MSF-PhyDRNN: A Physics-Driven Multi-Source Fusion Recurrent Neural Network for Short-Term Thunderstorm Gale Nowcasting
Remote Sensing · 27.04.2026 · 18 (9) · 1334
DOI: 10.3390/rs18091334 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 27.04.2026. Verfasst von Huantong Geng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Program of Guangdong Province, China Meteorological Administration Tornado Key Laboratory, China Meteorological Administration Joint Research Project on Capacity Enhancement.
Abstract (Originalsprache)
Accurate nowcasting of thunderstorm gales, a highly destructive form of severe convective weather, is critical for mitigating wind-related disasters and ensuring the safety of life and property. Existing deep learning approaches face challenges such as performance decay at high wind speed thresholds, limited capability in capturing extreme events, and difficulties in processing high-resolution data. To address these issues, this paper proposes a novel physics-driven multi-source fusion recurrent neural network named MSF-PhyDRNN. The model incorporates a multi-source fusion module that integrates radar composite reflectivity and surface wind field data through feature decoupling and hierarchical fusion. Additionally, we improved the recurrent unit in PhyDNet to enhance short-term wind capture and reduce redundancy, leveraging its cascaded memory and spatiotemporal propagation mechanisms. Experimental results indicate that, compared to the advanced MFWPN model, MSF-PhyDRNN achieves an average increase of 14.3% in the Critical Success Index (CSI), 27.2% in the Probability of Detection (POD), and 19.7% in the Heidke Skill Score (HSS) across the Jiangsu and South China datasets.
Förderung
- Science and Technology Program of Guangdong Province
- China Meteorological Administration Tornado Key Laboratory
- China Meteorological Administration Joint Research Project on Capacity Enhancement
- National Natural Science Foundation of China
- Joint Fund of Chongqing Natural Science Foundation for Innovation and Development
Zitieren
APA
Geng, H., Ma, S., Ma, K., Zhuang, X., Zhang, H., & Lan, Y. (2026). MSF-PhyDRNN: A Physics-Driven Multi-Source Fusion Recurrent Neural Network for Short-Term Thunderstorm Gale Nowcasting. Remote Sensing, 18(9), 1334. https://doi.org/10.3390/rs18091334
Vancouver
Geng H, Ma S, Ma K, Zhuang X, Zhang H, Lan Y. MSF-PhyDRNN: A Physics-Driven Multi-Source Fusion Recurrent Neural Network for Short-Term Thunderstorm Gale Nowcasting. Remote Sensing. 2026;18(9):1334. doi:10.3390/rs18091334
BibTeX
@article{Geng2026,
author = {Geng, Huantong and Ma, Shaoqiang and Ma, Kefei and Zhuang, Xiaoran and Zhang, Hualong and Lan, Yu},
title = {MSF-PhyDRNN: A Physics-Driven Multi-Source Fusion Recurrent Neural Network for Short-Term Thunderstorm Gale Nowcasting},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {9},
pages = {1334},
doi = {10.3390/rs18091334}
}
EUVIMED