Energy Data Analytics Lab (2016-2017)


There are increasingly many sources of high-frequency energy data in the modern world. Examples include electric utility smart meters capable of providing minute-by-minute data from millions of buildings, power markets that track real-time energy prices across the nation, thermostat and control system sensors that produce a rich stream of building operation data and satellite and other aerial platforms that produce imagery of energy systems worldwide. Despite the availability of unprecedented amounts of data, we are only beginning to explore how we may use this information to improve the ways in which we supply and use energy.

This project will focus on twin aspects of this challenge: developing analytical methods to learn from these emerging data sources; and assessing needs for the products of this learning.

Project Description

This project team will be part of Duke’s Energy Data Analytics Lab and will further its mission to develop and apply data analytics tools to transform diverse energy data into innovative solutions for increasing the reliability, security, resilience and environmental sustainability of energy systems, while reducing costs. 

This project builds on the work of previous Bass Connections and Data+ teams that developed data sets and techniques for automating the identification of distributed rooftop solar photovoltaics in satellite imagery data for improving national estimates of solar photovoltaic capacity. We will explore assessment methods for other energy resources and infrastructure that may include residential and commercial buildings (for quantifying energy efficiency); transmission, distribution lines and substations (for analyzing grid resilience); and wind turbines, oil tanks, coal piles and natural gas shipping vessels (for estimating resource availability). We will assess these other areas of research for their value through discussions with energy experts in the field and/or in consultation with U.S. State and Federal agencies.

Anticipated Outcomes

Possible outcomes include creating new techniques for energy resource and infrastructure assessment through satellite imagery; developing insights from analyses of satellite imagery data; publishing a paper on methods, findings or data; and/or engaging state and federal government agencies on techniques or findings developed.


Fall 2016 – Spring 2017

Team Outcomes to Date

Automated Building Energy Consumption Estimation from Aerial Imagery (Mitchell Kim, Sebastian Lin, Sophia Park, Eric Peshkin, Nikhil Vanderklaauw, Yue Xi, Samit Sura, Hoël Wiesner, Kyle Bradbury, Leslie Collins, Timothy Johnson)

This Team in the News

Duke Student Shares Energy Data Analytics Lab Research with North Carolina Legislators

Student Laurels and Honors for 2017

Students Present Their Research and Learn from Each Other at the Bass Connections Showcase

Students Share Research Journeys at Bass Connections Showcase

Bass Connections Poster Awards Highlight Neurosurgery and Energy Research

Real Problems, Real Teamwork

Reflections on Mentoring from Bass Connections Graduate Students

See earlier related team, Energy Data Analytics Lab (2015-2016) (also see a Data+ team from Summer 2015).


Faculty/Staff Team Members

Kyle Bradbury, Duke University Energy Initiative*
Leslie Collins, Pratt School - Electrical & Computer Engineering*
Timothy Johnson, Nicholas School - Earth & Ocean Sciences*
Guillermo Sapiro, Pratt School - Electrical & Computer Engineering

Graduate Team Members

Samit Sura, MA in Economics
Hoel Wiesner, Nicholas School - Master of Environmental Mgmt.

Undergraduate Team Members

Min Chul (Mitchell) Kim, Electrical & Computer Engineering, Statistical Science (AB2)
Jer Sheng (Sebastian) Lin, Mathematics (AB), Physics (AB2)
Jee Hye (Sophia) Park, Electrical & Computer Engineering
Eric Peshkin, Mathematics (BS)
Nikhil Vanderklaauw, Mechanical Engineering
Yue (Joyce) Xi, Electrical & Computer Engineering, Computer Science (AB2)

Community Team Members

Richard Newell, Resources for the Future

* denotes team leader