Abstract Replanning paths in emergencies is essential for the successful completion of coverage tasks. In this context, this study specifically focuses on centralized path replanning for multiple autonomous underwater vehicles (AUVs) equipped with side-scan sonar, aiming to efficiently allocate uncovered regions and plan optimal paths for covering these assigned areas. The issue is formulated as a customized multi-robot multi-regional coverage path planning (M $$ ^{2} $$ 2 CPP) problem. Taking account of the limited AUV energies, vulnerable imaging quality and paths’ structure, this study proposes a novel lawn-mower and cooperative co-evolution (LMCC) method. First, the lawnmower method is adopted to determine the intra-region paths as well as the entrance and exit locations of each region. Then, a customized cooperative co-evolution method is proposed to solve optimal region assignment, visiting order, and entrance positions. Additionally, a novel and simple population division strategy is designed for coding the area assignment results efficiently. According to simulation results, the LMCC method can balance AUV workloads and generate optimal paths based on positions and energies. In addition, fewer paths connect different regions to ensure that there is an adequate supply of energy to cover them which is an innovation abstracted from real task scenarios.

Feature super-resolution-based method for small-scale target detection and segmentation in side-scan sonar

Side-scan sonar imaging is essential for underwater target detection in marine exploration and engineering applications, yet small target detection faces significant challenges including limited frequency domain feature utilization, insufficient multi-scale feature fusion, and high computational complexity. This study develops Multi-Scale Spatial-Frequency Collaborative Detection Transformer (MSF-DETR), a novel end-to-end automatic detection algorithm specifically designed for small targets in side-scan sonar images. The method integrates three core innovations: a Multi-domain Adaptive Spatial-frequency Network (MASNet) backbone employing Cascaded dual-domain Mamba-enhanced Spatial-frequency Synergistic Convolution that simultaneously captures spatial geometric and frequency domain texture features; a Hierarchical Multi-scale Adaptive Feature Pyramid Network implementing intelligent weight allocation across different scales; and an Efficient Sparse Attention Transformer Encoder utilizing Window-based Adaptive Sparse Self-Attention mechanism that reduces computational complexity from quadratic to linear. Experimental validation was conducted on the self-built SSST-3K(Side-Scan Sonar Target Detection 3K Dataset) dataset containing approximately 3000 high-quality sonar images and the public KLSG dataset. Results demonstrate that MSF-DETR achieves 78.5% mAP50 and 38.5% mAP50-95 on the SSST-3K dataset, representing improvements of 2.8% and 3.3% respectively compared to baseline RT-DETR, while reducing computational complexity by 12.0% and achieving 71.2 FPS inference speed. The proposed MSF-DETR provides an effective solution for small target detection in complex marine environments, significantly advancing underwater sonar image processing technology.

Population estimates are a key component of fisheries management, particularly when assessing species of concern. However, the time and effort required to conduct those estimates logistically limits their frequency. To facilitate assessment of Shortnose Sturgeon (Acipenser brevirostrum; SNS) which are a species of concern in the Saint John River, New Brunswick, Canada, a combined side-scan sonar and acoustic telemetry-based method was employed to enumerate SNS within high density winter aggregations. During this study 12,005 SNS were enumerated in one main winter aggregation and 2,186 SNS were counted within a second in the Kennebecasis Bay. Winter residency patterns determined from acoustic tracking of 18 tagged SNS over 8 years (2015/16-2022/23) indicated that these two aggregations represented on average 74.3% of the overall population suggesting that the total Saint John River population was ~19,100 SNS > 40 cm FL in winter 2022/23. Although the development of more in depth, robust, and repeated assessments are needed to verify this estimate of abundance and size classes, we conclude that the abundance of SNS in the Saint John River has probably remained stable since the earliest population estimate completed in 1977.

