As climate change intensifies, there is an increasing exposure of electricity distribution grids to the threat of climate-induced extreme events, such as wildfires. What factors shape the grid vulnerability to wildfires and how to adapt grids to the  increasing wildfire threat in an affordable and equitable manner remain unknown. To answer these questions, spatially resolved information about distribution grids and their wildfire risk exposure is critically needed but largely unavailable. In this seminar, I will start by talking about how I filled such an information gap with a newly developed paradigm called "AI-Enabled Infrastructure Informatics". Then, I will discuss the new insights drawn from the spatially resolved information, including the identification of (1) non-uniform vulnerabilities of distribution grids to wildfires as well as the underlying driving factors, and (2) a policy approach for making power line undergrounding - an effective but expensive adaptation approach - equitably affordable to communities at all income levels. This study demonstrates the potential of AI to understand the climate-infrastructure nexus and to inform policy making for improving climate resilience and ensuring equity.

Speaker Bio

Zhecheng Wang is a postdoctoral fellow at Stanford University, affiliated with the Department of Civil and Environmental Engineering and the Institute for Human-Centered AI. He received his PhD degree in Civil and Environmental Engineering with a minor in Computer Science, as well as a M.S. degree in Mechanical Engineering, from Stanford University. His research focuses on AI-enabled infrastructure informatics, with the integration of AI and domain knowledge to study the nexus of infrastructure systems (especially energy infrastructures), climate-induced risks, and human factors. He is a recipient of the Human-Centered AI Postdoctoral Fellowship and the Stanford Interdisciplinary Graduate Fellowship.