Abstract Accurate nowcasting of severe convective precipitation is critical for early warning yet still remains challenging. Although deep learning methods show promise, most models lack physical constraints, limiting their consistency with atmospheric processes. We introduce FURECast, a deep learning model that not only leverages three‐dimensional structure of polarimetric radar variables ( Z H , Z DR , K DP ) but also embeds their intrinsic self‐consistency relation as a physical constraint. The model employs an encoder‐translator‐decoder architecture, integrating multi‐level inputs via late fusion and evolving features through cascaded multiscale blocks. Moreover, a novel physical loss term is introduced to enforce microphysical consistency during training. Evaluated on S‐band (GD‐SPOL) and C‐band (NJU‐CPOL) radar data sets, FURECast achieves a 14.1% improvement in 90‐min critical success index (35 dBZ threshold) over the 2D reflectivity‐only baseline, while reducing physical inconsistency by two orders of magnitude. These results underscore the value of 3D polarimetric structure and physics‐guided learning in advancing convective precipitation nowcasting.
Pan et al. (2026) studied this question.