An Approach to Improve the Spatial Resolution and Accuracy of AMSR2 Passive Microwave Snow Depth Product Using Machine Learning in Northeast China

Snow cover plays a highly critical role in the global water cycle and energy exchange. Accurate snow depth (SD) data are important for research on hydrologic processes, climate change, natural disaster prediction. However, existing passive microwave (PMW) SD products have high uncertainty Northeast China owing to their coarse spatial resolution. Surface environment parameters should also be considered reduce errors products. Otherwise, it is difficult accurately capture spatiotemporal variations, especially complex (e.g., mountain or forests areas). To improve inversion accuracy resolution of China, multifactor downscaling model was developed by combining PMW from AMSR2 sensor, optical extent data, surface environmental produce fine scale (500 m × 500 m) precision data. Validations at 98 ground meteorological stations show that greatly improved raw product; its root-mean-square error (RMSE) reduced 26.15 cm product 7.58 cm, correlation coefficient (R) increased 0.39 0.53. For other (WESTDC FY), still has good applicability, could further performance WESTDC FY time space achieve better than Furthermore, proposed exhibited agreement with observed field quadrat (3 km 2 km) within scale, an ranging between −2 cm. Compared methods, presented best performance.