Predicting Electricity Infrastructure Induced Wildfire Risk in California

TL;DR

This study develops machine learning risk models to predict wildfire ignition and wire-down events caused by electricity infrastructure in California, highlighting the importance of weather, vegetation, and infrastructure features.

Contribution

It introduces effective risk prediction models using HGB with data imbalance management, and identifies key features influencing wildfire risk from electrical infrastructure.

Findings

HGB with under-sampling achieves AUC of 0.776 and 0.824.

Vegetation features are crucial for ignition risk; weather features dominate wire-down risk.

Infrastructure features add small but meaningful improvements.

Abstract

This paper examines the use of risk models to predict the timing and location of wildfires caused by electricity infrastructure. Our data include historical ignition and wire-down points triggered by grid infrastructure collected between 2015 to 2019 in Pacific Gas & Electricity territory along with various weather, vegetation, and very high resolution data on grid infrastructure including location, age, materials. With these data we explore a range of machine learning methods and strategies to manage training data imbalance. The best area under the receiver operating characteristic we obtain is 0.776 for distribution feeder ignitions and 0.824 for transmission line wire-down events, both using the histogram-based gradient boosting tree algorithm (HGB) with under-sampling. We then use these models to identify which information provides the most predictive value. After line length, we find that weather and vegetation features dominate the list of top important features for ignition or wire-down risk. Distribution ignition models show more dependence on slow-varying vegetation variables such as burn index, energy release content, and tree height, whereas transmission wire-down models rely more on primary weather variables such as wind speed and precipitation. These results point to the importance of improved vegetation modeling for feeder ignition risk models, and improved weather forecasting for transmission wire-down models. We observe that infrastructure features make small but meaningful improvements to risk model predictive power.