我们的旗舰 AI 天气预报模型现已纳入实时卫星数据，支持每小时刷新、更高分辨率、精准降水预报，并新增清洁能源相关变量。该模型现已集成至 Search、Gemini、Maps、Google Maps Platform 和 Cloud 中。
WeatherNext 团队
Google 推出了 WeatherNext 3，这是一款先进的 AI 模型，通过使用实时卫星数据而非传统物理模拟，提供更准确、更高分辨率的天气预报。此次更新提供每小时更新的本地化预测，清晰度是此前版本的 5 倍，为农业、可再生能源和日常规划带来显著改进。你现在可以直接通过 Google Search、Maps 和 Gemini 获取这些增强版预报，或通过 Google Cloud 将数据集成到自己的项目中。
- 欢迎查看“Introducing WeatherNext 3”，这是我们迄今最先进、最准确的全球 AI 天气模型。
- 我们现在提供每小时更新的高分辨率预报，清晰度是此前的 5 倍。
- 我们的模型利用实时卫星数据，以极高的精度追踪快速变化的天气。
- 你将获得更准确的降雨和降雪预报，从而更有信心地规划每一天。
- 这些更新正在 Google 各应用中逐步推出，帮助每个人做出更好的决策。
Google 刚刚发布了 WeatherNext 3，这是一款能够大幅提升天气预报速度与准确度的 AI 模型。它利用实时卫星数据每小时更新一次，让你对户外的天气状况有更清晰的了解。这有助于人们更好地为暴风雨或晴天等情况做出规划。目前，它已在为你在 Google 搜索和地图中看到的天气信息提供支持。
探索其他风格：
每天，天气都影响着数十亿个决策。有些决策很简单，比如出门前拿把伞，但另一些决策则重要得多。风、雨以及热浪、干旱等极端天气事件，会对农业、全球供应链、清洁能源生产乃至国家经济产生连锁影响。
近年来，AI 彻底改变了天气预报领域，它利用历史记录，比传统方法做出更快、更准确的预测。然而，预测高度局部化且快速变化的天气仍然是一项挑战。以往的模型往往缺乏足够的空间分辨率，并且难以整合来自卫星等来源的实时天气数据。
今天，Google DeepMind 和 Google Research 推出了 WeatherNext 3。根据 Brightband 进行的独立实时评估，这是迄今为止最先进、最准确的全球天气模型。我们的模型直接从实时观测中学习，使其能够针对对人们影响最大的天气事件，提供及时且更具局部针对性的预测。通过利用原始卫星数据，以高分辨率每小时生成一次预报，我们的模型让全球用户都能在 Google 的各项产品中获取可靠的预报。
以空前分辨率实现快速天气预报
预报的价值往往取决于其细节程度，以及它在时间和空间两个维度上的解析精度。WeatherNext 3 以多种空间分辨率生成逐小时预报，从广阔的全球风场格局一直到局地地形，都能保持物理一致性。
借助 WeatherNext 3，我们能够以 5 公里分辨率可视化关键地表变量（如温度和湿度），以 10 公里分辨率呈现其他地表变量，并以 25 公里分辨率呈现风速等大气变量。总体而言，这提供的全球天气图像比我们上一代模型 WeatherNext 2 清晰约五倍——后者以 25 公里网格、6 小时间隔生成预报。
图 1：端到端 WeatherNext 3 系统架构。该模型将实时 1 小时静止卫星拼图与传统历史分析数据一同输入，馈送给一个灵活统一的 Functional Generative Network（FGN）网格 Transformer。它输出密集的网格化场、离散的气旋路径，并原生预测站点级稀疏坐标。
图 2：英国上空 2 米温度预报对比。WeatherNext 2（左）为 25 公里（0.25°）分辨率，WeatherNext 3（右）为原生 5 公里（0.05°）分辨率。WeatherNext 3 能够解析复杂的局地地形，避免了旧模型中出现的像素化、过度平滑的热力表征。
持续全球尺度下的真实世界数据
WeatherNext 3 最大的飞跃在于它的学习来源。大多数 AI 天气预报模型（包括 WeatherNext 2）都是在数值天气预报（NWP）模型的数据上训练的。虽然有用，但 NWP 模型是复杂的、由超级计算机驱动的物理模拟，存在六小时的数据延迟。这种延迟可能会给降雨或地表温度等快速变化的变量带来偏差。
通过摄取实时全球地球静止卫星数据的拼接图，我们的新模型获得了对大气丰富且持续更新的观测视角。这使得模型能够每小时生成一次新的预报，每次预报都基于最新的卫星观测数据，分辨率最高可达 5 公里。
这一点很重要，因为关键天气变化发展迅速。当风暴、锋面或降水系统突然出现时，我们快速的更新周期和更高的分辨率能提供更早、更详细的洞察，有助于推动有效的应急响应。
有些变量，比如温度和湿度，在仅仅几公里的范围内就可能发生剧烈波动，这对靠近海岸线、山谷或山脉的社区尤其重要。传统模型在这方面表现不佳，因为它们训练所用的大气表征缺乏细节，会遗漏极端的局部变化。
