Artificial Intelligence to Improve Proactive and Reactive Wildfire Response

Triage resources with real-time insights of fire perimeter from aerial full-motion video

Richard Purcell
Nov 5, 2019 · 4 min read
Image for post
Image for post

Climate change has increased the frequency and intensity of wildfires in recent years. With the increased threat of wildfires, firefighters and other first responders need improved or new tools to better understand the extent and behavior of wildfires so that they may plan their response accordingly. This year, CrowdAI was selected as the exclusive technology partner with California Air National Guard and Joint Artificial Intelligence Center (JAIC — a division of the US Department of Defense) to build a custom solution to help stop the spread of wildfires.

Before CrowdAI, analysts would manually comb over hours of video and point-and-click to draw a fire perimeter, often while working around-the-clock shifts. Depending on the size and extent of the fire, this process can take hours to complete — even for just a single section of the fire perimeter. Wildfires can sometimes spread as fast as 10 mph, so by the time an analyst can manually pinpoint the perimeter, the fire has spread.

This is where automation powered by CrowdAI can provide a force multiplier.

The AI-enabled solution involves flying unmanned aircraft equipped with Full Motion Video sensors over the wildfire regions. The AI computer vision algorithm automatically analyzes the video data, detects regions with active wildfires, and provides near real-time fire location updates to a digital map application on first responders’ mobile devices.

Speed and accuracy are both critical to response efforts. Machine learning algorithms and a more automated process can be used to provide first responders with more accurate information about the fire perimeter more often and with higher accuracy. Near-real-time updates of the fire perimeter are needed to inform the public and to coordinate response efforts. Accuracy is also important, especially as it relates to the precise location of the fire perimeter.

A detailed peer-reviewed paper on this use case can be read here.

CrowdAI created a similar solution in the aftermath of the Camp Fire in California. CrowdAI used imagery from after the fire to detect structures, comparing those structures to imagery from before the fire.

Insurers are also adopting this technology to target high-risk insured assets in fire hazard severity zones and proactively contact the homeowner to remove vegetation within close proximity of their property.

“CrowdAI is blazing a path for insurance carriers to follow. These advancements mark the beginning of a new era as carriers race to integrate artificial intelligence into underwriting and claims processes. There is market share to be had by savvy insurers who will soon be able to tap into this information in order to send evacuation routes and safety checklists to customers in the path of a wildfire.“

Tammy Nichols Schwartz, CEO of Black Swan Analytics and former Director of Homeowners Product Management at Farmers Insurance

Unfortunately, this will likely not be the last time this technology is used to reduce the risk of loss.

In the 1970s, the average length of the wildfire season was five months. Today, it lasts more than seven. 2017 was the costliest year on record for insurers, with total U.S. wildfire peril totaling $16bn in losses.

As of October 27, 2019, over 6,100 fires have been recorded so far this calendar year, according to CAL FIRE and the US Forest Service, totaling an estimated 198,800 acres of burned land. Fire behavioral experts and climatologists forecast that heavy rains from earlier in the year have produced an excess of vegetation that may become a tinder box later in the year as the fire season gets underway.

CrowdAI is committed to building technology that is used to make the world a better place. In keeping with that commitment, CrowdAI works on pro bono projects with nonprofits administering disaster relief.

Organizations send CrowdAI individual addresses of their assets and CrowdAI sends back relevant pre and post-disaster insights.

Learn more by emailing and visiting

About CrowdAI

CrowdAI’s mission is to empower organizations to make better operational decisions by forecasting changes in the physical world.

Extract a wide range of assets and produce predictive insights whenever imagery is available using proprietary computer vision deep learning technology.

CrowdAI is built by engineers from Google Maps and IBM Watson, backed by Y Combinator, and trusted by brands encompassing insurance, telecommunications, utility, oil & gas, ride-sharing, government agencies, location intelligence, and more.

CrowdAI, Inc.

Predict the Future of the Physical World

Medium is an open platform where 170 million readers come to find insightful and dynamic thinking. Here, expert and undiscovered voices alike dive into the heart of any topic and bring new ideas to the surface. Learn more

Follow the writers, publications, and topics that matter to you, and you’ll see them on your homepage and in your inbox. Explore

If you have a story to tell, knowledge to share, or a perspective to offer — welcome home. It’s easy and free to post your thinking on any topic. Write on Medium

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store