Google DeepMind's WeatherNext AI model improves cyclone forecasts by one day
Google DeepMind published a paper in Nature on August 6, 2026, showing that its WeatherNext AI model achieves state-of-the-art accuracy in predicting tropical cyclone track, intensity, and wind structure. The model, trained on nearly 20TB of global atmospheric data and historical cyclone records, provides forecasters with an extra day of predictive accuracy on average, and is now open-sourced.
Coverage timeline
Google DeepMind Blog
August 6, 2026 Science WeatherNext team WeatherNext enables accurate cyclone forecasts that can give an extra day of warning. Now we are open sourcing the model. Predicting how dangerous cyclones develop is a longstanding challenge where every hour counts. Tropical cyclones — also known as hurricanes or typhoons — are among the most destructive weather phenomena on Earth, responsible for more than 700,000 deaths and $1.4 trillion in economic losses globally over the past 50 years. For forecasters, issuing timely, accurate warnings is a constant race against time. Today, in a paper published in _Nature_, we show that our WeatherNext AI model achieved state-of-the-art accuracy in predicting a cyclone's track, intensity, and wind structure. On average, our model gives forecasters an extra day’s worth of predictive accuracy: our three-day forecasts are as good as what prior models were able to provide for only the next two days. This scale of improvement corresponds roughly to a decade’s w
机器之心ScienceAI
编辑丨& 飓风、台风等热带气旋，是地球上最复杂、最危险的天气系统之一。 对于气象学家而言，预测一场风暴会往哪里移动，已经取得了巨大进步；但判断它会不会突然增强，甚至从普通热带风暴迅速升级为灾难级飓风，仍然是长期以来最困难的问题之一。 近年来，人工智能正在进入天气预测领域。现在，Google DeepMind 推出的新一代 WeatherNext 模型，正在改变这一局面。 研究团队发现，AI 不仅能够预测气旋会往哪里移动，还能够提前判断它是否会快速增强，并为未来可能的发展路径提供概率预测。WeatherNext 在测试中平均比传统方法提供约一天的有效预报提前量——也就是说，过去需要提前两天才能达到的预测准确度，AI 如今能够提前三天达到。 相关信息以「 Operational Tropical Cyclone Forecasting with AI 」为题，于 2026 年 8 月 6 日发布于《 Nature 》。 论文链接： https://www.nature.com/articles/s41586-026-10953-2 让 AI 学习 45 年的地球天气规律 研究团队认为，气旋的发展无法脱离整个地球大气系统理解。因此，模型同时学习两类信息：一类是全球天气分析数据，用于理解大尺度的大气环境；另一类是专门整理的历史热带气旋数据库，用于学习风暴形成、增强和演化过程。 这种训练方式让 AI 获得了一种类似「气象背景知识」的能力。 WeatherNext 通过长期全球天气数据训练，使模型能够理解不同大气状态之间的关系，并预测未来可能发生的变化。通过改善全球气象及气旋的预报，WeatherNext 仅凭单一的人工智能模型，就能够以最先进的精度预测热带气旋的路径、强度和风向结构。 图 1：WeatherNext Cyclones 迭代预测全球天气模式和细尺度气旋路径，最早可提前15天。 该模型基于两种不同的数据模式共同训练：全球天气动态和专家策划的历史气旋观测数据。通过端到端训练近 20TB 的全球大气数据和涵盖近 5000 场历史风暴的历史 IBTrACS 数据库，模型学习复杂的大气模式以及如何模拟极端天气。 传统天气预报通常给出一个最可能的发展结果，但真实的大气系统充满不确定性。一个微小变化可能导致风暴未来轨迹完全不同。 因此，WeatherNext Cyclones
