Artificial Intelligence Could Prevent Hawaii Wildfires
Hawaii has long battled with inaccurate weather forecasts due to our unique island terrain. But artificial intelligence (AI) could change that—and help prevent devastating wildfires in the process.
Associate computer science professor Peter Sadowski at the University of Hawaii at Mānoa is working on incorporating AI into weather predictions, reported Savannah Harriman-Pote of Hawaii Public Radio yesterday. By refining existing computational models, the technology can provide hyperlocal forecasts across Hawaii’s mountainous regions.
This data goes beyond deciding whether you need an umbrella, Sadowski explains.
“The recipe for wildfires is dry areas with lots of brush that can catch fire easily, but also high winds. So one of the problems we’ve been looking at here is to use machine learning to help predict wind,” Sadowski told the station.
Now, Hawaii lawmakers aim to fund this research. Companion bills in the state Senate and House—SB2284 and HB1924—would establish a two-year program at UH to build an official AI wildfire warning system. The university supports the measure, stating it has the capabilities to “develop this important tool for Hawaii’s decision makers.”
Other states like California have already implemented similar strategies, the HPR report noted. CAL FIRE uses a network of AI-powered cameras that rapidly detect fires through images. Their goal is to contain 95% of wildfires to under 10 acres by catching them early. CAL FIRE assistant chief Andy Emerick shares that their AI system often discovers fires before 911 calls come in – flagging blazes 20% faster.
As climate change worsens, massive fires are burning quicker than ever before. Emerick explains that AI aids emergency planning: “Fires that used to burn maybe 1,000 acres a day are now burning anywhere between 10,000-20,000, even 100,000 acres in a day…AI tools are becoming essential for emergency managers to make the most sound decisions possible.”
Hawaii must take action to prepare for this destructive new normal. Funding university research into AI fire prevention is a critical first step. Advanced early warning can help save properties, ecosystems, and lives across our island chain.