A Scalable, Supervised Classification of Seabed Sediment Waves Using an Object-Based Image Analysis Approach

Abstract

National mapping programs (e.g., INFOMAR and MAREANO) and global efforts (Seabed 2030) acquire large volumes of multibeam echosounder data to map large areas of the seafloor. Developing an objective, automated and repeatable approach to extract meaningful information from such vast quantities of data is now essential. Many automated or semi-automated approaches have been defined to achieve this goal. However, such efforts have resulted in classification schemes that are isolated or bespoke, and therefore it is necessary to form a standardised classification method. Sediment wave fields are the ideal platform for this as they maintain consistent morphologies across various spatial scales and influence the distribution of biological assemblages. Here, we apply an object-based image analysis (OBIA) workflow to multibeam bathymetry to compare the accuracy of four classifiers (two multilayer perceptrons, support vector machine, and voting ensemble) in identifying seabed sediment waves across three separate study sites. The classifiers are trained on high-spatial-resolution (0.5 m) multibeam bathymetric data from Cork Harbour, Ireland and are then applied to lower-spatial-resolution EMODnet data (25 m) from the Hemptons Turbot Bank SAC and offshore of County Wexford, Ireland. A stratified 10-fold cross-validation was enacted to assess overfitting to the sample data. Samples were taken from the lower-resolution sites and examined separately to determine the efficacy of classification. Results showed that the voting ensemble classifier achieved the most consistent accuracy scores across the high-resolution and low-resolution sites. This is the first object-based image analysis classification of bathymetric data able to cope with significant disparity in spatial resolution. Applications for this approach include benthic current speed assessments, a geomorphological classification framework for benthic biota, and a baseline for monitoring of marine protected areas.

Evaluation of Satellite-Derived Bathymetry from High and Medium-Resolution Sensors Using Empirical Methods

“…Lyzenga followed the fundamental principle derived from the Beer-Lambert law. Lyzenga developed a linear method which assumes that the reflection at the bottom is a linear function of the reflectance of the seabed with the exponential function of the depth of water [5,6,30,43]. The estimation of the depth from a single band depends on the albedo and can be made using the following equation:…”

“…Monitoring of coastal areas is, thus, of great importance to implement sustainable coastal development and ecosystem protection strategies [1][2][3]. High spatiotemporal resolution and a vertical accuracy topographic and bathymetric data are also essential not only for understanding coastal systems evolution [2], but also for other environmental applications, such as benthic habitat mapping [4], seabed geomorphology [5], underwater archaeology [6], monitoring of coastal morphological changes, navigation, and fishing [7].…”

High-resolution 3D mapping of cold-water coral reefs using machine learning

“…The application of computer vision and machine learning (ML) methods in remote sensing has contributed to unprecedented progress in automated spatial (Gilardi 1995;Pal 2005;Mountrakis et al, 2011;Belgiu and Drăgu 2016;Durden et al, 2021) and marine data analyses (Beijbom et al, 2012;Beijbom et al, 2015;Williams et al, 2019;Summers, Lim, and Wheeler 2021). The use of supervised and unsupervised ML classification methods has rapidly grown, especially in the context of underwater image analysis (Huang, Brooke, and Harris 2011;Shihavuddin et al, 2013;Young 2018;Conti, Lim, and Wheeler 2019;Yu et al, 2019;Lim et al, 2020c;González-Rivero et al, 2020).…”

Global Satellite-Based Coastal Bathymetry from Waves

“…Overall, this missing bathymetry information limits our ability to understand and predict coastal evolution which on its own inherently leads to large uncertainties in predicting hazards such as coastal sea states, storm surges, and wave-induced surges and flooding [4][5][6]. The availability of fast, inexpensive, and efficient methods is also needed for studies of bottom variability, such as sandy shoreface or underwater dune dynamics but also some environmental applications such as benthic habitat mapping [7], seabed geomorphology [8], underwater archaeology [9], and exploration of unexploded ordnance [10]. There is currently a growing demand for coastal monitoring, where coastal bathymetry is of critical importance [11,12].…”