We saw that last year turned out to be the most damaging wildfire season ever for California, with over a million acres destroyed. Sadly, those records are being surpassed by the wildfire damages that are taking place this year. The Camp Fire itself has turned out to be the deadliest wildfire in all of California’s wildfire history, as it has claimed 85 lives with 249 more that are missing – and those numbers will probably grow even larger. Officials also claim the fire has destroyed around 19,000 buildings, with most of them being homes.
Experts claim that climate change could even expand the sizes of these fires and actually turn the fire season into a year around event. As the complexity of containing wildfires increase, we are seeing researchers, government agencies, and companies turn to artificial intelligence to help manage and analyze the chaos from the plethora of data that comes from these disasters. The goal and hope in the future is that authorities will improve their means of earlier detection which would allow firefighters to keep them from getting out of control and perhaps even keep fires in the future from starting in the first place.
Fighting Fire from Space
Currently, most fires are reported by 911 calls, commercial flights, or fire lookout stations. That spotty approach lets some wildfires go undiscovered for hours or even days. Satellites focused on the Earth can improve coverage. Already, two NASA satellites currently orbiting the Earth scan nearly the entire planet once a day and can spot the thermal signature of a fire. The process takes at least three hours, which is about the time it takes for the satellites to cross over Goddard Space Flight Center outside of Washington, D.C., beam down the data, and run the images through a supercomputer.
But an algorithm could be run on the satellites and process images in a matter of minutes, says James MacKinnon, a NASA computer engineer running a new AI project looking to do just that. MacKinnon scaled down the work that the supercomputer does into a neural network that is small enough to run on the simple, onboard computers typical of satellites. He trained the system on a year’s worth of satellite imagery from around the world and created a system that is 98% accurate at recognizing fires.
“The fires stick out like a sore thumb,” he says.
In the future, an AI-based system like this on a fleet of small satellites could provide more regular contact with Earth, with the ability to send near real-time alerts to emergency responders on the ground.
Even when immediate threats from wildfires recede, there is limited amount of time to find survivors and get help to those people who are in need. Determining the most effective way to get resources that are very limited to disaster victims continues to be a huge unsolved problem.
There have been some researchers out there that have utilized social media as a means of improving responses to disaster. The fact is that trying to sift through all the data manually is impossible, but it is believed that AI tools would greatly help in finding crucial messages quickly. Experts claim that such a function would save numerous lives and homes. It is imperative that modern tools and technologies be utilized in fighting a problem that appears to be a permanent fixture in the future.
A recent paper by researchers at Texas Tech and George Washington University titled “Coordinating Disaster Emergency Response with Heuristic Reinforcement Learning” documented a machine learning system that can analyze tweets and identify volunteers and victims, along with their locations.
“Our proposed new disaster relief framework bridges the gap when traditional emergency help lines such as 911 are overwhelmed, thus benefiting both the disaster victims and the non-governmental organizations seeking to help them,” the authors wrote.