内容来源：https://research.google/blog/neuralgcm-harnesses-ai-to-better-simulate-long-range-global-precipitation/

内容总结：

谷歌AI模型NeuralGCM在降水预测领域取得突破性进展。该模型融合物理建模与神经网络技术，通过直接学习NASA卫星降水观测数据，显著提升了全球范围降水模拟的准确度。

降水模拟一直是气候预测中的难点，因其涉及云层演化等亚网格尺度复杂过程。传统模型依赖近似参数化方法，难以精准刻画极端降水与日循环特征。NeuralGCM创新性地利用神经网络直接学习卫星观测数据，有效突破这一瓶颈。

测试数据显示，该模型在15天中期预报中，其24小时与6小时累积降水预测精度均超越欧洲中期天气预报中心的传统物理模型。在跨年代气候模拟中，其日均降水误差较联合国气候报告采用的主流工具降低约40%，对极端降水事件（前0.1%强降雨）的模拟能力尤为突出。

值得关注的是，模型成功再现了亚马逊雨林等地区夏季降水的日循环特征，修正了传统模型降水峰值提前数小时的系统性偏差。尽管当前280公里分辨率尚未达到业务预报要求，但其技术路径已展现应用潜力。印度农业部与芝加哥大学的合作项目已将该模型应用于季风预报试点，初步验证了实用价值。

研究团队已将模型开源，期待推动气候科学社区共同发展下一代降水预测工具，为应对气候变化提供更可靠的技术支撑。

中文翻译：

NeuralGCM利用人工智能提升全球远程降水模拟精度
2026年1月12日
Janni Yuval，谷歌研究院科学家

NeuralGCM融合基于物理的建模与基于NASA降水观测数据训练的神经网络，相比其他方法能更精准地模拟全球降水，尤其在捕捉日降水周期与极端天气事件方面表现突出。

快速了解
降水模拟始终是全球天气与气候模型中最棘手的难题之一。这是因为降水的具体位置、时间与强度取决于一系列通常低于模型分辨率尺度的复杂过程。对于极端天气事件和长期气候模拟而言，降水模拟尤为困难。无论是农民需要确定最佳播种日期以优化收成，还是城市规划者需为百年一遇的暴雨做准备，降水预报都是与人类生活最息息相关的预测领域之一。

去年，我们推出了开源混合大气模型NeuralGCM，该模型结合机器学习与物理原理，能够快速、高效且精准地运行全球大气模拟。在2024年的论文中，NeuralGCM生成了比传统大气模型更精确的2-15天天气预报，并以更高精度复现了过去四十年的历史温度数据，标志着我们在开发更易用的气候模型方面迈出了重要一步。

如今，在发表于《科学进展》期刊的论文《用于降水模拟的神经大气环流模型》中，我们阐述了如何基于卫星降水观测数据训练NeuralGCM，从而显著提升降水模拟能力。值得注意的是，在当前280公里的分辨率下，NeuralGCM在中短期天气预报（最长15天）方面超越了主流业务模型，在多年代际气候模拟方面也优于现有大气模型。我们发现，NeuralGCM能更准确地复现平均降水、极端降水（对最强0.1%的降雨事件模拟改进尤为显著）以及日天气周期。

NeuralGCM是推动天气与气候科学发展的广泛努力的一部分。作为融合物理与人工智能以解决长期预测问题的混合模型，它与纯人工智能天气模型（如谷歌同事近期发布的WeatherNext 2更新）形成了互补。

云层的多样性与瞬时性带来挑战
要模拟降水，必须追溯其源头：云。云层存在的尺度可小于100米（相当于一个运动场的大小），远低于全球天气模型的公里级分辨率或全球气候模型的数十公里级分辨率。云类型多样、变化迅速，而更微观尺度上的复杂物理过程会生成水滴或冰晶。所有这些复杂性都是大尺度模型无法直接解析或计算的。

