Search Results (2,469)

Vessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models failing to meet the accuracy requirements for practical applications. In this paper, we first construct a novel remote sensing vessel image dataset that includes various complex scenarios and enhance the data volume and diversity through data augmentation techniques. Secondly, we address the class imbalance between foreground (small vessels) and background in remote sensing imagery from two perspectives: the sensitivity of IoU metrics to small object localization errors and the innovative design of a cost-sensitive loss function. Specifically, at the dataset level, we select vessel targets appearing in the original dataset as templates and randomly copy–paste several instances onto arbitrary positions. This enriches the diversity of target samples per image and mitigates the impact of data imbalance on the detection task. At the algorithm level, we introduce the Normalized Wasserstein Distance (NWD) to compute the similarity between bounding boxes. This enhances the importance of small target information during training and strengthens the model’s cost-sensitive learning capabilities. Ablation studies reveal that detection performance is optimal when the weight assigned to the NWD metric in the model’s loss function matches the overall proportion of small objects in the dataset. Comparative experiments show that the proposed NWD-YOLO achieves Precision, Recall, and ${\mathrm{AP}}_{50}$ scores of 0.967, 0.958, and 0.971, respectively, meeting the accuracy requirements of real-world applications. Full article

Growing concern over anthropogenic underwater noise, highlighted by initiatives like the Marine Strategy Framework Directive (MSFD) and its Technical Group on Underwater Noise (TG Noise), emphasizes regions like the Western Black Sea, where increasing activities threaten marine habitats. This region is experiencing rapid growth in maritime traffic and resource exploitation, which is intensifying concerns over the noise impacts on its unique marine habitats. While machine learning offers promising solutions, a research gap persists in comprehensively evaluating diverse ML models within an integrated framework for complex underwater acoustic data, particularly concerning real-world data limitations like class imbalance. This paper addresses this by presenting a multi-faceted framework using passive acoustic monitoring (PAM) data from fixed locations (50–100 m depth). Acoustic data are processed using advanced signal processing (broadband Sound Pressure Level (SPL), Power Spectral Density (PSD)) for feature extraction (Mel-spectrograms for deep learning; PSD statistical moments for classical/unsupervised ML). The framework evaluates Convolutional Neural Networks (CNNs), Random Forest, and Support Vector Machines (SVMs) for noise event classification, alongside Gaussian Mixture Models (GMMs) for anomaly detection. Our results demonstrate that the CNN achieved the highest classification accuracy of 0.9359, significantly outperforming Random Forest (0.8494) and SVM (0.8397) on the test dataset. These findings emphasize the capability of deep learning in automatically extracting discriminative features, highlighting its potential for enhanced automated underwater acoustic monitoring. Full article

Accurate and rapid aquatic organism recognition is a core technology for fisheries automation and aquatic organism statistical research. However, due to absorption and scattering effects, images of aquatic organisms often suffer from poor contrast and color distortion. Additionally, the clustering behavior of aquatic organisms often leads to occlusion, further complicating the identification task. This study proposes a lightweight object detection model, Mobile-YOLO, for the recognition of four representative aquatic organisms, namely holothurian, echinus, scallop, and starfish. Our model first utilizes the Mobile-Nano backbone network we proposed, which enhances feature perception while maintaining a lightweight design. Then, we propose a lightweight detection head, LDtect, which achieves a balance between lightweight structure and high accuracy. Additionally, we introduce Dysample (dynamic sampling) and HWD (Haar wavelet downsampling) modules, aiming to optimize the feature fusion structure and achieve lightweight goals by improving the processes of upsampling and downsampling. These modules also help compensate for the accuracy loss caused by the lightweight design of LDtect. Compared to the baseline model, our model reduces Params (parameters) by 32.2%, FLOPs (floating point operations) by 28.4%, and weights (model storage size) by 30.8%, while improving FPS (frames per second) by 95.2%. The improvement in mAP (mean average precision) can also lead to better accuracy in practical applications, such as marine species monitoring, conservation efforts, and biodiversity assessment. Furthermore, the model’s accuracy is enhanced, with the mAP increased by 1.6%, demonstrating the advanced nature of our approach. Compared with YOLO (You Only Look Once) series (YOLOv5-12), SSD (Single Shot MultiBox Detector), EfficientDet (Efficient Detection), RetinaNet, and RT-DETR (Real-Time Detection Transformer), our model achieves leading comprehensive performance in terms of both accuracy and lightweight design. The results indicate that our research provides technological support for precise and rapid aquatic organism recognition. Full article