为解决这一问题，WeatherNext 3 改为直接在稀疏的气象站观测数据上进行训练。这使我们能够在 5 公里网格上做出全球预报，并纳入地形等区域细节。
这一突破对拉丁美洲、非洲以及亚太地区的意义尤为重大。由于传统区域模型依赖超级计算机、成本极其高昂，这些地区在历史上一直未能获得高分辨率天气预报服务。如今，该模型将本地化、高保真的天气预报带给了这些地区的数十亿人口和本地企业。
除了分辨率和预报频率的提升，我们的模型还引入了专门针对可再生能源生产设计的预测功能。该模型可预报100米高度（大致相当于风机轮毂高度）的风速，用于精确估算风能发电量；同时提供高分辨率的云量和太阳辐射数据，帮助太阳能电站估算其在地面能够接收到的光照量。
这些数据对全球清洁能源规划至关重要，能够让电网运营商和可再生能源开发商准确预测其清洁能源资产将产生多少电力，并将其与用户需求进行匹配。
降水预报实现突破性精度
全球天气模型在准确预测降水方面向来表现不佳。降雨和降雪系统由小尺度上快速运动的云过程驱动，而传统的基于物理的模拟很难对此进行精确建模。因此，AI预报常常产生模糊的估算结果，甚至完全遗漏强风暴的边界。
为解决这一问题，我们在两个质量极高的降水数据源上训练模型：NASA基于卫星的GPM综合多卫星反演数据（IMERG），以及我们基于卫星雷达建立的全球降水再分析数据。
其结果是降水预报精度实现了显著飞跃。在中长期全球预报中，与基线模型的评估对比显示，在较短的预报时效内，连续排序概率评分（CRPS）相较于 IMERG 提升了最高 60%，相较于 MRMS 提升了 30%，相较于雨量计观测数据提升了 10%。
图 3：中期降水概率（PoP > 1mm）预报对比。WeatherNext 2（左）在 25 公里分辨率下显示出高度弥散且像素化的降水足迹。WeatherNext 3（中）在 11 公里分辨率下与实际的卫星地面真值（右）高度吻合，准确捕捉到了天气系统中尖锐的对流雨带。
研究在生态系统中的广泛应用
我们的首要目标是推动天气智能的进步，使其具有普适价值——无论是追踪突发风向变化应急响应人员、规划飞行航线的空中交通管制员，还是管理农作物的农民，都能从中受益。
为了将这些突破从实验室带入现实世界，我们正在将 WeatherNext 3 集成到 Google 的核心生态系统及更广泛的领域：
- 高分辨率预报数据：我们正在提供全球天气预报数据，每小时更新，无需任何模型部署即可直接集成到您的工作流程中。这使得研究人员、开发者和企业能够在 BigQuery 和 Earth Engine 中查询这些数据，或从 Google Cloud Storage 批量下载。
- 全球可用：从今天起，WeatherNext 3 将开始为 Google 搜索、Gemini 应用、Google 地图、Google Maps Platform Weather API 以及 Google Earth Engine 中的天气体验提供支持。这一更新大幅提升了长期预报的准确性。当用户规划一天或更长时间之后的安排时，降水预报的准确率将提升最高 50%——其中，在历史上预报可靠性较低的地区，改进最为显著。因此，无论您是在为周末出行收拾行李，还是决定进行户外活动的最佳日期，现在都能获得更准确的预测来帮助您规划。
大气始终会保留一定程度的不确定性。然而，通过在真实世界观测数据上进行训练，并绕开传统建模的限制，WeatherNext 3 让我们更接近这样一个未来：预报真正与地面实际发生的情况相符。
要了解更多关于 Google 地理空间平台和 AI 工作的信息，请查看 Google Earth Engine、AlphaEarth Foundations 和 Earth AI。
免责声明：如需获取官方天气预报、恶劣天气警报和公共安全提示，请参考您当地的气象机构或国家气象部门。
了解更多关于 WeatherNext 3 的信息
- 阅读我们的论文
- 使用 WeatherNext 3 进行开发
- 探索 Weather Lab，实时查看 WeatherNext 3 的可视化效果
- 查看 WeatherNext 3 在 Brightband 独立实时排行榜上的排名。
Our flagship AI weather forecasting model now includes real-time satellite data, hourly refreshes, higher resolution, precise precipitation forecasting, and clean energy variables. It’s now integrated across Search, Gemini, Maps, Google Maps Platform, and Cloud.
