Bio

I am a Principal Research Science Manager in the Microsoft AI for Good Research Lab where I co-lead the Geospatial ML research group and focus on tackling large scale applied problems at the intersection of remote sensing and machine learning/computer vision. Generally, I’m interested in research topics that facilitate using remotely sensed data more effectively in conservation, sustainability, and damage response application. For example: self-supervised methods for training deep learning models with large amounts of unlabeled satellite imagery, human-in-the-loop methods for creating and validating modeled layers, and domain adaptation methods for developing models that can generalize over space and time. Similarly, I am also interested in creating open-source tools that facilitate using remotely sensed data in machine learning pipelines – I am a creator/maintainer of the torchgeo library and “satellite imagery labeling tool”.

I graduated from the Georgia Institute of Technology with a PhD in 2020 under the supervision of Bistra Dilkina with a dissertation titled, “Large scale machine learning for geospatial problems in computational sustainability”.

News

March 20th, 2024 – New website!

March 15th, 2024 – We have two papers accepted at IGARSS 2024!

• Seeing the Roads Through the Trees: A Benchmark for Modeling Spatial Dependencies with Aerial Imagery
  Project page / Paper / Code
• Weak Labeling for Cropland Mapping in Africa
  Project page / Paper

March 3rd, 2024 – We have two papers accepted at the Machine Learning for Remote Sensing Workshop at ICLR 2024!

• A Change Detection Reality Check
  Project page / Paper / Code
• Bootstrapping Rare Object Detection in High-Resolution Satellite Imagery
  Project page / Paper

February 2nd, 2024 – New preprint released, Mission Critical–Satellite Data is a Distinct Modality in Machine Learning
Project page / Paper

2023

December 15th, 2023 – I really enjoyed speaking on a panel at the 2023 NeurIPS Workshop on Computational Sustainability: Pitfalls and Promises from Theory to Deployment in New Orleans.

November 30th, 2023 – New preprint, SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
Project page / Paper / Code

September 22nd, 2023 – We have a paper accepted at the NeurIPS 2023 Datasets and Benchmarks track!

• SSL4EO-L: Datasets and Foundation Models for Landsat Imagery
  Project page / Paper / Code

July 26th, 2023 – Our paper, Harnessing AI and robotics in humanitarian assistance and disaster response, in Science Robotics is out!
Project page / Paper

July 22nd, 2023 – We have a paper accepted at the Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop at ICCV

• Rapid Building Damage Assessment Workflow: An Implementation for the 2023 Rolling Fork, Mississippi Tornado Event
  Project page / Paper

June 30th, 2023 – We have a paper accepted at ACM COMPASS

• Poverty Rate Prediction Using Multi-Modal Survey and Earth Observation Data
  Project page / Paper

June 9th, 2023 – New preprint, Open Data on GitHub: Unlocking the Potential of AI
Project page / Paper

May 22nd, 2023 – New preprint alert! Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters
Project page / Paper / Code