Latest news with #ParisPerdikaris
Newsweek
2 days ago
- Climate
- Newsweek
How AI Can Improve Storm Forecasting as Hurricane Season Arrives
Based on facts, either observed and verified firsthand by the reporter, or reported and verified from knowledgeable sources. Newsweek AI is in beta. Translations may contain inaccuracies—please refer to the original content. Weather models based on artificial intelligence (AI) are better than traditional forecasts at tracking tropical storms, new research has found, part of a wave of AI breakthroughs that could improve warnings for extreme weather such as hurricanes. "To our surprise, we saw that for the first time an AI system could outperform all existing operational forecasts for all those hurricane events," Paris Perdikaris, an associate professor in the School of Engineering and Applied Science at the University of Pennsylvania, told Newsweek. Perdikaris spent a year with Microsoft Research working on a large-scale AI model called Aurora that was trained on more than one million hours of data from various Earth systems. On May 21, Perdikaris and collaborators at Microsoft Research published results in the journal Nature. Aurora did better than traditional forecasts in a range of predictions, including a 20 to 25 percent improvement in tracking tropical storms over two to five days. "We see a uniform improvement across the board in terms of the accuracy," Perdikaris said. Weather forecasting systems using AI can now perform better than traditional forecasts when tracking the path of tropical storms. But researchers warn that AI cannot replace the need for physics-based systems and good data collection. Weather forecasting systems using AI can now perform better than traditional forecasts when tracking the path of tropical storms. But researchers warn that AI cannot replace the need for physics-based systems and good data collection. Photo-illustration by Newsweek/Getty It's the latest in a string of promising reports on AI forecasting for extreme weather. In December, researchers at the AI lab Google DeepMind also published in Nature results from its machine learning forecast system, called GenCast. The researchers wrote that GenCast "better predicts extreme weather, tropical cyclone tracks and wind power production." In February, the European Centre for Medium-Range Weather Forecasts (ECMWF) put its AI Forecasting System (AIFS) into operation and reported that it outperforms state-of-the-art physics-based models for many measures, including tropical cyclone tracks. "The AIFS typically does a more accurate job of moving large-scale weather systems around the globe," Matthew Chantry, strategic lead for machine learning at ECMWF, told Newsweek via email. "Storms, are typically more accurately positioned." AI is not a panacea for tropical storm forecasting, scientists said, and recent research has exposed some weaknesses in AI forecasting. One study found that while AI systems do well at tracking a hurricane's path, they tend to underestimate wind speed and storm strength. But with climate change supercharging storms, AI promises to be a valuable addition to our warning system, potentially helping to save lives and prevent property damage. Cheaper, Faster Weather Modeling The Weather Company, producers of The Weather Channel, Weather Underground and Storm Radar, have been developing AI and machine learning for forecasting tools for years, according to Peter Neilley, senior vice president of weather forecasting services and operations. "It's just gotten more sophisticated and that enabled us to create these data-driven models," Neilley told Newsweek. "So that's all culminated in this sort of revolution for weather." Neilley explained that, unlike traditional weather models in which supercomputers work through complicated physics formulas, AI systems operate by learning from patterns from historical weather data. Building the AI model takes a lot of work and computing power, he said, but "they're very cheap to run once you've built the model." That, Neilley said, is AI's main benefit. Where traditional physics-based models can take hours, an AI model could take less than a minute. "What that enables you to do is actually run them many, many times and each time, you're running a slightly different model," he said. "With that much better prediction of how it may play out, I can use that to help people and businesses make better decisions." Brad Reinhart, senior hurricane specialist at the National Hurricane Center, works on tracking Hurricane Beryl, the first hurricane of the 2024 season, at the National Hurricane Center on July 01, 2024 in Miami, Florida. Brad Reinhart, senior hurricane specialist at the National Hurricane Center, works on tracking Hurricane Beryl, the first hurricane of the 2024 season, at the National Hurricane Center on July 01, 2024 in Miami, Weather Company President Sheri Bachstein will be among the speakers at Newsweek's AI Impact Summit June 23 to 25 in Sonoma, California, to talk about how the company is investing in AI. In the past year, The Weather Company has partnered with NVIDIA to produce more granular forecasts using AI and to improve weather simulations. Another collaboration with government scientists aims for better integration of vast weather data to get a clear snapshot of the state of the atmosphere, the critical starting point for forecasting. AI Cannot Replace Need for Basic Data Neilley said the AI approach can also yield a different type of forecast, one with a probabilistic range of outcomes to consider. While that rich outlook offers many benefits in some extreme weather conditions, such as an approaching hurricane, it could lead to information overload. "Just giving decision makers more complicated information is probably making their job harder," he said. "What is needed is an AI-based decision modeling system on top of the weather model." The AI company Urbint