Estimating Residential Solar Potential Using Aerial Data

TL;DR

This paper introduces a deep learning method to enhance aerial data resolution, significantly expanding the coverage of residential solar potential estimation and improving accuracy of existing tools like Project Sunroof.

Contribution

It presents a novel deep learning approach to improve aerial data resolution, enabling broader and more accurate residential solar potential assessments.

Findings

Enhanced data resolution increases coverage of solar potential estimates.

Deep learning improves the accuracy of solar potential predictions.

Potential for further accuracy improvements with pipeline modifications.

Abstract

Project Sunroof estimates the solar potential of residential buildings using high quality aerial data. That is, it estimates the potential solar energy (and associated financial savings) that can be captured by buildings if solar panels were to be installed on their roofs. Unfortunately its coverage is limited by the lack of high resolution digital surface map (DSM) data. We present a deep learning approach that bridges this gap by enhancing widely available low-resolution data, thereby dramatically increasing the coverage of Sunroof. We also present some ongoing efforts to potentially improve accuracy even further by replacing certain algorithmic components of the Sunroof processing pipeline with deep learning.