WeatherNext AI Model Improves Cyclone Forecasting Lead Time by an Extra Day and Goes Open Source

WeatherNext AI Model Improves Cyclone Forecasting Lead Time by an Extra Day and Goes Open Source In a study published in Nature, researchers from Google DeepMind and Google Research unveiled WeatherNext, an AI model that unifies tropical cyclone track, intensity, and wind structure forecasting while extending predictive accuracy by an extra 24 hours. WeatherNext provides three-day cyclone forecasts that match previous two-day forecasts, representing an advance equivalent to approximately a decade of meteorological progress. The single model bridges the traditional divide between coarse global track models and fine-scale local intensity models by training on nearly 20 terabytes of atmospheric data and almost 5,000 historical storms from IBTrACS. Using Functional Generative Networks on TPUs, the system can generate a 15-day forecast in under a minute and scale ensemble sizes to 1,000 members while running on surprisingly coarse resolutions down to 28x28km and 111x111km. Google is open sourcing the code and weights for WeatherNext Cyclones, WeatherNext 2, and WeatherNext 2-mini, alongside visualizations in Weather Lab under Google Earth AI. Forecasting Accuracy and Real-World Impact Evaluated against historical cyclones from 2023 to 2024, WeatherNext Cyclones achieved state-of-the-art deterministic and probabilistic accuracy, gaining more than a full day of lead time for predicting track, intensity, and wind structure. Developed in collaboration with organizations including the National Hurricane Center (NHC), the Cooperative Institute for Research in the Atmosphere (CIRA), and the UK Met Office, the model previously helped NHC issue advance warnings during the 2025 hurricane season by predicting Hurricane Melissa's rapid intensification and Jamaican landfall. Architecture, Ensembles, and Resolution Dynamics Historically, cyclone modeling required separate systems: coarse models to follow steering currents for tracks, and high-resolution local models to capture core thermodynamic intensity. WeatherNext bridges this divide through co-training on global dynamics alongside historical cyclone observations. Powered by Functional Generative Networks, the system scales from prior 50-member runs to 1,000-member ensembles to expose rare tail risks such as rapid intensification. Surprisingly to researchers, the system achieves these intensity forecasts using coarse spatial inputs of 28x28km—roughly 100 times coarser than traditional specialized models—as well as 111x111km in the mini variant. Open-Source Availability and Tooling Google is releasing the code and model weights publicly to support academic researchers, operational agencies, and nonprofits. The release includes the hurricane season model WeatherNext Cyclones, an updated operational model called WeatherNext 2, and WeatherNext 2-mini, which can run on a single TPU within a free public Colab notebook. In addition, cyclone tracks and global atmospheric variables from WeatherNext have been integrated into the refreshed Weather Lab interface as part of Google Earth AI.

