Search Results (449)

Accurate evaluation of fish feeding intensity is crucial for optimizing aquaculture efficiency and the healthy growth of fish. Previous methods mainly rely on single-modal approaches (e.g., audio or visual). However, the complex underwater environment makes single-modal monitoring methods face significant challenges: visual systems are severely affected by water turbidity, lighting conditions, and fish occlusion, while acoustic systems suffer from background noise. Although existing studies have attempted to combine acoustic and visual information, most adopt simple feature-level fusion strategies, which fail to fully explore the complementary advantages of the two modalities under different environmental conditions and lack dynamic evaluation mechanisms for modal reliability. To address these problems, we propose the Adaptive Cross-modal Attention Fusion Network (ACAF-Net), a cross-modal complementarity learning framework with a two-stage attention fusion mechanism: (1) a cross-modal enhancement stage that enriches individual representations through Low-rank Bilinear Pooling and learnable fusion weights; (2) an adaptive attention fusion stage that dynamically weights acoustic and visual features based on complementarity and environmental reliability. Our framework incorporates dimension alignment strategies and attention mechanisms to capture temporal–spatial complementarity between acoustic feeding signals and visual behavioral patterns. Extensive experiments demonstrate superior performance compared to single-modal and conventional fusion approaches, with 6.4% accuracy improvement. The results validate the effectiveness of exploiting cross-modal complementarity for underwater behavioral analysis and establish a foundation for intelligent aquaculture monitoring systems. Full article

Skipjack tuna constitutes a crucial fishery resource in the Western and Central Pacific Ocean (WCPO) purse seine fishery, with high economic value and exploitation potential. It also serves as an essential subject for studying the interaction between fishery resource dynamics and marine ecosystems, as its resource abundance is significantly influenced by marine environmental factors. Skipjack tuna can be categorized into unassociated schools and associated schools, with the latter being predominant. Overfishing of the associated schools can adversely affect population health and the ecological environment. In-depth exploration of the spatial distribution responses of these two fish schools to environmental variables is significant for the rational development and utilization of tuna resources and for enhancing the sustainability of fishery resources. In sparsely sampled and complex marine environments, geographic similarity methods effectively predict tuna resources by quantifying local fishing ground environmental similarities. This study introduces geographical similarity theory. This study focused on 1° × 1° fishery data (2004–2021) released by the Western and Central Pacific Fisheries Commission (WCPFC) combined with relevant marine environmental data. We employed Geographical Convergent Cross Mapping (GCCM) to explore significant environmental factors influencing catch and variations in causal intensity and employed a Geographically Optimal Similarity (GOS) model to predict the spatial distribution of catch for the two types of tuna schools. The research findings indicate that the following: (1) Sea surface temperature (SST), sea surface salinity (SSS), and net primary productivity (NPP) are key factors in GCCM model analysis, significantly influencing the catch of two fish schools. (2) The GOS model exhibits higher prediction accuracy and stability compared to the Generalized Additive Model (GAM) and the Basic Configuration Similarity (BCS) model. R² values reaching 0.656 and 0.649 for the two types of schools, respectively, suggest that the geographical similarity method has certain applicability and application potential in the spatial prediction of fishery resources. (3) Uncertainty analysis revealed more stable predictions for unassociated schools, with 72.65% of the results falling within the low-uncertainty range (0.00–0.25), compared to 52.65% for associated schools. This study, based on geographical similarity theory, elucidates differential spatial responses of distinct schools to environmental factors and provides a novel approach for fishing ground prediction. It also provides a scientific basis for the dynamic assessment and rational exploitation and utilization of skipjack tuna resources in the Pacific Ocean. 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

This study evaluated the effects of supplementing early-lactation Holstein cows with rumen-protected omega-3 fatty acids (calcium salts) on productive and reproductive performance. Thirty-six multiparous cows were randomly assigned to one of two treatments from 21 ± 2 days before calving to 105 ± 5 days in milk (DIM): a Control group (C) or an Omega-3-supplemented group (O-3), receiving a blend of linseed and fish oil (60:40). Both groups were fed isoenergetic diets, with ground corn as the control supplement. Total dry matter and net energy intake did not differ between treatments. A treatment-by-time interaction was observed for milk yield, with cows in the O-3 group producing more milk than controls at specific time points. Additionally, O-3 cows had higher overall protein yield and improved feed efficiency. No differences were found in body weight, BCS, glucose, insulin, IGF-1, or urea concentrations, but a tendency toward higher plasma NEFA and BHBA concentrations and lower energy balance was observed in the O-3 group. Supplementation increased plasma cholesterol and progesterone concentrations and was associated with a higher proportion of cows being pregnant at 130 DIM. These findings suggest that omega-3 supplementation may improve specific aspects of lactational performance and reproductive efficiency without compromising metabolic status. Full article

