Wildfires on the West Coast May Trigger Hailstorms in the Central US

Scientists have found a strange and unexpected link between two vastly different types of extreme weather, hundreds of miles apart.

Using machine learning, researchers from the Pacific Northwest National Laboratory in Washington and the Argonne National Laboratory in Illinois discovered that there is an association between wildfires in the western states and hailstorms in the central U.S., according to a new paper in the journal Advances in Atmospheric Sciences.

The unique characteristics of wildfires on the West Coast may change the conditions of the atmosphere in certain ways—such as altering temperature and adding aerosols—subsequently triggering hailstorms far away. This phenomenon can be predicted by machine learning algorithms.

This was discovered with the use of machine learning algorithms such as Random Forest and Extreme Gradient Boosting, or XG Boost, which scrutinized extensive datasets covering a period from 2001 to 2020.

These algorithms are adept at forecasting significant hail events in the Central U.S. by analyzing a vast array of factors; these include meteorological conditions within the wildfire areas, wind dynamics, and the presence of wildfires hundreds of miles away in the west.

These machine learning models often surpass 90 percent accuracy in their predictions of weather, successfully identifying crucial variables and patterns that link wildfires in the western U.S. to hailstorms in the center of the country. They therefore also offer important insights into how wildfires can influence severe weather events at great distances.

Read more: Emergency Funds: How to Build One and Where to Keep It

"We are now able to paint a vivid picture of the intricate relationship between fire and hail across the American landscape. Wildfires in the western U.S, exert a far-reaching influence on atmospheric conditions, shaping the trajectory of severe weather events thousands of miles away, something that we never thought before," Jiwen Fan said in a statement. She is a researcher at the Argonne National Laboratory and was previously earth scientist at Pacific Northwest National Laboratory.

"Meteorological variables like westerly wind, the temperature and relative humidity in the fire region and the intensity of wildfires emerge as key players in this climatic symphony."

The primary factors highlighted by both machine learning models are the meteorological conditions in the fire region, such as temperature and moisture, the westerly winds along the path of plume transport, and the characteristics of the fire, including the maximum fire power and the area burned.

"The results confirm a linkage between [western U.S.] fires and severe weather in the [central U.S.]," the researchers wrote in the paper.

However, the machine learning algorithms aren't always right, as there are so many other factors that come into play when predicting a hailstorm or any other weather event. The researchers hope to improve these algorithms with time, so that they can become more accurate and better at predicting hailstorms and other weather.

Do you have a tip on a science story that Newsweek should be covering? Do you have a question about the weather? Let us know via science@newsweek.com.