Extraction of Offshore Wind Turbines in China by Combining Multispectral and SAR Image Data
Fangxiong Wang, Shuai Zhang, Yingzi Hou, Junfu Wang
Abstract
To address the energy crisis and the challenge of global climate change, it has become a consensus among countries to vigorously develop renewable energy sources, and wind energy, as a clean, efficient and nonpolluting renewable energy source, is being promoted and generated in an increasing number of offshore wind turbine (OWT) arrays worldwide. However, accurate and complete offshore wind turbine datasets are crucial for ensuring the safety of marine navigation, marine ecological and environmental protection, and the effective evaluation and optimization of offshore wind farms (OWFs). However, most previous studies focused on OWT information extraction using a single multispectral or SAR image dataset, failing to combine the respective advantages of multispectral and SAR imagery. Moreover, accurate land boundary data are needed to mask the land before extracting OWTs, which is inconvenient to perform. In view of the shortcomings of previous studies, the advantages of multispectral and radar satellite image data are fully exploited, and offshore China is selected as the study area. According to the spatial location characteristics of OWTs, a new extraction algorithm for OWTs, the double-loop cooperative detection (DLCD) algorithm, is designed. At the end of 2022, a total of 5,986 OWTs were detected in Chinese waters, with an extraction precision of 99.93%, a recall rate of 99.38%, and a comprehensive evaluation index value of 99.65%. The advantages of this algorithm are that it is fast, concise and effective, thus providing a new approach for extracting OWTs.