The current space race isn’t just for billionaires.
With the help of satellites, drones and artificial intelligence, new technology is changing the way fire departments and governments tackle the ever-growing threat of forest fires as hundreds of thousands of acres burn in the western United States.
New programs are being developed by startups and research institutions to predict fire behavior, monitor droughts, and even detect fires when they start. As climate change continues to increase the intensity and frequency of forest fires, these breakthroughs offer at least one tool in the growing arsenal of prevention and control strategies.
“This is not intended to replace fire fighting on site,” says Ilkay Altintas, a computer scientist at the University of California at San Diego, who developed a fire map for the region. “The more science and data we can make available to firefighters and the public, the faster we will have solutions to fight and contain forest fires.”
More than 80 major fires and complexes burned more than 1.3 million acres in 13 states this year through Friday, according to the National inter-agency fire service center, and more fires break out almost every week.
The country’s biggest inferno, the Bootleg Fire in southern Oregon, has forced thousands of residents to evacuate since it was struck by lightning on July 6. The smoke from the western flames is so thick that the residents of the east coast have experienced a spectacular, if unsettling, one this week fiery sunrise and misty sky.
“As the risk of catastrophic forest fires increases, so should our ability to predict forest fires and mitigate the risk of fire,” said Zoe Lofgren, Calif., Rep. Zoe Lofgren, California, last month during a House Committee on Science, Space and Technology hearing.
Her own district, which also includes San Mateo County, was one of several Northern California communities affected by last year’s CZU Lightning Complex Fire, which burned nearly 90,000 acres over five weeks. Lofgren is one of several congressional leaders working to introduce legislation that would strengthen the funding of “Understanding, Predicting, and Managing Forest Fires through Robust Research Initiatives”. Her bill would also aim to better integrate science agencies into state forest fire fighting strategies, she said.
Despite San Mateo’s proximity to Silicon Valley, it was the tech capital hug slowly Fire fighting innovation. That changed last year when more and more startups got into the industry and looked for federal and state partners to finance projects.
The US Forest Service is already using Prediction tools to monitor fire weather, fire hazards and fuels and provide information for operations managers, fire fighters and support personnel. However, many of the tools available are based on satellite imagery, which can take hours to transmit and analyze.
“A lot of the current surgeries just aren’t getting situational awareness as often as they’d like,” said Andre Coleman, who is a research team at Pacific Northwest National Laboratory in Richland, Washington.
With initial funding from the U.S. Department of Homeland Security, Coleman helped develop a system called Rapid Analytics for Disaster Response (RADR) in 2014, which uses imaging technology from satellites, aircraft, drones, artificial intelligence, and cloud computing to assess the impact of Natural disasters, including forest fires. An advanced version of the tool called RADR-Fire can reveal the boundaries of forest fires several times a day and link effects and risks to structures, substations and other critical infrastructure in the landscape.
When task force commanders can’t see exactly how big a fire is or exactly where it is burning, they usually instruct aircraft support to take pictures of the fire, Coleman explained. These images are then analyzed by support staff who create a map of the lines of fire. The process can take hours, with Coleman’s tool being able to provide the information in minutes.
“Coordination can be challenging,” he said. “This can help with evacuation routes to understand where search and rescue needs to go.”
The German company OroraTech is also striving to provide real-time fire data, but on a global basis. The Munich-based startup is building a constellation of 100 small satellites, each about the size of a shoebox and equipped with thermal imaging cameras to monitor the planet and to report any fire greater than 10 meters or about 33 within an hour of being ignited Foot.
The first of these nanosatellites will launch in December with the help of Silicon Valley-based Spire, a space-to-cloud data and analytics company, and Space X. 14 more satellites could be launched by 2023.
“Having an overview from above, with the highest possible refresh rate, is the most important part” in order to understand and predict fire behavior, said Björn Stoffers, Co-Founder and Chief Marketing Officer of OroraTech.
“We have seen that each state has its own system and warning tools, and we have seen large discrepancies with these maps, especially because they are out of date,” he said. “We are a lot faster.”
Last year, when the smoke from historic forest fires choked the air for millions of people across the country, OroraTech graduated from the Google Accelerator. Since then, the company has raised $ 7 million in investments to build its global forest fire warning system. Its software platform is already in use in Canada, South America, Africa and Australia, but the big goal is to have partners signed in the United States, Stoffers said.
A brief tutorial of the program revealed a map similar to that from Google Earth, showing not only the location of a fire, but all of the surrounding fire pits, air particles, wind patterns, and cloud cover. Researchers are currently working on adding a lightning strike layer to the existing platform. Users can also measure the distance from plumes of smoke and see in real time which direction dangerous air particles are moving.
OroraTech is just one of several companies using space-based technology to monitor forest fires. San Francisco-based artificial intelligence company Chooch AI uses a system that analyzes satellite images every 10 minutes to identify where new forest fires have broken out. The Associated Press reported. And tech startup Salo Sciences has partnered with Planet, a satellite company founded by NASA scientists, to create a surveillance system called the. to build California Forest Observatory, which uses AI and satellite imagery to create a detailed map of California forest areas to predict and prevent forest fires.
“Especially in California, with Silicon Valley next to these wildfire disasters, you can bet other companies are working to mitigate the effects,” said Stoffers.
In Southern California, Ilkay Altintas and her computer science team at the University of California, San Diego’s WIFIRE Lab, developed a fire map for the region that can be used by commanders and researchers to model fire behavior in real time.
The map uses artificial intelligence and information from previous fires to predict how new fires will burn and to schedule mandatory fires that can help keep forests thinned and healthy, and hence future mega-fires such as those affecting the West has experienced last years to prevent.
“We do science and technology really well in California,” Altintas said. “It’s an evolution of what we already have.”
WIFIRE Lab’s fire map is already being used by local and state agencies in Southern California and has helped create plans to attack the Palisades fire that threatened homes in affluent Los Angeles neighborhoods and the Bobcat fire that came in last year near the historic Mount Wilson Observatory in the Angeles National Forest.