TCBench: A Benchmark for Tropical Cyclone Track and Intensity Forecasting at the Global Scale

2026-01-30

AI Summary

This study addresses the lack of a unified and reproducible evaluation benchmark for tropical cyclone forecasting, which has hindered fair comparisons and synergistic development between AI-based and traditional numerical weather prediction models. The authors present the first standardized global benchmark for 1–5 day track and intensity forecasts of tropical cyclones, formalizing the prediction task as conditional system evolution based on initial states derived from IBTrACS observational data. The framework integrates diverse dynamical and neural weather models—including TIGGE, AIFS, Pangu-Weather, FourCastNet v2, and GenCast—and employs TempestExtremes for consistent storm trajectory extraction. Storm-following evaluation metrics enable both deterministic and probabilistic assessments. Experiments demonstrate that neural weather models excel in track forecasting, while intensity predictions require post-processing to achieve skillful performance, thereby validating the benchmark’s effectiveness and its potential to foster cross-disciplinary collaboration.

Technology Category

• Machine Learning: Evaluation and Analysis
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• tropical cyclone
• forecasting
• benchmark
• track prediction
• intensity prediction

Innovation

• TCBench
• tropical cyclone forecasting
• neural weather models
• model-agnostic benchmark
• storm-following evaluation