Abstract
Abstract. In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Accurate localized PV information, including location and size, is the basis for PV regulation and potential assessment of the energy sector. Automatic information extraction based on deep learning requires high-quality labeled samples that should be collected at multiple spatial resolutions and under different backgrounds due to the diversity and variable scale of PVs. We established a PV dataset using satellite and aerial images with spatial resolutions of 0.8, 0.3, and 0.1 m, which focus on concentrated PVs, distributed ground PVs, and fine-grained rooftop PVs, respectively. The dataset contains 3716 samples of PVs installed on shrub land, grassland, cropland, saline–alkali land, and water surfaces, as well as flat concrete, steel tile, and brick roofs. The dataset is used to examine the model performance of different deep networks on PV segmentation. On average, an intersection over union (IoU) greater than 85 % is achieved. In addition, our experiments show that direct cross application between samples with different resolutions is not feasible and that fine-tuning of the pre-trained deep networks using target samples is necessary. The dataset can support more work on PV technology for greater value, such as developing a PV detection algorithm, simulating PV conversion efficiency, and estimating regional PV potential. The dataset is available from Zenodo on the following website: https://doi.org/10.5281/zenodo.5171712 (Jiang et al., 2021).
Highlights
Fossil fuels used by our society have caused unprecedented levels of carbon dioxide (CO2) with widespread climate impacts that threaten human survival and development (Chu and Majumdar, 2012; Shin et al, 2021)
Our PV dataset includes three groups of PV samples collected at different spatial resolutions (Table 1), namely PV08 from Gaofen-2 and Beijing-2 imagery, PV03 from aerial photography, and PV01 from unmanned aerial vehicle (UAV) orthophotos
The unbalance of training samples led to the difference in segmentation accuracy, except that the spatial resolution was responsible for the poor performance on distributed PVs (Fig. 4c–d) that were mixed with background in the 0.8 m satellite images
Summary
Fossil fuels used by our society have caused unprecedented levels of carbon dioxide (CO2) with widespread climate impacts that threaten human survival and development (Chu and Majumdar, 2012; Shin et al, 2021). To help with PV integration and monitoring, there are strong interests among governments and utility decision-makers in obtaining localized information of existing PVs, such as the location, size, capacity, and power output (Rico Espinosa et al, 2020; Yao and Hu, 2017). Traditional methods, such as in situ survey and bottom-up reporting, are generally timeconsuming and incomplete. Our dataset will contribute to a variety of PV applications in the future
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
