ATS performed high-powered data analysis to measure the wildfire risk in a customer’s service territory, along with quantifying the effectiveness of various mitigations. ATS built a cutting edge analysis tool bench that conveys these results for various classes of users, from executives to asset managers. Additionally, ATS provides recommendations for future wildfire mitigation investments that maximally reduce the risk at the lowest cost. Launch this tool to see for yourself the power of analytics combined with visualization.
ATS’ Wildfire Risk Analysis and Management (AWRAM) Platform
Launch ATS’ Wildfire Risk Analysis and Management (AWRAM) Platform, which utilizes cutting edge machine learning and artificial intelligence methods to assess the wildfire risk of electric utility service territories, along with providing detailed mitigation effectiveness analyses for an extensive array of mitigation strategies. This platform serves all levels of management, from executives to wildfire managers, to evaluate the current state of wildfire risk and to direct future wildfire mitigation investments with the greatest risk spend efficiency possible. Explore the capability for yourself and contact us to see how AWRAM can help your organization perform wildfire management more effectively.
Operational Summary
Where does risk concentrate?
Recorded from the current public AWRAM demoACME Utility · Synthetic data
See the network, compare risk by circuit and investigate the assets behind the overview.
Stochastic Wildfire Impact Model (SWIM) is a cutting-edge wildfire modeling tool that uses epidemic-inspired stochastic simulations to predict how wildfires are likely to spread across the landscape, based on real-world environmental conditions.
Recorded SWIM scenario · Berkeley · 21 October 2026
SWIM success requires predictions that satisfy two conditions:
SWIM’s 90th percentile predicted wildfire perimeter encompasses a wildfire’s actual final perimeter.
SWIM's predicted wildfire perimeter exceeds a shape geometry similarity threshold with respect to the actual final perimeter.
Condition (1) mandates that SWIM predict the correct burn areas, while condition (2) serves as a control mechanism to prevent arbitrarily large estimations.
Together, SWIM is judged on the accuracy and usefulness of its predictions.
SWIM accuracy is measured as the proportion of times both conditions are satisfied.