The WeatherNext team
Google has launched WeatherNext 3, an advanced AI model that provides more accurate, high-resolution weather forecasts by using real-time satellite data instead of traditional physics simulations. This update delivers hourly, localized predictions that are five times sharper than previous versions, offering significant improvements for agriculture, renewable energy, and daily planning. You can now access these enhanced forecasts directly through Google Search, Maps, and Gemini, or integrate the data into your own projects via Google Cloud.
- Check out "Introducing WeatherNext 3," our most advanced and accurate global weather AI model yet.
- We now provide hourly, high-resolution forecasts that are five times sharper than before.
- Our model uses real-time satellite data to track fast-changing weather with incredible precision.
- You’ll get much better rain and snow predictions, helping you plan your day confidently.
- These updates are rolling out across Google apps to help everyone make better decisions.
Google just released WeatherNext 3, an AI model that makes weather forecasts much faster and more accurate. It uses live satellite data to update every hour, giving you a much sharper picture of what’s happening outside. This helps people plan better for things like storms or sunny days. It’s now powering the weather info you see in Google Search and Maps.
Explore other styles:
Every day, the weather influences billions of decisions. Some are as simple as grabbing an umbrella before heading out the door, but others are far more consequential. Wind, rain, and extreme weather events, like heatwaves and droughts, have cascading impacts across agriculture, global supply chains, clean energy production, and national economies.
In recent years, AI has revolutionized weather forecasting, using historical records to make faster and more accurate predictions than traditional methods. Yet predicting highly local and rapidly changing weather has remained a challenge. Previous models often lacked sufficient spatial resolution, and struggled to incorporate real-time weather data from sources like satellites.
Today, Google DeepMind and Google Research are introducing WeatherNext 3, the most advanced and accurate global weather model to date, according to independent live evaluations by Brightband. Our model learns directly from real-time observations, enabling it to provide timely and more localized predictions for the weather events that impact people the most. By using raw satellite data to produce a forecast every hour in high resolution, our model makes reliable forecasts accessible across Google products worldwide.
Rapid weather prediction at unprecedented resolution
A forecast's utility often comes down to detail and how finely it resolves both time and space. WeatherNext 3 generates hourly forecasts at multiple spatial resolutions, maintaining physical consistency from broad global wind patterns all the way down to local topography.
With WeatherNext 3, we can visualize key surface variables — like temperature and moisture — at a 5-kilometer resolution, other surface variables at 10 kilometers, and atmospheric variables, like wind speed, at 25 kilometers. Overall, this provides a global weather picture roughly five times sharper than our previous model, WeatherNext 2, which produced forecasts on a 25-kilometer grid in 6-hour increments.
Figure 1: The end-to-end WeatherNext 3 system architecture. The model ingests live 1-hour geostationary satellite mosaics alongside traditional historical analysis to feed a single, flexible Functional Generative Network (FGN) mesh transformer. It outputs dense gridded fields, discrete cyclone tracks, and predicts station-level sparse coordinates natively.
Figure 2: Comparison of 2-meter temperature forecasts over the UK. WeatherNext 2 (left) at 25-kilometer (0.25°) resolution vs. WeatherNext 3 (right) at a native 5-kilometer (0.05°) resolution. WeatherNext 3 resolves the intricate local topography, preventing the pixelated, over-smoothed thermal representations seen in older models.
Real-world data at continuous global scale
WeatherNext 3's biggest leap forward is what it learns from. Most AI weather models, including WeatherNext 2, are trained on data from numerical weather prediction (NWP) models. Although useful, NWP models are complex, supercomputer-driven physics simulations that carry a six-hour data lag. This lag can lead to biases for fast-changing variables like rain or surface temperature.
