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

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 Statistical Tree (QUEST), Random Forest (RF) and Support Vector Machine (SVM) were evaluated to classify angular backscatter response into habitat classes using training data acquired from underwater video observations. Results for biota classifications indicated that SVM and RF produced the highest accuracies, followed by QUEST and MLC, respectively. The most important backscatter data were from the moderate incidence angles between 30° and 50°. This study presents initial results for understanding how acoustic backscatter from MBES can be optimized for the characterization of marine benthic biological habitats.

[1]  Jacquomo Monk,et al.  Victorian marine habitat mapping project , 2007 .

[2]  Iain Parnum,et al.  Benthic habitat mapping using multibeam sonar systems , 2007 .

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  Á. Borja,et al.  Predicting suitable habitat for the European lobster (Homarus gammarus), on the Basque continental shelf (Bay of Biscay), using Ecological-Niche Factor Analysis , 2009 .

[5]  Alexandre C. G. Schimel,et al.  Quantitative experimental comparison of single-beam, sidescan, and multibeam benthic habitat maps , 2010 .

[6]  A Hagen,et al.  Multi-method assessment of map similarity , 2002 .

[7]  Robert Sean Galway.  Comparision of Target Detection Capabilities of the Reson Seabat 8101 and Reson Seabat 9001 Multibeam Sonars , 2001 .

[8]  D. Simons,et al.  A Bayesian approach to seafloor classification using multi-beam echo-sounder backscatter data , 2009 .

[9]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[10]  D. Ierodiaconou,et al.  Hydro-acoustic remote sensing of benthic biological communities on the shallow South East Australian continental shelf , 2009 .

[11]  Tiho Ancev,et al.  Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data Using Post-Classification Enhancement , 2009, Remote. Sens..

[12]  Yuri Rzhanov,et al.  Construction of seafloor thematic maps from multibeam acoustic backscatter angular response data , 2012, Comput. Geosci..

[13]  V. Lucieer,et al.  Unsupervised fuzzy classification and object-based image analysis of multibeam data to map deep water substrates, Cook Strait, New Zealand , 2011 .

[14]  Guangzhe Fan,et al.  Classification tree analysis using TARGET , 2008, Comput. Stat. Data Anal..

[15]  B. Calder,et al.  Angular range analysis of acoustic themes from Stanton Banks Ireland: A link between visual interpretation and multibeam echosounder angular signatures , 2009 .

[16]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[17]  Geoff Smith,et al.  An evaluation of per-parcel land cover mapping using maximum likelihood class probabilities , 2003 .

[18]  Iain Parnum,et al.  Relationships between multibeam backscatter, sediment grain size and Posidonia oceanica seagrass distribution , 2010 .

[19]  A. Ishimaru,et al.  Application of the composite roughness model to high‐frequency bottom backscattering , 1986 .

[20]  S. Theodoridis,et al.  Classifiers Based on Bayes Decision Theory , 2010 .

[21]  Iain Parnum,et al.  High-frequency multibeam echo-sounder measurements of seafloor backscatter in shallow water: Part 2 - Mosaic production, analysis and classification , 2011 .

[22]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[23]  D. Ierodiaconou,et al.  Marine benthic habitat mapping using Multibeam data, georeferencedvideo and image classification techniques in Victoria, Australia , 2007 .

[24]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[25]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[26]  Luciano E. Fonseca,et al.  Remote estimation of surficial seafloor properties through the application Angular Range Analysis to multibeam sonar data , 2007 .

[27]  Dorin Comaniciu,et al.  Mean shift analysis and applications , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[28]  Taskin Kavzoglu,et al.  A kernel functions analysis for support vector machines for land cover classification , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[29]  Xavier Lurton,et al.  Contribution of the multibeam acoustic imagery to the exploration of the sea-bottom , 1996 .

[30]  Iain Parnum,et al.  Statistical analysis of high-frequency multibeam backscatter data in shallow water , 2006 .

[31]  Rudy J. Kloser,et al.  Multi-beam backscatter measurements used to infer seabed habitats , 2010 .

[32]  Chris McGonigle,et al.  Insonification orientation and its relevance for image-based classification of multibeam backscatter , 2010 .

[33]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[34]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[35]  Daniel Ierodiaconou,et al.  Combining angular response classification and backscatter imagery segmentation for benthic biological habitat mapping , 2012 .

[36]  Philippe Blondel,et al.  Textural analyses of multibeam sonar imagery from Stanton Banks, Northern Ireland continental shelf , 2009 .

[37]  Xavier Lurton,et al.  Quantitative characterisation of seafloor substrate and bedforms using advanced processing of multibeam backscatter—Application to Cook Strait, New Zealand , 2011 .

[38]  Chris McGonigle,et al.  Detection of deep water benthic macroalgae using image-based classification techniques on multibeam backscatter at Cashes Ledge, Gulf of Maine, USA , 2011 .

[39]  Iain Parnum,et al.  Acoustic seabed segmentation from direct statistical clustering of entire multibeam sonar backscatter curves , 2011 .

[40]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[41]  W. Loh,et al.  SPLIT SELECTION METHODS FOR CLASSIFICATION TREES , 1997 .

[42]  J. Clarke,et al.  Areal Seabed Classification using Backscatter Angular Response at 95 kHz , 1997 .

[43]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.