MBFE-UNet: A Multi-Branch Feature Extraction UNet with Temporal Cross Attention for Radar Echo Extrapolation

Abstract

Radar echo extrapolation is a critical technique for short-term weather forecasting. Timely warnings of severe convective weather events can be provided according to the extrapolated images. However, traditional echo extrapolation methods fail to fully utilize historical radar echo data, resulting in limited accuracy for future radar echo prediction. Existing deep learning echo extrapolation methods often face issues such as high-threshold echo attenuation and blurring distortion. In this paper, we propose a UNet-based multi-branch feature extraction model named MBFE-UNet for radar echo extrapolation to mitigate these issues. We design a Multi-Branch Feature Extraction Block, which extracts spatiotemporal features of radar echo data from various perspectives. Additionally, we introduce a Temporal Cross Attention Fusion Unit to model the temporal correlation between features from different network layers, which helps the model to better capture the temporal evolution patterns of radar echoes. Experimental results indicate that, compared to the Transformer-based Rainformer, the MBFE-UNet achieves an average increase of 4.8% in the critical success index (CSI), 5.5% in the probability of detection (POD), and 3.8% in the Heidke skill score (HSS).

Keywords

• radar echo extrapolation
• deep learning
• UNet
• multi-branch