SPIN (v1.0): A spontaneous synthetic tropical cyclone model empowered by NeuralGCM for hazard assessment

Gao, Yurong; Xi, Dazhi

doi:10.5194/gmd-19-7303-2026

Articles | Volume 19, issue 15

https://doi.org/10.5194/gmd-19-7303-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-7303-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 15

Model description paper

|

06 Aug 2026

Model description paper |

| 06 Aug 2026

SPIN (v1.0): A spontaneous synthetic tropical cyclone model empowered by NeuralGCM for hazard assessment

Yurong Gao and Dazhi Xi

Supplement

https://doi.org/10.5194/gmd-19-7303-2026-supplement

Data sets

Simulation Outputs from SPIN v1.0 for Tropical Cyclone Risk Assessment Y. Gao and D. Xi https://doi.org/10.5281/zenodo.20795548

Archived model and dataset used for benchmarking SPIN v1.0 Y. Gao https://doi.org/10.5281/zenodo.18230393

Model code and software

SPIN (v1.0): A Spontaneous Synthetic Tropical Cyclone Model Empowered by NeuralGCM for Hazard Assessment Y. Gao and D. Xi https://doi.org/10.5281/zenodo.20796397

ClimateGlobalChange/tempestextremes: Version 2.1 P. Ullrich et al. https://doi.org/10.5281/zenodo.4385656

Short summary

Artificial intelligence offers a new way to assess tropical cyclone hazards. We developed a hybrid hazard model that combines a Neural General Circulation Model for storm tracks with a dynamical method for intensity. Our results highlight the potential of rapid, low-cost, hourly simulations of synthetic tropical cyclones to assess compound hazards, exemplified by the model's ability to represent tropical cyclone clusters with dynamical connections.