CSE Faculty Candidate Seminar - Zhecheng Wang

Name: Zhecheng Wang, Postdoctoral Scholar from Stanford University

Date: Tuesday, January 28, 2024 at 11:00 am

Location: Scheller College of Business, Room 101 (Google Maps link)

Link: The recording of this in-person seminar will be uploaded to CSE's MediaSpace

Coffee, drinks, and snacks provided!

Title: AI-Enabled Computational Sustainability for Human-Centered Decarbonization and Climate Adaptation

Abstract: Data and information are critical for shaping a sustainable, climate-resilient future. Policymakers need granular spatiotemporal data on renewable energy adoption to design effective financial incentives. Infrastructure planners require detailed information about infrastructure vulnerabilities to prioritize upgrades for disaster risk mitigation. Individuals depend on timely situational awareness in the face of disasters. Unfortunately, much of this information is fragmented in “information silos”. In this talk, I will introduce my work on “AI-Enabled Sustainability Informatics”—developing label-efficient, domain-aware AI models to bridge the information gaps, transforming large-scale, unstructured geospatial data (e.g., remote sensing images) into actionable sustainability insights. 

On the AI front, I will present my work on (1) developing task-specific models that address the label scarcity and multi-modal fusion challenges for mapping distributed energy infrastructures (e.g., solar PVs, electricity distribution grid); and (2) creating task-agnostic, multi-modal AI foundation models for efficiently searching the Earth at scale. On the front of knowledge discovery for sustainability, I will present how I utilize these new models to build the first and, by far, the most comprehensive solar PV database in the U.S., advance our understanding of solar PV adoption and electrical grid vulnerability to wildfires, and generate actionable insights for designing effective solar PV incentives and affordable infrastructure upgrade plans. I will conclude this talk by sharing my vision on advancing computational sustainability to support human-centered climate adaptation.

Bio: Zhecheng Wang is a postdoctoral scholar at Stanford University. He received his Ph.D. degree in Civil and Environmental Engineering and a Ph.D. minor degree in Computer Science from Stanford University. His research centers on AI-enabled sustainability informatics—combining problem-driven AI innovations with domain knowledge to transform large-scale, unstructured geospatial data into sustainability insights. The goal is to create new knowledge and AI-enabled solutions for accelerating decarbonization, improving disaster resilience, and ensuring equity. His research outcomes have been published in leading multi-disciplinary journals and AI conferences (e.g., Nature Energy, Joule, Nature Communications, AAAI), covered by many media outlets (e.g., MIT Technology Review, The Hill), and translated into a startup for advancing sustainable AI called GridCARE. He is a recipient of the Human-Centered AI Postdoctoral Fellowship and the Stanford Interdisciplinary Graduate Fellowship.