为考虑云形成等小尺度大气过程对气候的影响，传统模型采用基于其他变量的近似方法（即参数化方案）。NeuralGCM则摒弃了这类参数化方案，转而通过神经网络直接从现有天气数据中学习小尺度过程的影响。

在此版本中，我们通过基于卫星降水观测数据直接训练NeuralGCM的机器学习模块，显著提升了模型的降水表征能力。与多数机器学习天气模型类似，NeuralGCM初始版本是基于再分析数据（即融合物理模型与观测数据以填补观测空白的过往大气状态重建数据）进行训练的。但云的物理过程极为复杂，即使再分析数据也难以准确表征降水。基于再分析数据输出进行训练意味着会复现其缺陷，例如在极端降水和日周期模拟方面的不足。

为此，我们直接使用NASA 2001年至2018年的卫星降水观测数据训练了NeuralGCM的降水模块。NeuralGCM的微分动力核心架构使其能够基于卫星观测数据进行训练。此前结合物理与人工智能的混合模型只能使用高保真模拟或再分析数据的输出。通过直接基于高质量卫星观测数据（而非依赖再分析数据）训练NeuralGCM的人工智能组件，我们实质上为降水模拟找到了一种更优的机器学习参数化方案。

未来15天的降水预报
我们使用WeatherBench 2评估了NeuralGCM在两周预报中的表现，并将其与欧洲中期天气预报中心（ECMWF）的主流物理模型进行对比。在2020年每日正午和午夜启动预报的测试中（训练未使用该年份数据），NeuralGCM在低分辨率下的大部分降水平均指标上显著优于ECMWF模型，包括全部15个预报日的24小时和6小时累积降水。这一优势在对人类和生态系统至关重要的陆地区域尤为明显。

掌握降水的时间和地点有助于社区管理洪旱灾害、高效利用灌溉资源、规划活动并保障公共安全。尽管NeuralGCM当前280公里的分辨率对于业务预报而言仍较粗糙，但这些结果表明该技术具备在更小尺度应用的潜力，可改进现有业务预报工具。

年际至年代际降水规律
在年际到年代际的长期尺度上，理解平均降水规律有助于防洪规划、作物种植和饮用水资源管理。鉴于NeuralGCM的280公里分辨率，我们当前的研究聚焦于更大尺度的地理与时间范围。将NeuralGCM的多年模拟结果与用于气候研究的主流全球大气模型对比时，NeuralGCM的平均误差低于每日0.5毫米。相比政府间气候变化专门委员会最新报告采用的主流工具，这一结果平均误差降低了40%，在陆地区域的改进更为显著。

NeuralGCM在极端降水（特定地点最强0.1%的降雨事件）模拟方面也取得重大突破。极端事件因历史样本稀少而最难复现，且基于物理的模型所用参数化方案往往高估弱降水事件、低估强降水事件（即"毛毛雨问题"）。在2002年至2014年的模拟中，NeuralGCM更准确地捕捉了降水事件的强度，尤其是强降水事件。准确模拟这些最具破坏性的极端降水事件，对于从气候科学到公共安全的应用领域都是关键一步。

最后，我们还研究了长期气候模拟中单日降水的分布特征。以亚马逊雨林为例，该地区具有显著的日循环规律——夏季午后常出现强降雨。当前气候模型往往使降雨时间比实际情况提前数小时，而NeuralGCM则更准确地复现了日降水峰值的时间和强度，尤其在陆地区域和夏季表现突出。研究重点集中于日循环更强、传统模型表现薄弱的陆地区域，并选取日循环特征明显的夏季作为标准气候评估时段。准确捕捉日内降水时间对生态系统、天气系统和水文研究具有广泛意义。

展望未来
我们相信这是大尺度降水预报与模拟领域的重要进展，并已在现实应用中获得早期验证。芝加哥大学与印度农业与农民福利部的合作项目采用NeuralGCM开展试点，利用人工智能预报预测季风季节起始时间。该团队经过严格测试后选定NeuralGCM与另一模型，并构建了于去年夏季首次投入业务的预报工具。