谷歌DeepMind发布WeatherNext气象AI模型，热带气旋预报提前量获重大突破并开源 Google DeepMind 与 Google Research 联合多家气象机构在《自然》期刊发表研究，推出气象 AI 模型 WeatherNext。该模型在热带气旋的路径、强度和风场结构预测上实现突破，平均增加逾24小时的有效预报提前量，相当于气象领域约十年的技术进步，目前相关代码与模型权重已面向公众开源。 WeatherNext 在3天气旋预测上的表现比肩过去传统模型2天的水平，平均争取到超过24小时的预警提前量。 模型基于近20TB全球大气数据及涵盖近5000场历史风暴的IBTrACS数据库进行端到端联合训练。 采用功能生成网络（FGNs），单次15天预测在单个TPU上仅需不足1分钟，并可扩展至1000个集合成员以评估极端小概率风险。 该模型仅需28×28公里的低分辨率输入（比传统模型粗糙100倍），官方现已开源 WeatherNext 2、WeatherNext Cyclones 以及轻量级 WeatherNext 2-mini。 跨越路径与强度的双重建模壁垒 传统气旋预报往往面临技术取舍：气旋移动路径由宏观全球大气环流决定，适合粗分辨率全局模型；强度则由风暴核心高度局域化的微观物理过程驱动，依赖高分辨率局部模型。WeatherNext 通过统一的 AI 架构消除了这一鸿沟，仅使用 28×28 公里分辨率的输入数据（甚至轻量版 111×111 公里）即可实现极高精度，突破了高空间分辨率才能做好强度预测的传统认知。 高效集合预测与实战表现 WeatherNext 利用功能生成网络生成多样化预测集合，单次15天的预测可在单个 TPU 上于1分钟内完成。研究团队将预测集合扩展至1000个成员，用于捕捉罕见但破坏力极大的尾部风险。在2025年飓风季节，该模型曾协助美国国家飓风中心提前预测飓风梅丽莎的快速增强与登陆牙买加，争取到了关键应对时间。 开源模型与生态协作 谷歌将 WeatherNext Cyclones、WeatherNext 2 以及可在免费 Colab 笔记本单个 TPU 上运行的 WeatherNext 2-mini 的代码和权重全部开源，供学界、预报机构及非营利组织使用。相关预测结果已接入 Google Earth AI 旗下的 Weather Lab 平台，支持可视化呈现温度、降水及风速等多维气象数据。

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 worth of meteorological progress. This collaborative work brought together AI researchers and engineers at Google DeepMind and Google Research, with expert forecasters at the National Hurricane Center (NHC), the Cooperative Institute for Research in the Atmosphere (CIRA), the UK Met Office , and weather agencies around the world. Our research has already had real-world impact. During the 2025 hurricane season, our model helped the NHC to make a historic forecast for Hurricane Melissa by predicting the storm’s rapid intensification and landfall in Jamaica. This enabled the NHC to issue an advance warning, giving teams on the ground critical time to prepare. This year, we continue to work together and are now predicting 1,000 possible scenarios for each cyclone to help support forecasters in their decision-making. Weather affects everyone. Given this broad impact, we are now open sourcing our WeatherNext 2 and WeatherNext Cyclones models used during the hurricane season. By making this technology openly available, we hope to empower the research community and amplify AI's impact in building more resilient communities – whether that be providing local forecasters with the tools they need to prepare for natural disasters , supporting the growth of renewable energy, or anticipating extreme weather. How WeatherNext predicts weather and cyclones Starting from global atmospheric conditions during Hurricane Milton (October 2024), WeatherNext Cyclones iteratively predicts both global weather patterns and fine-scale cyclone tracks up to 15 days in advance. Running a 1,000-member ensemble generates localised probability maps of tropical storm to hurricane-force winds. Predicting cyclones has typically forced a trade-off requiring two distinct modeling techniques. A cyclone's track (where it goes) is steered by massive, global atmospheric currents, which before now have been best modeled by coarser global models. However, a cyclone’s intensity (how strong it gets) is driven by highly localized, fine-scale thermodynamic physical processes around its core, which are best modeled by specialized, higher resolution, local models. Our WeatherNext model bridges this gap by improving forecasting for global weather overall as well as cyclones. It is a single AI model that predicts a tropical cyclone’s track, intensity, and wind structure with state-of-the-art accuracy. It achieves this breakthrough through a unique combination of its training, architecture and approach to low resolution inputs. We evaluated WeatherNext Cyclones on historical cyclones from 2023 to 2024, benchmarking its deterministic and probabilistic performance against other top weather models. On average, WeatherNext Cyclones gains more than a full day (24 hours) of lead time advantage for predicting cyclone tracks, intensity, and wind structure. The model was co-trained on two distinct data modalities: global weather dynamics and expert-curated historical cyclone observations. By training end-to-end on nearly 20 terabytes of global atmospheric data and the historical IBTrACS database spanning nearly 5,000 historical storms, the model learns complex atmospheric patterns and how to model extreme weather. Cyclone forecast accuracy has been steadily advancing over recent decades. The plots show the 3-day accuracy of ECMWF-ENS track