Vibrios are widespread in marine environments, and their persistence is often linked to natural reservoirs such as filter-feeding bivalves. This study investigated the capacity of the Mediterranean mussel, Mytilus galloprovincialis, to act as a reservoir of Vibrio harveyi using a GFP-tagged strain in controlled experiments. Mussels (shell length 4–6 cm) were exposed to V. harveyi gfp in estuarine and seawater at 12 °C and 20 °C over six days. Bacterial accumulation in gills, digestive gland, and gonads, as well as in feces and pseudofeces, was quantified, and the immune response following microbial challenge was assessed by histopathological analysis. Mussels actively removed V. harveyi from the water, but not completely. Vibrios were rapidly accumulated in organs, with the highest densities in the digestive gland (up to 10⁷–10⁸ CFU g⁻¹), and substantial bacterial loads detected in biodeposits (1.55–3.77 × 10⁷ CFU g⁻¹). Salinity had a greater effect than temperature on bacterial accumulation, with consistently higher counts in seawater assays. Concurrently with bacterial accumulation, mussels activated their immune system, as evidenced by the detection of granulocytomas and hemocytic infiltrations. Overall, these results demonstrate that M. galloprovincialis accumulates V. harveyi in tissues and biodeposits, serving as a natural reservoir for this bacterium. Full article

Excessive levels of Pb²⁺ and Cd²⁺ in seawater pose significant combined toxicity to marine organisms, resulting in harmful effects and further threatening human health through biomagnification in the food chain. Traditional methods for detecting marine Pb²⁺ and Cd²⁺ rely on laboratory analyses, which are hindered by limitations such as sample degradation during transport and complex operational procedures. In this study, we present an electrochemical sensor based on intelligent mobile detection devices. By combining G-COOH-MWCNTs/ZnO with differential pulse voltammetry, the sensor enables the efficient, simultaneous detection of Pb²⁺ and Cd²⁺ in seawater. The G-COOH-MWCNTs/ZnO composite film is prepared via drop-coating and is applied to a glassy carbon electrode. The film is characterized using cyclic voltammetry, electrochemical impedance spectroscopy, and scanning electron microscopy, while Pb²⁺ and Cd²⁺ are quantified using differential pulse voltammetry. Using a 0.1 mol/L sodium acetate buffer (pH 5.5), a deposition potential of −1.1 V, and an accumulation time of 300 s, a strong linear correlation was observed between the peak response currents of Pb²⁺ and Cd²⁺ and their concentrations in the range of 25–450 µg/L. The detection limits were 0.535 µg/L for Pb²⁺ and 0.354 µg/L for Cd²⁺. The sensor was applied for the analysis of seawater samples from Maowei Sea, achieving recovery rates for Pb²⁺ ranging from 97.7% to 103%, and for Cd²⁺ from 97% to 106.1%. These results demonstrate that the sensor exhibits high sensitivity and stability, offering a reliable solution for the on-site monitoring of heavy metal contamination in marine environments. Full article

