Search Results (251)

Accurate identification and quantitative assessment of fish feeding intensity are pivotal for enhancing aquaculture production efficiency. Currently, feeding intensity is mainly assessed based on fish school feeding images with a single feature, overlooking the interdependencies between individual fish and the fish school’s behavior. Therefore, this paper presents a method based on detecting individual fish heads to characterize the feeding aggregation speed and the average swimming speed of the fish school, thereby quantifying the fish school’s feeding intensity. First, the improved YOLOv11n-ALL model was employed to detect individual fish heads, resulting in improved detection performance, increasing inference speed, and reducing computational complexity. Additionally, feeding aggregation speed and average swimming speed indices for fish schools were constructed by combining the YOLOv11n-ALL model with the ByteTrack algorithm to track and extract the centers of individual fish heads’ detection boxes. Finally, the fish school feeding kinetic energy was assessed using the feeding aggregation speed and average swimming speed dual indices, and the fish school feeding intensity levels were classified according to the feeding kinetic energy. Experimental results reveal that the improved YOLOv11n-ALL model achieved an average detection precision (mAP50) of 94.13% for detecting fish heads, reduced the parameter count by 22.09%, and exhibited a computational complexity of 6.4 GFLOPs. Furthermore, the classification model of fish school feeding intensity, quantified by the dual indices of average swimming speed and feeding aggregation speed, achieved a detection accuracy of 97.41%. This method digitizes detection results, enabling rapid classification of fish school feeding intensity and demonstrating its effectiveness for feeding intensity assessment and the development of scientific feeding strategies. Full article

Nearshore mariculture is a major contributor to the supply of “blue food”; however, its rapid expansion in bay systems has intensified sea-space competition and environmental pressures, underscoring the need for accurate and long-term monitoring. This study used multitemporal Sentinel-2 imagery processed using Google Earth Engine (GEE) to develop an automated identification framework for raft and cage aquaculture along the coast of Fujian, China, from 2017 to 2024. Three widely used classifiers—U-Net, DeepLabV3+, and random forest (RF)—were comparatively evaluated. Of these methods, U-Net had the most stable overall performance under optically complex nearshore conditions and was, therefore, used for province-scale mapping. Based on the U-Net-derived maps, the spatiotemporal evolution of mariculture was quantified. The results showed that mariculture in Fujian exhibited a persistent bay-oriented, dual-core clustering pattern, with major hotspots concentrated in Ningde and Zhangzhou. In the 2024 winter–summer comparison, raft aquaculture displayed a clear seasonal contrast, characterized by expansion in winter and contraction in summer, whereas cage aquaculture showed relatively smaller seasonal variation. Interannually, the mariculture system shifted from a mixed cage–raft configuration toward the dominance of raft aquaculture, accompanied by a spatial redistribution of mapped aquaculture density from inner nearshore waters toward bay mouths and more open waters. Overall, in this study, we demonstrate the potential of deep learning-enabled Sentinel-2 remote sensing for monitoring nearshore mariculture structures and provide mode-specific observational evidence for marine spatial planning, environmental risk management, and sustainable mariculture development in nearshore waters and semi-enclosed bay systems. Full article

This paper details the implementation of an integrated engineering framework for the real-time assessment of pose and size in fusiform fish, utilizing laser-camera technology. The design, comprising a camera and laser emitter, leverages laser triangulation for accurately measuring distances between key points, providing a reliable baseline for data comparison. Enhanced with the yolov7 model backbone, it includes detection and segmentation features, enabling precise image instance segmentation of fish and laser lines. The system’s dual-network structure, which combines fully connected regression and DSNT-MobileFaceNet networks, efficiently identifies six crucial landmarks on fish—an essential step for detailed pose analysis. This method facilitates the accurate determination of two-dimensional fish posture by analyzing the relative positions of these landmarks. A notable capability of this system is its ability to infer depth information from laser lines on the fish’s body, aiding in the accurate measurement of dimensions such as body length and depth. Empirical results demonstrate the system’s effectiveness, with high mean Average Precision (mAP) values for both object detection (0.9560 for fish, 0.8550 for laser lines) and segmentation (0.9740 for fish, 0.8420 for laser lines). The DSNT-MobileFaceNet network, in particular, shows excellent fitting accuracy with an $R^2$ value of 0.9170. The deep learning model achieves an average error rate of 7.75% in detecting fish data, markedly improving upon the baseline error rate of 14.70%. Overall, this study confirms the proposed system’s capability in accurately assessing fish pose and size. As a rigorous proof of concept validated in a controlled laboratory environment, this work establishes a foundational framework for non-invasive morphological monitoring, suggesting its future applicability in marine biology and aquaculture. Full article

