Swiss startup Jua has launched an AI weather model it says outperforms leading systems from tech giants — potentially making it the most accurate forecaster in the world.
Jua claims its model — dubbed EPT-2 — is faster and more accurate than both Microsoft’s Aurora and Google DeepMind’s Graphcast. In separate, peer-reviewed studies, both of those models were shown to be more accurate than the European Centre for Medium-Range Weather Forecasts (ECMWF)’s ENS forecast, widely regarded as the world leader.
Jua backs up its bold claims with a new report, published today, that puts EPT-2 head-to-head with top-tier models — including Aurora and two of ECMWF’s best: ENS and IFS HRES.
According to the paper, EPT-2 came out on top, delivering the most accurate forecasts across the board. It beat Aurora on key variables like 10-metre wind speed and 2-metre air temperature over a 10-day period, ran forecasts 25% faster, and posted the lowest error scores of all models tested. Jua says it achieved all this while using 75% less computing power than Aurora, the second most efficient system tested.
The 💜 of EU tech
The latest rumblings from the EU tech scene, a story from our wise ol’ founder Boris, and some questionable AI art. It’s free, every week, in your inbox. Sign up now!
The research is due to be published on the open-access archive arXiv next week, according to Jua.
DeepMind’s Graphcast model was not included in the study. Nevertheless, Marvin Gabler, Jua’s CEO and co-founder, is confident that it can beat all of the competition.
“We respect players like Microsoft Aurora, GraphCast, and Tomorrow.io, but they’re either too slow, too narrow, or still reliant on legacy infrastructure,” said Gabler.
AI-based weather forecasting has been making waves in recent years, driven by demand for more accurate and cheaper ways to predict the Earth’s climate.
Traditional weather models, like those from ECMWF or NOAA, use complex physics equations run on billion-dollar supercomputers. AI models skip the equations, learning patterns from massive datasets, potentially making accurate forecasts thousands of times faster on far cheaper, less energy-intensive machines.
However, Gabler says Jua takes it a step further than previous AI-based forecasters. “While others are retrofitting AI onto legacy systems, we’ve built a native physics simulation that understands how Earth’s atmosphere actually behaves,” he said.
Jua released its first global AI weather model three years ago. The startup has since raised a total of $27mn in funding from backers including 468 Capital, Future Energy Ventures, and Promus Ventures.
Be the first to comment