By ingesting a mosaic of live, global geostationary satellite data, our new model gains a rich, continuously updating view of the atmosphere. This allows the model to generate a new forecast every hour, each one grounded in the most recent satellite observations available, at up to 5-kilometer resolution.
This is important because critical weather develops fast. When storms, fronts, or precipitation systems materialize suddenly, our rapid update cycle and higher resolution provides earlier, more detailed insights needed to help drive an effective response.
Some variables, like temperature and humidity, can fluctuate dramatically over just a few kilometers, which is particularly relevant for communities near coastlines, valleys, or mountain ranges. Traditional models struggle here because they train on representations of the atmosphere that lack detail and miss extreme local variations.
To address this, WeatherNext 3 instead trains directly on sparse weather station observation data. This allows us to make global forecasts on a 5-kilometer grid that account for regional details like topography.
This breakthrough is particularly vital for regions across Latin America, Africa, and Asia-Pacific that have historically been underserved by high-resolution forecasting due to the immense supercomputing costs of traditional regional models. It brings localized, high-fidelity forecasting to billions of people and local businesses in these areas.
Beyond improved resolution and forecast frequency, our model introduces predictions specifically engineered for renewable energy production. The model forecasts 100-meter wind speeds (roughly at turbine-height) for precise wind-energy output, alongside high-resolution cloud cover and sun radiation levels to help solar farms estimate how much light they will receive on the ground.
This data is crucial for global clean energy planning, allowing grid operators and renewables developers to accurately predict how much power their clean energy assets will generate and match it with consumer demand.
Precipitation forecasting at breakthrough accuracy
Global weather models notoriously struggle to accurately predict precipitation. Rain and snow systems are driven by fast-moving cloud processes on tiny scales that are hard to model accurately using traditional physics-based simulations. Consequently, AI forecasts often produce blurry estimates or miss the boundaries of severe storms entirely.
To solve this, we train our model on two exceptionally high-quality sources of precipitation data: NASA’s satellite-based Integrated Multi-satellite Retrievals for GPM (IMERG) and our own global precipitation reanalysis based on satellite radar.
The result is a significant leap in precipitation forecasting accuracy. In medium-range global forecasts, evaluations against baselines show a Continuous Ranked Probability Score (CRPS) improvement of up to 60% against IMERG, 30% for MRMS, and 10% against rain gauge measurements for early lead times.
Figure 3: Medium-range probability of precipitation (PoP > 1mm) forecast comparison. WeatherNext 2 (left) at 25-kilometer resolution shows a highly diffused and pixelated precipitation footprint. WeatherNext 3 (middle) at 11-kilometer resolution closely mirrors the actual satellite ground truth (right), accurately capturing the sharp, convective bands of the weather systems.
Research applied across the ecosystem
Our primary goal is to advance weather intelligence to make it universally useful — whether for an emergency responder tracking sudden wind shifts, an air traffic controller planning flight paths, or a farmer managing crops.
To bring these breakthroughs out of the lab and into the real world, we’re integrating WeatherNext 3 across Google’s core ecosystem and beyond:
- High-resolution forecast data: We’re making global weather predictions, updated hourly and ready to integrate into your workflows with no model setup required. This enables researchers, developers and businesses to query the data in BigQuery and Earth Engine, or bulk-download from Google Cloud Storage.
- Available globally: WeatherNext 3 will begin powering weather experiences within Google Search, Gemini app, Google Maps, Google Maps Platform Weather API, and Google Earth Engine starting today. The update dramatically improves longer term forecasts. When planning a day or more ahead, people will see up to 50% more accurate precipitation forecasts — with the greatest improvements in regions where forecasts have historically been less reliable. So if you’re packing for a weekend trip or deciding the best day for an outdoor activity, you’ll now get more accurate predictions to help you plan.
The atmosphere will always retain a degree of unpredictability. However, by training on real-world observations and bypassing traditional modeling constraints, WeatherNext 3 brings us closer to a future where forecasts truly match what is happening on the ground.
To learn more about geospatial platforms and AI work at Google, check out Google Earth Engine, AlphaEarth Foundations, and Earth AI.
Disclaimer: For official weather forecasts, severe weather warnings, and public safety advisories, please refer to your local meteorological agency or national weather service.
Learn more about WeatherNext 3
- Read our paper
- Build with WeatherNext 3
- Explore Weather Lab to see WeatherNext 3 visualized in real-time
- See where WeatherNext 3 ranks on independent live leaderboards from Brightband.