Chenhui Zhang
PhD Student, MIT Institute for Data, Systems, and Society
I am a second-year graduate student at the MIT Institute for Data, Systems, and Society (IDSS), advised by Prof. Sherrie Wang. I’m part of the Laboratory for Information and Decision Systems and the Earth Intelligence Lab, where we try to democratize the access to geospatial machine learning and better understand our planet.
Before that, I obtained my B.S. degree in Computer Science at the University of Illinois Urbana-Champaign, where I was fortunate to be advised by Prof. Bo Li, Prof. Kaiyu Guan, and Prof. Sheng Wang. I also worked closely with Prof. Zhangyang “Atlas” Wang.
My long-term research agenda aims to build accurate, efficient, trustworthy, and democratized machine learning systems for climate and geospatial science. In pursuit of this objective, I leverage the advancements in vision/language pretraining, benchmark design, model auditing, and domain knowledge augmentation, to improve the machine learning systems for geospatial data, in particular aerial and satellite remote sensing images. By tailoring these methodologies to the unique challenges of geospatial data, I hope we can address the pressing issues in sustainable agriculture, land management, and agroecosystem modeling, thereby contributing to our collective efforts to mitigate and adapt to climate change.
news
Apr 22, 2024 | I will be attending ICLR 2024. See you in Vienna! |
---|---|
Feb 01, 2024 | New preprint on a comprehensive benchmark of instruction-following vision-language models on Earth observation data. |
Dec 11, 2023 | Our paper DecodingTrust received the Outstanding Paper Award at NeurIPs 2023! |
Oct 20, 2023 | I’m grateful to receive the 2023 Fiddler Innovation Fellowship from the National Center for Supercomputing Applications (NCSA) for our project, “Cross-scale Sensing and Deep Learning for Sustainable Agriculture.” |
Sep 06, 2023 | I’m honored to receive the Michael Hammer Fellowship to support my study MIT. |
selected publications
- Cross-scale Sensing of Field-Level Crop Residue Cover: Integrating Field Photos, Airborne Hyperspectral Imaging, and Satellite DataRemote Sensing of Environment, 2023