Historically, the Mediterranean Sea has been an area of cultural exchange and maritime commerce. One out of many submerged archaeological sites is the Roman shipwreck that was discovered in 2006 off the coast of Santo Stefano al Mare, in the Ligurian Sea, Italy. The wreck was dated to the 1st century B.C. and consists of a well-preserved cargo ship of Roman amphorae that were likely used for transporting wine. In this study, we present the results of the first underwater survey of the wreck using an Autonomous Underwater Vehicle (AUV) industrialized by Graal Tech. The AUV was equipped with a NORBIT WBMS multibeam sonar, a 450 kHz side-scan sonar, and inertial navigation systems. The AUV conducted multiple high-resolution surveys on the wreck site and the collected data were processed using geospatial analysis methods to highlight local anomalies directly related to the presence of the Roman shipwreck. The main feature was an accumulation of amphorae, covering an area of approximately 10 × 7 m with a maximum height of 1 m above the seabed. The results of this interdisciplinary work demonstrated the effectiveness of integrating AUV technologies with spatial analysis techniques for underwater archaeological applications. Furthermore, the success of this mission highlighted the potential for broader applications of AUVs in the study of the seafloor, such as monitoring seabed movements related to offshore underground energy storage or the identification of objects lying on the seabed, such as cables or pipelines.

Amazon River dolphins often form multi-species aggregations at water confluences. This study used a multi-year data set to examine dolphins, fish, and geomorphology at dolphin aggregations. Methods included dolphin transect surveys, dolphin point counts, net and line fish captures, side-scan sonar, and eDNA analyses at five dolphin aggregations and two control sites. Amazon River dolphins (Inia geoffrensis and Sotalia fluviatlis) are typically found at aggregation sites that occur at water confluences that have greater dolphin numbers than control sites. The confluences had riverbed depressions averaging six metres in depth where fish were concentrated. Pink river dolphins preferred to form aggregations in flooded forest tributaries and large rivers, while grey river dolphins preferred the larger rivers. There were eighty-nine fish species at the confluences within the size of fish consumed by dolphins, and a higher abundance of fish occurred in and around the aggregation sites compared to control sites. The number of dolphins present at the aggregation sites correlated with fish abundance. Dolphin life history, such as fishing, resting, raising calves, and social interactions, occur at the aggregation sites. The aggregation sites are important conservation areas of the endangered pink and grey river dolphins, and through their folklore, Indigenous people living at confluence sites assist in the conservation of the aggregations and have lived with dolphins at confluences for thousands of years, contributing to their survival.

Three-dimensional reconstruction of shallow seabed topographic surface based on fusion of side-scan sonar and echo sounding data

This article presents the development of software designed for the automated generation of geospatial data from hydroacoustic echograms obtained via side-scan sonar (SSS). SSS is a key tool for mapping the underwater environment, allowing for high-resolution echograms of the bottom and coastal zone. The combination of SSS data with satellite navigation (GPS) creates conditions for an accurate geospatial representation of underwater features, which is critical for oceanographic research, engineering work and environmental monitoring. Software processing of "raw" (initial) SSS data requires several stages: separation of port and starboard channels, reading GPS tags, smoothing the ship's track and converting echogram pixels into a georeferenced raster. The primary objective is to create a tool that facilitates efficient processing and visualization of SSS data, enabling the georeferencing of results in the GeoTIFF format. The developed software implements algorithms for preliminary signal processing, noise filtering, coordinate transformation, and the automatic creation of echogram mosaics. The practical application of this tool is demonstrated through a case study of surveying a section of the Dnipro River channel, resulting in high-quality geospatial images of the riverbed. The outcomes indicate the effectiveness of the proposed approach for integrating hydroacoustic data into geographic information systems (GIS), thereby opening new opportunities for monitoring aquatic ecosystems and supporting scientific research in the field of oceanography.