Precise identification and quantification of fish movement states are of significant importance for conducting fish behavior research and guiding aquaculture production, with object tracking serving as a key technical approach for achieving behavioral quantification. The traditional DeepSORT algorithm has been widely applied to object tracking tasks; however, in practical aquaculture environments, high-density cultured fish exhibit visual characteristics such as similar textural features and frequent occlusions, leading to high misidentification rates and frequent ID switching during the tracking process. This study proposes an underwater fish object tracking method based on the improved DeepSORT algorithm, utilizing ResNet as the backbone network, embedding Deformable Convolutional Networks v2 to enhance adaptive receptive field capabilities, introducing Triplet Loss function to improve discrimination ability among similar fish, and integrating Convolutional Block Attention Module to enhance key feature learning. Finally, by combining the aforementioned improvement modules, the ReID feature extraction network was redesigned and optimized. Experimental results demonstrate that the improved algorithm significantly enhances tracking performance under frequent occlusion conditions, with the MOTA metric improving from 64.26% to 66.93% and the IDF1 metric improving from 53.73% to 63.70% compared to the baseline algorithm, providing more reliable technical support for underwater fish behavior analysis. Full article

Fine-mesh netting, with mesh dimensions of the order of a few millimeters, is widely used in sampling nets for the collection of larval and juvenile fishes. The wave force characteristics of fine-mesh netting significantly affect the operational performance of these nets. This study employed both wave tank experiments and numerical simulations to analyze the hydrodynamic performance of fine-mesh netting under varying wave conditions. A series of numerical simulations and particle image velocimetry (PIV) experiments were conducted to investigate the damping effects of fine-mesh netting on wave propagation. The results revealed that horizontal wave forces increased with both the wave period and wave height. When the wave period was held constant, the drag and inertial coefficients of the netting generally decreased as the Reynolds number and the Keulegan–Carpenter (KC) number increased. The wave transmission coefficients of the netting decreased as the wave height increased for the same wave period. However, at a constant wave height, the transmission coefficients initially increased and then decreased with the increasing wave period. The water particle velocity was significantly affected by the netting, with a notable reduction in velocity downstream of the netting at both the wave crest and trough phases. The simulation results and PIV measurements of the water particle velocity field distribution were in good agreement. This study provides important insights for the design and optimization of sampling nets. Full article

Overfishing and climate change have led to the depletion of fishery resources in the offshore South China Sea. The purpleback flying squid (Sthenoteuthis oualaniensis) has emerged as a promising alternative due to its ecological and economic value. However, information on its preferred habitat conditions remains scarce. This study integrates geostatistical and fisheries oceanographic approaches to explore optimal spatial–temporal scales for habitat modeling and to assess habitat changes under warming scenarios. Utilizing fishery data from 2013 to 2017, environmental variables including SST, sea surface temperature anomaly (SSTA), and chlorophyll-a concentration (CHL) were analyzed. Fishing effort data revealed significant seasonal differences, with the highest vessel numbers in summer and the lowest in autumn. Among the six modeling schemes, the combination of 0.5° × 0.5° spatial resolution and seasonal temporal resolution yielded the highest HSI model accuracy (84.02%). Optimal environmental ranges varied by season. Simulations of SST deviations (±0.2 °C, ±0.5 °C, and ±1 °C) showed that extreme warming or cooling could eliminate suitable habitats. These findings highlight the vulnerability of squid habitats to thermal shifts and support adaptive fishery strategies in the South China Sea. Full article

Accurate segmentation of the ventricular region in embryonic heart videos of medaka fish (Oryzias latipes) holds significant scientific value for research on heart development mechanisms. However, existing medaka ventricular datasets are overly simplistic and fail to meet practical application requirements. And the video frames contain multiple complex interfering factors, including optical interference from the filming environment, dynamic color changes caused by blood flow, significant diversity in ventricular scales, image blurring in certain video frames, high similarity in organ structures, and indistinct boundaries between the ventricles and atria. These challenges mean existing methods still face notable technical difficulties in medaka embryonic ventricular segmentation tasks. To address these challenges, this study first constructs a medaka embryonic ventricular video dataset containing 4200 frames with pixel-level annotations. Building upon this, we propose a semi-supervised video segmentation model based on the hierarchical propagation feature decoupling framework (DeAOT) and innovatively design an architecture that combines the LA-ResNet encoder with the AFPViS decoder, significantly improving the accuracy of medaka ventricular segmentation. Experimental results demonstrate that, compared to the traditional U-Net model, our method achieves a 13.48% improvement in the mean Intersection over Union (mIoU) metric. Additionally, compared to the state-of-the-art DeAOT method, it achieves a notable 4.83% enhancement in the comprehensive evaluation metric Jaccard and F-measure (J&F), providing reliable technical support for research on embryonic heart development. Full article

