niño years (1997, 2009, 2019, 2023) revealed that El Niño consistently triggers dry conditions across the province, with drought intensity scaling with ENSO strength and peak dryness occurring in July–August. The most severe drought was recorded during the Very Strong El Niño of 1997, which caused extreme dryness across most of the province, while Weak and Strong El Niño events of 2019 and 2023 produced less extensive but still significant mid-year drying. These findings demonstrate that the RF model is effective for spatio-temporal drought estimation under varying El Niño intensities and has strong potential to support drought early warning system development in West Kalimantan.
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.