scholarly journals An evaluation of supervised and unsupervised classification techniques for marine benthic habitat mapping using multibeam echosounder data

2014 ◽  
Vol 72 (5) ◽  
pp. 1498-1513 ◽  
Author(s):  
Jay Calvert ◽  
James Asa Strong ◽  
Matthew Service ◽  
Chris McGonigle ◽  
Rory Quinn
Keyword(s):  
Selection Process ◽  
Ground Truth ◽  
Unsupervised Classification ◽  
Horizontal Resolution ◽  
Habitat Mapping ◽  
Benthic Habitat ◽  
Marine Habitat ◽  
Ground Truth Data ◽  
Multibeam Echosounder ◽  
Acoustic Data

Abstract Marine habitat mapping provides information on seabed substrata and faunal community structure to users including research scientists, conservation organizations, and policy makers. Full-coverage acoustic data are frequently used for habitat mapping in combination with video ground-truth data in either a supervised or unsupervised classification. In this investigation, video ground-truth data with a camera footprint of 1 m2 were classified to level 4 of the European Nature Information System habitat classification scheme. Acoustic data with a horizontal resolution of 1 m2 were collected over an area of 130 km2 using a multibeam echosounder, and processed to provide bathymetry and backscatter data. Bathymetric derivatives including eastness, northness, slope, topographic roughness index, vector rugosity measure, and two measures of curvature were created. A feature selection process based on Kruskal–Wallis and post hoc pairwise testing was used to select environmental variables able to discriminate ground-truth classes. Subsequently, three datasets were formed: backscatter alone (BS), backscatter combined with bathymetry and derivatives (BSDER), and bathymetry and derivatives alone (DER). Two classifications were performed on each of the datasets to produce habitat maps: maximum likelihood supervised classification (MLC) and ISO Cluster unsupervised classification. Accuracy of the supervised habitat maps was assessed using total agreement, quantity disagreement, and allocation disagreement. Agreement in the unsupervised maps was assessed using the Cramer's V coefficient. Choice of input data produced large differences in the accuracy of the supervised maps, but did not have the same effect on the unsupervised maps. Accuracies were 46, 56, and 49% when calculated using the sample and 52, 65, and 51% when using an unbiased estimate of the population for the BS, BSDER, and DER maps, respectively. Cramer's V was 0.371, 0.417, and 0.366 for the BS, BSDER, and DER maps, respectively.

scholarly journals Nearshore Benthic Habitat Mapping Based on Multi-Frequency, Multibeam Echosounder Data Using a Combined Object-Based Approach: A Case Study from the Rowy Site in the Southern Baltic Sea

2018 ◽  
Vol 10 (12) ◽  
pp. 1983 ◽  
Author(s):  
Lukasz Janowski ◽  
Karolina Trzcinska ◽  
Jaroslaw Tegowski ◽  
Aleksandra Kruss ◽  
Maria Rucinska-Zjadacz ◽  
...  
Keyword(s):  
Baltic Sea ◽  
Ground Truth ◽  
Habitat Mapping ◽  
Acoustic Properties ◽  
Benthic Habitat ◽  
Marine Habitat ◽  
Multibeam Echosounder ◽  
Southern Baltic Sea ◽  
Object Based ◽  
Southern Baltic

Recently, the rapid development of the seabed mapping industry has allowed researchers to collect hydroacoustic data in shallow, nearshore environments. Progress in marine habitat mapping has also helped to distinguish the seafloor areas of varied acoustic properties. As a result of these new developments, we have collected a multi-frequency, multibeam echosounder dataset from the valuable nearshore environment of the southern Baltic Sea using two frequencies: 150 kHz and 400 kHz. Despite its small size, the Rowy area is characterized by diverse habitat conditions and the presence of red algae, unique on the Polish coast of the Baltic Sea. This study focused on the utilization of multibeam bathymetry and multi-frequency backscatter data to create reliable maps of the seafloor. Our approach consisted of the extraction of 70 secondary features of bathymetric and backscatter data, including statistic and textural attributes of different scales. Based on ground-truth samples, we have identified six habitat classes and selected the most relevant features of the bathymetric and backscatter data. Additionally, five types of image processing pixel-based and object-based classifiers were tested. We also evaluated the performance of algorithms using an accuracy assessment based on the validation subset of the ground-truth samples. Our best results reached 93% overall accuracy and a kappa coefficient of 0.90, confirming that nearshore seabed habitats can be accurately distinguished based on multi-frequency, multibeam echosounder measurements. Our predictive habitat mapping of shallow euphotic zones creates a new scientific perspective and provides relevant data for the management of natural resources. Object-based approaches previously used in various environments and areas suggest that methodology presented in this study may be scalable.