The detection of seabed boulders is a critical step in mitigating geological hazards during the planning and construction of offshore wind energy infrastructure, as well as in supporting benthic ecological and palaeoglaciological studies. Traditionally, side-scan sonar (SSS) has been favoured for such detection, but the growing availability of high-resolution multibeam echosounder (MBES) data offers a cost-effective alternative. This study presents a semi-automated, hybrid GIS-AI approach that combines bathymetric position index filtering and a Random Forest classifier to detect boulders and delineate boulder fields from MBES data. The method was tested on a 0.24 km2 site in Long Island Sound using 0.5 m resolution data, achieving 83% recall, 73% precision, and an F1-score of 77—slightly outperforming the average of expert manual picks while offering a substantial improvement in time-efficiency. The workflow was validated against a consensus-based master dataset and applied across a 79 km2 study area, identifying over 75,000 contacts and delineating 89 contact clusters. The method enables objective, reproducible, and scalable boulder detection using only MBES data. Its ability to reduce reliance on SSS surveys while maintaining high accuracy and offering workflow customization makes it valuable for geohazard assessment, benthic habitat mapping, and offshore infrastructure planning.

Abstract Comprehensive knowledge of habitat requirements is vital to the conservation of species. The dynamic environments inhabited by stream‐dwelling taxa are particularly complex and challenging to describe. We investigated habitat selection across multiple spatial scales to identify key habitat characteristics of the flattened musk turtle (Sternotherus depressus), which is a federally threatened species that is poorly studied and imperiled by habitat destruction. From 2013 to 2018, we conducted trapping, visual encounter, and habitat surveys while employing radio telemetry and side scan sonar to explore habitat selection at the population, within home range, and microhabitat levels. Study sites comprised relatively small, second‐ to fourth‐order streams in Alabama, USA. Turtles selected bedrock or rock substrates across multiple scales, while snail prey affected selection only at the within‐home‐range scale. At the within‐home‐range scale, turtles selected deeper water. Though inconclusive because 95% confidence intervals overlapped 0, relationships trended toward support for larger streams and more bedrock substrate at the population scale. Results demonstrate that spatial hierarchy of habitat use is relevant to management of riverine turtles. By replicating our habitat survey methods in other streams throughout the flattened musk turtle range, data from this study will aid in identifying areas to focus conservation efforts and provide quantifiable goals for restoration projects. Our research identifies the crucial role of rock and bedrock structures, though these habitat features are threatened by anthropogenic sedimentation.

Представлены результаты изучения гравитационных процессов в Черноморской впадине по данным мультичастотного сейсмоакустического профилирования, гидролокации бокового обзора и многолучевого эхолотирования. Рассмотрены примеры проявления на сейсмоакустических разрезах отложений подводных оползней и гравитационных потоков. Особое внимание уделено интерпретации данных, полученных с использованием автономного необитаемого подводного аппарата в глубоководной зоне моря. The results of studying gravity processes in the Black Sea basin based on data from multifrequency continuous seismic profiling, sidescan sonar, and echo sounding are presented. Examples of the occurrence of underwater landslides and gravity flows on seismic acoustic sections of sediments are considered. Special attention is paid to the interpretation of data obtained using an autonomous uninhabited underwater vehicle in the deep-sea zone.

Side-scan sonar (SSS) image classification is crucial for underwater applications, but the trade-off between the accuracy afforded by high-resolution images and the associated computational cost challenges deployment, particularly on resource-constrained platforms like AUVs. This study systematically investigates and quantifies this accuracy–efficiency trade-off in SSS image classification by varying input resolution. Using two distinct SSS datasets and a resolution-adaptive deep learning strategy employing MobileNetV2 and ResNet variants across six resolutions, we evaluated classification accuracy and computational metrics. Results demonstrate a clear inverse relationship: decreasing resolution significantly reduces computational load and processing times but lowers classification accuracy, with the degradation being more pronounced for the more complex four-class dataset. Notably, model test accuracy did not necessarily increase monotonically with resolution. Importantly, acceptable accuracy levels above 90% or 80% could be maintained at significantly lower resolutions, offering substantial efficiency gains. In conclusion, strategically reducing SSS image resolution based on application-specific accuracy requirements is a viable approach for optimizing computational resources. This work provides a quantitative framework for navigating this trade-off and underscores the need for developing SSS-specific architectures for future advancements.

