The automatic segmentation of residential solar panels based on satellite images: A cross learning driven U-Net method

• Published in: Applied soft computing Vol. 92; p. 106283
• Main Authors: Zhuang, Li, Zhang, Zijun, Wang, Long
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2020
• Subjects: Computational intelligence; Data mining; Neural networks; Satellite images; Solar panels; Satellite images; Data mining; Solar panels; Neural networks; Computational intelligence
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2020.106283

Segmenting small-scale residential solar panels (RSPs) based on satellite images is an emerging data science problem in the renewable energy field. In this paper, we develop a cross learning driven U-Net (CrossNets) method and its extension, adaptive CrossNets, to automatically segment RSPs in satellite images. Proposed methods employ a group of generic U-Nets as a community and target to enhance the RSP segmentation performance. First, parameters of each generic U-Net in the community of CrossNets are initialized individually via the initialization with transfer learning and the classical initialization methods. Next, a novel training mechanism, cross learning, is developed to serve as a constraint for better optimizing CrossNets. Based on cross learning, each generic U-Net in the community first individually updates parameters at every epoch and next learns parameters from the best individual at specific epochs. Cross learning relieves the reliance of generic U-Nets on a careful initialization and better optimizes U-Nets. In testing, the result of the best performed generic U-Net in the community is selected as the final segmentation result of CrossNets. Adaptive CrossNets, a variant of CrossNets, is developed by applying an additional threshold to reduce the possibility of over-learning caused by cross learning. Satellite images collected from one city in U.S. are utilized to validate the performance of proposed methods. These images cover a large area of 135 km2 with 2794 RSPs. Compared with two generic U-Nets based benchmarks, our method can enhance the overall segmentation IoU by around 34% and 1.5%. Moreover, the segmentation robustness is improved from 1.191e−2 and 1.286e−4 to 2.481e−5. In addition, two new image datasets collected from other two cities in U.S. are applied to further examine the applicability of proposed methods. •An automatic segmentation of residential solar panels from satellite images is studied.•A cross learning driven U-net method and its adaptive version are developed.•Effectiveness of developed cross learning U-nets on segmenting solar panels in satellite images is evaluated.•Three sets of satellite images are utilized in computational experiments.•The developed method offers a new option for surveying the solar energy utilization in residential regions.