Crime & Safety

Wildfires To Hit CA Hard In Coming Months, New Tool Predicts

The first-of-its-kind tool which can calculate outbreak risks within minutes—months in advance—may soon be available to the public for free.

CALIFORNIA—Can wildfires be predicted? Researchers at Columbia University and New York University say yes and an app may soon be available for that.

They've devised a way to forecast the risk of forest fires in any particular region of the western United States months in advance, and they say it can be done within minutes— as opposed to hours.

This would be welcome news to firefighters and some 350,000 Californians whom a McClatchy analysis revealed live in towns and cities that exist almost entirely within "very high fire hazard severity zones," Cal Fire's designation for places highly vulnerable to devastating wildfires.

Find out what's happening in Healdsburgfor free with the latest updates from Patch.

Thus far this year, 5,210 wildfires have burned a cumulative 821,827 acres in California. The largest of the blazes, the Park Fire, was 429,401 acres in size Tuesday and growing, making it the fourth-largest wildfire in state history.

Yet researchers who conducted an analysis with the new tool SEASFire say it is "highly probable" California and the Pacific Northwest will be hit hard with even more forest fires in the coming months. They said hotter temperatures and below-normal precipitation will drive the high fire risk in these regions.

Find out what's happening in Healdsburgfor free with the latest updates from Patch.

Touted as a "breakthrough approach," SEASFire uses mathematics to assess the problem of fire based on climate data and is the first tool to use machine learning to make seasonal forecasts on a monthly basis.

It was unveiled recently in SIAM News, a publication of the Society for Industrial and Applied Mathematics, and presented at the 2024 SIAM Conference on Mathematics of Planet Earth in Portland, Oregon. The international society is comprised of more than 14,000 individual, academic and corporate members from 85 countries and helps build cooperation between mathematics and the fields of science and technology to solve real-world problems.

The creation of SEASFire was spurred by last summer's record-breaking fire season, which originated in Canada and lasted longer than normal. Larger burn areas and more severe fires significantly impacted air quality in large parts of North America.

The researchers said SEASFire uses math models and machine-learning algorithms to pull fire predictors within minutes based on several sources, including the flagship European Centre for Medium-Range Weather Forecasts’ seasonal forecasting system SEAS5. The predictors capture long-term trends such as climate history, vegetation topography, lightning, and human influences in a given area for months or years.

Jatan Buch (left) of Columbia University and Gabriel Provencher Langlois (right) of NYU created the SEASFire tool. (Photos courtesy of SIAM.org)

"Fires are getting more intensive and destructive as a result of our warming world, and if we can identify risk areas with a high level of certainty early on — even months in advance — we can ensure better fire control, evacuation and public awareness planning at the start of the season," said Jatan Buch, a postdoctoral research scientist in the Department of Earth and Environmental Engineering at Columbia University.

Buch collaborated on the project with Gabriel Provencher Langlois, a visiting assistant professor at NYU’s Courant Institute of Mathematical Sciences.

"Our model can analyze the volumes of data that exist and provides significantly more information than what’s currently available with other forecasts," Langlois said. "We’re able to identify risk areas while also accounting for the uncertainty in climate predictions, and we do so more efficiently, faster and on a longer-term scale, including a seasonal outlook months out."

More enhancements are in the works as the team prepares to make its tool available to the public free of charge. Also planned is a website where people can input a ZIP code to see the wildfire risk in a particular area months in advance.

"Fires cause significant personal and ecological damage and involve huge costs," Buch said. "It’s a major public health issue, and it's therefore important to increase awareness and bring groups together to better predict fire risks, understand where they come from, be best prepared to fight them, and work to prevent them."

Get more local news delivered straight to your inbox. Sign up for free Patch newsletters and alerts.