Google DeepMind Unveils AI-Powered Weather Lab for Enhanced Cyclone Predictions

Google Has a New AI-Weather Model for Cyclones. Should Experts Trust It?

Dashia is the consumer insights editor for CNET. She specializes in data-driven analysis and news at the intersection of tech, personal finance and consumer sentiment. Dashia investigates economic shifts and everyday challenges to help readers make well-informed decisions, and she covers a range of topics, including technology, security, energy and money. Dashia graduated from the University of South Carolina with a bachelor's degree in journalism. She loves baking, teaching spinning and spending time with her family. On Thursday, Google announced a new advancement powered by artificial intelligence that could change the way we predict hurricanes. Weather Lab is an interactive website that shows live and historic AI weather models, including its latest tropical cyclone model, which includes hurricanes. It was developed by Google DeepMind, the company's London-based AI research lab. The cyclone model can predict the formation, track, intensity, size and shape of the storm. And it can create 50 possible scenarios up to 15 days ahead. A representative for Google did not immediately respond to a request for comment. Weather Lab's website lets experts compare AI weather models to physics-based models from the European Centre for Medium-Range Weather Forecasts to get more cyclone information sooner. If experts are able to predict the storm earlier than a physics model, the extra time could help you and experts prepare for the impact of storms, especially those that could be life-threatening. The problem with physics-based models is that they don't track a cyclone's intensity or track as accurately as Google's AI-powered model. When experts look at both types of models, "they can better anticipate a cyclone's path and intensity," according to Google. The lab is running a few AI weather models in real time, but has included two years of previous predictions on the website so other researchers and experts can evaluate the models Google Deep Mind is creating. The two years researched are not specified. It's worth noting that the Weather Lab can be helpful for future hurricane seasons, and maybe even this one. Weather Lab accurately predicted the paths of two 2025 cyclones, Honde and Garance. Other storm paths were accurately predicted almost seven days in advance. Google DeepMind partnered with the US National Hurricane Center to confirm that their approach and outputs were correct to make predictions. However, Weather Lab is a research tool and even the live predictions are not official warnings. The lab still recommends relying on your local or national weather service.

Google has a new AI model and website for forecasting tropical storms

Google is using a new AI model to forecast tropical cyclones and working with the US National Hurricane Center (NHC) to test it out. Google DeepMind and Google Research launched a new website today called Weather Lab to share AI weather models that Google is developing. It says its new, experimental AI-based model for forecasting cyclones -- also called typhoons or hurricanes when they reach a certain strength -- can generate 50 different scenarios for a storm's possible track, size, and intensity up to 15 days in advance. The NHC is working with Google to evaluate the effectiveness of the model.

Google DeepMind is sharing its AI forecasts with the National Weather Service

Here's an AI-government collaboration of a less... unsettling variety than some. Google DeepMind is teaming up with the National Hurricane Center (NHC) for tropical cyclone season. The AI research lab claims it can predict hurricane paths and intensities with at least the same accuracy as traditional methods. NHC forecasters have already begun using DeepMind's AI model. Google says they're designed to support, not replace, human NHC forecasters. (Although President Trump's National Weather Service cuts have already reduced its headcount.) The company is also careful to repeatedly describe its models as "experimental." Google claims that its models offer fewer trade-offs than physics-based predictions. The more accurate those methods are at forecasting a hurricane's path, the worse they are at predicting its intensity. (And vice versa.) The company says its experimental system offers "state-of-the-art" accuracy for both. DeepMind backs that up with data from real-life storms over the last two years. On average, its five-day hurricane track prediction gets 87 miles closer to the storm's actual path than ENS, a widely used traditional model. Google's was comparable to a 3.5-day prediction model. In other words, it's like gaining an extra 1.5 days of warning with the same level of confidence. The company says such an improvement typically takes over a decade to achieve. Alongside the NHC collab, Google is launching a new website that you can try. Now in a public preview, Weather Lab lets you see the AI storm predictions. It lets you view both live and historical predictions. You can even compare them to physics-based models to see how the AI version measures up. It's important not to treat Weather Lab's experimental forecasts as official. But the website could come in handy if you live in Hurricane Alley. You can check it out now.

