EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Advancing Convective Precipitation Nowcasting via 3D Polarimetric Radar Data and Physics‐Constrained Deep Learning Model

Xiang Pan, Yinghui Lu, Hao Huang, Gang Chen, Ang Zhou, Kun Zhao

Geophysical Research Letters · 16.03.2026 · 53 (5)

DOI: 10.1029/2025gl120431 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 26.02.2026. Verfasst von Xiang Pan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Pan, X., Lu, Y., Huang, H., Chen, G., Zhou, A., & Zhao, K. (2026). Advancing Convective Precipitation Nowcasting via 3D Polarimetric Radar Data and Physics‐Constrained Deep Learning Model. Geophysical Research Letters, 53(5). https://doi.org/10.1029/2025gl120431

Vancouver

Pan X, Lu Y, Huang H, Chen G, Zhou A, Zhao K. Advancing Convective Precipitation Nowcasting via 3D Polarimetric Radar Data and Physics‐Constrained Deep Learning Model. Geophysical Research Letters. 2026;53(5). doi:10.1029/2025gl120431

BibTeX
@article{Pan2026,
  author = {Pan, Xiang and Lu, Yinghui and Huang, Hao and Chen, Gang and Zhou, Ang and Zhao, Kun},
  title = {Advancing Convective Precipitation Nowcasting via 3D Polarimetric Radar Data and Physics‐Constrained Deep Learning Model},
  journal = {Geophysical Research Letters},
  year = {2026},
  volume = {53},
  number = {5},
  doi = {10.1029/2025gl120431}
}
Kostenlos starten →