文献类型：期刊文献

英文题名：A variable-resolution unstructured spatio-temporal graph neural network: an application to very short-range weather forecasting in Guangdong, China

作者：Li, Delin[1,2,3];Chen, Zhiqiang[1,2,3];Huang, Gang[4,5];Xu, Jianjun[2,3];Zhang, Yu[1,2,3]

机构：[1]Guangdong Ocean Univ, Coll Ocean & Meteorol, Zhanjiang, Peoples R China;[2]Guangdong Ocean Univ, Shenzhen Inst, Shenzhen, Peoples R China;[3]Guangdong Ocean Univ, Sea Inst Marine Meteorol, GDOU Joint Lab Marine Meteorol & South China, CMA, Zhanjiang, Peoples R China;[4]Chinese Acad Sci, Inst Atmospher Phys, State Key Lab Earth Syst Numer Modeling & Applicat, Beijing, Peoples R China;[5]Univ Chinese Acad Sci, Beijing 100049, Peoples R China

年份：2026

卷号：13

期号：1

外文期刊名：GEOSCIENCE LETTERS

收录：SCI-EXPANDED(收录号：WOS:001683461800001)、、WOS

基金：This work is supported by the National Natural Science Foundation of China (42206253, 42205025, 42130605, 42141019, 42261144687, 42575170), the program for scientific research start-up funds of Guangdong Ocean University (060302032305, 060302032105), and the Hainan Key Research and Development Project under Grant (ZDYF2023SHFZ125).

语种：英文

外文关键词：Spatio-temporal graph neural network; Very short-range forecasting; Unstructured variable-resolution grid; Guangdong China

外文摘要：The increase in extreme weather events has raised the demand for very short-range forecasts in Guangdong, the most populous province in China. Although global AI-based weather forecasting models provide strong medium-range guidance, they remain suboptimal for regional very short-range predictions. To address this, we developed a spatio-temporal graph neural network (STGNN) for Guangdong, featuring an unstructured, variable-resolution graph refined over the Pearl River Delta. The core of the network is 1-D dilated causal temporal convolutions and spatial convolutions on combined static and dynamic graphs. A spatial mean constraint and Laplacian-residual regularization were incorporated into the loss function to enhance physical consistency. Trained on historical reanalysis dataset, the model generates hourly forecasts for multiple near-surface atmospheric variables for the next six hours. Verification against an independent test-set and observations, using multiple metrics, demonstrates high predictive skill and strong spatio-temporal coherence for 2 m temperature and sea-level pressure. For 10 m winds and 2 m humidity, model errors grow larger with lead time. Case studies of an extreme heatwave event in Guangzhou and the post-landfall evolution of Super Typhoon Saola effectively capture the evolution characteristics and spatial patterns, while underestimates the peak temperatures, maximum winds and minimum sea-level pressures. These results support the use of variable-resolution STGNN as a practical approach for very short-range regional forecasting in Guangdong, China.