Estimation of 100 m root zone soil moisture by downscaling 1 km soil water index with machine learning and multiple geodata

Root zone soil moisture (RZSM) is crucial for agricultural water management and land surface processes. The 1 km soil water index (SWI) dataset from Copernicus Global Land services, with eight fixed characteristic time lengths (T), requires root zone depth optimization (T_opt) and is limited in use due to its low spatial resolution. To estimate RZSM at 100-m resolution, we integrate the depth specificity of SWI and employed random forest (RF) downscaling. Topographic synthetic aperture radar (SAR) and optical datasets were utilized to develop three RF models (RF1: SAR, RF2: optical, RF3: SAR + optical). At the DEMMIN experimental site in northeastern Germany, T_opt (in days) varies from 20 to 60 for depths of 10 to 30 cm, increasing to 100 for 40-60 cm. RF3 outperformed other models with 1 km test data. Following residual correction, all high-resolution predictions exhibited strong spatial accuracy (R ≥ 0.94). Both products (1 km and 100 m) agreed well with observed RZSM during summer but overestimated in winter. Mean R between observed RZSM and 1 km (100 m; RF1, RF2, and RF3) SWI ranges from 0.74 (0.67, 0.76, and 0.68) to 0.90 (0.88, 0.81, and 0.82), with the lowest and highest R achieved at 10 cm and 30 cm depths, respectively. The average RMSE using 1 km (100 m; RF1, RF2, and RF3) SWI increased from 2.20 Vol.% (2.28, 2.28, and 2.35) at 30 cm to 3.40 Vol.% (3.50, 3.70, and 3.60) at 60 cm. These negligible accuracy differences underpin the potential of the proposed method to estimate RZSM for precise local applications, e.g., irrigation management.