CRWN.ai has developed technology aimed at enhancing wildfire prediction and prevention on transmission lines. Using receiving devices, CRWN can monitor entire sections of remote transmission lines providing real-time data, without the need for an operator.
Globally, utility-caused ignitions remain a significant contributor to catastrophic wildfires, leading to substantial GHG emissions, ecosystem loss, and economic damage. Utilities and wildfire managers currently rely on periodic manual inspections, reactive maintenance, and broad mitigation measures, which are costly, disruptive, and insufficient given climate-driven increases in wildfire frequency and severity. CRWN’s approach addresses this acute market need by enabling earlier, more precise intervention, shifting wildfire management upstream from suppression to prevention.
Predicting wildfire ignition risks on power lines using edge AI to detect failures before they spark fires.
CRWN’s edge-based wildfire ignition prediction system uses multi-modal electrical sensing and on-device machine learning to detect early indicators of insulator degradation and abnormal electrical activity—known precursors to wildfire ignitions—that are not currently monitored continuously or at scale. NorthX funding is critical to advancing CRWN’s technology to a deployment-ready prediction system through scaled field data collection, systematic refinement of ML models, and independent validation. By preventing wildfires, the project avoids significant GHG emissions while also delivering critical co-benefits such as reducing forest loss, improving air quality, and protecting watersheds.