Google releases Weather Lab with AI-based cyclone predictions

Another place AI is marking a particular big impact is weather forecasting. Google is continuing its work in the area with a new Weather Lab website and experimental cyclone, or hurricane, predictions. Weather Lab comes from Google DeepMind and Google Research, with this interactive website featuring AI weather models, including an experimental AI-based tropical cyclone model that can "predict a cyclone's formation, track, intensity, size and shape -- generating 50 possible scenarios, up to 15 days ahead." (Cyclones, hurricanes, and typhoons are all tropical storms, with what they are called dependent on their location.) Based on stochastic neural networks, it is "often more accurate than, current physics-based methods" at predicting cyclone track and intensity. Google worked with the U.S. National Hurricane Center (NHC) to scientifically validate the work. First and foremost, Weather Lab is a research tool and "not intended for consumer use." It's meant to "help weather agencies and emergency service experts better anticipate a cyclone's path and intensity." A persistent message at the bottom says: "For official weather forecasts and warnings, refer to your local meteorological agency or national weather service." With that in mind, this Google Maps-like interface shows "live and historical cyclone predictions for different AI weather models, alongside physics-based models from the European Centre for Medium-Range Weather Forecasts." It can be used to "explore and compare the predictions from various AI and physics-based models."

How we're supporting better tropical cyclone prediction with AI

Weather Lab shows live and historical cyclone predictions for different AI weather models, alongside physics-based models from the European Centre for Medium-Range Weather Forecasts (ECMWF). Several of our AI weather models are running in real time: WeatherNext Graph, WeatherNext Gen and our latest experimental cyclone model. We're also launching Weather Lab with over two years of historical predictions for experts and researchers to download and analyze, enabling external evaluations of our models across all ocean basins. Weather Lab users can explore and compare the predictions from various AI and physics-based models. When read together, these predictions can help weather agencies and emergency service experts better anticipate a cyclone's path and intensity. This could help experts and decision-makers better prepare for different scenarios, share news of risks involved and support decisions to manage a cyclone's impact. It's important to emphasise that Weather Lab is a research tool. Live predictions shown are generated by models still under development and are not official warnings. Please keep this in mind when using the tool, including to support decisions based on predictions generated by Weather Lab. For official weather forecasts and warnings, refer to your local meteorological agency or national weather service. In physics-based cyclone prediction, the approximations required to meet operational demands mean it's difficult for a single model to excel at predicting both a cyclone's track and its intensity. This is because a cyclone's track is governed by vast atmospheric steering currents, whereas a cyclone's intensity depends on complex turbulent processes within and around its compact core. Global, low-resolution models perform best at predicting cyclone tracks, but don't capture the fine-scale processes dictating cyclone intensity, which is why regional, high-resolution models are needed. Our experimental cyclone model is a single system that overcomes this trade-off, with our internal evaluations showing state-of-the-art accuracy for both cyclone track and intensity. It's trained to model two distinct types of data: a vast reanalysis dataset that reconstructs past weather over the entire Earth from millions of observations, and a specialized database containing key information about the track, intensity, size and wind radii of nearly 5,000 observed cyclones from the past 45 years. Modeling the analysis data and cyclone data together greatly improves cyclone prediction capabilities. For example, our initial evaluations of NHC's observed hurricane data, on test years 2023 and 2024, in the North Atlantic and East Pacific basins, showed that our model's 5-day cyclone track prediction is, on average, 140 km closer to the true cyclone location than ENS -- the leading global physics-based ensemble model from ECMWF. This is comparable to the accuracy of ENS's 3.5-day predictions -- a 1.5-day improvement that has typically taken over a decade to achieve. While previous AI weather models have struggled to calculate cyclone intensity, our experimental cyclone model outperformed the average intensity error of the National Oceanic and Atmospheric Administration (NOAA)'s Hurricane Analysis and Forecast System (HAFS), a leading regional, high-resolution physics-based model. Preliminary tests also show our model's predictions of size and wind radii are comparable with physics-based baselines. Here we visualize track and intensity prediction errors, and show evaluation results of our experimental cyclone model's average performance up to five days in advance, compared to ENS and HAFS.

