This AI model 'studied' physics - and learnt to forecast extreme weather

"Artificial-intelligence tools have transformed weather forecasting, thanks to their ability to learn past patterns from observations and predict how future patterns might unfold. But until now, models have sometimes struggled to forecast extreme weather events that they've never seen before, but that are happening more frequently as the planet warms. It's like trying to "forecast the future with yesterday's climate", as Jacob Landsberg, a data scientist at Boston University in Massachusetts, puts it."

"One new approach that's showing success combines an artificial-intelligence (AI) model with a conventional climate model, plus mathematical tools that describe rare events, to forecast weather extremes more effectively. In early tests, this hybrid approach simulated the probabilities of extreme heatwaves as accurately as the older, non-AI method, which takes much longer to run. "We think this is the way forward," says Pedram Hassanzadeh, a climate physicist at the University of Chicago in Illinois who is involved in several of the early studies."

Artificial-intelligence tools can learn historical atmospheric patterns and improve weather forecasting but often struggle with unprecedented extremes that are increasing with global warming. Hybrid systems combine AI components with conventional climate models and rare-event mathematical tools to better represent and predict extreme events. Early tests show hybrid models can simulate probabilities of extreme heatwaves with accuracy comparable to computationally intensive non-AI methods while running much faster. Limited observational records constrain AI training because datasets spanning decades are insufficient to capture millennial-scale rare events. Notable deadly and disruptive extremes illustrate the urgency of methods that can extrapolate beyond past observations.

Read at Nature