Deep Learning for Rare Energy Infrastructure in Satellite Imagery (2020-2021)
Key stakeholders in electrification planning processes often do not have up-to-date information on energy infrastructure, limiting energy access planning efforts. Additionally, traditional methods of collecting this locational data, such as on-ground surveys, are time-consuming and expensive.
This project is part of a larger effort to develop detailed, up-to-date maps of energy infrastructure by using deep learning techniques that can automatically and rapidly scan massive volumes of remotely sensed data, such as satellite imagery. Deep learning approaches provide a powerful tool for researchers, policy-makers and governments to continuously collect energy systems information and make informed decisions about providing electricity to underserved communities.
The 2020-2021 team demonstrated the effectiveness of using synthetic imagery to enhance the ability of energy infrastructure detection algorithms to automatically map the locations of infrastructure across diverse geographic domains by creating synthetic overhead imagery that supplements real training data.
Synthetic images can be made rapidly and cheaply, and come with automatic labels for the objects. The team created an efficient pipeline for synthetic data generation that can be applied to many different types of energy infrastructure. Experiments focused on wind turbines, but the model can be expanded to other types of infrastructure.
Team members conducted a set of experiments to test the impact of augmenting the training dataset with synthetic data and found that synthetic imagery data significantly improved the model’s performance accuracy and generalizability. Results show that adding synthetic imagery can be particularly useful when training data is limited and when it is cost-prohibitive to collect and label more data for the region of interest.
Fall 2020 – Spring 2021
Synthetic Imagery Aided Geographic Domain Adaptation for Rare Energy Infrastructure Detection in Remotely Sensed Imagery. Wei Hu, Tyler Feldman, Eddy Lin, Jose Luis Moscoso, Yanchen J Ou, Natalie Tarn, Baoyan Ye, Wendy Zhang, Jordan Malof, Kyle Bradbury. Presented at the Tackling Climate Change with Machine Learning Workshop, NeurIPS, online, December 14, 2021.
Estimating Solar PV Capacity and Building Energy Use with Satellite Imagery (presentation by Kyle Bradbury, Energy Data Analytics Symposium, Duke University, December 8-9, 2020)
This Team in the News
See related teams, Creating Artificial Worlds with AI to Improve Energy Access Data (2021-2022) and A Wider Lens on Energy: Adapting Deep Learning Techniques to Inform Energy Access Decisions (2019-2020), and Data+ summer project, Deep Learning for Rare Energy Infrastructure in Satellite Imagery (2020).
Image from Electric Transmission and Distribution Infrastructure Imagery Dataset by Varun Nair, Tamasha Pathirathna, Xiaolan You, Qiwei Han, Kyle Bradbury
- Kyle Bradbury, Pratt School of Engineering-Electrical & Computer Engineering|Energy Initiative
- Jordan Malof, Pratt School of Engineering-Electrical & Computer Engineering
/graduate Team Members
Jose Moscoso, Interdisciplinary Data Science - Masters
/undergraduate Team Members
Tyler Feldman, Electrical & Computer Egr(BSE)
Yanchen Ou, Statistical Science (BS)
Baoyan Ye, Computer Science (BS)
Wendy Zhang, Computer Science (BS)
/yfaculty/staff Team Members
Leslie Collins, Pratt School of Engineering-Electrical & Computer Engineering
T. Robert Fetter, Nicholas Institute for Environmental Policy Solutions
Marc Jeuland, Sanford School of Public Policy
Luana Lima, Nicholas School of the Environment-Environmental Sciences and Policy
Robyn Meeks, Sanford School of Public Policy