自发布NeuralGCM以来，我们已将全部代码开源，期待更多人能在此基础上进行开发。此次降水模型也向更广泛的社区开放发布。我们最终希望这些努力能推动人类更接近实现精准的长期降水预测，特别是在气候变化背景下的未来降水趋势研判。

致谢
感谢NeuralGCM团队（Dmitrii Kochkov、Ian Langmore和Stephan Hoyer）。同时感谢Hannah Hickey和Elise Kleeman对本博客文章的协助，以及Lizzie Dorfman、Michael Brenner和John Platt的支持与指导。

英文来源：

NeuralGCM harnesses AI to better simulate long-range global precipitation
January 12, 2026
Janni Yuval, Research Scientist, Google Research
NeuralGCM combines physics-based modeling and a neural network trained on NASA precipitation observations to simulate global precipitation more accurately than other methods, particularly for capturing the daily precipitation cycle and extreme events.
Quick links
Precipitation remains one of the trickiest tasks for global-scale weather and climate models. That’s because exactly where, when and how much precipitation will fall depends on a series of events happening at scales that are typically below the model resolution. Simulating precipitation is especially challenging for extreme events and over long periods of time. Whether it’s farmers knowing which day to plant seeds to optimize their harvest, or city planners knowing how to prepare for a 100-year storm, precipitation forecasts are some of the most relevant for humans.
Last year, we introduced our open-sourced hybrid atmospheric model NeuralGCM, which combines machine learning (ML) and physics to run fast, efficient and accurate global atmospheric simulations. In the 2024 paper, NeuralGCM generated more accurate 2–15 day weather forecasts and reproduced historical temperatures over four decades with greater precision than traditional atmospheric models, marking a significant step towards developing more accessible climate models.
Now in “Neural general circulation models for modeling precipitation”, published in Science Advances, we describe how NeuralGCM was trained on satellite-based precipitation observations to achieve improved simulations of precipitation. Notably, at the current resolution of 280 km, we see improvements against a leading operational model for medium-range weather forecasting (up to 15 days) and against atmospheric models used for multi-decadal climate simulations. We find NeuralGCM more accurately reproduces average precipitation, precipitation extremes — with major improvements for the top 0.1% of rainfall — and the daily weather cycle.
NeuralGCM is part of a broader effort to advance weather and climate science. As a hybrid model that combines physics and AI to tackle longer-range questions, it complements other AI-only weather models like the recently introduced WeatherNext 2 update from our Google colleagues.
Clouds’ diversity and fleeting nature pose challenges
To simulate precipitation, we must go to its source: clouds. Clouds can exist at scales smaller than 100 meters, the size of an athletic field — far below the kilometers-scale resolution of global weather models, or the tens-of-kilometers–scale resolution of global climate models. Clouds come in different types, change quickly, and the intricate physics happening at even smaller scales can generate water droplets or ice crystals. All this complexity is impossible for large-scale models to resolve or calculate.
To account for the effect of small-scale atmospheric processes like cloud formation on the climate, models use approximations, called parameterizations, which are based on other variables. Rather than depending on these parameterizations, NeuralGCM uses a neural network to learn the effects of such small-scale events directly from existing weather data.
We improved the representation of precipitation in this version of our model by training the ML portion of NeuralGCM directly on satellite-based precipitation observations. The initial offering of NeuralGCM was, like most ML weather models, trained on recreations of previous atmospheric conditions, i.e., reanalyses, that combine physics-based models with observations to fill in gaps in observational data. But the physics of clouds is so complex that even reanalyses struggle to get precipitation right. Training on output from reanalyses means reproducing their weaknesses, for example, on precipitation extremes and the daily cycle.
Instead, we trained the precipitation part of NeuralGCM directly on NASA satellite-based precipitation observations spanning from 2001 to 2018. NeuralGCM’s differential dynamical core infrastructure allowed us to train it on satellite observations. Previous hybrid models that combine physics and AI could only use output from high-fidelity simulations or reanalysis data. By training the AI component of NeuralGCM directly on high-quality satellite observations instead of relying on reanalyses, we are effectively finding a better, machine-learned parameterization for precipitation.
