Satellite image

Energy Resource Assessment


The team built a ground truth dataset comprising satellite images, building footprints, and building heights (LIDAR) of 40,000+ buildings, along with road annotations. This dataset can be used to train computer vision algorithms to determine a building’s volume from an image, and is significant contribution to the broader research community with applications in urban planning, civil emergency mitigation and human population estimation.

Project Results

Download the Executive Summary (PDF)

Faculty Sponsors

  • Richard Newell, Director, the Energy Initiative at Duke
  • Leslie Collins, Duke University Electrical and Computer Engineering
  • Timothy Johnson, Energy and the Environment
  • Kyle Bradbury, Managing Director, Energy Data Analytics Lab

Project Managers


  • Benjamin Brigman, Columbia University Electrical and Computer Engineering
  • Sophia Park, Duke University Biomedical Engineering

Related People


Electrical and Computer Engineering


Environmental Management

Computer Science, Statistics

Related News

The Council on Foreign Relations released Digital Decarbonization, an anthology of 13 experts’ perspectives on how the unfolding of the digital revolution could help to drive a transition toward clean energy. The volume...