Google发布WeatherNext 2天气预报AI模型

本仓库包含 WeatherNext 2（WN2）的代码，这是由 Google DeepMind 和 Google Research 开发的全球中程大气和台风预报模型。

同时包含上一代模型 GraphCast 和 GenCast 的代码。

访问预报数据馈送

如果您不想自己运行模型，而是希望直接访问 WN2 模型输出的每日数据流，我们通过多个平台提供：

Google Cloud（含 Earth Engine、BigQuery 和 Vertex AI）。

WeatherLab（含台风路径）。

OpenMeteo（含 API 和交互式构建器）。

模型指南与文档

Model Guide & Documentation: Google Developers WeatherNext Guide

WeatherNext Cyclones Paper: Operational tropical cyclone forecasting with AI

FGN/WN2 Technical Report: Skillful joint probabilistic weather forecasting from marginals (arXiv:2506.10772)

WeatherNext 2 Blog Post: WeatherNext 2: Our most advanced weather forecasting model

WeatherNext Cyclones Blog Post: WeatherNext: AI model achieves breakthrough in forecasting cyclones

本仓库是 WeatherNext 系列模型的主要所在地。除 WN2 外，本仓库还托管以下旧版和专业模型的代码和文档：

WeatherNext Graph: Deterministic medium-range weather forecasting using graph neural networks. Published as GraphCast.

WeatherNext Gen: Diffusion-based ensemble forecasting for medium-range weather. Published as GenCast.

提供的预训练模型

本仓库提供了运行 WeatherNext 2 和 WeatherNext Cyclones 不同版本的代码。两者之间的唯一区别在于 WN2 还能预测 100 米风速。WN2 使用与 WN Cyclones 完全相同的算法进行台风预报，由于训练过程相互独立，两者的权重存在差异。

WeatherNext2_<2025 (Used Operationally): 0.25° resolution (~30km). Fine-tuned on ECMWF HRES data and designed to be initialized directly from operational HRES initial conditions rather than ERA5 reanalysis. Trained on data through 2024. Corresponding weights files: WeatherNext2_<2025_model{1,2,3,4}.npz.

WeatherNext Cyclones - 用于复现论文结果的模型

WeatherNextCyclones_<2025 (Used Operationally): 0.25° resolution. The model that ran live during the 2025 Atlantic hurricane season, publicly referred to as FNV3 (NHC's postprocessed version was called GDMI). Trained on data through 2024. The paper appendix contains a partial evaluation of 2025 in NHC basins for this model checkpoint, and how the tracker improvement in September 2025 improved results. Corresponding weights files: WeatherNextCyclones_<2025_model{1,2,3,4}.npz.

WeatherNextCyclones_<2024: 0.25° resolution. Reproduces results from the paper on 2024. Trained on data through 2023. Corresponding weights files: WeatherNextCyclones_<2024_model{1,2,3,4}.npz.

WeatherNextCyclones_<2023: 0.25° resolution. Reproduces results from the paper on 2023. Trained on data through 2022. Corresponding weights files: WeatherNextCyclones_<2023_model{1,2,3,4}.npz.

WeatherNext Cyclones Mini

WeatherNextCyclones_Mini_<2024: 1° resolution. A lightweight version suitable for lower memory and compute constraints (e.g., local testing or single TPUs or GPUs). Not expected to match the performance of the larger versions. Forecasts the same things as WeatherNext2_<2025, including cyclones. Trained on data through 2023. Corresponding weights file: WeatherNextCyclones_Mini_<2024.npz.

WeatherNextCyclones_Mini_<2023: As above, but only trained on data through 2022. Corresponding weights file: WeatherNextCyclones_Mini_<2023.npz.

Evaluation results for WeatherNextCyclones_Mini can be found in the appendix of the WeatherNext Cyclones Paper.

上手 WeatherNext 2 最简单的方式是运行我们的交互式 Colab Notebook，可从 Colaboratory 打开。该 notebook 默认使用 WeatherNext Cyclones Mini，我们推荐使用 v5e-1 runtime 运行（可作为 Colab runtime 免费使用）。不过该 notebook 也可用于运行上述其他模型（但需要 v5p 加速器）。

一般来说，我们推荐尽可能在 TPU 上运行 WeatherNext 2，因为其实现已针对 TPU 进行了优化。但是，如果选择使用 GPU，则必须更换注意力实现方式，如 demo notebook 中所示。非 Mini 模型需要 H100 以提供足够的 VRAM。Mini 模型应该可以在 P100 上完成推理。

预训练权重和样本数据可在我们的 Google Cloud Bucket 获取。

Inside the notebook, you will learn how to:

• Automatically load the required model weights from our storage bucket.
• Load initial state weather data (e.g., HRES initial conditions).
• Initialize the WN2 (FGN) architecture.
• Run auto-regressive rollout steps to generate a forecast prediction.
• Visualize the outputs (e.g., temperature, wind speed, geopotential height).
• Run the direct tracker on model outputs to obtain track data for cyclones.
• Compute the training loss on model predictions and targets, and take a gradient step.

