Zhongying (Stephen) Wang

Postdoctoral Associate @ Earth Intelligence Lab, MIT

prof_pic_2026.jpg

Hi there! 😃

I’m Zhongying, a Postdoctoral Associate in the Earth Intelligence Lab at MIT (Department of Mechanical Engineering), working with Prof. Sherrie Wang. I build geospatial AI for Earth observation and environmental health. My current work includes pretrained location encoders and geospatial foundation models, soil organic carbon mapping from hyperspectral remote sensing, and high-resolution air pollution estimation from satellite, ground, and simulation data.

I received my PhD in Geography from the University of Colorado Boulder in 2026, advised by Prof. Morteza Karimzadeh in the GeoHAI Lab. Before that, I earned an MS in Spatial Data Science at the University of Southern California and a BS in Geographic Science at East China Normal University.

news

Aug 15, 2026 New preprint: SLED: Scalable Location Encoding via Distillation, led by Kevin Lane.
Jul 1, 2026 Joined the Earth Intelligence Lab at MIT as a Postdoctoral Associate with Prof. Sherrie Wang. :sparkles:
Jun 4, 2026 Presented our Proxy Consistency Loss paper at the CVPR 2026 EarthVision Workshop in Denver.
May 26, 2026 Released our 1 km daily PM2.5 dataset for the contiguous US (2005–2021) on Zenodo. :earth_americas:
May 1, 2026 Completed my PhD in Geography at CU Boulder! :mortar_board:
Apr 3, 2023 Aerosol Optical Depth Imputation work is accepted to IGARSS 2023! :sparkles:
Mar 26, 2023 Presented PM2.5 estimation work at AAG 2023 in Denver.

selected publications

  1. CVPRW
    pcl_embeddings.gif
    A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders
    Zhongying Wang, Kevin Lane, Levi Cai, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026
    arXiv HTML
  2. arXiv
    SLED: Scalable Location Encoding via Distillation
    Kevin Lane, Zhongying Wang, Esther Rolf, and 1 more author
    arXiv preprint arXiv:2608.06612, 2026
    Submitted to AAAI 2027
    arXiv HTML
  3. SciData
    The United States COVID-19 Forecast Hub Dataset
    Estee Y. Cramer, Yuxin Huang, Yijin Wang, and 5 more authors
    Scientific Data, 2022
  4. SIGSPATIAL
    Sensitivity Analysis for COVID-19 Epidemiological Models Within a Geographic Framework
    Zhongying Wang, and Orhun Aydin
    In Proceedings of the 1st ACM SIGSPATIAL International Workshop on Modeling and Understanding the Spread of COVID-19, 2020
  5. IJGIS
    wang2025integrating.jpg
    Integrating Spatiotemporal Features in LSTM for Spatially Informed COVID-19 Hospitalization Forecasting
    Zhongying Wang, Thoai D. Ngo, Hamidreza Zoraghein, and 2 more authors
    International Journal of Geographical Information Science, 2025
    Advance online publication
  6. RS
    wang2025pm25.jpg
    High-Resolution Estimation of Daily PM2.5 Levels in the Contiguous US Using Bi-LSTM with Attention
    Zhongying Wang, James L. Crooks, Elizabeth A. Regan, and 1 more author
    Remote Sensing, 2025
    Code Website
  7. GISciRS
    karimzadeh2025performance.png
    Performance and Generalizability Impacts of Incorporating Geolocation into Deep Learning for Dynamic PM2.5 Estimation
    Morteza Karimzadeh, Zhongying Wang, and James L. Crooks
    GIScience and Remote Sensing, 2025
    In press; also available as arXiv:2505.18461
  8. medRxiv
    Respiratory Exacerbations Increase with Chronic PM2.5 Exposure in Current and Former Smokers
    James L. Crooks, Zhongying Wang, Morteza Karimzadeh, and 6 more authors
    medRxiv, 2025
    medRxiv preprint