{"id":242978,"date":"2026-07-14T10:06:22","date_gmt":"2026-07-14T10:06:22","guid":{"rendered":"https:\/\/www.newsbeep.com\/us-pa\/242978\/"},"modified":"2026-07-14T10:06:22","modified_gmt":"2026-07-14T10:06:22","slug":"ai-is-changing-how-pittsburgh-meteorologists-track-tornadoes","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us-pa\/242978\/","title":{"rendered":"AI is changing how Pittsburgh meteorologists track tornadoes"},"content":{"rendered":"

by Oliver Morrison, Pittsburgh’s Public Source
July 14, 2026<\/p>\n

Matthew Kramar has added a new step to his weather prediction routines: At the end of his analysis, he looks at a map of predictions generated by an AI model.<\/p>\n

\u201cI look at the AI and say \u2013 does it agree with me?\u201d said Kramar, the science and operations officer for the National Weather Service in Pittsburgh. \u201cIf it does agree with me, then I feel pretty good about what my reasoning is. If it doesn’t, then I have to ask myself why.\u201d<\/p>\n

One of the reasons he\u2019s added this extra step, he said, happened in May of 2024.<\/p>\n

Kramar said an AI weather model called Nadocast<\/a> was predicting a roughly 3% to 5% chance of tornadoes southwest of Pittsburgh in two days. Although 3% may not seem very likely, Kramar said, it\u2019s hundreds of times more likely than average. And the odds seemed to be increasing as the day got closer.<\/p>\n

But when Kramar and his fellow meteorologists looked at the underlying weather data, he said, they didn\u2019t see anything worrisome<\/a>. \u201cWe were examining [the AI prediction] thinking, \u2018Well this has got to be out to lunch,\u2019\u201d he said.<\/p>\n

Then, on May 11, 2024, there were three confirmed tornadoes. The same thing happened a week later on May 17: The AI model showed a small chance of tornadoes and then six tornadoes appeared.\u00a0<\/p>\n

In surveillance footage from the 17th about two hours west of Pittsburgh in Carroll County, Ohio, a vortex appears out of seemingly nowhere and picks up a handful of docked pontoon boats and tosses them across the harbor. In hindsight, Kramar said, the weather service probably should have issued some kind of alert.\u00a0<\/p>\n

Then, on April 29 this year, \u201cthe atmospheric profiles were eerily similar\u201d to May 2024, Kramar said.\u00a0<\/p>\n

This time, Kramar said, their understanding of the AI models had grown and they were prepared.<\/p>\n

The challenge is that being prepared does not always mean knowing exactly what will happen, where it will happen or how disruptive a warning should be.<\/p>\n

\"AMatthew Kramar, the science and operations Officer of the National Weather Service in Pittsburgh, talks to a reporter about how AI has impacted severe weather tracking, at the National Weather Service building in Moon, on June 25. (Photo by Claira Tokarz\/Pittsburgh\u2019s Public Source)<\/p>\n

That tension was on display June 6, when country singer Morgan Wallen canceled his second Pittsburgh concert at Acrisure Stadium because of the threat of severe weather.<\/p>\n

The National Weather Service eventually confirmed that six tornadoes landed that day, but they hit south of Pittsburgh and were long gone hours before the concert was scheduled to start.<\/p>\n

The gap between a real regional threat and a clear local decision \u2014 whether to issue an alert, staff up or cancel a stadium concert \u2014 is exactly where meteorologists are trying to understand what AI can and cannot do.<\/p>\n

\n

Morgan Wallen cancelled in Pittsburgh tonight due to weather. In his defense, it is perhaps the most beautiful night I\u2019ve ever seen pic.twitter.com\/kKJsB4qLaJ<\/a><\/p>\n

— Dustin Nickerson (@DustinNickerson) June 7, 2026<\/a><\/p><\/blockquote>\n