scholarly journals Spectral features of dual-frequency multibeam echosounder data for benthic habitat mapping

2020 ◽  
Vol 427 ◽  
pp. 106239 ◽  
Author(s):  
Karolina Trzcinska ◽  
Lukasz Janowski ◽  
Jaroslaw Nowak ◽  
Maria Rucinska-Zjadacz ◽  
Aleksandra Kruss ◽  
...  
Keyword(s):  
Habitat Mapping ◽  
Benthic Habitat ◽  
Spectral Features ◽  
Dual Frequency ◽  
Multibeam Echosounder

scholarly journals The use of Sentinel-2 MSI data in small island's nearshore benthic habitat mapping

2018 ◽  
Author(s):  
Muhammad Afif Fauzan
Keyword(s):  
Coastal Management ◽  
Satellite Remote Sensing ◽  
Reference Data ◽  
Habitat Mapping ◽  
Aerial Photographs ◽  
Benthic Habitat ◽  
Marine Habitat ◽  
Mapping Techniques ◽  
Management And Conservation ◽  
Sentinel 2

Maps of nearshore marine habitat are vital for coastal management and conservation. While traditional field mapping techniques are still commonly used, airborne and satellite remote sensing have proven to be efficient alternatives for creating benthic habitat maps. This paper evaluates the capability of new satellite data, Sentinel-2 MSI, to map nearshore benthic habitat of Derawan Island. Available aerial photographs were used as reference data. The results show that Sentinel-2 MSI data can be used to map benthic habitat with accuracy up to 75%.

Improving marine habitat mapping using high-resolution acoustic data; a predictive habitat map for the Firth of Lorn, Scotland

2018 ◽  
Vol 168 ◽  
pp. 39-47 ◽  
Author(s):  
Karen Boswarva ◽  
Alyssa Butters ◽  
Clive J. Fox ◽  
John A. Howe ◽  
Bhavani Narayanaswamy
Keyword(s):  
High Resolution ◽  
Habitat Mapping ◽  
Marine Habitat ◽  
Acoustic Data ◽  
Marine Habitat Mapping

scholarly journals PEMETAAN HABITAT PERAIRAN DANGKAL MENGGUNAKAN CITRA RESOLUSI MENENGAH DENGAN METODE KLASIFIKASI BERBASIS PIKSEL (STUDI KASUS PULAU TIKUS)

2020 ◽  
Vol 5 (1) ◽  
pp. 78-90
Author(s):  
Ari Anggoro ◽  
Zamdial Zamdial ◽  
Dede Hartono ◽  
Deddy Bakhtiar ◽  
Nurlaila Ervina Herliany ◽  
...  
Keyword(s):  
Maximum Likelihood ◽  
Shallow Water ◽  
Ground Truth ◽  
Small Island ◽  
Benthic Habitat ◽  
Landsat 8 ◽  
Landsat 8 Oli ◽  
Ground Truth Data ◽  
Maximum Likelihood Classification ◽  
Medium Resolution

