AI Case Study
US Department of Energy remotely assesses rooftop potential for solar panels with 98% accuracy using Aurora Solar's computer vision
The US Department of Energy has partnered with Aurora Solar to help solar companies facilitate the adoption of solar energy. Aurora Solar uses computer vision to remotely assess the rooftop area potential for solar panels with 98% accuracy.
Public And Social Sector
"Aurora Solar developed advanced measurement tools that utilizes Google Street View as a basis for remotely measuring roof slope, roof edge lengths, and other distances. These measurements are the inputs into a three-dimensional model, which is used to calculate the aforementioned irradiance and solar access values." (NREL)
From the NREL: "As part of the U.S. Department of Energy (DOE) SunShot Incubator program, Aurora Solar has developed a web-based application that quickly and precisely calculates the solar potential of a roof. The results of this application will increase the ability of solar firms to accurately assess large numbers of potential solar installation sites and increase closing rates."
Proof of concept: a blindy study was conducted and determined Aurora's remote measurement tools yielded results found to be within their stated accuracy bounds 98% of the time.
According to Aurora: "Aurora Envision’s 3D Metric Estimation tool uses any satellite or aerial imagery (such as Google, Bing or even aerial imagery captured from a drone) and Google Street View imagery to provide those two different viewpoints needed to use triangulation. These images also provide information on the camera position that is accurate within a few feet. With this data, computer vision allows project designers to extract 3D measurements from the scene—such as the slope of a roof or the heights of chimneys or trees—ensuring the accuracy of the site model."
Google Street View imagery and satellite/aerial imagery