forecasts (a) and HWRF intensity forecasts (b) over the years, and how WeatherNext Cyclones contributes a step change in accuracy for both track and intensity. This improvement is the equivalent to a one-decade progress according to trends over the last 20 years. Our model uses Functional Generative Networks (FGNs) to efficiently produce ensembles of different predictions, which captures the inherent uncertainty of the weather. We can now generate a single 15-day forecast in less than a minute on a TPU, empowering forecasters to quickly evaluate the probability distribution of potentially devastating tail-risks. Last year, our system produced 50 predictions at a time, matching global physics models. This year we scaled our ensemble size to 1,000 members, capturing rare but consequential scenarios like rapid intensification events, as occurred during Hurricane Melissa in 2025. Up until now, operating at very high spatial resolution has been considered the main driver for making accurate intensity forecasts. However, WeatherNext Cyclones only needs data with a resolution of 28x28km, 100x coarser than traditional models. A smaller version of the model, WeatherNext 2-mini, which operates at a coarser 111x111km resolution, also shows great performance. This has surprised scientists, and it remains an open research question to fully understand how our models produce such accurate predictions at this resolution. We hope that, together with the research community, we can find out. Opening up WeatherNext to the research community Alongside our Nature paper, we are open sourcing the code and model weights, making them freely available for anyone to build on. This includes academic research, operational forecasting, or developing more specialized, localized models. We hope to accelerate progress across the global weather community and empower meteorological agencies, researchers, and nonprofits to better predict weather events of all kinds and make key decisions to protect lives and infrastructure. We are also releasing two sets of similar models: WeatherNext Cyclones, which ran during the hurricane season (results can be seen in the paper); and WeatherNext 2, a later update that we operationalized in October. Additionally, we are releasing WeatherNext 2-mini, a compact version of the model that can run on a single TPU in a free public Colab notebook . You can explore our latest cyclone forecasts on Weather Lab , which we recently refreshed with a new interface and expanded to include global weather forecasts alongside cyclone tracks. Weather Lab now lets you visualize WeatherNext predictions for temperature, precipitation, wind speed, and more, all in a single view. Both Weather Lab and WeatherNext models are a part of Google Earth AI . Pushing the frontiers of AI for weather forecasting We have achieved a historic breakthrough by gaining more than a full day of lead time for predicting cyclones — delivering an advance equivalent to a decade of meteorological progress. As we prepare for future storm seasons, we invite researchers, meteorological agencies, and experts to partner with us, build on our open source models, and explore our forecasts on Weather Lab. By combining advanced machine learning with the indispensable real-world expertise of human forecasters, we aim to create a collaborative weather forecasting ecosystem that can save lives and help communities adapt to a changing climate. Note: For official weather forecasts and warnings, refer to your local meteorological agency or national weather service. Acknowledgements This research was co-developed by Google DeepMind and Google Research teams. We’d like to thank our collaborators NOAA/NWS/NCEP National Hurricane Center, Cooperative Institute for Research in the Atmosphere (CIRA) and the UK Met Office for their partnership and contributions to the paper. This work reflects the contributions of the paper’s co-authors: Ferran Alet, Tom Andersson, Ilan Price, Stratis Markou, Andrew El-Kadi, Dominic Masters, Amy Li, Samier Merchant, Natalie Williams,Gregory Thornton, Ken MacKay, Olivia Graham, Akib Uddin, Ben Gaiarin, Devaja Shah, Elinor Kruse, Wallace Hogsett, David Zelinsky, John Cangialosi, Jonathan Martinez, James Franklin, Mark DeMaria, Kate Musgrave, Caroline L. Bain, Helen Titley, Jacklynn Stott, Remi Lam, Aaron Bell, Paul Komarek, Matthew Willson, Alvaro Sanchez-Gonzalez, and Peter Battaglia.