collaborators

8 papers

physics.ao-ph2026

Machine Learning (ML)-Physics Fusion Model Outperforms Both Physics-Only and ML-Only Models in Typhoon Predictions

Zeyi Niu, Wei Huang, Hao Li +4

Data-driven machine learning (ML) models, such as FuXi, exhibit notable limitations in forecasting typhoon intensity and structure. This study presents a comprehensive evaluation o…

physics.ao-ph2026

ML-Physical Fusion Models Are Accelerating the Paradigm Shift in Operational Typhoon Forecasting

Zeyi Niu

In this study, we develop a hybrid operational typhoon forecasting model that integrates the FuXi machine-learning (ML) model with the physics-based Shanghai Typhoon Model (SHTM) i…

physics.ao-ph2026

Global kilometre-scale tropical cyclone inner-core vector winds from sparse scalar CYGNSS observations

Xinhai Han, Xiaohui Li, Jingsong Yang +11

Tropical cyclone (TC) inner-core surface wind vectors underpin intensity forecasting and storm-surge prediction, yet direct observations remain scarce: routine aircraft reconnaissa…

physics.ao-ph2026

FuXi-TC: A generative framework integrating deep learning and physics-based models for improved tropical cyclone forecasts

Shan Guo, Lei Chen, Yangyang Zhao +6

Tropical cyclones (TCs) are among the most devastating natural hazards, yet their intensity remains notoriously difficult to predict. NWP models are constrained by both computation…

physics.ao-ph2026

A Data-Driven Regional Model for Skillful Medium-Range Typhoon Prediction

Zeyi Niu, Wei Huang, Sirong Huang +7

Accurate prediction of tropical cyclones remains a major challenge for both numerical weather prediction and emerging artificial intelligence weather prediction systems. While rece…

physics.ao-ph2026

StormDiT: A generative AI model bridges the 2-6 hour 'gray zone' in precipitation nowcasting

Haofei Sun, Yunfan Yang, Wei Han +6

Accurate short-term warnings for extreme precipitation are critical for global disaster mitigation but are hindered by a persistent predictability barrier at the 2-6 hour horizon -…