The ocean encompasses the majority of the Earth’s surface and harbors substantial energy resources. Nevertheless, the intricate and asymmetrically distributed underwater environment renders existing target detection performance inadequate. This paper presents an enhanced YOLOv8s approach for underwater robot object detection to address issues of subpar image quality and low recognition accuracy. The precise measures are enumerated as follows: initially, to address the issue of model parameters, we optimized the ninth convolutional layer by substituting certain conventional convolutions with adaptive deformable convolution DCN v4. This modification aims to more effectively capture the deformation and intricate features of underwater targets, while simultaneously decreasing the parameter count and enhancing the model’s ability to manage the deformation challenges presented by underwater images. Furthermore, the Triplet Attention module is implemented to augment the model’s capacity for detecting multi-scale targets. The integration of low-level superficial features with high-level semantic features enhances the feature expression capability. The original CIoU loss function was ultimately substituted with Shape IoU, enhancing the model’s performance. In the underwater robot grasping experiment, the system shows particular robustness in handling radial symmetry in marine organisms and reflection symmetry in artificial structures. The enhanced algorithm attained a mean Average Precision (mAP) of 87.6%, surpassing the original YOLOv8s model by 3.4%, resulting in a marked enhancement of the object detection model’s performance and fulfilling the real-time detection criteria for underwater robots. Full article

Fish kills are sudden mass mortalities that occur in freshwater and marine systems worldwide. Fish kill surveys are essential for assessing the ecological and economic impacts of fish kill events, but are often labor-intensive, time-consuming, and spatially limited. This study aims to address these challenges by exploring the application of unoccupied aerial systems (or drones) and deep learning techniques for coastal fish carcass detection. Seven flights were conducted using a DJI Phantom 4 RGB quadcopter to monitor three sites with different substrates (i.e., sand, rock, shored Sargassum). Orthomosaics generated from drone imagery were useful for detecting carcasses washed ashore, but not floating or submerged carcasses. Single shot multibox detection (SSD) with a ResNet50-based model demonstrated high detection accuracy, with a mean average precision (mAP) of 0.77 and a mean average recall (mAR) of 0.81. The model had slightly higher average precision (AP) when detecting large objects (>42.24 cm long, AP = 0.90) compared to small objects (≤14.08 cm long, AP = 0.77) because smaller objects are harder to recognize and require more contextual reasoning. The results suggest a strong potential future application of these tools for rapid fish kill response and automatic enumeration and characterization of fish carcasses. Full article

Industry currently generates numerous substances, such as food additives, whose environmental impacts, particularly in marine environments, remain inadequately assessed. This study employed Aurelia aurita for the first time as a model organism to evaluate the toxicity of such compounds. The main goal was to evaluate the toxicity of two food additives, 2-methyl-1-phenylpropan-2-ol (S1) and 1-phenylethan-1-ol (S2), on A. aurita ephyrae, comparing the results with other organisms representing different trophic levels, specifically the alga Phaeodactylum tricornutum and the crustacean Artemia salina. Acute toxicity tests were conducted on each organism. In A. aurita, S1 exhibited high toxicity (LC₅₀ ≈ 10 mg/L), while S2 had lower toxicity (LC₅₀ ≈ 80 mg/L). The pulsation frequency data for A. aurita revealed that S1 initially increased the pulsation rates at lower concentrations (maximum at 10 mg/L), followed by a significant decrease at higher concentrations. Conversely, S2 showed a steady decrease in pulsation rates up to 10 mg/L, with a slight increase at concentrations of 15, 20, and 25 mg/L. The results demonstrate varying sensitivities to the toxic effects of the two compounds across different trophic levels, with A. aurita ephyrae being the most sensitive. This suggests the potential efficacy of jellyfish as novel ecotoxicological models due to their heightened sensitivity, enabling the detection of lower contaminant concentrations in test samples. Further research is required to enhance the efficiency of ecotoxicological assays using this model. Full article

