TailWeather: from tail to extremes, a global climatological dataset for machine-learning weather forecasting

2026-09-11

AI Summary

该研究通过构建TailWeather数据集，提供了一种全球范围内评估极端天气事件的方法，解决了传统天气预报模型在极端天气预测上的不足。

Abstract

Weather forecasting models commonly use the average forecast skill for short-range forecasts. However, it does not necessarily imply skill in the tails of the weather distribution. Evaluating tail events requires a consistently defined target with broad spatial and temporal coverage. Disaster catalogs record societal consequences, but are sparse and reporting-dependent; climatological tails describe unusual weather without necessarily implying harm. We present TailWeather, a global 0.25-degree, land-only dataset derived from ERA5, covering 1981-2022 and extending into January 2023. It labels heatwaves, cold waves, heavy precipitation, and extreme wind daily, and meteorological drought monthly. Each event has an ordinal severity tier and a numerical intensity score referenced to the local 1991-2020 climate. The scores support alternative thresholds within their stored resolution and valid domain. Comparison with documented disasters shows greater impact enrichment towards stricter tails, with differences among hazards and substantial gaps in catalog coverage. Forecast examples illustrate how low average errors can coexist with weak event detection, particularly for wind. TailWeather provides a reusable physical target for studying and evaluating extremes, while complementing the information in disaster catalogs.

Problem

• weather forecasting
• extreme weather events
• forecast skill
• disaster catalogs
• climatological tails

Innovation

• machine-learning weather forecasting
• extreme events
• global climatological dataset
• ERA5
• ordinal severity tier