AI提升飓风预报精度,但决定权仍在人类

本文已按照 Science X 的编辑流程与政策进行审核。编辑在确保内容可信度的同时,重点标注了以下属性:
同行评审出版物
添加到首选来源
2026 年 10 月 10 日,飓风 Isaias 过后,佛罗里达州 Gulf Breeze 一处加油站可见风暴造成的损毁。
AI 常因数据中心耗电而受到批评,这推动了更多化石燃料的使用,并加剧了气候变化。
但它也在帮助气象学家做出明显更准确的预报,包括对飓风的预报——飓风向来难以预测,而且在气候变暖的背景下正构成日益严重的威胁。
美国国家飓风中心(NHC)去年开始使用 Google DeepMind 的 AI 模型,并正与该公司合作开发其后续版本。
这项工作在今年凸显出来——强烈的厄尔尼诺气候模式导致太平洋飓风数量创下纪录,而上个月飓风 Isaias 以强风暴之势袭击了美国东南部。
DeepMind 研究科学家 Ferran Alet 负责领导该公司的气旋相关工作,他解释说,Google 并没有专门针对飓风的模型——它所用的其实是同一款用于日常天气的模型,只是被推到了极限。
“我们把极端天气几乎看作是我们应当努力追求的目标,因为它对我们来说是最具挑战性的,攻克它之后其他一切都会随之而来,”他告诉 AFP。
在 AI 出现之前,NHC 使用多种模型来预报热带气旋。“动力”模型利用超级计算机求解支配大气运动的流体运动方程和热力学方程。
统计模型依赖风暴行为与位置、日期等变量之间的历史关系,而混合模型则将物理方法与统计方法结合起来。
另一方面,AI 模型与统计模型一样从大型数据集中学习,但规模要大得多,并且能够捕捉远远更为复杂的模式。
更长的预警时间,更高的精度
DeepMind 于 8 月在《Nature》上发表的论文发现,该模型平均为预报员多提供了一天的预测准确度,其三天预报的准确度相当于早先模型仅能对未来两天作出的预报水平。
对于 Isaias,DeepMind 的模型在其形成整整一周前就识别出它可能成为热带气旋。
该模型还能为每个气旋生成 1000 种可能情景,并在预测风暴路径与强度的同时预报降雨量——也就是风暴将沿哪条路径移动、强度会增强到何种程度。
“NHC 于 2025 年 6 月下旬开始在日常业务中使用 AI 模型,Google DeepMind 的模型则在 2026 年被纳入 NHC 部分路径与强度共识辅助工具,”NHC 业务部门主管 Dan Brown 对法新社表示。
NHC 还使用欧洲中期天气预报中心和美国国家气象局的 AI 模型,并与 Google 达成协议,共同开发其模型。
“在伊萨亚斯期间,AI 模型在路径预测上表现相当不错,”Brown 说,并补充道,“AI 模型似乎擅长快速预测复杂引导气流型式的变化。”
Brown 特别提到 DeepMind 以及 NHC 自己的模型 HCCA,称它们是表现最好的两个路径与强度辅助工具。
这项技术并非没有局限。Brown 表示,单个模型可能会“在每个更新周期之间大幅翻转其路径或强度预测”,这使飓风专家不得不依靠经验与判断,来决定哪些模型最能把握某场风暴,并将它们融合起来。
他还指出,基于物理学的模型构建了 AI 模型训练所依据的基线。
“至于飓风专家呢?专家的作用比以往任何时候都更重要。算法可以给出路径概率,但它不会去看实时的飞机与卫星数据来判断风暴当前的结构,”Brown 说。
预报精度的提升正值美国数据中心建设迅速改变电网构成之际,而根据 Cleanview 的一项分析,计划新建的数据中心将主要由天然气供电,这会增加美国的碳足迹,并加剧气候变化。
气候变化反过来又使飓风变得更强、携带更多降雨、移动速度更慢,从而加重其影响。
期刊信息:Nature
这篇报道背后是谁?
物理学硕士,拥有科研经历。长期的科学新闻爱好者。在 Science X 的编辑工作成功中发挥关键作用。完整简介 →
引用:AI 提升了飓风预报精度,但最终仍由人类拍板(2026年11月11日),2026年11月11日检索自 https://techxplore.com/news/2026-11-ai-sharpens-hurricane-humans-shots.html
本文档受版权保护。除为私人学习或研究目的进行的合理使用外,未经书面许可不得复制任何部分。内容仅供参考。
AI 气旋预报可增加 30 小时的预警时间
AI 天气模型在飓风预报中展现前景,但新研究发现关键物理局限
研究显示,Microsoft AI 天气预报更快、更便宜、更准确
AI 如何改进风暴潮预报以帮助拯救生命
AI 擅长天气预报。它能预测异常天气事件吗?
新型铁基催化剂能否让锂-CO₂ 电池更接近现实?
