Rooftop solar is one of the most promising tools for drawing down greenhouse gas (GHG) emissions and is cost-competitive with fossil fuels in many areas of the world today. One of the most important criteria for determining the suitability of a building for rooftop solar is the current age of its roof. The reason for this is simple -- because rooftop solar installations are long-lived, the roof needs to be new enough to last for the lifetime of the solar array or old enough to justify being replaced. In this paper we present a data-driven method for determining the age of a roof from historical satellite imagery, which removes one of the last obstacles to a fully automated pipeline for rooftop solar site selection. We estimate that a full solution to this problem would reduce customer acquisition costs for rooftop solar by ∼20\%, leading to an additional ∼750 megatons of CO2 displaced between 2020 and 2050.
@article{arxiv.2001.04227,
title = {Roof Age Determination for the Automated Site-Selection of Rooftop Solar},
author = {Chris Heinrich and Michael Laskin and Simas Glinskis and Evert van Nieuwenburg},
journal= {arXiv preprint arXiv:2001.04227},
year = {2020}
}