Google DeepMind just changed hurricane forecasting forever with new AI model

Join the event trusted by enterprise leaders for nearly two decades. VB Transform brings together the people building real enterprise AI strategy. Learn more Google DeepMind announced Thursday what it claims is a major breakthrough in hurricane forecasting, introducing an artificial intelligence system that can predict both the path and intensity of tropical cyclones with unprecedented accuracy -- a longstanding challenge that has eluded traditional weather models for decades. The company launched Weather Lab, an interactive platform showcasing its experimental cyclone prediction model, which generates 50 possible storm scenarios up to 15 days in advance. More significantly, DeepMind announced a partnership with the U.S. National Hurricane Center, marking the first time the federal agency will incorporate experimental AI predictions into its operational forecasting workflow. "We are presenting three different things," said Ferran Alet, a DeepMind research scientist leading the project, during a press briefing Wednesday. "The first one is a new experimental model tailored specifically for cyclones. The second one is, we're excited to announce a partnership with the National Hurricane Center that's allowing expert human forecasters to see our predictions in real time." The announcement marks a critical juncture in the application of artificial intelligence to weather forecasting, an area where machine learning models have rapidly gained ground against traditional physics-based systems. Tropical cyclones -- which include hurricanes, typhoons, and cyclones -- have caused $1.4 trillion in economic losses over the past 50 years, making accurate prediction a matter of life and death for millions in vulnerable coastal regions. Why traditional weather models struggle with both storm path and intensity The breakthrough addresses a fundamental limitation in current forecasting methods. Traditional weather models face a stark trade-off: global, low-resolution models excel at predicting where storms will go by capturing vast atmospheric patterns, while regional, high-resolution models better forecast storm intensity by focusing on turbulent processes within the storm's core. "Making tropical cyclone predictions is hard because we're trying to predict two different things," Alet explained. "The first one is track prediction, so where is the cyclone going to go? The second one is intensity prediction, how strong is the cyclone going to get?" DeepMind's experimental model claims to solve both problems simultaneously. In internal evaluations following National Hurricane Center protocols, the AI system demonstrated substantial improvements over existing methods. For track prediction, the model's five-day forecasts were on average 140 kilometers closer to actual storm positions than ENS, the leading European physics-based ensemble model. More remarkably, the system outperformed NOAA's Hurricane Analysis and Forecast System (HAFS) on intensity prediction -- an area where AI models have historically struggled. "This is the first AI model that we are now very skillful as well on tropical cyclone intensity," Alet noted. How AI forecasts beat traditional models on speed and efficiency Beyond accuracy improvements, the AI system demonstrates dramatic efficiency gains. While traditional physics-based models can take hours to generate forecasts, DeepMind's model produces 15-day predictions in approximately one minute on a single specialized computer chip. "Our probabilistic model is now even faster than the previous one," Alet said. "Our new model, we estimate, is probably around one minute" compared to the eight minutes required by DeepMind's previous weather model. This speed advantage allows the system to meet tight operational deadlines. Tom Anderson, a research engineer on DeepMind's AI weather team, explained that the National Hurricane Center specifically requested forecasts be available within six and a half hours of data collection -- a target the AI system now meets ahead of schedule. National Hurricane Center partnership puts AI weather forecasting to the test The partnership with the National Hurricane Center validates AI weather forecasting in a major way. Keith Battaglia, senior director leading DeepMind's weather team, described the collaboration as evolving from informal conversations to a more official partnership allowing forecasters to integrate AI predictions with traditional methods. "It wasn't really an official partnership then, it was just sort of more