To meet the energy needs of those without access, we need to know where existing infrastructure, especially transmission and distribution lines, are in relation to communities in need. Current databases track approximately 85% of global energy infrastructure capacity. The remaining 15% may dramatically impact global emissions, but are particularly hard to find, often because there is not public record of their installation. This projects aims to identify the likely locations of currently undocumented pieces of energy infrastructure by using a large amount of labeled energy infrastructure data to build a method for predicting the locations of energy infrastructure in publicly available satellite imagery. The partner for this project is an emerging leader in energy data analytics. MIDS students on this project should be interested in, or willing to learn, computer vision techniques.