aims to provide that sort of informed weather preparation for electric utility companies. In April, Urbint acquired StormImpact, an AI company that predicts the risk of storms, wildfires and floods for utility infrastructure. "They don't just need to know that a storm is coming—they need to know which circuits will go down, how many customers will be impacted, and what resources they'll need on the ground to restore power quickly and safely," Urbint CEO Corey Capasso told Newsweek via email. The system predicts what transformers, substations and overhead lines are most vulnerable. "That means utilities can anticipate not just if, but where and how the grid will be impacted, and start planning for the exact number and type of crews needed," he said. StormImpact's technology is already being used by major utility companies, including Southern Company, American Electric Power and FirstEnergy. Weather-related disruptions cost utility companies an average of $70 billion annually, Urbint said. A report released earlier this month by the Electric Power Research Institute shows extreme weather events causing at least $1 billion in damage are becoming more frequent. From 2019 to 2023, billion-dollar disasters happened about 20 times a year. Climate scientists warn that our warmer atmosphere is contributing to many extreme weather events. Warmer air holds more moisture leading to more intense rainfall and flooding, and higher sea surface temperatures fuel tropical storms. As we head into this Atlantic hurricane season on the heels of the two hottest years on record, several forecasts predict a busier than average season. Several veteran storm forecasters have voiced concerns about the Trump administration's deep cuts to the National Weather Service and its parent agency, the National Oceanic and Atmospheric Administration (NOAA), warning that some key weather bureaus are understaffed and basic data gathering has been compromised. It may be tempting to look to the advances in AI to fill gaps left by those cutbacks. But for all the potential benefits AI holds for weather forecasting, researchers caution that it is not a replacement for existing systems of gathering and analyzing weather data. "We still need the raw data," the University of Pennsylvania's Paris Perdikaris said. "We still need high quality data coming from physics-based simulation models that have been in place all these years."
The Hindu
22-05-2025
- Science
- The Hindu
Microsoft AI weather forecast faster, cheaper, truer: study
Microsoft has developed an artificial intelligence (AI) model that beats current forecasting methods in tracking air quality, weather patterns, and climate-addled tropical storms, according to findings published Wednesday. Dubbed Aurora, the new system, which has not been commercialised, generated 10-day weather forecasts and predicted hurricane trajectories more accurately and faster than traditional forecasting, and at lower costs, researchers reported in the journal Nature. "For the first time, an AI system can outperform all operational centres for hurricane forecasting," said senior author Paris Perdikaris, an associate professor of mechanical engineering at the University of Pennsylvania. Trained only on historical data, Aurora was able to correctly forecast all hurricanes in 2023 more accurately than operational forecasting centres, such as the U.S. National Hurricane Center. Traditional weather predicting models are designed on first physical principles, such as conservation of mass, momentum and energy, and require massive computer power. The computational costs of Aurora were several hundred times lower, the study said. The experimental results follow on the heels of the Pangu-Weather AI model developed and unveiled by Chinese tech giant Huawei in 2023, and could herald a paradigm shift in how the world's major weather agencies forecast weather and potentially deadly extreme events exacerbated by global warming. "I believe that we're at the beginning of a transformation age in air system science," Perdikaris said in a video presentation distributed by Nature. "In the next five to 10 years the holy grail is how to build systems that can directly work with observations from remote sensing sources like satellites and weather stations to generate forecasts at high resolution anywhere we like." According to its designers, Aurora is the first AI model to consistently outperform seven forecasting centres in predicting the five-day trajectory of devastating cyclones. In its simulation, for example, Aurora correctly forecast four days in advance where and when Doksuri, the most costly typhoon ever recorded in the Pacific, would hit the Philippines. Official forecasts at the time, in 2023, had it heading north of Taiwan. Microsoft's AI model also outperformed the European Centre for Medium-Range Weather Forecasts (ECMWF) model in 92 percent of cases for 10-day global forecasts, on a scale of approximately 10 square kilometres (3.86 square miles). The ECMWF, which provides forecasts for 35 European countries, is considered the global benchmark for weather accuracy. In December, Google announced that its GenCast model had surpassed the European centre's accuracy in more than 97 percent of the 1,320 climate disasters recorded in 2019. These promising performances, all experimental and based on observed events, are being closely scrutinised by weather agencies. Several, including Meteo-France, are developing their own AI learning models alongside traditional digital models. "This is something we have taken very seriously," Florence Rabier, Director General of the ECMWF, told AFP. Their first "learning model", made available to member states in February, is "about 1,000 times less expensive in terms of computing time than the traditional physical model", she added. While operating as a lower resolution (30 sq km) than Aurora, the ECMWF model is already operational.
