<![CDATA[Monitoring soil surface moisture is a crucial aspect of drought detection and management, significantly contributing to informed decision-making in agriculture and natural resource management. Remote sensing technologies have been widely applied to predict surface soil moisture. This study aimed to develop and analyze a surface soil moisture prediction model based on remote sensing data for drought mitigation. This research was conducted in the administrative area of Sleman Regency, Yogyakarta Special Region Province. This study employed a method that integrates field measurements with remote sensing-derived data to develop a predictive model of surface soil moisture. The model was constructed using the Extreme Gradient Boosting (XGBoost) machine learning algorithm. The modeling results yielded an R² value of 0.62 and an RMSE of 0.83. The model was then applied to generate spatial estimates of surface soil moisture for the period from May to October 2024. Spatially, all six months exhibited a consistent distribution pattern, with low soil moisture levels concentrated in the central southern part of the study area. The findings can serve as a basis for highlighting land management in line with SDG Goal 15, which aims to protect, restore, and enhance the sustainable use of terrestrial ecosystems, sustainably manage forests, halt and reverse land degradation, and halt biodiversity loss.]]>
Copyrights © 2025
