An official website of the United States government
Some of the most catastrophic fire events that have occurred in the western US in recent decades, such as the 2018 Camp Fire in California, were ignited by electric utility infrastructure. As wildfires and fire seasons intensify across the western United States, policymakers and utilities alike are working to mitigate the risk of wildfire as it relates to utility infrastructure. We pose the following research question: Is there an association between risk factors such as wildfire hazard potential and social vulnerability, and the inclusion of various strategies in mitigation planning by public or cooperative electric utilities in Washington, such as PSPS provisions and non-expulsion fuse installation? By applying statistical tools including t-tests and logistic regression modeling to test these potential associations, our analysis reveals statistically significant relationships between risk factors and the inclusion of specific wildfire mitigation strategies. We find that the inclusion of PSPS provisions in mitigation planning is significantly and nonlinearly associated with wildfire hazard potential, while social and socioeconomic vulnerability in the utility service area are negatively associated. Additionally, the installation of non-expulsion fuses is negatively associated with socioeconomic vulnerability in service populations. Overall, understanding the factors associated with wildfire mitigation planning can assist policymakers and state agencies in the prioritization of resources and practical support for utilities that may have limited capacity to mitigate wildfire risk.
more »
« less
This content will become publicly available on September 29, 2026
Data-Driven Analysis of Wildfire Post-Event Reports: Patterns, Causes, and Mitigation Strategies
Public Safety Power Shutoffs (PSPS) are a critical yet disruptive wildfire mitigation strategy used by electric utilities to reduce ignition risk during periods of elevated fire danger. However, current PSPS decisions often lack transparency and consistency, prompting the need for data-driven tools to better understand utility behavior. This paper presents a Support Vector Machine (SVM) framework to model and interpret PSPS decision-making using post-event wildfire reports. Forecast-based weather and fire behavior features are used as model inputs to represent decision-relevant variables reported by utilities. The model is calibrated using Platt scaling for probabilistic interpretability and adapted across utilities using importance- weighted domain adaptation to address feature distribution shifts. A post-hoc clustering segments PSPS events into wildfire risk zones based on ignition risk metrics excluded from model train- ing. Results demonstrate that the proposed framework supports interpretable, transferable analysis of PSPS decisions, offering insight into utility practices and informing more transparent de- energization planning.
more »
« less
- Award ID(s):
- 2330582
- PAR ID:
- 10644269
- Publisher / Repository:
- IEEE
- Date Published:
- Page Range / eLocation ID:
- 1 to 7
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Wildfires pose a growing risk to public safety in regions like the western United States, and, historically, electric power systems have ignited some of the most destructive wildfires. To reduce wildfire ignition risks, power system operators preemptively de-energize high-risk power lines during extreme wildfire conditions as part of "Public Safety Power Shutoff" (PSPS) events. While capable of substantially reducing acute wildfire risks, PSPS events can also result in significant amounts of load shedding as the partially de-energized system may not be able to supply all customer demands. In this work, we investigate the extent to which infrastructure investments can support system operations during PSPS events by enabling reduced load shedding and wildfire ignition risk. We consider the installation of grid-scale batteries, solar PV, and line hardening or maintenance measures (e.g., undergrounding or increased vegetation management). Optimally selecting the locations, types, and sizes of these infrastructure investments requires considering the line de-energizations associated with PSPS events. Accordingly, this paper proposes a multi-period optimization formulation that locates and sizes infrastructure investments while simultaneously choosing line de-energizations to minimize wildfire ignition risk and load shedding. The proposed formulation is evaluated using two geolocated test cases along with realistic infrastructure investment parameters and actual wildfire risk data from the US Geological Survey. We evaluate the performance of investment choices by simulating de-energization decisions for the entire 2021 wildfire season with optimized infrastructure placements. With investment decisions varying significantly for different test cases, budgets, and operator priorities, the numerical results demonstrate the proposed formulation's value in tailoring investment choices to different settings.more » « less
-
Quantifying Metrics for Wildfire Ignition Risk from Geographic Data in Power Shutoff Decision-MakingFaults on power lines and other electric equipment are known to cause wildfire ignitions. To mitigate the threat of wildfire ignitions from electric power infrastructure, many utilities preemptively de-energize power lines, which may result in power shutoffs. Data regarding wildfire ignition risks are key inputs for effective planning of power line de-energizations. However, there are multiple ways to formulate risk metrics that spatially aggregate wildfire risk map data, and there are different ways of leveraging this data to make decisions. The key contribution of this paper is to define and compare the results of employing six metrics for quantifying the wildfire ignition risks of power lines from risk maps, considering both threshold- and optimization-based methods for planning power line de-energizations. The numeric results use the California Test System (CATS), a large-scale synthetic grid model with power line corridors accurately representing California infrastructure, in combination with real Wildland Fire Potential Index data for a full year. This is the first application of optimal power shutoff planning on such a large and realistic test case. Our results show that the choice of risk metric significantly impacts the lines that are de-energized and the resulting load shed. We find that the optimization-based method results in significantly less load shed than the threshold-based method while achieving the same risk reduction.more » « less
-
Background Near-term forecasts of fire danger based on predicted surface weather and fuel dryness are widely used to support the decisions of wildfire managers. The incorporation of synoptic-scale upper-air patterns into predictive models may provide additional value in operational forecasting. Aims In this study, we assess the impact of synoptic-scale upper-air patterns on the occurrence of large wildfires and widespread fire outbreaks in the US Pacific Northwest. Additionally, we examine how discrete upper-air map types can augment subregional models of wildfire risk. Methods We assess the statistical relationship between synoptic map types, surface weather and wildfire occurrence. Additionally, we compare subregional fire danger models to identify the predictive value contributed by upper-air map types. Key results We find that these map types explain variation in wildfire occurrence not captured by fire danger indices based on surface weather alone, with specific map types associated with significantly higher expected daily ignition counts in half of the subregions. Conclusions We observe that incorporating upper-air map types enhances the explanatory power of subregional fire danger models. Implications Our approach provides value to operational wildfire management and provides a template for how these methods may be implemented in other regions.more » « less
-
In recent years, the increasing threat of devastating wildfires has underscored the need for effective prescribed fire management. Process-based computer simulations have traditionally been employed to plan prescribed fires for wildfire prevention. However, even simplified process models are too compute-intensive to be used for real-time decision-making. Traditional ML methods used for fire modeling offer computational speedup but struggle with physically inconsistent predictions, biased predictions due to class imbalance, biased estimates for fire spread metrics (e.g., burned area, rate of spread), and limited generalizability in out-of-distribution wind conditions. This paper introduces a novel machine learning (ML) framework that enables rapid emulation of prescribed fires while addressing these concerns. To overcome these challenges, the framework incorporates domain knowledge in the form of physical constraints, a hierarchical modeling structure to capture the interdependence among variables of interest, and also leverages pre-existing source domain data to augment training data and learn the spread of fire more effectively. Notably, improvement in fire metric (e.g., burned area) estimates offered by our framework makes it useful for fire managers, who often rely on these estimates to make decisions about prescribed burn management. Furthermore, our framework exhibits better generalization capabilities than the other ML-based fire modeling methods across diverse wind conditions and ignition patterns.more » « less
