Spatial Distribution of Solar PV Deployment: An Application of the Region-Based Convolutional Neural Network
share
This paper presents a comprehensive analysis of the social and environmental determinants of solar photovoltaic (PV) deployment rates in Colorado, USA. Using 652,795 satellite imagery and computer vision frameworks based on a convolutional neural network, we estimated the proportion of households with solar PV systems and the roof areas covered by solar panels. At the census block group level, 7 2.5 machine learning models predict solar PV deployment based on 43 natural and social characteristics of neighborhoods. Using four algorithms (Random Forest, CATBoost, LightGBM, XGBoost), we find that the share of Democratic party votes, hail risks, strong wind risks, median home value, and solar PV permitting timelines are the most important predictors of solar PV count per household. In addition to the size of the houses, PV-to-roof area ratio is highly dependent on solar PV permitting timelines, proportion of renters and multifamily housing, and winter weather risks. We also find racial and ethnic disparities in rooftop solar deployment. The average marginal effects of median household income on solar deployment are lower in communities with a greater proportion of African American and Hispanic residents and are higher in communities with a greater proportion of White and Asian residents. In the ongoing energy transition, knowing the key predictors of solar deployment can better inform business and policy decision making for more efficient and equitable grid infrastructure investment and distributed energy resource management.
READ FULL TEXT