Accurate fish species identification is crucial for marine biodiversity conservation, environmental monitoring, and sustainable fishery management, particularly as marine ecosystems face increasing pressures from human activities and climate change. Traditional morphological identification methods are inherently labor-intensive and resource-demanding, while contemporary automated approaches, particularly deep learning models, often suffer from significant computational overhead and struggle with the pervasive issue of class imbalance inherent in ecological datasets. Addressing these limitations, this research introduces a novel computationally parsimonious fish classification framework leveraging the hybrid Mobile–Former neural network architecture. This architecture strategically combines the local feature extraction strengths of convolutional layers with the global context modeling capabilities of transformers, optimized for efficiency. To specifically mitigate the detrimental effects of the skewed data distributions frequently observed in real-world fish surveys, the framework incorporates a sophisticated robust asymmetric loss function designed to enhance model focus on under-represented categories and improve resilience against noisy labels. The proposed system was rigorously evaluated using the comprehensive FishNet dataset, comprising 74,935 images distributed across a detailed taxonomic hierarchy including eight classes, seventy-two orders, and three-hundred-forty-eight families, reflecting realistic ecological diversity. Our model demonstrates superior classification accuracy, achieving 93.97 percent at the class level, 88.28 percent at the order level, and 84.02 percent at the family level. Crucially, these high accuracies are attained with remarkable computational efficiency, requiring merely 508 million floating-point operations, significantly outperforming comparable state-of-the-art models in balancing performance and resource utilization. This advancement provides a streamlined, effective, and resource-conscious methodology for automated fish species identification, thereby strengthening ecological monitoring capabilities and contributing significantly to the informed conservation and management of vital marine ecosystems. Full article

The National Institute of Fisheries Science in Korea is developing marine mammal bycatch reduction devices (BRDs) for midwater trawl gear. In this study, we tested two BRD-type guide nets (inclined net panel) with 30° and 45° tilt angles to prevent marine mammals from reaching the codend and facilitating their escape from the net. Fishing operations were conducted along the east and south coasts of South Korea, and cameras were installed in front of the BRDs to monitor their performance. The catch loss of herring with the 30° guide net was 13% and 11% in number and weight. The catch loss of hairtail was 53% and 51% in number and weight with the 30° guide net. Mackerel showed a 97% catch loss in number and weight with the 45° guide net. The 30° guide net resulted in lower catch loss for rudderfish and jack mackerel compared to the 45° guide net. The jellyfish discard rate of the BRD was 5% and 7% in number and weight with the 30° guide net and 12% and 11% with the 45° guide net, indicating that the 30° guide net was more effective at discarding jellyfish. Mesh selectivity was not strongly related to target species body length. Full article

With the rising global demand for aquatic products, aquaculture has become a cornerstone of food security and sustainability. This review comprehensively analyzes the application of deep learning in sustainable aquaculture, covering key areas such as fish detection and counting, growth prediction and health monitoring, intelligent feeding systems, water quality forecasting, and behavioral and stress analysis. The study discusses the suitability of deep learning architectures, including CNNs, RNNs, GANs, Transformers, and MobileNet, under complex aquatic environments characterized by poor image quality and severe occlusion. It highlights ongoing challenges related to data scarcity, real-time performance, model generalization, and cross-domain adaptability. Looking forward, the paper outlines future research directions including multimodal data fusion, edge computing, lightweight model design, synthetic data generation, and digital twin-based virtual farming platforms. Deep learning is poised to drive aquaculture toward greater intelligence, efficiency, and sustainability. Full article