The Star
22-05-2025
- Science
- The Star
Study: Microsoft AI weather forecast faster, cheaper, truer
Trained only on historical data, Aurora was able to correctly forecast all hurricanes in 2023 more accurately than operational forecasting centres, such as the US National Hurricane Center. — Reuters PARIS: Microsoft has developed an artificial intelligence (AI) model that beats current forecasting methods in tracking air quality, weather patterns, and climate-addled tropical storms, according to findings published on May 21. Dubbed Aurora, the new system – which has not been commercialised – generated 10-day weather forecasts and predicted hurricane trajectories more accurately and faster than traditional forecasting, and at lower costs, researchers reported in the journal Nature. "For the first time, an AI system can outperform all operational centres for hurricane forecasting," said senior author Paris Perdikaris, an associate professor of mechanical engineering at the University of Pennsylvania. Trained only on historical data, Aurora was able to correctly forecast all hurricanes in 2023 more accurately than operational forecasting centres, such as the US National Hurricane Center. Traditional weather predicting models are designed on first physical principles – such as conservation of mass, momentum and energy – and require massive computer power. The computational costs of Aurora were several hundred times lower, the study said. The experimental results follow on the heels of the Pangu-Weather AI model developed and unveiled by Chinese tech giant Huawei in 2023, and could herald a paradigm shift in how the world's major weather agencies forecast weather and potentially deadly extreme events exacerbated by global warming. 'Holy grail' "I believe that we're at the beginning of a transformation age in air system science," Perdikaris said in a video presentation distributed by Nature. "In the next five to 10 years the holy grail is how to build systems that can directly work with observations from remote sensing sources like satellites and weather stations to generate forecasts at high resolution anywhere we like." According to its designers, Aurora is the first AI model to consistently outperform seven forecasting centres in predicting the five-day trajectory of devastating cyclones. In its simulation, for example, Aurora correctly forecast four days in advance where and when Doksuri – the most costly typhoon ever recorded in the Pacific – would hit the Philippines. Official forecasts at the time, in 2023, had it heading north of Taiwan. Microsoft's AI model also outperformed the European Centre for Medium-Range Weather Forecasts (ECMWF) model in 92% of cases for 10-day global forecasts, on a scale of approximately 10 square kilometres (3.86 square miles). The ECMWF, which provides forecasts for 35 European countries, is considered the global benchmark for weather accuracy. In December, Google announced that its GenCast model had surpassed the European centre's accuracy in more than 97% of the 1,320 climate disasters recorded in 2019. These promising performances – all experimental and based on observed events – are being closely scrutinised by weather agencies. Several, including Meteo-France, are developing their own AI learning models alongside traditional digital models. "This is something we have taken very seriously," Florence Rabier, Director General of the ECMWF, told AFP. Their first "learning model", made available to member states in February, is "about 1,000 times less expensive in terms of computing time than the traditional physical model", she added. While operating as a lower resolution (30 sq km) than Aurora, the ECMWF model is already operational. – AFP
Times
21-05-2025
- Climate
- Times
AI will soon eclipse traditional weather forecasting, says expert
The weather app on your phone could be largely powered by artificial intelligence rather than traditional forecasting methods within just two years, an expert has claimed. Paris Perdikaris, of the University of Pennsylvania, has created an AI model that appears to predict global weather patterns more accurately than today's best supercomputer-based forecasts. The Aurora model, developed by Microsoft, worked particularly well at forecasting extreme events such as Storm Ciarán two years ago. • 'It will probably lead to the end of the world' — what tech bros really think about AI 'If traditional weather models miss the mark by 100 miles for a hurricane's path in five days, Aurora might miss by only 75-80 miles. It also better captures wind speeds in severe storms —
New York Times
21-05-2025
- Climate
- New York Times
A.I. Is Poised to Revolutionize Weather Forecasting. A New Tool Shows Promise.
