Presentation by Dr. Brian Min, University of Michigan | While global #energyaccess has increased dramatically in recent years, many electrified areas continue to experience profound #reliability challenges, with frequent disruptive #poweroutages. As this talk notes, reliability is a technical problem, as well as a fundamentally political one; for example, if #electricity supply falls very short of actual demand, every decision about who experiences power outages can be a profoundly political one. Understanding and addressing reliability challenges requires moving past annual composites, which don't do enough to reveal what is happening in individual households (i.e., settlements) and communities on a day-to-day basis.

This talk describes research applying automated techniques to high-resolution nighttime #VIIRS #satelliteimagery (collected each night) along with new data on human settlement (collected by Facebook and others). With #machinelearning, researchers can leverage these public datasets to estimate and monitor indicators of energy access and reliability on a nightly basis and compute an overall annual estimate of a human settlement's likely access and reliability. Aggregating settlement data can then allow for a national estimate of the #electrification access rate.
https://registry.opendata.aws/wb-ligh...

0:00 - 13:30 - Presentation
13:30 - end - Audience Q&A

About the Presenter: Dr. Brian Min is an Associate Professor of Political Science at the University of Michigan, Ann Arbor. Dr. Min studies the political economy of development with an emphasis on distributive politics, public goods provision, and energy politics. His research uses high-resolution satellite imagery to study the distribution of electricity, including collaboration with the World Bank to monitor electricity access in India and Africa. Dr. Min has a Ph.D. in Political Science from UCLA.

This presentation was a part of the Energy Data Analytics Symposium hosted by Duke University on December 8-9, 2020. The Symposium’s theme was “Transforming Energy Systems with Data Science Techniques.”

Learn more about the 2020 Energy Data Analytics Symposium and view all presentations:
https://energy.duke.edu/energy-data-a...
All presentations are also available on a YouTube playlist:
   • Energy Data Analytics Symposium  

The 2020 Energy Data Analytics Symposium was organized by the Energy Data Analytics Lab at Duke University and was supported by a grant from the Alfred P. Sloan Foundation. Note: Conclusions reached or positions taken by researchers or other grantees represent the views of the grantees themselves and not those of the Alfred P. Sloan Foundation or its trustees, officers, or staff.

Learn about the Energy Data Analytics Lab at Duke University: https://energy.duke.edu/research/ener...

Get email updates on energy news and events at Duke University: https://bit.ly/energyduke