Machine‐Learning (ML)‐Physics Fusion Model Accelerates the Paradigm Shift in Typhoon Forecasting With a CNOP‐Based Assimilation Framework

In this study, we develop an advanced hybrid forecasting system for short‐term (0–120 hr) typhoon predictions, seamlessly integrating the FuXi machine‐learning model with the physics‐based Shanghai Typhoon Model (SHTM). By employing spectral nudging, the hybrid FuXi‐SHTM model leverages FuXi's...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Geophysical research letters Ročník 52; číslo 15
Hlavní autoři: Niu, Zeyi, Wang, Dongliang, Mu, Mu, Huang, Wei, Fan, Xuliang, Yang, Mengqi, Qin, Bo
Médium: Journal Article
Jazyk:angličtina
Vydáno: Washington John Wiley & Sons, Inc 16.08.2025
Wiley
Témata:
Assimilation
CNOP
Forecasting
FuXi model
Hurricanes
Learning algorithms
Machine learning
Perturbation method
Perturbation methods
Physics
Satellite observation
Typhoon forecasting
typhoon forecasts
Typhoons
ISSN:0094-8276, 1944-8007
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this study, we develop an advanced hybrid forecasting system for short‐term (0–120 hr) typhoon predictions, seamlessly integrating the FuXi machine‐learning model with the physics‐based Shanghai Typhoon Model (SHTM). By employing spectral nudging, the hybrid FuXi‐SHTM model leverages FuXi's robust large‐scale forecasting capabilities alongside SHTM's mesoscale strengths, significantly enhancing track, intensity, and precipitation predictions for super typhoons Yagi (2024) and Krathon (2024). To further improve the forecasting capability for extreme typhoons, the Conditional Nonlinear Optimal Perturbation method is employed for the first time to identify sensitive regions for the hybrid model. Despite being constrained by FuXi's large‐scale forecast fields, the dense assimilation of satellite observations within these sensitive regions can further enhance typhoon forecasts. This study emphasizes the synergy between data‐driven strategies and established physical modeling, which can inspire further depth in understanding of extreme typhoon events. Plain Language Summary Accurate typhoon forecasting is crucial for effective disaster preparedness. In this study, we developed a hybrid model that integrates the machine‐learning (ML)‐based FuXi model with the physics‐based Shanghai Typhoon Model (SHTM) using spectral nudging. This approach leverages FuXi's strength in capturing large‐scale weather patterns and SHTM's ability to resolve finer mesoscale details, thereby improving predictions of short‐term typhoon's track, intensity, and rainfall. Additionally, we identified observation‐sensitive regions using the Conditional Nonlinear Optimal Perturbation method and found that assimilating satellite data from these regions further improved the forecasts. Overall, our findings highlight the potential of integrating ML with physical models to advance operational typhoon predictions. Key Points This study combines the FuXi model and the Shanghai Typhoon Model (SHTM) to create a hybrid operational typhoon forecasting paradigm Using the strengths of both models, FuXi‐SHTM improves the accuracy of typhoon track, intensity, and precipitation prediction Proposed a novel workflow of assimilating target observation in Conditional Nonlinear Optimal Perturbation‐sensitive area of FuXi‐SHTM hybrid model
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0094-8276
1944-8007
DOI:10.1029/2025GL115926