Sherrie Wang

Assistant Professor, MIT MechE, IDSS, and LIDS

prof_pic.jpg

We are hiring PhD students and postdocs to start in 2024-25! Please visit our lab website for more details.

I am PI of the Earth Intelligence Lab at MIT, where our research uses novel data and computational algorithms to monitor our planet and enable sustainable development. Our focus is on improving agricultural management and mitigating climate change, especially in low- or middle-income regions of the world. To this end, we frequently use satellite imagery, crowdsourced data, LiDAR, and other spatial data. Due to the scarcity of ground truth data in these regions and the noisiness of real-world data in general, our methodological work is geared toward developing machine learning methods that work well with these constraints.

Prior to MIT, I was a Ciriacy-Wantrup Postdoctoral Fellow at UC Berkeley, hosted by Solomon Hsiang and the Global Policy Lab. In 2021, I obtained my PhD in Computational and Mathematical Engineering from Stanford University, where I was advised by David Lobell and benefited from mentors at the Center on Food Security and the Environment and the Sustainability and AI Lab.

You can find a copy of my CV here.

news

May 11, 2024 I gave a keynote at the ICLR ML4RS Workshop. Our paper on benchmarking vision-language models on Earth observation data, led by PhD student Chenhui Zhang, received the Best Paper Award at the workshop!
Feb 15, 2024 Our lab’s work mapping crops in Thailand, led by PhD student Jordi Laguarta, was featured on MIT News and MIT’s front page!
Jan 25, 2024 We mapped, for the first time, which water bodies are regulated by the Clean Water Act in the US – the paper is now published in Science.

selected publications

  1. Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data
    Chenhui Zhang, and Sherrie Wang
    2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024
  2. Combining deep learning and street view imagery to map smallholder crop types
    Jordi Laguarta, Thomas Friedel, and Sherrie Wang
    Proceedings of the AAAI Conference on Artificial Intelligence, 2024
  3. Machine learning predicts which rivers, streams, and wetlands the Clean Water Act regulates
    Simon Greenhill, Hannah Druckenmiller*, Sherrie Wang*, and 6 more authors
    Science, 2024
  4. Current benefits of wildfire smoke for yields in the US Midwest may dissipate by 2050
    A. Patrick Behrer, and Sherrie Wang
    Environmental Research Letters, 2024
  5. Unlocking large-scale crop field delineation in smallholder farming systems with transfer learning and weak supervision
    Sherrie Wang, Francois Waldner, and David B. Lobell
    Remote Sensing, 2022
  6. SustainBench: Benchmarks for monitoring the Sustainable Development Goals with machine learning
    Christopher Yeh*, Chenlin Meng*, Sherrie Wang*, and 7 more authors
    NeurIPS Datasets and Benchmarks Track, 2021
  7. Combining GEDI and Sentinel-2 for wall-to-wall mapping of tall and short crops
    Stefania Di Tommaso, Sherrie Wang, and David B. Lobell
    Environmental Research Letters, 2021
  8. Mapping crop types in southeast India with smartphone crowdsourcing and deep learning
    Sherrie Wang, Stefania Di Tommaso, Joey Faulkner, and 4 more authors
    Remote Sensing, 2020
  9. Meta-learning for few-shot land cover classification
    Marc Rußwurm*, Sherrie Wang*, Marco Körner, and 1 more author
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020
  10. Tile2Vec: Unsupervised representation learning for spatially distributed data
    Neal Jean, Sherrie Wang, Anshul Samar, and 3 more authors
    Proceedings of the AAAI Conference on Artificial Intelligence, 2019