PCSSR‐DNNWA: A Physical Constraints Based Surface Snowfall Rate Retrieval Algorithm Using Deep Neural Networks With Attention Module.

Global surface snowfall rate estimation is crucial for hydrological and meteorological applications but is still a challenging task. A novel approach is developed to comprehensively use passive microwave, infrared data and physical constraints in deep‐learning neural networks with an attention module for retrieving surface snowfall rate (PCSSR‐DNNWA). The PCSSR‐DNNWA consistently outperforms traditional approaches in predicting surface snowfall rates with a correlation coefficient of ∼0.76, mean error of ∼−0.02 mm/hr, and root mean squared error of ∼0.21 mm/hr. It is found that graupel water path is of vital importance with largest contributions in retrieving surface snowfall rate. By integrating the physical constraints, the algorithm of PCSSR‐DNNWA opens a new avenue for retrieving the surface snowfall rate from satellites since some predictors are intelligently considered, resulting in an increased accuracy, interpretability, and computational efficiency. Plain Language Summary: Comprehensively monitoring surface snowfall on Earth can effectively be achieved through space‐borne instruments. However, estimating surface snowfall from space is a challenging task as the signals measured by space sensors are indirectly related to surface snowfall rate. In this study, a novel deep learning algorithm is developed based on deep neural networks, which is more accurate, interpretable and computationally efficient, compared with traditional approaches, in estimating surface snowfall rate using observations from various space‐borne sensors and physically relevant parameters. Key Points: Physical constraints greatly improve the ability of surface snowfall rate retrievalAttention module in deep neural networks could intelligently adjust the weights of predictors [ABSTRACT FROM AUTHOR]