Advances and prospects on estimating solar photovoltaic installation capacity and potential based on satellite and aerial images. (June 2023)

• Record Type: Journal Article
• Authors: Mao, Hongzhi; Chen, Xie; Luo, Yongqiang; Deng, Jie; Tian, Zhiyong; Yu, Jinghua; Xiao, Yimin; Fan, Jianhua
• Is Part Of: Renewable & sustainable energy reviews. Volume 179(2023)
• Publication Date: 2023-06
• Subjects: Solar photovoltaic -- Identification -- Satellite and aerial images -- Deep learning; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.rser.2023.113276
• Languages: English
• ISSNs: 1364-0321

Abstract

Abstract: Solar photovoltaic (PV) system, as one kind of the most promising renewable energy technologies, plays a key role in reducing carbon emissions to achieve the targets of global net zero carbon. In the past few decades, PV installations have seen a rapid growth. Predicting the installed amount and the capacity of solar PV systems is therefore useful for formulating effective carbon reduction policies in the related area. In the present study, the methods of identifying PV installation based on satellite and aerial images have been reviewed. Suggestions have been put forward to optimize the identification process and to predict the potential of rooftop PV installation. The results show that the specific purposes of PV identification can be categorized as image classification, object detection and semantic segmentation. The available identification methods encompass pixel-based analysis method (PBIA), object-based analysis method (OBIA) and deep learning. Deep learning has a high accuracy in segmentation for all sizes of PV systems, with precision and recall of rooftop PV segmentation in the range of 41–98.9% and 54.5–95.8%, respectively. OBIA has the best accuracy in detecting centralized PV systems with relatively low-resolution multispectral images. Furthermore, a grading segmentation strategy for PV segmentation in the large region is presented, combining the three identification methods and the images with different resolutions. In addition, the potential of rooftop PV installation can be predicted by segmenting the available roof area in the images. After considering the shading effects, upper structure and other uses, the roof availability coefficient tends to be in the range of 0.25–0.46. It is also suggested to combine PV and roof segmentation to estimate the installation potential more accurately, in the context of rapid growth of the rooftop PV. Highlights: The sources and their characteristics of satellite and aerial images are analyzed. The methods of PBIA, OBIA, and deep learning are classified and compared. The applications of PV identification model are summarized. Optimization of potential prediction of rooftop PV is discussed. A grading strategy for PV segmentation with high efficiency, low cost and ensuring accuracy is proposed.