FLASH Weather AI announced the launch of its 1-Hour Hail Swath Prediction Model, the first high-resolution hail prediction model. The deep-learning system forecasts hail size and arrival time at 1-kilometer resolution, refreshed every five minutes, with predictions extending up to 55 minutes into the future.
Trained on four years of U.S. convective storm data spanning 2021 through 2024, the model produces deterministic forecasts of hail size in inches or millimeters, predicting down to the hundredth of an inch. A companion Hail Arrival Time product estimates when quarter-size or larger hail will reach any location in the forecast window. Following a month of beta testing across multiple severe weather events, the model has demonstrated significant accuracy and operational usability, with verification examples available on request.
The product begins rolling out this week via API and inside the FLASH Weather Command Center (WCC), the company's web-based operations platform, with native integration into the FLASH mobile app following in the coming weeks.
"For the first time, insurers, fleet operators, and infrastructure managers have a tool that doesn't just tell you a storm is coming; it tells you exactly where hail will fall, how large it will be, and gives you enough lead time to act,” said Jason Deese, founder and CEO. “That's not an incremental improvement. That's a fundamental shift in how the world manages hail risk."
Why Hail Prediction Matters
According to Cotality's 2026 Severe Convective Storm Risk Report, more than 43.5 million U.S. homes (roughly 42 percent of all analyzed properties) now sit in moderate or greater hail risk categories, representing 17.8 trillion dollars in reconstruction cost value. The same report concludes that a single severe hailstorm is now capable of generating insured losses approaching 30 billion dollars at a 50-year return period, rivaling the financial impact of a Category 4 hurricane. In 2025 alone, State Farm paid out more than 5.6 billion dollars in hail claims, and Cotality recorded 142 days of damaging hail across the United States, the highest total in over two decades.
Exposure is concentrated, but no longer regional. Texas leads with 3.1 trillion dollars in at-risk reconstruction value, while the greater Chicago metro now ranks as the most financially exposed city in the country at 1.0 trillion dollars. Losses cut across property insurance, roofing, construction, agriculture, automotive fleets, solar energy, and outdoor sports.
Until now, the industry has relied almost entirely on radar-based detection, which only confirms hail after it has already begun to fall, or on broad convective outlooks that lack the precision required to protect a specific job site, fleet yard, solar array, golf course, or rooftop. The FLASH 1-Hour Hail Swath Prediction Model closes that gap with location-specific, minute-by-minute forecasts.
"Hail is one of the toughest convective hazards to forecast at high resolution. Getting size and arrival time right at a 1-kilometer grid, refreshed every five minutes, is a leap forward in convective forecasting. After a month in beta, I trust this model the way I trust our proprietary lightning prediction, and that's not a comparison I make lightly."