受象鼻启发,可变形机器人能弯曲、抓取并协同合作
额外机械拇指让佩戴者用一只手完成双手任务
雷达腕带将你的手臂变成智能手表触控板
AI、计算机图形学与波动光学相结合,打造更逼真的全息 VR/AR 显示
绿氢生产存在气泡问题——新模型揭示了能耗急剧上升的阈值
获取即时摘要文本(Gist)
一个 AI 天气模型的三天飓风预报准确度,已与早先模型的两天预报相当。AI 模型能够预判风暴形成并追踪其变化,但不同批次运行的预测结果可能差异很大。在解读实时观测数据和整合模型输出方面,人类预报员仍然不可或缺。
本摘要由 LLM 自动生成。完整免责声明
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(AI sharpens hurricane forecasts, but humans still call the shots)
This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
peer-reviewed publication
Add to Preferred Sources
Storm damage is seen at a gas station in Gulf Breeze, Florida, on Oct. 10, 2026, in the aftermath of Hurricane Isaias.
AI is often criticized for the energy its data centers consume, which is driving more fossil fuel use and contributing to climate change.
But it is also helping meteorologists make markedly more accurate forecasts, including for hurricanes, which are notoriously complex to predict and pose a growing threat in a warming world.
The U.S. National Hurricane Center (NHC) began using Google DeepMind's AI model last year and is working with the company on developing its successor.
The work has come to the fore this year—as an intense El Niño weather pattern led to a record number of hurricanes in the Pacific, and Hurricane Isaias struck the southeastern United States last month as a major storm.
Ferran Alet, a DeepMind research scientist who leads its cyclone work, explained that Google doesn't have a hurricane-specific model—rather, it is the same model used for everyday weather, pushed to its limits.
"We see extreme weather as almost like something we should strive for because it's the most challenging thing for us and then everything will follow," he told AFP.
Prior to AI, the NHC used several kinds of models to forecast tropical cyclones. "Dynamical" models use supercomputers to solve the equations of fluid motion and thermodynamics that govern the atmosphere.
Statistical models rely on historical relationships between storm behavior and variables such as location and date, and hybrids combine physics and statistics.
AI models, on the other hand, learn from large data sets, like statistical models, but on a vastly bigger scale and with the ability to pick up far more complicated patterns.
More lead time, higher precision
A DeepMind paper published in Nature in August found the model gave forecasters on average an extra day's worth of predictive accuracy, with three-day forecasts as good as what earlier models could provide for only the next two days.
For Isaias, DeepMind's model recognized it could become a tropical cyclone a full week before it formed.
The model can also generate 1,000 possible scenarios for each cyclone and forecast rainfall alongside the storm's track and intensity, meaning the path it will follow and how strong it will get.
"NHC began using AI models in operations in late June of 2025, and the Google DeepMind model was added to some of NHC's track and intensity consensus aids in 2026," Dan Brown, NHC operations division chief, told AFP.
The NHC also uses AI models from the European Centre for Medium-Range Weather Forecasts and the National Weather Service, and has an agreement with Google to work on developing its models.
"During Isaias, the AI models performed quite well for track," said Brown, adding that "AI models appear to be good at quickly predicting shifts in complex steering patterns."
Brown singled out DeepMind and the NHC's own model, called HCCA, as two of the best-performing track and intensity aids.
The technology isn't without limitations. Brown said that individual models can "wildly flip their tracks or intensity projections from cycle to cycle," leaving hurricane specialists to use their experience and judgment to decide which models best capture a given storm, and to blend them.
He also noted that physics-based models built the baseline on which the AI models were trained.
"As for the hurricane specialist? The specialist becomes more important than ever. An algorithm can show a track probability, but it doesn't look at live aircraft and satellite data to determine the current structure of the storm," said Brown.
The gains in forecasting precision are taking place as the U.S. data center buildout is rapidly changing the composition of the electric grid, and planned newer data centers are set to be largely powered by natural gas, according to an analysis by Cleanview, increasing the United States' carbon footprint and worsening climate change.
Climate change in turn is causing hurricanes to become more powerful, carry more rainfall and move more slowly, thus worsening impacts.
Journal information:Nature
Who's behind this story?
Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →
Citation: AI sharpens hurricane forecasts, but humans still call the shots (2026, November 11) retrieved 11 November 2026 from https://techxplore.com/news/2026-11-ai-sharpens-hurricane-humans-shots.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
AI cyclone forecasts could add 30 hours of warning time
AI weather models show promise for hurricane forecasts, but new study finds key physical limitations
Microsoft AI weather forecast faster, cheaper, truer: Study
How AI can improve storm surge forecasts to help save lives
AI is good at weather forecasting. Can it predict freak weather events?
Could new iron-based catalysts bring lithium-CO₂ batteries closer to reality?
Inspired by elephant trunks, shape-shifting robots bend, grab and team up
Extra robotic thumb lets wearers complete two-handed tasks with one hand
Radar wristband turns your arm into a smartwatch trackpad
AI, computer graphics and wave optics combine for more realistic holographic VR/AR displays
Green hydrogen production has a bubble problem—new model reveals threshold for steep energy losses
Get Instant Summarized Text (Gist)
An AI weather model achieved three-day hurricane forecasts as accurate as earlier models’ two-day forecasts. AI models can anticipate storm formation and track shifts, but predictions may vary sharply between runs. Human forecasters remain essential for interpreting live observations and combining model outputs.
This summary was automatically generated using LLM. Full disclaimer
This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.
原文为英文,正文由自动抓取并保留原文。
原文发布于 TechXplore(AI sharpens hurricane forecasts, but humans still call the shots),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。