Using deep-towed side-scan sonar (SSS) and sub-bottom profiler (SBP) data, we have investigated the hydrothermal activity around the Mienhua submarine volcano (MHV) at the northern margin of the southern Okinawa Trough. Our result reveals widespread acoustic transparent zones (TZs) in the shallow subsurface, which are generally interpreted as porous strata filled with hydrothermal fluid. These acoustic transparent zones exhibit lateral thinning and overpressure characteristics. Because the fluid channels are usually found beneath the thicker part of the transparent zones, a vertical migration of the hydrothermal fluid at depth and a horizontal migration or diffusion of the hydrothermal fluid in shallow high-porosity sediments are suggested. Our SBP profiles indicate multiple fluid channels vertically cutting through sedimentary layers and connecting with the upper TZs. The over-pressured hydrothermal fluid sometimes escapes from the seafloor and forms gas flares in the seawater column. The associated chimney structures (possibly black smokers) at the seafloor can be observed in the SSS imagery. The existence of the fluid channels, TZs, chimney features, and gas flares indicates an active and focused hydrothermal activity. However, the hydrothermal activity is vigorous in the eastern side of MHV. In contrast, the western and southern sides of the MHV display a waning or cessation of the hydrothermal activity, because of few chimney structures, seabed subsidence, and almost no gas flares. The hydrothermal activity in the MHV area reveals a temporal and spatial shift from west to east. By calculating the distribution of the mound-like or chimney structures from the SSS data, we estimate that the possibly hydrothermal mineralization area is approximately 2.2 km2. Our findings provide important insights into a submarine hydrothermal activity that is helpful for potential seabed mining in the MHV area.

The integrity of submarine pipelines and cables is crucial for safeguarding marine oil, gas, and information transmission, as well as ecological security. Employing automated identification of side-scan sonar (SSS) images can enhance marine geophysical survey efficiency, enabling high-frequency assessment of seabed anthropogenic footprints. However, there is a notable gap in research regarding the comparative performance of different models and the impact of data expansion. This study presents an in-depth comparison of various convolutional neural network (CNN) models-specifically, AlexNet, GoogleNet, and VGG-16-focusing on their prediction accuracy and computational efficiency in analyzing SSS datasets. Our findings reveal that GoogleNet outperforms the others, offering superior prediction accuracy with balanced computational demands. While AlexNet is less accurate, it is beneficial for scenarios with limited computational resources. Conversely, VGG-16 shows comparatively weaker performance, making it less suitable for SSS image analysis. Notably, data expansion significantly influences model accuracy, although its impact varies across different models. This research contributes critical insights into model selection for marine geological applications, demonstrating the potential of intelligent interpretation systems in modern marine geology.

ABSTRACT Poor feature representation, confusing background topography, and excessive data volume render detecting sparse targets in large-size acoustic imagery challenging. Especially when conducting real-time processing tasks, accuracy and speed are required to be optimized with limited computational resources. Therefore, this paper proposes an efficient method for real-time side-scan sonar (SSS) image processing and detection of sparse targets in large-scale images. Primarily, an intelligent real-time processing method is proposed for the raw SSS data to acquire high-quality SSS images. Aiming at the characteristics of large-size SSS images and sparse targets, we propose an innovative two-stage inference method: The SSS image slices are pre-classified based on the MobileViTv3-XXS model, and then the optimized detection model of RepVGG+YOLOv5m is employed for target detection of image slices containing targets. Experiments show that real-time preprocessing yields SSS images with an average PSNR of 27.112 and SSIM of 0.816, comparable to the post-processing methods. Meanwhile, it maintains high efficiency and achieves 88.2% mAP, significantly outperforming the slice-only method in detection accuracy and efficiency.

