Google DeepMind's WeatherNext 3 AI Weather Model Produces Hourly Forecasts at 5-Kilometer Resolution

Google's latest AI weather model gives you no excuse to forget your umbrella

Scientists at Google Deepmind and Google Research released a new artificial intelligence model for weather forecasting today that sees our changing atmosphere more clearly and predicts its behavior more often. WeatherNext 3 is the latest wave of a sea change in meteorology brought out by deep learning techniques, and Google says it will start feeding into weather information users see in search, Google Maps, and Gemini, as well as being available to users and researchers on Google's cloud platforms. "This is going to be the first time that some of the core variables feed and power a lot of the Google products," Samier Merchant, a Google senior staff engineer, told TechCrunch. The new model has already proven to be the most accurate among leading contenders tested on Operational WeatherBench, a utility for comparing AI forecasts built by the startup Brightband. It looks at metrics like temperature, windspeed, and humidity. As well as beating out other deep-learning models built by Google, Microsoft, Nvidia, and the European Center for Medium-Range Weather Forecasting, it also beats traditional forecasts from the US National Weather service and the ECMWF. Most weather forecasts come from government-owned supercomputers laboriously churning through mathematical equations written to describe the physics of weather; while these systems have become remarkably accurate, they are expensive and comparatively slow. After the ECMWF released more than half a century of weather data produced by these systems in 2018, deep learning researchers began training models that could make predictions far more quickly and with comparable accuracy to government tools. "Weather is chaotic, and so small differences really start to perturb massively...Machine learning targets the problem we are really solving, which is approximate noisy physics from incomplete information and finite compute, and so it learns patterns from a lot of data," Ferran Alet, a staff research scientist manager at DeepMind. Since then, model-makers have pushed on the key weaknesses of AI forecasting models: They tend to forecast over a wider area -- 15 to 25 square km -- than is truly useful, they're not always great with rain, and they still depend on the formatted data-sets produced by government agencies. WeatherNext 3 takes on all three challenges. On key variables, researchers told TechCrunch, it can predict down to a resolution of 5km. Its evaluations on rain are 60% improved over WeatherNext 2, and it can now produce hourly forecasts, instead of the standard prediction every six hours. Those improvements are the result of specific choices made by the designers. WeatherNext 3 is a larger model, with 2.4 times more parameters than its predecessor, and tailoring the targets for the decoder heads to give more useful answers. While most weather forecasts output as metrics averaged across a 3D grid, DeepMind researchers have already won plaudits by tuning their model to also visualize cyclone paths. This time around, the designers also trained the model to target its forecasts to specific weather data stations. This is important not only for offering more granular predictions, but also for being able to evaluate its work against specific, ground-truth data. "The idea, with a lot of AI applications, is to try to run tasks as end-to-end as possible," Daniel Rothenberg, an atmospheric scientist at Brightband, said. "Adding a capability where this model is now also predicting, say, what Denver's airport's weather station is going to measure on an hourly basis, just connects that forecasting task closer to the core." The model is able to forecast more frequently because it can ingest weather satellite data collected in real-time on an hourly basis. Feeding AI models on raw empirical observations, rather than the analysis produced by weather supercomputers, promises a more accurate forecast, but it is still technically challenging to get models to work with unformatted data. Google says WeatherNext 3 is the "first" AI model to directly incorporate raw observations for a high-resolution global forecast, but the AI weather startup WindBorne says its model, WeatherMesh 6, has been incorporating raw observations from its fleet of weather balloons and other sources since late 2025. Asked about that, Google pointed out that its forecasts are higher resolution across the globe. Regardless, both models still rely on national weather datasets to perform forecasts, so more work will be required for true direct data assimilation. While LLMs get the bulk of the attention, the transformer revolution in meteorology has been just as important. European and US weather agencies are already using AI models in their forecast products, and their speed and low cost promise to bring economic impact to poorer regions where the expense of high-quality sensors and supercomputers has put accurate forecasts out of reach. Bill Gates recently cited AI-powered weather forecasting as a crucial benefit of the technology, with better forecasts improving crop yields in developing countries. Alet, the DeepMind researcher, said that higher-resolution forecasts of wind, rain, and cloud cover will be useful to make renewable energy projects more dependable. "At the end of the day, I think Google is about providing useful information to the user, and a lot of what users are looking for has to do with the weather in some way or another," Alet said.

Google says its AI weather model is getting better

Google is rolling out an updated AI weather model that's supposed to be more accurate, especially when it comes to predicting rain and snowfall. In the announcement today, the company says it's now able to make forecasts with "unprecedented resolution" using its new WeatherNext 3 AI model. It can produce a global picture that's five times sharper than Google's previous model by learning from real-time weather observations, according to the company. "One of the main developments is for [WeatherNext 3] to go beyond what data most global AI models train on," says Samier Merchant, a research engineer at Google Research. "We're able to leverage fresher and richer observational data sets." Weather forecasting has traditionally relied primarily on supercomputers that simulate the physics of the atmosphere. That involves solving complex equations, and ultimately comes with a time-lag. AI weather models created by Google and other developers, in contrast, can make faster predictions by recognizing patterns in historical weather data. Google is going a step further by incorporating live satellite data in its new model. WeatherNext 3 is able to produce a forecast each hour based on the most recent satellite observations. That allows for faster predictions than its previous AI models, as well as higher spatial and temporal resolution. For comparison, the previous model, WeatherNext 2, produced forecasts every 6 hours on a 25-kilometer grid. The newer model can visualize certain variables, including temperature and moisture, at up to a 5-kilometer resolution. That speed and resolution is particularly helpful when it comes to predicting rain and snow stemming from fast-moving weather systems, Google says. Using satellite data to make predictions also fills in gaps left in locations where there are fewer rain gauges on the ground. These are places -- primarily outside of the US and Europe -- where Google says WeatherNext 3 can provide the biggest improvements to weather forecasts. Google says users will see precipitation forecasts that are up to 50 percent more accurate when looking at least a day in advance. Google also designed its latest AI weather model to produce forecasts for renewable energy generation. That includes predictions on wind speed at 100 meters, for example, at about the height of a turbine. Google, like other tech companies developing generative AI tools, is demanding more energy for data centers. "As the energy needs of Google, but [also] entire humanity, is increasing its energy needs, to make sure that we make renewable a very appealing opportunity is very important for us," Ferran Alet, a research scientist at Google DeepMind tells The Verge. WeatherNext 3 is now incorporated into Search, Maps, Gemini, and other Google products. Google has also worked with the US National Hurricane Center and other agencies in Asia to improve weather forecasting using its AI models. While AI models are becoming more accurate, they're still expected to work in tandem with traditional physics-based models. WeatherNext 3 is still trained on data from physics-based models and weather agencies typically look at a range of predictions to issue warnings.

Introducing WeatherNext 3, our most advanced and accurate global weather AI model

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.