Hybrid physics and machine learning improve tropical cyclone intensity forecasts
FAST-ML: A Hybrid Physics-Machine Learning Framework for Tropical Cyclone Intensity Forecasting
Machine Learning
Summary
Forecasting how strong tropical cyclones will get, especially sudden increases in strength, is very hard. The authors created a new method called FAST-ML that combines weather physics with machine learning to better predict these changes. Their method uses weather data and physical laws to make more accurate and understandable predictions while running efficiently. Tests showed FAST-ML made fewer false alarms and worked well even when applied to storms from different ocean regions. This approach could help weather teams make better hurricane forecasts.
What this means in practice
- •For weather forecast centers: Generate more accurate and interpretable intensity forecasts for tropical cyclones using a hybrid physical and machine learning model.
- •For emergency management teams: Improve tropical cyclone rapid intensification warnings to reduce false alarms and better prepare communities.
Authors
Shijie Xiao, Jonathan Lin, Thomas Ehrmann, Ali Sarhadi
Abstract
Rapid intensification (RI) remains one of the most consequential and difficult aspects of tropical cyclone (TC) forecasting. Although full-physics numerical weather prediction models can represent the processes governing RI, resolving storm-environment interactions remains computationally expensive, while purely data-driven approaches often lack physical interpretability. We present FAST-ML, a hybrid framework that bridges data-driven efficiency with physical constraints. A physically informed dual-stream neural parameterization ingests 3D ERA5 fields to diagnose ventilation controls---environmental wind shear and mid-level entropy deficit. By optimizing these parameters end-to-end through a differentiable FAST intensity model, this architecture establishes a robust new paradigm for observation-driven parameter optimization, ensuring storm evolution remains strictly governed by thermodynamic principles. By better capturing the storm's continuous intensity evolution, FAST-ML improves upon its physical baseline, reducing ensemble CRPS across forecast lead times, with a reduction of approximately 31% at 60 h and nearly halving the RI false alarm ratio without sacrificing detection skill. In a 100-member ensemble configuration, FAST-ML produces intensity forecasts comparable to FNV3 for selected storms under the evaluated input configurations. Furthermore, zero-shot tests on selected Eastern Pacific storms provide encouraging evidence of cross-basin transferability. FAST-ML provides a modular intensity forecasting framework that can be coupled with externally supplied storm tracks and environmental fields. It demonstrates that observation-driven parameter learning within physically constrained dynamics simultaneously enhances accuracy, interpretability, and computational efficiency.