Along with the Energy Data Analytics Lab and the Sustainable Energy Transitions Initiative, students will explore how machine learning can be developed to better identify and characterize energy infrastructure and scale up its application across geographies. Using synthetic data generation such as style transfer and/or 3D models to create images of artificial cities and communities, we will examine how well an algorithm trained on one set of training data is able to adapt to new places and types of energy infrastructure. This research will increase the speed and scale of assessment towards an automated, global assessment of energy infrastructure. The resulting data would empower decisionmakers and energy system planners to make better decisions for planning electricity system development for communities with limited electricity access or reliability.
Project Lead: Kyle Bradbury
Project Manager: Wei Hu