MambaCast: An Efficient Precipitation Nowcasting Model With Dual-Branch Mamba

Precipitation nowcasting using radar echo data is critical for issuing timely extreme weather warnings, yet existing models struggle to balance computational efficiency with prediction accuracy when modeling complex, nonlinear echo sequences. To address these challenges, we propose MambaCast, a novel dual-branch precipitation nowcasting model built upon the Mamba framework. Specifically, MambaCast incorporates three key components: an SSM Branch, a CNN Branch and a CastFusion module. The SSM Branch captures global low-frequency evolution features in the radar echo field through a selective scanning mechanism, while the CNN Branch extracts local high-frequency transient features using gated spatiotemporal attention. The CastFusion module dynamically integrates features across different frequency scales, enabling adaptive fusion of spatiotemporal distribution. Experiments on two public radar datasets show that MambaCast consistently outperforms baseline models.