Remote sensing of energy resources with machine learning in a time of system transitions

Authors: Kyle Bradbury*, Duke University Energy Initiative, Jordan Malof, Electrical & Computer Engineering, Duke University
Topics: Energy, Remote Sensing, Global Change
Keywords: Machine learning, remote sensing, energy systems, electricity access, solar
Session Type: Paper
Presentation File: No File Uploaded

Energy systems are in a time of rapid change: the growth of renewable (but intermittent) energy systems; the distribution of small, often rooftop, generation systems; and major expansion of access to electricity across the globe. Monitoring and optimizing these system transitions to minimize climate impacts and both physical and financial system risks requires high resolution geospatial information on electricity infrastructure including generation, transmission, and end-use consumption. We will discuss recent advances in using machine learning and remotely sensed data to provide key geographic energy data inputs to these questions while also exploring the future applications these techniques may enable.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login