PNNL

Abstract

While power outages caused by tropical cyclones (TCs) already pose a great threat to coastal communities, how---and why---these risks will change in a changing climate is poorly understood. To address this need, we develop a robust machine learning model to capture TC-induced power outage risk. When applied to 900,000 synthetic TCs downscaled from CMIP6-modeled historical and future climate conditions under a strong warming scenario, we find outage risk in the United States is expected to increase broadly by an average of 34% by the end of the century, with some states seeing increases of 60% and higher. Further, we discover that rising rainfall rates will play an increasingly important role in TC-induced power outage risk as the climate changes, explaining more than 50% of the projected change in risk in some regions. These insights are important for guiding decision-makers in their future outage risk investment and mitigation plans.