The rapid advancement of environmental DNA (eDNA) technology has transformed ecological research, particularly in aquatic ecosystems. However, the optimal sampling matrix (e.g., water or sediment) and the potential for eDNA to replace or complement traditional underwater visual census (UVC) remain unclear. Here, we integrate water eDNA, sediment eDNA, and UVC approaches to systematically compare the diversity of benthic macrofauna in the subtidal zones of the Nanji Islands, China. Our results show that sediment eDNA samples exhibited the highest species richness, while UVC had the lowest. Each method revealed distinct species profiles, with relatively few shared taxa at the order level and below. Environmental eDNA showed significant advantages in detecting key phyla such as Annelida and Arthropoda. In contrast, traditional UVC was crucial for identifying certain taxa, such as Bryozoa, which were undetectable by eDNA methods. The low overlap in species detected by these methods underscores their complementary nature, highlighting the necessity of integrating multiple approaches to achieve a more comprehensive and accurate biodiversity assessment. Future research should focus on refining eDNA techniques, such as developing more universal primers, to further enhance their applicability in biodiversity monitoring. Full article

Ship seismic wave signals represent one of the most critical physical field characteristics of vessels. To achieve the high-precision detection of ship seismic wave field signals in marine environments, an underwater seismic wave signal detection system was designed. The system adopts a three-stage architecture consisting of watertight instrument housing, a communication circuit, and a buoy to realize high-capacity real-time data transmissions. The host computer performs the collaborative optimization of multi-modal hardware architecture and adaptive signal processing algorithms, enabling the detection of ship targets in oceanic environments. Through verification in a water tank and sea trials, the system successfully measured seismic wave signals. An improved ALE-LOFAR (Adaptive Line Enhancer–Low-Frequency Analysis) joint framework, combined with DEMON (Demodulation of Envelope Modulation) demodulation technology, was proposed to conduct the spectral feature analysis of ship seismic wave signals, yielding the low-frequency signal characteristics of vessels. This scheme provides an important method for the covert monitoring of shallow-sea targets, providing early warnings of illegal fishing and ensuring underwater security. Full article

Saxitoxin (STX) is a potent toxin produced by marine dinoflagellates and freshwater or brackish water cyanobacteria, and is a member of the paralytic shellfish toxins (PSTs). As a highly specific blocker of voltage-gated sodium channels (NaVs), STX blocks sodium ion influx, thereby inhibiting nerve impulse transmission and leading to systemic physiological dysfunctions in the nervous, respiratory, cardiovascular, and digestive systems. Severe exposure can lead to paralysis, respiratory failure, and mortality. STX primarily enters the human body through the consumption of contaminated shellfish, posing a significant public health risk as the causative agent of paralytic shellfish poisoning (PSP). Beyond its acute toxicity, STX exerts cascading impacts on food safety, marine ecosystem integrity, and economic stability, particularly in regions affected by harmful algal blooms (HABs). Moreover, the complex molecular structure of STX—tricyclic skeleton and biguanide group—and its diverse analogs (more than 50 derivatives) have made it the focus of research on natural toxins. In this review, we traced the discovery history, chemical structure, molecular biosynthesis, biological enrichment mechanisms, and toxicological actions of STX. Moreover, we highlighted recent advancements in the potential for detection and treatment strategies of STX. By integrating multidisciplinary insights, this review aims to provide a holistic understanding of STX and to guide future research directions for its prevention, management, and potential applications. Full article

Recently, China has become a hotspot for farming golden pompano (Trachinotus ovatus), a commercially valuable marine fish. The genetic mechanisms underlying ovarian development, particularly those regulated by insulin-like growth factors (IGFs), remain poorly understood. Existing research on T. ovatus has focused primarily on growth metrics, developmental stages, and immune responses, leaving a critical gap in knowledge regarding the hepatic regulatory pathways activated by IGFs. In this study, differentially expressed genes (DEGs) were detected through RNA sequencing (RNA-Seq) and associated pathways in response to IGF treatment. Comparisons between the IGF1, IGF2, and IGF3 treated groups and the control revealed 113 (46 upregulated, 67 downregulated), 637 (567 upregulated, 70 downregulated), and 587 DEGs (273 upregulated, 314 downregulated), respectively. KEGG enrichment analysis highlighted key pathways that may be linked to ovarian growth and development, including biotin metabolism, biosynthesis of amino acids, drug-cytochrome p450 pathways, MAPK signaling, estrogen signaling pathways, ECM receptor interaction, steroid biosynthesis, and ovarian steroidogenesis. These findings advance our understanding of hepatic metabolic regulation in golden pompano via the IGF system and provide actionable insights for optimizing aquaculture practices and selective breeding programs for this species. Full article