Pulau Tikus adalah pulau kecil yang terletak di Kota Bengkulu yang memiliki potensi terumbu karang disekitar perairan dangkal. Tujuan penelitian ini untuk memetakan kawasan habitat perairan dangkal ekosistem terumbu karang Pulau Tikus menggunakan citra satelit Landsat 8 OLI dan menguji akurasi klasifikasi peta habitat perairan dangkal di Pulau Tikus. Metode klasifikasi yang digunakan adalah klasifikasi terbimbing maximum likelihood classification. Hasil klasifikasi citra Landsat 8 OLI berdasarkan skema klasifikasi yang digunakan dari lima kelas habitat di Pulau Tikus tersebut yaitu karang hidup seluas 71,46 ha, karang campur pasir 106,9425 ha, karang mati 67,365 ha, makro alga 31,815 ha, dan pasir 40,05 ha. Uji akurasi dari perbandingan hasil klasifikasi citra dan data lapangan mendapatkan total akurasi keseluruhan yaitu sebesar 77%.SHALLOW WATER HABITATS MAPPING USING A MEDIUM RESOLUTION IMAGE WITH CLASSIFICATION METHOD PIKSEL-BASED (CASE STUDY OF THE TIKUS ISLAND). Tikus Island is a small island which located in Bengkulu City has the potential of coral reefs around the shallow water. The aims of this research were to map the area of benthic habitat in Tikus Island Bengkulu using Landsat 8 OLI satellite imagery and to test the accuracy on the benthic habitat map in Tikus Island. The method used supervised classification using maximum likelihood classification. The result of Landsat 8 OLI classification base on the five class habitats classification scheme used obtained in Tikus island showed coral reef (71,46 ha), coral mix sand (106,9425 ha), dead coral (67,365 ha), macroalgae (31,815 ha), and sand (40,05 ha). Accuracy test from the comparison of classification results and ground truth data get a total overall accuracy of 77%.

scholarly journals Extraction of Spread Surface Water Body using Supervised and Unsupervised Classification Techniques

2020 ◽  
Vol 8 (6) ◽  
pp. 2345-2350
Keyword(s):  
Surface Water ◽  
Ground Truth ◽  
Unsupervised Classification ◽  
Water Area ◽  
Landsat 8 ◽  
Classification Methods ◽  
Statistical Parameters ◽  
Ground Truth Data ◽  
Classification Techniques ◽  
Water Board

In this paper different classification techniques are applied to extract spread surface water area in the Nagarjuna sagar reservoir, Andhra Pradesh from Landsat-8 (OLI) image. In addition, the separability of reservoir features are tested to evaluate the thematic correctness of the classified data. This is to evaluate the application of a supervised and unsupervised classification techniques using the ERDAS software to extract the changes of surface water features for the period of 2014 to 2019. Furthermore, the statistical parameters are evaluated for the classification techniques. In supervised and unsupervised classification methods the minimum distance classifier gives better result (overall accuracy is 98.01%) than other classification methods. These obtained results are validated with ground truth data which is provided by Central Water-board Commission(CWC).

scholarly journals Automated Filtering of Multibeam Water-Column Data to Detect Relative Abundance of Giant Kelp (Macrocystis pyrifera)

2020 ◽  
Vol 12 (9) ◽  
pp. 1371 ◽  
Author(s):  
Alexandre C. G. Schimel ◽  
Craig J. Brown ◽  
Daniel Ierodiaconou
Keyword(s):  
Water Column ◽  
Aquatic Vegetation ◽  
Macrocystis Pyrifera ◽  
Habitat Mapping ◽  
Giant Kelp ◽  
Experimental Site ◽  
Marine Habitat ◽  
Multibeam Echosounder ◽  
Slant Range ◽  
Marine Habitat Mapping

Modern multibeam echosounders can record backscatter data returned from the water above the seafloor. These water-column data can potentially be used to detect and map aquatic vegetation such as kelp, and thus contribute to improving marine habitat mapping. However, the strong sidelobe interference noise that typically contaminates water-column data is a major obstacle to the detection of targets lying close to the seabed, such as aquatic vegetation. This article presents an algorithm to filter the noise and artefacts due to interference from the sidelobes of the receive array by normalizing the slant-range signal in each ping. To evaluate the potential of the filtered data for the detection of aquatic vegetation, we acquired a comprehensive water-column dataset over a controlled experimental site. The experimental site was a transplanted patch of giant kelp (Macrocystis pyrifera) forest of known biomass and spatial configuration, obtained by harvesting several individuals from a nearby forest, measuring and weighing them, and arranging them manually on an area of seafloor previously bare. The water-column dataset was acquired with a Kongsberg EM 2040 C multibeam echosounder at several frequencies (200, 300, and 400 kHz) and pulse lengths (25, 50, and 100 μs). The data acquisition process was repeated after removing half of the plants, to simulate a thinner forest. The giant kelp plants produced evident echoes in the water-column data at all settings. The slant-range signal normalization filter greatly improved the visual quality of the data, but the filtered data may under-represent the true amount of acoustic energy in the water column. Nonetheless, the overall acoustic backscatter measured after filtering was significantly lower, by 2 to 4 dB on average, for data acquired over the thinned forest compared to the original experiment. We discuss the implications of these results for the potential use of multibeam echosounder water-column data in marine habitat mapping.

