Boulders provide ecologically important hard grounds in shelf seas, and form protected habitats under the European Habitats Directive. Boulders on the seafloor can usually be recognized in backscatter mosaics due to a characteristic pattern of high backscatter intensity followed by an acoustic shadow. The manual identification of boulders on mosaics is tedious and subjective, and thus could benefit from automation. In this study, we train an object detection framework, RetinaNet, based on a neural network backbone, ResNet, to detect boulders in backscatter mosaics derived from a sidescan-sonar operating at 384 kHz. A training dataset comprising 4617 boulders and 2005 negative examples similar to boulders was used to train RetinaNet. The trained model was applied to a test area located in the Kriegers Flak area (Baltic Sea), and the results compared to mosaic interpretation by expert analysis. Some misclassification of water column noise and boundaries of artificial plough marks occurs, but the results of the trained model are comparable to the human interpretation. While the trained model correctly identified a higher number of boulders, the human interpreter had an advantage at recognizing smaller objects comprising a bounding box of less than 7 × 7 pixels. Almost identical performance between the best model and expert analysis was found when classifying boulder density into three classes (0, 1-5, more than 5) over 10,000 m 2 areas, with the best performing model reaching an agreement with the human interpretation of 90%.
This study contributes to a better understanding of geogenic reef distribution in the southern Baltic Sea and highlights the implications of survey-related factors on automated boulder classification when utilizing data from multiple surveys. The distribution of hard grounds and reefs is needed as a baseline for geological and biological studies, but also for offshore construction, navigation and coastal management. In this study we provide maps of the distribution of geogenic reefs for about 750 km2 in the southern Baltic Sea, at the sites Wismar Bay, Darss Sill and Plantagenet Ground. The maps are based on full-coverage backscatter surveys with different side scan sonar and multibeam echo sounder systems. The distribution and number of boulders in the backscatter maps was determined using a convolutional neural network combined with quality control by human experts. The extent of the geogenic reefs was calculated on the basis of the number of boulders in 50 m x 50 m grid cells. We compare the results with previous reef maps based on point sampling, which show reefs of either biogenic or geogenic origin. According to the earlier maps, 11% of the Plantagenet Ground seabed was classified as reef habitat type. This is similar to the result of our study (12%), although we only considered reefs of geogenic origin. In the Darss Sill, geogenic reefs are larger in this study than in previous maps (30% versus 23%). In both regions, the spatial distribution of reefs differs significantly between old and new maps. For Wismar Bay, previous maps classify 3% of the seafloor as habitat type reef, whereas this study classifies 35% as geogenic reef. The use of automated classification during seafloor mapping allowed large areas to be interpreted in a few days. It also provided more information on the distribution of boulders within the geogenic reef. However, the boulder distribution maps show the negative effects of survey geometry, frequency and environmental conditions on automated boulder classification when data from different surveys are combined.
<p>The increasing demand by national legislation and European marine policy amplifies the need for high resolution and area-wide habitat maps of the seafloor. The basis for a consistent and objective delineation of habitats is a consistent derivation of sediment classes. For this reason, the German Federal Maritime and Hydrographic Agency (BSH) has published a guideline for high-resolution, hydroacoustic sediment mapping, with the advice of scientific experts. Large areas within the German exclusive economic zone, in particular in the special areas of conservation (SAC) have already been mapped in agreement with this guideline.</p><p>We will introduce the mapping guideline and its sediment classification system, present the mapping progress and demonstrate the successful use of sediment maps for the creation of habitat maps. The approach by the BSH works very well for the large-scale mapping of the German North and Baltic Sea. However, more specific tasks like environmental investigations for approval procedures or scientific questions need adjustments to the mapping criteria. We will show this exemplary for hard substrate habitats. According to the guideline of the BSH (update is in progress), hard substrates presence is given as raster information with cell size of at least 100 x 100 m. For e.g. approval procedures, this raster information is not sufficient to map the protected natural habitat &#8220;reefs&#8221; in a large scale. Therefore, the German Federal Agency for Nature Conservation (BfN) has developed its own criteria where individual objects have to be detected. The object detection is still to be done manually which might be acceptable for small study sites, but not practicable for large-scale mapping. Consequently, current work is concerned with the automation of object detection to speed up the interpretation and make it objective / reproducible.</p>
<p>Sublittoral hard substrates, for example formed by blocks and boulders, are hotspots for marine biodiversity, especially for benthic communities. Knowledge on boulder occurrence is also important for marine and coastal management, including offshore wind parks and safety of navigation. The occurrence of boulders have to be reported by member states to the European Union. Typically, boulders are located by acoustic surveys with multibeam echo sounders and side scan sonars. The manual interpretation of these data is subjective and time consuming. This presentation reports on recent work concerned with the detection of boulders in different acoustic datasets by convolutional neural networks, highlighting current approaches, challenges and future opportunities.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.