Understanding how thermal variability affects marine ectotherms is essential for predicting species resilience under climate change. We investigated the physiological responses of juvenile Nodipecten subnodosus (lion’s paw scallop), offspring of two genetically distinct populations (Bahía de Los Ángeles and Laguna Ojo de Liebre), reared under common garden conditions and exposed to three temperature regimes: constant, regular oscillation, and stochastic variability. After 15 days of exposure, scallops underwent an acute hyperthermia challenge. We measured metabolic rates, scope for growth (SFG), tissue biochemical composition, and oxidative stress markers (SOD, CAT, GPx, TBARS). No significant differences were detected between populations for most traits, suggesting that phenotypic plasticity predominates over evolutionary divergence in thermal responses. However, the temperature regime significantly influenced metabolic, biochemical and oxidative stress markers, indicating that scallops in variable conditions compensated through improved energy balance and food assimilation but also showed higher oxidative stress compared to the constant regime. Following acute hyperthermic exposure, energy demand escalated, compensatory mechanisms were impaired, and scallops attained a state of physiological maintenance and survival under stress, irrespective of their population or prior thermal regime exposure. Full article

Marine oil spills cause significant environmental damage worldwide. Marine radar imagery is used for oil spill detection. However, the rapid attenuation of backscatter intensity with increasing distance limits detectable coverage. A multi-stage image enhancement framework integrating background clutter fitting subtraction, Multi-Scale Retinex, and Gamma correction is proposed. Experimental results using marine radar images sampled in the oil spill incident in Dalian 2010 are used to demonstrate the significant improvements. Compared to Contrast-Limited Adaptive Histogram Equalization and Partially Overlapped Sub-block Histogram Equalization, the proposed method enhances image contrast by 24.01% and improves the measurement of enhancement by entropy by 17.11%. Quantitative analysis demonstrates 95% oil spill detection accuracy through visual interpretation, while significantly expanding detectable coverage for oil extraction. Full article

Copiapoa solaris is an endemic cactus species from the Antofagasta region, Chile, thriving in arid coastal ecosystems known as “fog oases,” where the rising marine moisture is the primary water source. This study investigates the role of microbial communities associated with the rhizosphere of C. solaris in adapting to extreme environmental conditions, particularly focusing on the acdS gene, which encodes ACC deaminase—an enzyme that reduces ethylene production under stress. This research aims to elucidate the gene’s contribution to the adaptation of C. solaris in these challenging environments. Samples were collected from three sites (El Cobre, Quebrada Botija, and Quebrada Izcuña) that differ in relative humidity, temperature, and topography. Environmental DNA was extracted, phylogenetic diversity was analyzed, and metagenomic annotation of the acdS gene was conducted. The acdS gene was detected in all samples, with the highest relative abundance at Quebrada Izcuña (0.05%), characterized by low relative humidity (<70%) and severe water stress. Phylogenetic analysis revealed conserved sequences across sites, while taxonomic and alpha diversity were similar among them. However, beta diversity indicated that Quebrada Izcuña was the least homogeneous, hosting distinct taxa potentially associated with stress mitigation. The acdS gene was detected on plasmids at El Cobre and Quebrada Izcuña, suggesting its potential mobility within the metagenome. The results of this study highlight the intricate relationships between microbial communities and the resilient cactus species C. solaris in extreme environments. The conservation and abundance of the acdS gene, particularly in low-humidity conditions, suggest its vital role in facilitating stress tolerance through microbial interactions. Understanding these dynamics is crucial for developing strategies to enhance plant resilience in arid ecosystems, with potential applications in sustainable agriculture and ecosystem management under changing climatic conditions. Full article