Facial recognition set to unlock secrets behind hail
TECHNOLOGY similar to what Facebook uses for recommending what friends you should “tag” might soon be coming to hailstorms.
David Gagne, a machine learning scientist at the National Centre for Atmospheric Research, is using facial recognition technology to predict the size of hailstorms.
Working with computer-simulated storms, he created software that is trained to determine which storms produce hail and then to recognise patterns associated with the storms behind the largest hailstones.
His latest work is published Monthly Weather Review.
While other studies often looked at finer-scale processes within the storm, Gagne is broadening outward to consider the storm’s entire structure.
The work he’s doing deals with computer-generated storms.
“We create storms and derive their hail size with the microphysics,” he said. Gagne uses the raw data of what the storm looks like structurally to train software to predict its hail size. Over time, his machine learning model is refined, improving its predictions with each successive run.
“The data we have is skewed. The hail reports cluster near cities or interstates. In rural areas, the largest hail might strike in areas where nobody lives, leading to a missed event. Public-submitted hail reports might not be mapped correctly; even subtle discrepancies have a compounding effect over time.”
Gagne hopes his endeavour might eventually serve as a supplement to meteorologists when dealing with hail forecasting. If forecasters can predict the structure of storms before they form, his work will bridge the gap needed to translate that information into potential hail size.
“Then we could tell folks to maybe change their plans, put their car in the garage, tweak their outdoor schedules…” | The Washington Post