I am a HAI (Human-Centered AI) Postdoctoral Fellow at Stanford University. My research focuses on developing machine learning and other data-driven approaches to enable large-scale mapping, monitoring, and modeling of energy systems, infrastructure networks, and the urban environment. The goal of my research is to provide algorithms, data, and actionable insights for decision making (e.g., urban planning, policymaking) to enable effective, equitable, and human-centered transitions towards decarbonization and climate resilience.

My current research topics include: distributed energy resources, infrastructure networks (especially electricity distribution networks), and their interactions with other components of natural/built environments as well as the changing climate. More recently, I am interested in developing machine learning foundation models for mapping, modeling, and analyzing such interactions and for informing decision making.

Previously, I obtained my PhD degree in Civil and Environmental Engineering with minor in Computer Science at Stanford, co-advised by Prof. Ram Rajagopal and Prof. Arun Majumdar. I obtained my M.S. degree in Mechanical Engineering also from Stanford, and my Bachelor’s degree in Energy, Power System and Automation from Tsinghua University.

Email: zhecheng (at) stanford (dot) edu

Recent News

• 03/28/2024 Our paper on the potential of non-residential solar has been published in Nature Energy and covered by many media outlets (e.g., Stanford News, Tech Xplore).

• 02/08/2024 Invited talk at the Solar Colloquium hosted by DOE Solar Energy Technologies Office (SETO).

• 12/19/2023 We published SkyScript, a large and semantically diverse remote sensing image-text dataset for developing and evaluating vision-language models for remote sensing imagery. Its corresponding paper is accepted by AAAI 2024.

• 11/08/2023 Invited talk “From Raw Pixels to Actionable Insights” at Swissnex.

• 11/01/2023 Presented the research outcomes of our DOE-funded project at the DOE workshop: solar applications of AI/ML, hosted by the DOE Solar Energy Technologies Office (SETO).

• 10/18/2023 Presented research on AI for tackling climate change to Mr. Bill Gates and the Breakthrough Energy leadership.

• 10/11/2023 Invited to visit PG&E and give a talk.

• 08/17/2023 Our paper on fine-grained distribution grid mapping has been published in Nature Communications.

• 08/07/2023 Our paper on improving grid resilience to wildfires has been published in Nature Energy (featured as cover) and covered by many media outlets (e.g., Stanford News, The Hill).