TCBench: A Benchmark for Tropical Cyclone Track and Intensity Forecasting at the Global Scale
Abstract
TCBench is a benchmark for evaluating global, short to medium-range (1-5 days) forecasts of tropical cyclone (TC) track and intensity. To allow a fair and model-agnostic comparison, TCBench builds on the IBTrACS observational dataset and formulates TC forecasting as predicting the time evolution of an existing tropical system conditioned on its initial position and intensity. TCBench includes state-of-the-art dynamical (TIGGE) and neural weather models (AIFS, Pangu-Weather, FourCastNet v2, GenCast). If not readily available, baseline tracks are consistently derived from model outputs using the TempestExtremes library. For evaluation, TCBench provides deterministic and probabilistic storm-following metrics. On 2023 test cases, neural weather models skillfully forecast TC tracks, while skillful intensity forecasts require additional steps such as post-processing. Designed for accessibility, TCBench helps AI practitioners tackle domain-relevant TC challenges and equips tropical meteorologists with data-driven tools and workflows to improve prediction and TC process understanding. By lowering barriers to reproducible, process-aware evaluation of extreme events, TCBench aims to democratize data-driven TC forecasting.
Keywords
Cite
@article{arxiv.2601.23268,
title = {TCBench: A Benchmark for Tropical Cyclone Track and Intensity Forecasting at the Global Scale},
author = {Milton Gomez and Marie McGraw and Saranya Ganesh S. and Frederick Iat-Hin Tam and Ilia Azizi and Samuel Darmon and Monika Feldmann and Stella Bourdin and Louis Poulain--Auzéau and Suzana J. Camargo and Jonathan Lin and Dan Chavas and Chia-Ying Lee and Ritwik Gupta and Andrea Jenney and Tom Beucler},
journal= {arXiv preprint arXiv:2601.23268},
year = {2026}
}
Comments
28 Pages, Including SI