Energy Data Analytics Lab: Energy Infrastructure Map of the World through Satellite Data (2018-2019)

Background

Over 15% of humanity has no access to electricity, and far more have unreliable access that precludes most productive energy uses that are beneficial for improving economic prosperity, health and education.

Decision-makers require information to determine the optimal strategies for deploying energy resources to decide where to prioritize development and whether that development should be through grid expansion, microgrids or distributed generation.

However, two critical data sources for such planning—who has access to electricity and the location of electric infrastructure—are often unavailable or overly time-consuming to collect and maintain.

Project Description

To address these needs, this Bass Connections project sets a bold goal of working toward creating an energy infrastructure map of the world using satellite imagery. The project team will employ state-of-the-art machine learning tools in order to detect critical energy infrastructure in satellite imagery including power distribution lines and off-grid distributed energy generation sources such as solar photovoltaics.

Team members will approach their analysis from an integrated systems perspective. Instead of modeling individual components of the system independently (generation, distribution, consumption), the team will employ techniques that consider these components as part of an integrated whole, comprising a national grid and perhaps local off-grid microgrids. This will be the first step toward a functional energy infrastructure map of the world.

The focus of this team will be in mapping out transmission and distribution lines: the foundation of the bulk energy system. A Data+ team will lay the groundwork for this project by generating a ground-truth dataset for power transmission and distribution infrastructure including power transmission lines, power stations and substations. The Bass Connections 2018-2019 project team will then develop machine learning techniques capable of automatically identifying these objects of interest in satellite data.

Team members will use both publicly available data from the U.S. as well as purchased data covering underserved parts of south and central Asia. This work, combined with the research from previous Bass Connections and Data+ projects, will provide a toolset that will enable the remote assessment of generation, transmission, distribution, end-use and access to electricity. Once all of these pieces are complete, the team will unify these components toward a vision of a methodology for automatically mapping and assessing energy systems in any place on Earth.

Anticipated Outcomes

New dataset of transmission, distribution and substation data in satellite imagery and publication on the online data repository Figshare; collection of code implementing the algorithm for identifying the power system infrastructure shared on Github; team poster and final presentation open to the public; conference or journal paper based on the methods and/or datasets developed

Student Opportunities

Student team members will meet twice per week with team leaders. Participating graduate students will serve as project managers for the team. 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 empower students 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 Python
  • Explain the fundamentals of machine learning and pattern recognition
  • Implement and understand the implications of results from experimental research techniques

The team is likely to be comprised of six to nine students (a mix of undergraduates and graduate students) from disciplines such as engineering, economics, public policy, computer science, environmental science, mathematics and statistics. Students with some experience in quantitative methods are preferable. Graduate students will take on a leadership role as project managers; graduate students that have excellent management skills and preferably strong technical skills or a willingness to get up-to-speed rapidly with respect to technical skills are especially encouraged to apply.

Students will have the opportunity to interact with external experts, and the project will receive guidance and feedback to ensure the maximum applicability of the research to real-world policy and decision-maker needs.

Students will receive a grade and course credit. They are expected to enroll for full credit for two semesters, and to devote at least 10 hours per week to this project. This grade will be based on four peer assessments, team and individual written and oral reports, twice weekly reading assessments (from relevant journal papers and a textbook on machine learning) through the boot camp and a final presentation and poster each semester.

Timing

Fall 2018 – Spring 2019  

Team meetings will take place on Mondays and Wednesdays, 11:45 a.m. – 1:00 p.m.

  • Fall 2018: Short course and Kaggle competition (August-October); goal and role development (November); first semester sprint (December)
  • Spring 2019: Project execution (January-February; Report out (March-May)

Crediting

Independent study credit available for fall and spring semesters

See earlier related team, Energy Data Analytics Lab: Electricity Access in Developing Countries from Aerial Imagery (2017-2018), and a related Data+ summer project, Energy Infrastructure Map of the World (2018).

Faculty/Staff Team Members

Kyle Bradbury, Energy Initiative*
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
Jordan Malof, Pratt School of Engineering-Electrical & Computer Engineering
Robyn Meeks, Sanford School of Public Policy
Guillermo Sapiro, Pratt School of Engineering-Electrical & Computer Engineering

Graduate Team Members

Wendell Cathcart, Master of Environmental Management, Energy and Environment

Undergraduate Team Members

Ben Alexander
Yutao Gong
Xinchun Hu
Varun Nair, Mechanical Engineering (BSE), Computer Science (BS2)
Lin Zuo, Statistical Science (BS), Computer Science (AB2)

* denotes team leader

Status

Active, New