Spatial distribution of solar PV deployment: an application of the region-based convolutional neural network

EPJ Data Science

Regular Article

Koushik Ganesan¹  Raven O’Rourke²  Crystal Soderman³  Serena Y. Kim⁴ 

[1] Physics, University of Colorado Boulder, 2000 Colorado Ave, 80309, Boulder, CO, USA;RadiaSoft, 6525 Gunpark Dr, Suite 370-411, 80301, Boulder, CO, USA;School of Public Affairs, University of Colorado Denver, 1380 Lawrence St, 80204, Denver, CO, USA;School of Public and International Affairs, North Carolina State University, 2221 Hillsborough St, 27607, Raleigh, NC, USA;College of Engineering, Design and Computing, University of Colorado Denver, 1200 Larimer St, 80204, Denver, CO, USA;School of Public Affairs, University of Colorado Denver, 1380 Lawrence St, 80204, Denver, CO, USA;

关键词: Solar PV;    Data mining;    Computer vision;    Region-based convolutional neural network;    Energy transition;    Renewable energy;    Energy justice;   

DOI  :  10.1140/epjds/s13688-023-00399-1

 received in 2022-07-17, accepted in 2023-06-16,  发布年份 2023

来源: Springer

【 摘 要 】

Solar photovoltaic (PV) deployment plays a crucial role in the transition to renewable energy. However, comprehensive models that can effectively explain the variations in solar PV deployment are lacking. This study aims to address this gap by introducing two innovative models: (i) a computer vision model that can estimate spatial distribution of solar PV deployment across neighborhoods using satellite images and (ii) a machine learning (ML) model predicting such distribution based on 43 factors. Our computer vision model using Faster Regions with Convolutional Neural Network (Faster RCNN) achieved a mean Average Precision (mAP) of 81% for identifying solar panels and 95% for identifying roofs. Using this model, we analyzed 652,795 satellite images from Colorado, USA, and found that approximately 7% of households in Colorado have rooftop PV systems, while solar panels cover around 2.5% of roof areas in the state as of early 2021. Of our 16 predictive models, the XGBoost models performed the best, explaining approximately 70% of the variance in rooftop solar deployment. We also found that the share of Democratic party votes, hail and strong wind risks, median home value, the percentage of renters, and solar PV permitting timelines are the key predictors of rooftop solar deployment in Colorado. This study provides insights for business and policy decision making to support more efficient and equitable grid infrastructure investment and distributed energy resource management.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

12974_2023_2839_Article_IEq6.gif

41116_2023_38_Article_IEq198.gif

Fig. 4

41116_2023_38_Article_IEq196.gif

41116_2023_38_Article_IEq195.gif

Fig. 3

41116_2023_38_Article_IEq193.gif

Fig. 2

Fig. 4

Fig. 1

Fig. 1

41116_2023_38_Article_IEq188.gif

41116_2023_38_Article_IEq187.gif

41116_2023_38_Article_IEq186.gif

41116_2023_38_Article_IEq185.gif

41116_2023_38_Article_IEq184.gif

41116_2023_38_Article_IEq183.gif

41116_2023_38_Article_IEq182.gif

41116_2023_38_Article_IEq181.gif

41116_2023_38_Article_IEq180.gif

41116_2023_38_Article_IEq179.gif

41116_2023_38_Article_IEq178.gif

13073_2023_1204_Article_IEq28.gif

41116_2023_38_Article_IEq177.gif

41116_2023_38_Article_IEq176.gif

41116_2023_38_Article_IEq175.gif

41116_2023_38_Article_IEq174.gif

41116_2023_38_Article_IEq173.gif

41116_2023_38_Article_IEq172.gif

41116_2023_38_Article_IEq171.gif

41116_2023_38_Article_IEq170.gif

41116_2023_38_Article_IEq169.gif

41116_2023_38_Article_IEq168.gif

41116_2023_38_Article_IEq167.gif

41116_2023_38_Article_IEq166.gif

41116_2023_38_Article_IEq164.gif

41116_2023_38_Article_IEq150.gif

41116_2023_38_Article_IEq149.gif

41116_2023_38_Article_IEq147.gif

41116_2023_38_Article_IEq146.gif

41116_2023_38_Article_IEq144.gif

41116_2023_38_Article_IEq137.gif

Fig. 2

41116_2023_38_Article_IEq132.gif

41116_2023_38_Article_IEq129.gif

41116_2023_38_Article_IEq127.gif

41116_2023_38_Article_IEq126.gif

41116_2023_38_Article_IEq124.gif

41116_2023_38_Article_IEq122.gif

Fig. 1