scholarly journals NeMO-Net – Gamifying 3D Labeling of Multi-Modal Reference Datasets to Support Automated Marine Habitat Mapping

2021 ◽  
Vol 8 ◽  
Author(s):  
Jarrett van den Bergh ◽  
Ved Chirayath ◽  
Alan Li ◽  
Juan L. Torres-Pérez ◽  
Michal Segal-Rozenhaimer
Keyword(s):  
Coral Reef ◽  
Citizen Science ◽  
Video Game ◽  
Habitat Mapping ◽  
Benthic Habitat ◽  
Marine Habitat ◽  
Shallow Marine ◽  
Learning Framework ◽  
User Data ◽  
Marine Habitat Mapping

NASA NeMO-Net, The Neural Multimodal Observation and Training Network for global coral reef assessment, is a convolutional neural network (CNN) that generates benthic habitat maps of coral reefs and other shallow marine ecosystems. To segment and classify imagery accurately, CNNs require curated training datasets of considerable volume and accuracy. Here, we present a citizen science approach to create these training datasets through a novel 3D classification game for mobile and desktop devices. Leveraging citizen science, the NeMO-Net video game generates high-resolution 3D benthic habitat labels at the subcentimeter to meter scales. The video game trains users to accurately identify benthic categories and semantically segment 3D scenes captured using NASA airborne fluid lensing, the first remote sensing technology capable of mitigating ocean wave distortions, as well as in situ 3D photogrammetry and 2D satellite remote sensing. An active learning framework is used in the game to allow users to rate and edit other user classifications, dynamically improving segmentation accuracy. Refined and aggregated data labels from the game are used to train NeMO-Net’s supercomputer-based CNN to autonomously map shallow marine systems and augment satellite habitat mapping accuracy in these regions. We share the NeMO-Net game approach to user training and retention, outline the 3D labeling technique developed to accurately label complex coral reef imagery, and present preliminary results from over 70,000 user classifications. To overcome the inherent variability of citizen science, we analyze criteria and metrics for evaluating and filtering user data. Finally, we examine how future citizen science and machine learning approaches might benefit from label training in 3D space using an active learning framework. Within 7 months of launch, NeMO-Net has reached over 300 million people globally and directly engaged communities in coral reef mapping and conservation through ongoing scientific field campaigns, uninhibited by geography, language, or physical ability. As more user data are fed into NeMO-Net’s CNN, it will produce the first shallow-marine habitat mapping products trained on 3D subcm-scale label data and merged with m-scale satellite data that could be applied globally when data sets are available.

scholarly journals Effect of track spacing and data interpolation on the interpretation of benthic community distributions derived from RoxAnn™ acoustic surveys

2003 ◽  
Vol 60 (6) ◽  
pp. 1288-1297 ◽  
Author(s):  
Eunice H Pinn ◽  
M.R Robertson
Keyword(s):  
Action Plan ◽  
Ground Truth ◽  
Habitat Types ◽  
Ground Truth Data ◽  
Seabed Sediment ◽  
Acoustic Data ◽  
Acoustic Surveys ◽  
Priority Habitat ◽  
The Uk ◽  
Site Identification

Abstract A 150 mile2 (388 km2) area in the South Minch on the Scottish west coast was surveyed acoustically using the seabed discrimination system RoxAnn™. This site was chosen from BGS seabed sediment maps because of the wide variety of substratum types present within a relatively small area. The work presented here investigates different combinations of survey track spacing in relation to interpolation of acoustic data for mapping benthic biodiversity. Three different survey track spacings (4, 2 and 1 km) and three pixel sizes (1000, 500 and 250 m) were utilised. The results indicated considerable variations in the fine scale variations of the substratum maps produced and their accuracy in relation to ground truth data. Depending on the track spacing and level of interpolation utilised, the survey site could be considered relatively important under the UK Biodiversity Action Plan in terms of priority habitat types present or completely insignificant. These variations have serious implications for the use of this technology in site identification, conservation and management.

Sign in / Sign up

Export Citation Format

Share Document