GenCast, a new ai model from Google DeepMind, is accurate enough to compete with traditional weather forecasting. It managed to outperform a leading forecast model when tested with data from 2019, according to recently published research.
ai won't replace traditional forecasts anytime soon, but it could add to the arsenal of tools used to predict the weather and warn the public about severe storms. GenCast is one of several ai weather forecasts <a target="_blank" href="https://www.technologyreview.com/2024/12/04/1107892/google-deepminds-new-ai-model-is-the-best-yet-at-weather-forecasting/”>models in development that could lead to more accurate forecasts.
GenCast is one of several ai weather forecasting models that could generate more accurate forecasts.
“Climate basically affects every aspect of our lives… it's also one of the big scientific challenges, predicting the climate,” says Ilan Price, senior research scientist at DeepMind. “Google DeepMind is on a mission to advance ai for the benefit of humanity. And I think this is an important way, an important contribution on that front.”
Price and his colleagues tested GenCast against the ENS system, one of the world's premier forecast models managed by the European Center for Medium-Range Weather Forecasts (ECMWF). GenCast outperformed ENS 97.2 percent of the time, research finds published this week in the magazine Nature.
GenCast is a machine learning weather prediction model trained on weather data from 1979 to 2018. The model learns to recognize patterns in the four decades of historical data and uses them to make predictions about what could happen in the future. This is very different from how traditional models like ENS work, which still rely on supercomputers to solve complex equations in order to simulate the physics of the atmosphere. Both GenCast and ENS produce joint forecastsThey offer a variety of possible scenarios.
When it comes to predicting the path of a tropical cyclone, for example, GenCast was able to provide an average of 12 additional hours of warning. Overall, GenCast was better at predicting cyclone tracks, extreme weather conditions, and wind energy production up to 15 days in advance.
One caveat is that GenCast was tested with an older version of ENS, which now works at a higher resolution. The peer-reviewed research compares GenCast predictions to ENS forecasts for 2019, looking at how close each model was to real-world conditions that year. The ENS system has improved significantly since 2019, according to ECMWF machine learning coordinator Matt Chantry. That makes it difficult to say how well GenCast might work against ENS today.
Resolution is certainly not the only important factor when it comes to making solid predictions. ENS was already working at a slightly higher resolution than GenCast in 2019, and GenCast still managed to surpass it. DeepMind says it conducted similar studies using data from 2020 to 2022 and found similar results, although they have not been peer-reviewed. But I didn't have the data to make comparisons for 2023, when ENS began operating at significantly higher resolution.
By dividing the world into a grid, GenCast operates at a resolution of 0.25 degrees, meaning that each square on that grid is a quarter-degree latitude by a quarter-degree longitude. ENS, by comparison, used a resolution of 0.2 degrees in 2019 and now has a resolution of 0.1 degrees.
However, the development of GenCast “marks an important milestone in the evolution of weather forecasting,” Chantry said in an emailed statement. In addition to ENS, the ECMWF says it is also running its own version of a machine learning system. Chantry says he “takes some inspiration from GenCast.”
Speed is an advantage for GenCast. It can produce a 15-day forecast in just eight minutes using a single Google Cloud TPU v5. Physics-based models like ENS can take several hours to do the same. GenCast skips all the equations that ENS has to solve, so it takes less time and computational power to produce a forecast.
“Computationally, running traditional forecasts is much more expensive than a model like Gencast,” Price says.
That efficiency could alleviate some of the concerns about the environmental impact of energy-intensive ai data centers that have already contributed to Google's rising greenhouse gas emissions in recent years. But it's difficult to determine how GenCast compares to physics-based models when it comes to sustainability without knowing how much energy is used to train the machine learning model.
There are still improvements that GenCast can make, including the ability to upscale it to a higher resolution. Additionally, GenCast makes predictions at 12-hour intervals compared to traditional models that typically do so at shorter intervals. That can make a difference in how these forecasts can be used in the real world (to assess how much wind power will be available, for example).
“We're thinking, is this good? And why?”
“You'd want to know what the wind will be doing throughout the day, not just at 6 a.m. and 6 p.m.,” says Stephen Mullens, an assistant professor of meteorology at the University of Florida who was not involved in the GenCast research.
While there is growing interest in how ai can be used to improve forecasting, it has yet to prove its worth. “People are looking at it. I don't think it will be bought and sold to the meteorological community as a whole,” says Mullens. “We're trained scientists who think in terms of physics… and because ai fundamentally isn't that, there's still an element where we're going back and forth, is this good? And why?”
Forecasters can check out GenCast for themselves; DeepMind launched the code for its open source model. Price says he sees GenCast and more improved ai models being used in the real world alongside traditional models. “Once these models get into the hands of professionals, it builds even more confidence,” says Price. “We really want this to have some kind of widespread social impact.”
