Skillful Precipitation Nowcasting Based on Multi-scale fusion and Radar Observations

Accurate and reliable precipitation nowcasting plays a critical role in disaster prevention and mitigation. The heavy precipitation forecast is a challenging task for most deep learning (DL)-based models. To address this challenge, we develop a novel DL architecture called “multi-scale feature fusion” (MFF) that can give skillful precipitation forecast with a lead time of up to 3 h. The MFF model uses convolution kernels with varying sizes to create multi-scale receptive fields. This helps to capture the movement features of precipitation systems, such as their shape, movement direction, and speed. Additionally, the architecture makes use of the mechanism of discrete probability to reduce uncertainties and forecast errors, enabling it to predict heavy precipitation even at longer lead times. Four-year radar observation data from 2018 to 2021 are used for model training, and the data of 2022 for model testing. The MFF model is compared with three existing extrapolative models: time series residual convolution (TSRC), optical flow (OF), and UNet. The results show that MFF achieves superior forecast skills with high probability of detection (POD), low false alarm rate (FAR), small mean absolute error (MAE), and high structural similarity index (SSIM). Particularly, MFF can predict high-intensity precipitation fields at 3 h lead time, while the other three models cannot. Furthermore, MFF shows improvement in the smoothing effect of the forecast field, as observed from the results of radially averaged power spectral (RAPS).