Acoustic mapping and classification of benthic habitat using unsupervised learning in artificial reef water

详细信息    查看全文

• 作者：Dong Li^a ; ^b ; Cheng Tang^a ; ^{ctang@yic.ac.cn} ; Chunlei Xia^a ; Hua Zhang^a ; ^{hzhang@yic.ac.cn}
• 关键词：Artificial reef ; Acoustic mapping ; Automated classification ; Multibeam echosounder
• 刊名：Estuarine, Coastal and Shelf Science
• 出版年：2017
• 出版时间：5 February 2017
• 年：2017
• 卷：185
• 期：Complete
• 页码：11-21
• 全文大小：3844 K
• 卷排序：185

文摘

Artificial reefs (ARs) are effective means to maintain fishery resources and to restore ecological environment in coastal waters. ARs have been widely constructed along the Chinese coast. However, understanding of benthic habitats in the vicinity of ARs is limited, hindering effective fisheries and aquacultural management. Multibeam echosounder (MBES) is an advanced acoustic instrument capable of efficiently generating large-scale maps of benthic environments at fine resolutions. The objective of this study is to develop a technical approach to characterize, classify, and map shallow coastal areas with ARs using an MBES. An automated classification method is designed and tested to process bathymetric and backscatter data from MBES and transform the variables into simple, easily visualized maps. To reduce the redundancy in acoustic variables, a principal component analysis (PCA) is used to condense the highly collinear dataset. An acoustic benthic map of bottom sediments is classified using an iterative self-organizing data analysis technique (ISODATA). The approach is tested with MBES surveys in a 1.15 km2 fish farm with a high density of ARs off the Yantai coast in northern China. Using this method, 3 basic benthic habitats (sandy bottom, muddy sediments, and ARs) are distinguished. The results of the classification are validated using sediment samples and underwater surveys. Our study shows that the use of MBES is an effective method for acoustic mapping and classification of ARs.