Near real-time updated wildfire risk map model informed by powerline fault status

This project aims to enhance the pre-fire situational awareness for wildfires caused by power lines. The project represents a collaborative endeavor, uniting investigators from an academic institution and key stakeholder entities. These stakeholders encompass a fire department, the state forestry service, an electric utility, and an insurance company. Our team boasts expertise spanning diverse fields, including power system fault analysis, fire experimentation, ecology and wildfire modeling, wildland fire management, earth science and remote sensing, risk assessment, and emergency and protective services. Furthermore, the team is bolstered by a network of collaborators drawn from targeted stakeholders, featuring another electric utility company, fire departments, and state and federal agencies involved in fire management, all of whom will contribute their valuable support to the project. Failure in electrical infrastructure has regularly been ranked among the top identified causes of wildfires, and thus, effective wildfire risk assessment will increasingly depend upon systematically understanding the triggering mechanism of wildfires caused by electrical infrastructure. This project will develop an operational approach for determining the risk of electrical wildfires and updating wildfire danger rating in near-real time, via integration of ignition source data and higher resolution of fire danger biophysical factors (fuel conditions, fire weather, vegetation, and topography), all within a geospatial framework afforded by fine-resolution earth observing data. To this end, the project will 1) evolve the wildland fire potential map to satisfy the level of details needed for risk assessment of electrical wildfire. In particular, one of the novelties of this project is to improve existing fuel models by using fine spatial and temporal resolution multispectral data from PlanetScope CubeSats. Simultaneously, this project seeks to create novel AI-based fire danger indices that has the capacity to incorporate spatial information of fuel types as well as other high-resolution fuel properties, such as vegetation biomass, greenness, etc., 2) identify the ignition probability of vegetation electric faults. Another novelty in this project is to combine experimental fire ignition tests with power-hardware-in-the-loop grid simulation to understand the ignition dynamics and propagation patterns of ignition and non-ignition electrical faults across the gird under different ignition and environmental conditions. The unique and valuable dataset generated as part of these experiments will be used to identify the ignition probability as a new data product, leveraging machine learning techniques, and finally 3) advance wildfire risk mapping through an operational field demonstration, in collaboration with project collaborators, including utility companies and forest services, contributing to the FireSense field campaign mission. This project advances biophysical data precision via fine-resolution PlanetScope data and deep learning, aligning with NASA's "Science 2020-2024: A Vision for Scientific Excellence" and "Decadal Survey.", emphasizing diverse data integration for wildfire solutions. The use of advanced machine learning on the uniquely generated vegetation electric faults dataset to obtain ignition probability and development of a custom wildfire potential model will help to fulfill NASA's Earth Science Division's mission to enhance US wildfire prediction and management via novel observations. The field demonstration in an operational environment aims to aid first responders with rapid, precise wildfire threat intel, reducing risks and costs, aligning with airborne field campaigns and the capstone mission, and NASA's 2022 Strategic Plan for innovation in national challenges.

Enhances the capabilities for existing science instruments for monitoring pre-fire, active-fire, and post-fire situations, reduces the power and mass of these instruments, and enables unprecedented observations in support of wildfire science through distributed observing systems and the information technologies needed for their support.

This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.