FusionCast: Enhancing Precipitation Nowcasting with Asymmetric Cross-Modal Fusion and Future Radar Priors

ArXi:2603.13298v1 Announce Type: cross Deep learning has significantly improved the accuracy of precipitation nowcasting. However, most existing multimodal models typically use simple channel concatenation or interpolation methods for data fusion, which often overlook the feature differences between different modalities. This paper therefore proposes a novel precipitation nowcasting optimisation framework called FusionCast.