[!NOTE] This is research code provided as-is for the purpose of running and experimenting with the published models. There are no guarantees of API stability and future updates may introduce breaking changes without notice. We recommend pinning to a specific release.

pip install git+https://github.com/google-deepmind/weathernext.git@v0.3.0

要运行 WeatherNext 2 或 WeatherNext Cyclones，需要下载预训练模型权重。可通过 Google Cloud Bucket 获取权重。

The utils/ directory contains shared libraries used by multiple WeatherNext models, providing common infrastructure for autoregressive rollouts, input normalization, graph building blocks, loss computation, and JAX-compatible xarray utilities. See the per-model READMEs for model-specific code.

完整模型训练需要从 ECMWF 下载 ERA5 数据集，最佳方式是通过 WeatherBench2 以 Zarr 格式访问。业务微调数据可通过 WeatherBench2 的 HRES 数据获取。

These datasets may be governed by separate terms and conditions. Check that you can comply with any applicable restrictions before use.

版权所有 2026 Google LLC。

Colab notebook 及相关代码采用 Apache License, Version 2.0 (Apache 2.0) 授权；除非遵守 Apache 2.0 许可证，否则不得使用这些材料。可在此处获取许可证副本：https://www.apache.org/licenses/LICENSE-2.0。

所有其他材料采用 Creative Commons Attribution 4.0 International (CC BY 4.0) 授权。可在此处获取许可证副本：https://creativecommons.org/licenses/by/4.0/。

除非适用法律要求或书面同意，否则根据 Apache 2.0 或 CC-BY 4.0 许可证分发的所有软件和材料均按"原样"分发，不提供任何形式的明示或暗示担保。请参阅许可证了解具体的权限和限制。

这不是 Google 官方支持的产品。

WeatherNext 模型是一个实验性研究项目的一部分。您需自行判断使用或分发这些模型或其生成的任何输出的适当性，并承担与此类使用或分发相关的所有风险，以及您行使 Google 相关许可证授予的权利和权限的责任。在依赖、发布、下载或以其他方式使用这些模型或其任何输出之前，请谨慎行事。

WeatherNext 模型未经任何政府气象机构或部门协作或背书，绝不能替代此类机构发布的官方警报、警告或通知。

如果您在研究中使用 WeatherNext 2，请引用我们的论文：

@article{Alet2026,
  title={Operational Tropical Cyclone Forecasting with AI},
  author={Alet, Ferran and Andersson, Tom R. and Price, Ilan and Markou, Stratis and El-Kadi, Andrew and Masters, Dominic and Li, Amy and Merchant, Samier and Williams, Natalie and Thornton, Gregory and MacKay, Ken and Graham, Olivia and Uddin, Akib and Gaiarin, Ben and Shah, Devaja and Kruse, Elinor and Hogsett, Wallace and Zelinsky, David and Cangialosi, John and Martinez, Jonathan and Franklin, James and DeMaria, Mark and Musgrave, Kate and Bain, Caroline L. and Titley, Helen and Stott, Jacklynn and Lam, Remi and Bell, Aaron and Komarek, Paul and Willson, Matthew and Sanchez-Gonzalez, Alvaro and Battaglia, Peter},
  journal={Nature},
  year={2026},
  issn={1476-4687},
  doi={10.1038/s41586-026-10953-2},
  url={https://doi.org/10.1038/s41586-026-10953-2}
}

@article{alet2025skillful,
  title={Skillful joint probabilistic weather forecasting from marginals},
  author={Alet, Ferran and Price, Ilan and El-Kadi, Andrew and Masters, Dominic and Markou, Stratis and Andersson, Tom R and Stott, Jacklynn and Lam, Remi and Willson, Matthew and Sanchez-Gonzalez, Alvaro and Battaglia, Peter},
  journal={arXiv preprint arXiv:2506.10772},
  year={2025}
}

WeatherNext 模型与以下独立库和包进行数据交互：

Data and products of the European Centre for Medium-range Weather Forecasts (ECMWF), as modified by Google.

Modified Copernicus Climate Change Service information 2023.

NOAA's International Best Track Archive for Climate Stewardship (IBTrACS) data, first accessed on 1 Dec 2022.

Additionally, the colab notebooks include a few examples of ECMWF's ERA5 and HRES data that can be used as input to the models.

Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains. ECMWF HRES datasets Copyright statement: Copyright "© 2023 European Centre for Medium-Range Weather Forecasts (ECMWF)". Source: www.ecmwf.int License Statement: ECMWF open data is published under a Creative Commons Attribution 4.0 International (CC BY 4.0). https://creativecommons.org/licenses/by/4.0/ Disclaimer: ECMWF does not accept any liability whatsoever for any error or omission in the data, their availability, or for any loss or damage arising from their use.

Use of the third-party materials referred to above may be governed by separate terms and conditions or license provisions. Your use of the third-party materials is subject to any such terms and you should check that you can comply with any applicable restrictions or terms and conditions before use.

如对代码库或模型有反馈或问题，请通过 weathernext@google.com 联系我们。

通过电子邮件收集的任何信息将按照 Google 的隐私政策使用。