casual conversation," Battaglia said of the early discussions that began about 18 months ago. "Now we're sort of working toward a kind of a more official partnership that allow us to hand them the models that we're building, and then they can decide how to use them in their official guidance." The timing proves crucial, with the 2025 Atlantic hurricane season already underway. Hurricane center forecasters will see live AI predictions alongside traditional physics-based models and observations, potentially improving forecast accuracy and enabling earlier warnings. Dr. Kate Musgrave, a research scientist at the Cooperative Institute for Research in the Atmosphere at Colorado State University, has been evaluating DeepMind's model independently. She found it demonstrates "comparable or greater skill than the best operational models for track and intensity," according to the company. Musgrave stated she's "looking forward to confirming those results from real-time forecasts during the 2025 hurricane season." The training data and technical innovations behind the breakthrough The AI model's effectiveness stems from its training on two distinct datasets: vast reanalysis data reconstructing global weather patterns from millions of observations, and a specialized database containing detailed information about nearly 5,000 observed cyclones from the past 45 years. This dual approach is a departure from previous AI weather models that focused primarily on general atmospheric conditions. "We are training on cyclone specific data," Alet explained. "We are training on IBTracs and other types of data. So IBTracs provides latitude and longitude and intensity and wind radii for multiple cyclones, up to 5000 cyclones over the last 30 to 40 years." The system also incorporates recent advances in probabilistic modeling through what DeepMind calls Functional Generative Networks (FGN), detailed in a research paper released alongside the announcement. This approach generates forecast ensembles by learning to perturb the model's parameters, creating more structured variations than previous methods. Past hurricane predictions show promise for early warning systems Weather Lab launches with over two years of historical predictions, allowing experts to evaluate the model's performance across all ocean basins. Anderson demonstrated the system's capabilities using Hurricane Beryl from 2024 and the notorious Hurricane Otis from 2023. Hurricane Otis proved particularly significant because it rapidly intensified before striking Mexico, catching many traditional models off guard. "Many of the models were predicting that the storm would remain relatively weak throughout its lifetime," Anderson explained. When DeepMind showed this example to National Hurricane Center forecasters, "they said that our model would have likely provided an earlier signal of the potential risk of this particular cyclone if they had it available at the time." What this means for the future of weather forecasting and climate adaptation The development signals artificial intelligence's growing maturation in weather forecasting, following recent breakthroughs by DeepMind's GraphCast and other AI weather models that have begun outperforming traditional systems in various metrics. "I think for a pretty early, you know, the first few years, we've been mostly focusing on scientific papers and research advances," Battaglia reflected. "But, you know, as we've been able to show that these machine learning systems are rivaling, or even outperforming, the kind of traditional physics-based systems, having the opportunity to take them out of the sort of scientific context into the real world is really exciting." The partnership with government agencies is a crucial step toward operational deployment of AI weather systems. However, DeepMind emphasizes that Weather Lab remains a research tool, and users should continue relying on official meteorological agencies for authoritative forecasts and warnings. The company plans to continue gathering feedback from weather agencies and emergency services to improve the technology's practical applications. As climate change potentially intensifies tropical cyclone behavior, advances in prediction accuracy could prove increasingly vital for protecting vulnerable coastal populations worldwide. "We think AI can provide a solution here," Alet concluded, referencing the complex interactions that make cyclone prediction so challenging. With the 2025 hurricane season underway, the real-world performance of DeepMind's experimental system will soon face its ultimate test.