Weather forecasters rely on models to help them make decisions that can have life-or-death consequences, so any advantage is welcome. Artificial intelligence holds promise to deliver more accurate forecasts quickly, and tech companies including Google, Nvidia and Huawei have produced A.I.-based forecasting models. The latest entrant is Aurora, an A.I. weather model from Microsoft, and it stands out for several reasons, according to a report published Wednesday in the journal Nature. It's already in use at one of Europe's largest weather centers, where it's running alongside other traditional and A.I.-based models. The Aurora model can make accurate 10-day forecasts at smaller scales than many other models, the paper reports. And it was built to handle not only weather, but also any Earth system with data available. That means it can be trained, relatively easily, to forecast things like air pollution and wave height in addition to weather events like tropical cyclones. Users could add almost any system they like down the road; for instance, one start-up has already honed the model to predict renewable energy markets. 'I'm most excited to see the adoption of this model as a blueprint that can add more Earth systems to the prediction pipeline,' said Paris Perdikaris, a professor at the University of Pennsylvania who led the development of Aurora while working at Microsoft. It's also fast, able to return results in seconds as opposed to the hours that non-A.I. models can take. Traditional models, the basis of weather forecasting over the last 70 years, use layers of complex mathematical equations to represent the physical world: the sun heating the planet, winds and ocean currents swirling around the globe, clouds forming, and so on. Researchers then add real weather data and ask the computer models to predict what will happen next. Human forecasters look at results from many of these models and combine those with their own experience to tell the public what scenario is most likely. 'Final forecasts are ultimately made by a human expert,' Dr. Perdikaris said. (That is true for A.I.-based forecasts, too.) This system has worked well for decades. But the models are incredibly complex and require expensive supercomputers. They also take many years to build, making them difficult to update, and hours to run, slowing down the forecasting process. Artificial intelligence weather forecasting models are faster to build, run and update. Researchers feed the models on huge amounts of weather and climate data and train them to recognize patterns. Then, based on these patterns, the model predicts what comes next. But the A.I. models still need equation-based models and real-world data for their starting points, and for reality checks. 'It doesn't know the laws of physics, so it could make up something completely crazy,' said Amy McGovern, a computer scientist and meteorologist at the University of Oklahoma who was not involved in the study. So most, but not all, A.I. weather forecasting models still rely on data and the physics-based models in some capacity, and human forecasters need to interpret results carefully. Dr. Perdikaris and his collaborators built Aurora using this method, training it on data from physics-based models and then making purely A.I. predictions, but they didn't want it to be limited to weather. So they trained it on multiple, big Earth system data sets, creating a broad background of artificial expertise Aurora 'is an important step toward more versatile forecasting systems,' said Sebastian Engelke, a professor of statistics at the University of Geneva who was not involved in the study. The model's flexibility and resolution are its most novel contributions, he said. As in other areas, there's been a big push toward using A.I. for weather forecasting in the past few years, but the major A.I. forecasting models are still global, not local. Forecasts at the scale of a single storm barreling toward a city need to come from a specialized model, and those are mostly the old-school variety, at least for now. Extreme weather events like heat waves or heavy downpours are still challenging for both traditional and A.I. models to predict. A.I. forecasting models need careful calibration and human verification before they're widely used, Dr. Perdikaris said. But some are already being tested in the real world. The European Center for Medium-Range Weather Forecasting, which provides meteorological forecasts to dozens of countries, developed their own A.I. forecasting model, which they deployed in February. They use that, along with Aurora and other A.I. models, for their weather services. They've had a good experience using A.I. models so far. 'It's absolutely an exciting time,' said Peter Düben, who leads the European center's Earth modeling team. Other researchers are more conservative, given the checks and improvements the models need. And artificial intelligence tools come with a significant energy cost to train, though Dr. Perdikaris said this would be worth it in the long run as more people use the models. 'We're all in the hype right now,' said Dr. McGovern, who leads the NSF's institute that studies trust in A.I. applications to climate and weather problems. 'A.I. weather is amazing. But I think there's still a long way to go.' And the Trump administration's cuts to agencies including the National Oceanic and Atmospheric Administration, the National Science Foundation and the National Weather Service could stymie further improvements in A.I. forecasting tools, because federal data sets and models are critical to developing and improving A.I. models, Dr. Perdikaris said. 'It's quite unfortunate, because I think it's going to slow down progress,' he said.