Forecasting precipitation over the next 15 days
We evaluated NeuralGCM’s performance on two-week forecasts using WeatherBench 2, comparing it against a leading physics-based model from the European Centre for Medium-range Weather Forecasts (ECMWF). In tests using forecasts starting at noon and midnight on each day in 2020 (data was not used during training), NeuralGCM significantly outperformed the ECMWF model at low resolution across most averaged measures of precipitation. This included both 24-hour and 6-hour accumulated precipitation for all 15 forecast days. The advantage remained significant over land masses, which are critical for humans and ecosystems.
Knowing when and where precipitation is going to fall helps communities manage flooding and drought, use irrigation resources most efficiently, plan events and protect public safety. While NeuralGCM’s current resolution of 280 kilometers is too coarse for operational forecasts, these results suggest there’s potential to leverage this technique at smaller scales to improve the tools used for operational forecasts.
Precipitation patterns over years to decades
Over longer timescales, from years to decades, understanding average precipitation patterns can help with flood control, crop planning, and managing drinking water supplies. Given NeuralGCM’s 280 kilometer resolution, our current focus extends to larger scales of geography and time. When comparing multi-year runs of NeuralGCM against leading global atmospheric models used to study climate, NeuralGCM had an average mean error of less than half a millimeter per day. This represents a 40% average error reduction compared to the leading tools used in the latest Intergovernmental Panel on Climate Change report, with an even bigger improvement over land.
NeuralGCM also showed major improvements for extreme precipitation, the top 0.1% of rainfall at a given location. Extreme events are some of the hardest to reproduce because fewer previous examples exist, and the parameterizations that physics-based models use to estimate precipitation often overrepresent light events while underrepresenting heavy events — known as the drizzle problem. NeuralGCM more accurately captured the intensity of precipitation events, especially of heavy precipitation, in simulations from 2002 to 2014. Capturing these most extreme, damaging precipitation events is an important step for applications ranging from climate science to public safety.
Finally, we also looked at how precipitation falls during a single day of the long-range climate simulations. The Amazon rainforest, for example, has a very strong daily cycle. In summer you can expect heavy rains in the afternoon. While today’s climate models tend to have rain fall several hours earlier than in the real world, NeuralGCM more accurately reproduces the timing and amount of peak daily precipitation, particularly over land and in summer. The focus is on precipitation over land, where the diurnal cycle is stronger and where traditional models struggle, and in summer, a standard climate science evaluation period because of its marked diurnal cycle. Capturing when precipitation falls during the day matters at a large scale for ecosystems, weather systems and hydrology.
Looking ahead
We believe this is a step forward for large-scale precipitation forecasts and simulations, and we already have early support in the real world. A partnership between the University of Chicago and the Indian Ministry of Agriculture and Farmers’ Welfare used NeuralGCM for a pilot program using AI-based forecasts to predict the onset of the monsoon season. The team selected NeuralGCM and one other model after rigorous testing, and built a forecasting tool that was deployed for the first time this past summer.
Since introducing NeuralGCM we have made everything available as open-source code on which we hope people can build. This precipitation model is also being openly released to the extended community. Ultimately our hope is that these efforts will bring us one step closer to accurate long-term projections of future precipitation, especially under climate change.
Acknowledgments
We would like to acknowledge the NeuralGCM Team (Dmitrii Kochkov, Ian Langmore and Stephan Hoyer). Thanks also to Hannah Hickey and Elise Kleeman for assistance with this blog post, and to Lizzie Dorfman, Michael Brenner and John Platt for their support and leadership.