DBAC: A Novel Method for Grayscale Correction of Underwater Pipeline Images Using Side-Scan Sonar

For endangered shortnose sturgeon (Acipenser brevirostrum), the ability to estimate and monitor population size is critical for tracking species’ recovery. Yet, contemporary abundance estimates have not been completed for many shortnose sturgeon populations, largely owing to the difficulty in using traditional abundance estimators for sturgeons. Here, we estimate the adult shortnose sturgeon population size of the Hudson River, NY by integrating data from two largely passive sampling methods – acoustic telemetry and side-scan sonar – into a Bayesian hierarchical model of abundance. We estimated the adult abundance to be 69,798 individuals (95% CI = 9,207-185,666), making the Hudson River the largest extant shortnose sturgeon population. Despite this, the population remains vulnerable to localized disturbances, as over 40% of the population congregated in a small overwintering habitat that coincides with an area of high anthropogenic activity. Accordingly, recurrent demographic surveys may be beneficial for gaining insight into the relative effects of anthropogenic and naturally stochastic processes shaping shortnose sturgeon demography. Our modeling framework provides a relatively low-cost alternative for future demographic monitoring of species of conservation concern.

The authors describe creating a corporate template for a spatial database that allows collecting all materials obtained during sea engineering complex geological and geophysical surveys conducted by the JSC Marine Arctic Geological Expedition into a systematized structure. Organization, features and functionality of the database are considered due to the data collected in 2022 as a result of field work aimed at justifying the feasibility of using a site on the Kara Sea shelf for the place of a semi-submersible drilling rig. The developed database is unique for the region, but at the same time universal for the specifics of the research. It does not only provide for the storage of information on a wide variety of work types (including high-resolution seismic exploration, low- and high-frequency continuous seismoacoustic profiling, side-scan sonar, differential magnetometry, multibeam bathymetric survey, sampling and electrical exploration using the near-zone field establishment sounding method) but also serves as a convenient tool for preparing a unified catalog of thematic maps

Coastal zone management necessitates a comprehensive and shared interdisciplinary understanding of the various processes involved in the anthropogenically accelerated rapid spatiotemporal evolution, including the climatic perspective, that defines the littoral system. This study aims to present an initial assessment of the atypical occurrence and distribution of biogenic reefs belonging to the Sabellariidae family on the sandy coastal beds of the northern Adriatic Sea. Although sporadic mentions of their potential presence have been made, their specific locations and distribution have never been accurately identified and mapped. These fragile biogenic reefs have the potential to serve a functional role in coastal ecosystems, as recognized by the conservation strategies of the Mediterranean and the objectives of the EU Habitats Directive. In addition to describing the primary physiographic, physical-dynamic, and environmental characteristics of the study area, this article outlines the key findings from preliminary geomorphological-sedimentological investigations and compares them with similar Sabellaria structures studied in diverse environmental conditions along the Italian coasts. The research conducted thus far, utilizing side-scan sonar and direct observations by scuba divers, has confirmed their coherence and functionality as valuable habitats and hotspots.

Abstract With the rapid advancement of unmanned technology, autonomous underwater vehicles equipped with side-scan sonar are playing an increasingly vital role in the realm of underwater exploration. The detection of underwater small targets such as mine-like objects, unexploded ordnance, and rod-shaped items is a focal point of current sonar technology research, playing a crucial role in military struggle. However, existing methods overly rely on the prior shadow information and are prone to missing numerous small targets. To address this, we propose a weighted SSS patch-image model. The method is an improved method for small target detection in SSS images based on iterative steering kernel regression and patch-image model. The method enables effective detection of small targets without considering shadow information. Firstly, kernel regression is employed using steering kernels to denoise the images while preserving edge information. Subsequently, a small target detection model is constructed using the patch-image model by considering the reconstructed SSS image, the target image, the background image, and the noise image. According to the experimental results, the improved small target detection method combining the two aforementioned algorithms demonstrates high accuracy and reliability in detecting underwater small targets on SSS images. Comparative experiments further reveal that this approach overcomes the limitations of traditional methods that rely heavily on target shadow information, establishing it as an efficient and robust solution for underwater small target detection in SSS images.