AI weather forecasting can’t replace humans—yet
Artificial intelligence-based forecasting tools such as GraphCast offer a whole new way to predict the weather, but they have limits. Because of their reliance on past data, most AI models seem poorly equipped to forecast rare and never-before-seen events such as Hurricane Harvey, which dropped an unprecedented 60 inches of rain on parts of Texas in 2017, or the exceptionally rapid intensification of Hurricane Otis from a tropical storm to a Category 5 monster just before it hit Mexico's Pacific Coast last year. "The events it sees most often (in training data), it's going to be best at capturing. So on average, it's probably pretty good," said University of Arizona associate professor of hydrology and atmospheric sciences Kim Wood, a hurricane researcher. "But the kind of events that can change peoples' lives forever – maybe it would struggle more with that."