How to Count Every Solar Panel in the U.S.? ML and a Billion Satellite Images

DeepSolar uses satellite data to locate and count solar panel installations in the U.S. (Image courtesy of DeepSolar.) The DeepSolar Project, developed by engineers and computer scientists at Stanford University, is a machine learning framework that analyzes a dataset of satellite images in order to identify the size and location of installed solar panels. Once the training period was completed and the team knew that DeepSolar could identify most solar panels in images, they moved on to the real task: analyzing the billion satellite images of the U.S. to find solar installations.

Source: www.engineering.com