Efficient deep learning models are crucial in resource-constrained environments, especially for marine image classification in underwater monitoring and biodiversity assessment. This paper presents LatentResNet, a computationally lightweight deep learning model involving two key innovations: (i) using the encoder from the proposed LiteAE, a lightweight autoencoder for image reconstruction, as input to the model to reduce the spatial dimension of the data and (ii) integrating a DeepResNet architecture with lightweight feature extraction components to refine encoder-extracted features. LiteAE demonstrated high-quality image reconstruction within a single training epoch. LatentResNet variants (large, medium, and small) are evaluated on ImageNet-1K to assess their efficiency against state-of-the-art models and on Fish4Knowledge for domain-specific performance. On ImageNet-1K, the large variant achieves 66.3% top-1 accuracy (1.7M parameters, 0.2 GFLOPs). The medium and small variants reach 60.8% (1M, 0.1 GFLOPs) and 54.8% (0.7M, 0.06 GFLOPs), respectively. After fine-tuning on Fish4Knowledge, the large, medium, and small variants achieve 99.7%, 99.8%, and 99.7%, respectively, outperforming the classification metrics of benchmark models trained on the same dataset, with up to 97.4% and 92.8% reductions in parameters and FLOPs, respectively. The results demonstrate LatentResNet’s effectiveness as a lightweight solution for real-world marine applications, offering accurate and lightweight underwater vision. Full article

The detection of fish freshness is crucial for ensuring food safety. This study addresses the limitations of traditional detection methods, which rely on laboratory equipment and complex procedures, by proposing a smartphone-based detection method, termed FreshFusionNet, that utilizes a pitaya peel pH intelligent indicator film in conjunction with multimodal deep learning. The pitaya peel indicator film, prepared using high-pressure homogenization technology, demonstrates a significant color change from dark red to yellow in response to the volatile alkaline substances released during fish spoilage. To construct a multimodal dataset, 3600 images of the indicator film were captured using a smartphone under various conditions (natural light and indoor light) and from multiple angles (0° to 120°), while simultaneously recording pH values, total volatile basic nitrogen (TVB-N), and total viable count (TVC) data. Based on the lightweight MobileNetV2 network, a Multi-scale Dilated Fusion Attention module (MDFA) was designed to enhance the robustness of color feature extraction. A Temporal Convolutional Network (TCN) was then used to model dynamic patterns in chemical indicators across spoilage stages, combined with a Context-Aware Gated Fusion (CAG-Fusion) mechanism to adaptively integrate image and chemical temporal features. Experimental results indicate that the overall classification accuracy of FreshFusionNet reaches 99.61%, with a single inference time of only 142 ± 40 milliseconds (tested on Xiaomi 14). This method eliminates the need for professional equipment and enables real-time, non-destructive detection of fish spoilage through smartphones, providing consumers and the food supply chain with a low-cost, portable quality-monitoring tool, thereby promoting the intelligent and universal development of food safety detection technology. Full article

As the sea ice reduces in both extent and thickness and the Arctic Ocean opens, there is substantial interest in mapping the marine ecosystem in this remote and until now largely inaccessible ocean. We used the R/V Kronprins Haakon during surveys in the Central Arctic Ocean (CAO) in 2022 and 2023 to record the marine ecosystem using modern fisheries acoustics and net sampling. The 2022 survey reached all the way to the North Pole. In a first, principally manually based post-processing of these acoustic recordings using the Large-Scale Survey Post-processing System (LSSS), much effort was used to remove segments of noise due to icebreaking operations. In a second, more sophisticated post-processing, the KORONA module of LSSS with elements of machine learning was applied for further noise reduction and to allocate the area back-scattering recordings to taxonomic groups as order, families and even species of fish and plankton organisms. These results highlight the need for further advances in post-processing systems to enable the direct allocation of back-scattered acoustic energy to taxonomic categories, including species-level classifications. Full article

Abandoned, lost, or discarded fishing gear (ALDFG) poses significant environmental threats, namely contributing to microplastic (MP) pollution. However, the release of MPs from ALDFG remains poorly studied, despite its crucial role in understanding plastic pollution in marine ecosystems. This study is, to the best of our knowledge, the first to assess the environmental impact of ALDFG as a source of MPs, using an integrated approach combining laboratory experiments, in situ field trials, and environmental surveys. Laboratory tests showed that in the presence of light and sediment, braided polyethylene net released 1 fibre after incubation, demonstrating that the studied plastic fishing nets had the potential to release MPs. In situ experiments in a semi-enclosed marine environment did not show a clear influence of submerged fishing nets on water MPs, due to the high MP contamination in the selected location (5322 ± 4936 MP m⁻³). Nonetheless, at ALDFG hotspots off northwest Portugal, an increased presence of MPs in water samples compared to locations without ALDFG suggested potential MP release. These findings demonstrate the potential of ALDFG to act as a source of MPs and showcase the need for further studies, in order to comprehensively investigate the degradation of different plastic fishing nets in the field. Reducing ALDFG pollution is critical to mitigating its environmental impact and preserving marine ecosystems. Full article