Peatland degradation in Indonesia, caused by large-scale drainage for oil palm plantations and timber estates, leads to forest fires and the loss of peatland hydrological functions. Monitoring groundwater level (GWL) is a critical mitigation measure for preventing fires. However, manual GWL measurements face high operational costs and limited coverage. This study aims to develop a more accurate GWL estimation model by combining field data with drought indices derived from remote sensing technology, such as NDWI and VSDI, to support water resource management, drought risk mitigation, and sustainable peatland management in Indonesia. The research utilized primary data from Landsat 8 OLI satellite images (March, April, and June 2016) and secondary data, including a 1:50,000 scale topographic map, hotspot data from VIIRS, and measurements of peat depth, water table height, and physical peat properties. A statistical model was developed using 12 variables, including drainage distance, peat depth, bulk density, fiber content, and drought indices. Among 1,023 model variations, the best model was selected based on the Akaike Information Criterion with correction (AICc) and validated through cross-validation, achieving an RMSE of 16.1 cm and an R2 of 84%. The study found that maintaining GWL above 66 cm is crucial for reducing the risk of peatland fires. This model provides a precise method for monitoring groundwater levels in tropical peatland areas and offers critical insights for designing effective fire risk mitigation strategies and managing peatland ecosystems.