Energy Data Analytics Lab: Electricity Access in Developing Countries from Aerial Imagery (2017-2018)


Access to reliable electricity is strongly correlated with economic prosperity and health. Over 15% of humanity has no access to it at all, and far more have access only to intermittent supplies that preclude most productive energy uses. According to the World Bank, in some nations like South Sudan, Chad and Burundi, fewer than 7% of people have any access at all.

Research on sustainable energy transitions being conducted at Duke and elsewhere is trying to better understand the drivers and impacts of electrification on health, land use, the environment and the local economy. However, current methods for assessing access rely almost completely on household surveys or highly aggregated (e.g., national-level) data sources.

Project Description

This Bass Connections project will develop means to evaluate electricity access in developing countries through machine learning techniques applied to aerial imagery data. This work will provide the needed basis for research groups at Duke and elsewhere interested in understanding the path to electrification in underserved areas.

The project team will fill critical gaps by piloting and then applying automated algorithms for generating spatially-disaggregated data on electricity access in developing countries using aerial imagery. The team will develop new machine learning techniques to extract information on energy infrastructure and consumption using high-resolution aerial imagery.

In high-resolution aerial imagery, power transmission and distribution lines are often visible to the naked eye, and the poles and pylons supporting them and substations linking them are clearly visible. Utilizing the information from these images, the team will develop estimate network topologies of electric power lines. Additionally, imagery of lights at night can provide indicators of energy consumption.

The initial phase of this work will involve a related Data+ summer research project, which will launch the larger Bass Connections project by compiling, curating and publishing an initial ground-truthed dataset. The Bass Connections team will then use this as the basis of its work.

Anticipated Outcomes

Dataset of fully-identified electricity infrastructure in aerial imagery; published version of the dataset made available on the data repository Figshare; collection of code implementing the algorithm for identifying the power system infrastructure; conference or journal paper based on the methods developed and/or the dataset

Student Opportunities

The goals of this experience are to train students in both the subject matter and tools they need to succeed in advancing cutting-edge energy data analytics research, while empowering students to develop as effective team members and learn project management, organizational and communication skills. An intensive two-semester schedule includes twice-weekly meetings with team leaders. The year will begin with team leader-guided content dissemination and transition to student-facilitated team meetings with weekly status updates.

At the end of this project experience, students should be able to:

  • Recognize improvements in their verbal and written communication skills for technical and nontechnical information
  • Engage in team-based problem solving and be empowered to take ownerships of project management and organization
  • Describe the relationship between access to electricity, economic well-being, human health, land use and environmental impacts
  • Apply a formalized research process including problem definition, literature review, research project design, execution, analysis and interpretation
  • Apply advanced data analytics tools to energy data, including computational tools such as Matlab
  • Explain the fundamentals of machine learning, pattern recognition and/or big data algorithms
  • Implement and understand the implications of results from experimental research techniques.

The team will include approximately six students, a mix of undergraduates and graduate students, with interest in advanced data analysis techniques, energy systems and energy access and with some experience in quantitative methods.

  • Project manager (1 position): This position is a graduate-level opportunity for a student to take on a leadership role. The project manager will collaborate with faculty, staff and the team to develop and refine the scope of the project; track progress toward milestones and report on that progress; manage team resources and work with the team on task management, operations and communications.
  • Technical manager (1 position): This position is a graduate-level or senior undergraduate opportunity for a student to take on a role guiding the technical development of a data science project. The ideal candidate will be highly organized, have technical expertise in either machine learning, statistics, engineering, econometrics or another technical discipline and an interest in collaborating closely with students across disciplines and providing technical leadership, management of computational infrastructure and mentorship.
  • Research associate (4 positions): This position is open to undergraduate and graduate students interested in advanced data analysis techniques and energy systems. Research associates form the core of the team and work closely together and with faculty and staff toward achieving project goals. A willingness to learn, interest in working on a team and a strong work ethic are required. Students with some experience in quantitative methods are preferred, but not required. The disciplines that may be most interested are engineering, economics, computer science, environmental science, energy, mathematics, and statistics; however, interested students outside of those disciplines are welcome and encouraged to apply.

Team members are expected to enroll for full credit for two semesters, and to devote at least 10 hours per week. They will transition into team-specific roles identified by their own strengths and interests, which may include scribe, scheduler, meeting facilitator, task manager, technical lead and other project-specific roles.

Students will receive a grade and course credit. This grade will be based on peer assessment, team and individual reports, reading assessments and a final presentation and poster each semester. Additionally, students will have required readings before each meeting and a team-based reading assessment at the start of each meeting. These readings will begin from textbooks, but will transition to journal papers gradually throughout the year, giving students important content and familiarizing them with best practices on research and cutting-edge research methods.

Students may be interested in a related Data+ summer project, Electricity Access in Developing Countries from Aerial Imagery (May 22 – July 28).


Fall 2017 – Spring 2018

  • Fall 2017: Intensive short course on data analytics, energy systems, energy access, research techniques and project management; Kaggle machine learning competition; clearly defined subset of goals
  • Spring 2018: Project execution; reflections and presentations to wider community


Independent study credit available for fall and spring semesters; summer funding

See earlier related team, Energy Data Analytics Lab (2016-2017).


Faculty/Staff Team Members

Kyle Bradbury, Duke University Energy Initiative*
Leslie Collins, Pratt School - Electrical & Computer Engineering*
Marc Jeuland, Sanford School of Public Policy and Duke Global Health Institute
Timothy Johnson, Nicholas School - Earth & Ocean Sciences*
Guillermo Sapiro, Pratt School - Electrical & Computer Engineering

* denotes team leader


Active, New