Home »
Academic Articles »
C »
RadarDiT: An advanced radar echo extrapolation model for three gorges reservoir area via diffusion transformer
RadarDiT: An advanced radar echo extrapolation model for three gorges reservoir area via diffusion transformer
Jiaquan Wan
(College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China; Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Haikou 570203, China; National Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China)
Junchao Wang
(Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Haikou 570203, China; Institute of Heavy Rain, China Meteorological Administration, Wuhan 430205, China)
Wei Zhang
(Pearl River Water Resources Research Institute, Guangzhou 510611, China)
Hao Song
(The Business School, Beijing Normal University, Beijing 100875, China)
Congyi Nai
(National Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China)
Fengchang Xue
(School of Remote Sensing and Surveying Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China)
Tao Yang
(College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China)
Chunxiang Shi
(National Meteorological Information Center, Beijing 100081, China)
Quan J. Wang
(Department of Infrastructure Engineering, Faculty of Engineering and Information Technology, The University of Melbourne, Victoria 3010, Australia)
Baoxiang Pan
(National Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China; Corresponding author.)
Study region: The Three Gorges Reservoir Area (TGRA) Study focus: TGRA faces increasing vulnerability to extreme precipitation events driven by complex convective weather systems. Radar echo extrapolation—predicting future precipitation patterns from current radar data—is essential for early warning systems but faces significant challenges in this topographically complex region. While data-driven approaches have advanced the field, current convolutional neural network-based diffusion models struggle with the TGRA's dynamic meteorological conditions due to their reliance on translational invariance, which often fails to capture rapid weather transitions in complex terrain. New hydrogeological insights from the region: To address these limitations, we introduce RadarDiT, a Vision Transformer-based diffusion model specifically engineered for radar extrapolation in the TGRA. First, we develop a five-year radar dataset capturing diverse convective weather phenomena unique to this region. Then, leveraging this dataset, RadarDiT employs multi-layer Vision Transformers that effectively model global dependencies and complex spatial relationships, enabling accurate prediction of convective cell evolution. Our model demonstrates superior performance in maintaining strong echo and spatial coherence over longer forecast horizons. Quantitative evaluations across multiple metrics and thresholds confirm RadarDiT's enhanced skill in forecasting heavy precipitation events, with particular improvements in Critical Success Index at higher radar echo values. This work establishes a foundation for more reliable nowcasting systems in regions with complex terrain and dynamic weather patterns, directly supporting enhanced disaster preparedness and response strategies.
Jiaquan Wan, Junchao Wang, Wei Zhang, et al. (2025). "RadarDiT: An advanced radar echo extrapolation model for three gorges reservoir area via diffusion transformer". Journal of Hydrology: Regional Studies. https://doi.org/10.1016/j.ejrh.2025.102703