Evaluation of Four Supervised Learning Methods for Benthic Habitat Mapping Using Backscatter from Multi-Beam Sonar.docVIP

Remote Sens. 2012, 4, 3427-3443; doi:10.3390/rs4113427 OPEN ACCESS Remote Sensing ISSN 2072-4292 /journal/remotesensing Article Evaluation of Four Supervised Learning Methods for Benthic Habitat Mapping Using Backscatter from Multi-Beam Sonar Rozaimi Che Hasan 1,2, Daniel Ierodiaconou 1,* and Jacquomo Monk 1 1 School of Life Environmental Sciences, Faculty of Science and Technology, Deakin University, PO Box 423, Warrnambool, VIC 3280, Australia; E-Mails: jacquomo.monk@.au 2 Razak School of Engineering and Advanced Technology, Universiti Teknologi Malaysia, 54100 Kuala Lumpur, Malaysia; E-Mail: rozaimi@ic.utm.my * Author to whom correspondence should be addressed; E-Mail: iero@.au; Tel.: +613-5563-3224; Fax: +613-5563-3143. Received: 27 August 2012; in revised form: 2 November 2012 / Accepted: 5 November 2012 / Published: 12 November 2012 Abstract: An understanding of the distribution and extent of marine habitats is essential for the implementation of ecosystem-based management strategies. Historically this had been difficult in marine environments until the advancement of acoustic sensors. This study demonstrates the applicability of supervised learning techniques for benthic habitat characterization using angular backscatter response data. With the advancement of multibeam echo-sounder (MBES) technology, full coverage datasets of physical structure over vast regions of the seafloor are now achievable. Supervised learning methods typically applied to terrestrial remote sensing provide a cost-effective approach for habitat characterization in marine systems. However the comparison of the relative performance of different classifiers using acoustic data is limited. Characterization of acoustic backscatter data from MBES using four different supervised learning methods to generate benthic habitat maps is presented. Maximum Likelihood Classifier (MLC), Quick, Unbiased, Efficient