Google develops AI model for forecasting tropical cyclones - SiliconANGLE

Google develops AI model for forecasting tropical cyclones Google LLC today detailed an artificial intelligence model that can forecast the path and intensity of tropical cyclones days in advance. According to the company, the algorithm was developed through a collaboration between its Google Research and DeepMind units. It's available through a newly launched website called Weather Lab. Usually, scientists rely on algorithms known as physics-based weather prediction models to forecast cyclones. Such algorithms generate projections by running a large number of data points through differential equations. According to Google, this approach has certain limitations that can complicate cyclone forecasting efforts. "In physics-based cyclone prediction, the approximations required to meet operational demands mean it's difficult for a single model to excel at predicting both a cyclone's track and its intensity," the company's researchers explained in a blog post. "This is because a cyclone's track is governed by vast atmospheric steering currents, whereas a cyclone's intensity depends on complex turbulent processes within and around its compact core." According to Google, its newly detailed AI model doesn't share that limitation. The company claims that the algorithm can predict both the track and intensity of a cyclone with "state-of-the-art accuracy." Moreover, its forecasts encompass other details such as the manner in which a cyclone forms, its size and shape. Google trained the model using two datasets. The first described the path, intensity and other key properties of nearly 5,000 cyclones from the past 45 years. The other dataset included information about past weather conditions that was distilled from millions of observations. During internal tests, Google successfully used the algorithm to predict the paths of four recent cyclones. For two of the storms, the model generated accurate forecasts nearly a week ahead of time. It can predict storms up to 15 days in advance by "generating 50 possible scenarios," Google's researchers wrote. The company has made the AI accessible to researchers through a new website called Weather Lab. The model is available alongside two years' worth of historical forecasts, as well as data from traditional physics-based weather prediction algorithms. "Weather Lab users can explore and compare the predictions from various AI and physics-based models," the researchers detailed. "When read together, these predictions can help weather agencies and emergency service experts better anticipate a cyclone's path and intensity."

Google Has Launched an AI-Powered Cyclone Prediction Website

Weather Lab can compare data from AI models and physics-based models Google DeepMind and Google Research launched a public preview of Weather Lab on Thursday. It is an interactive website where the company will share its artificial intelligence (AI) weather models and share weather predictions based on their output. The Mountain View-based tech giant has also released its latest experimental AI-based tropical cyclone model. This model is said to be able to predict a cyclone's formation, track, intensity, size, and shape up to 15 days in advance. Notably, the company says a scientific validation of the AI model is currently pending. In a blog post, DeepMind announced the launch of the new Weather Lab website and detailed its new cyclone-focused AI model. The website shows live and historical cyclone predictions using both AI weather models and physics-based models from the European Centre for Medium-Range Weather Forecasts (ECMWF). Google DeepMind highlighted that on the website, several AI models, such as the WeatherNext Graph, WeatherNext Gen, and the new cyclone model, run in real-time to analyse weather data and make predictions. Additionally, Weather Lab also contains more than two years of historical AI-generated predictions that researchers can download to evaluate the efficiency of the models. Weather Lab also allows users to compare predictions from different AI and physics-based models. Notably, the company emphasises that the website is a research tool and is not meant to provide official warnings. Coming to the new AI-based cyclone model, Google has published a pre-print version of its paper. However, it is yet to be peer reviewed. For scientific validation from the research community, Google has partnered with the US National Hurricane Center (NHC). DeepMind says that in traditional cyclone prediction, two different physics-based models are used. A global low-resolution model predicts cyclone tracks, which requires analysing the atmospheric steering currents, whereas a regional high-resolution model is used to track a cyclone's intensity, which requires observing the complex turbulent processes within and around its compact core. The new AI model is said to solve this dual-approach problem by unifying both cyclone track and intensity prediction. As per the post, the model is trained on both the "reanalysis dataset that reconstructs past weather over the entire Earth from millions of observations, and a specialised database containing key information about the track, intensity, size and wind radii of nearly 5,000 observed cyclones from the past 45 years." Highlighting an example, DeepMind said that the model was deployed in the North Atlantic and East Pacific basins between 2023-24 for testing, and during the time, its five-day cyclone track prediction was, on average, 140km closer to the true location compared to the prediction of ECMWF's ENS model. Additionally, the company claimed that the cyclone model's results, based on internal testing, are at least on par with physics-based models.