With the growing demand for intelligent monitoring in land-based aquaculture, rapid and accurate fish counting from visual data has become important for stocking density regulation, feeding management, and production decisions. To address the challenges in above-water fish images, including scale variation, severe occlusion and adhesion, blurred boundaries, and frequent switching between low- and high-density scenes, this study proposes MultiTask-Fish, a shared backbone multitask counting method. The network uses ResNet34 as the backbone and integrates a feature pyramid network and channel attention to learn unified feature representations. It jointly predicts detection heatmaps, foreground masks, separation boundaries, density maps, density gating, and global count regression, allowing the model to combine local localization cues, structural information, and global statistics. Based on existing polygon annotations, heatmap, mask, boundary, and density supervision are automatically generated for integrated multitask training. Experiments on 495 fish images, including 346 training and 149 validation images, showed that the proposed method achieved an MAE of 5.875, an RMSE of 11.839, and an MAPE of 0.152 on the validation set, while reducing the MAE on the high-density subset from 16.717 to 13.895. These results demonstrate its effectiveness for fish counting in complex above-water aquaculture scenes. Full article

Efficient detection of fish diseases is essential for intelligent health monitoring and timely intervention in aquaculture. However, current computer vision models remain computationally intensive, hindering their deployment on resource-constrained edge devices in aquaculture applications. To this end, this study developed a lightweight detection framework based on an improved You Only Look Once (YOLO), aiming to achieve a favorable balance between detection accuracy and on-site inference efficiency. First, a Dual-Branch Feature-Preserving Downsampling (DFPD) module was proposed to enhance the extraction of valuable disease-related cues with minimal computational overhead. Subsequently, structured pruning was applied to compress the optimized baseline model. Four pruning techniques, including Slim, GroupTaylor, Layer-Adaptive Magnitude-Based Pruning (LAMP), and L1-based, were evaluated under the same conditions. The enhanced baseline model improved precision from 0.864 to 0.908 and mAP@0.5:0.95 from 0.613 to 0.632, while already reducing the Number of Parameters (Params) and Giga Floating-point Operations Per Second (GFLOPs) compared with the original YOLOv8n. Among the pruning techniques, L1-based produced the best overall trade-off, yielding a final model that maintained a F1-score of 0.860 while reducing Params and GFLOPs by 54.7% and 49.4%, respectively, relative to the original detector. Ablation studies further revealed that a moderate FLOPs reduction of approximately 41% to 47% was optimal for preserving diagnostic performance while enhancing compactness. Edge deployment tests on an RK3588S device verified the framework’s practical inference speed advantage. Therefore, this study offers a deployment-friendly computer vision solution for on-site fish disease detection in aquaculture management, particularly suited to real-world scenarios with limited computational resources. Full article

Across production and processing systems, biological residuals are inconsistently defined, with the same materials treated as waste, by-products, or resources depending on context. This ambiguity constrains the identification of valorization pathways and limits the design of sustainable and resource-efficient operational strategies. This study addresses the issue by compiling a sector-resolved inventory of 94 bioresiduals across 12 bioeconomy-related activities. Analyzing 1763 firm–bioresidual observations from a national survey in Estonia using binomial logistic regression. The results show that bioresidual use is primarily shaped by operational and data-handling practices, particularly collection and accounting, rather than by structural firm characteristics. Separate collection emerges as a key precondition for higher-value use, while accounting practices are associated with external and energy-related pathways by increasing visibility and traceability. In contrast, irregular or seasonal bioresiduals tend to default to waste handling due to variability and perishability. The findings also indicate that many effective uses remain internal to production systems and are under-documented. Improving the definitions and monitoring practices of bioresiduals could support more efficient and sustainable resource management by reducing biowaste generation and enhancing coordination across value chains, thereby fostering the development of a circular bioeconomy. Full article

Background: Edwardsiella piscicida is a significant intracellular pathogen of channel catfish (Ictalurus punctatus) and a major threat to U.S. aquaculture. A recently developed recombinant attenuated vaccine strain (χ16016) uses arabinose-regulated murA expression to trigger delayed cell wall lysis in vivo, ensuring biological containment while conferring strong protection against virulent challenge. Although its efficacy has been demonstrated, the host immune programs underlying protection remain incompletely defined. Methods: We used RNA sequencing to characterize tissue-specific transcriptomic responses in the intestines and kidneys of channel catfish at 7 days post-vaccination. Fish were vaccinated with χ16016 by either bath immersion or intracoelomic (IC) injection, and differentially expressed genes and enriched immune pathways were analyzed to determine how the vaccine delivery route shapes systemic and mucosal immune responses. Results: Across comparisons, 19,101 differentially expressed genes revealed pronounced route- and tissue-dependent immune remodeling. As aquaculture vaccination strategies increasingly prioritize scalability and practical deployment, understanding how the delivery route shapes immune outcomes is critical. Here, IC vaccination induced broader systemic transcriptional changes, particularly in the intestine, whereas bath immunization elicited a more focused yet coordinated mucosal response. Overall, intestinal tissue exhibited greater transcriptional responsiveness than kidney tissue, underscoring its central role in early vaccine-induced immunity. Functional enrichment analyses identified the activation of innate recognition pathways, MAPK and calcium signaling cascades, complement components, antigen processing machinery, and cell adhesion networks. Notably, bath immunization enriched the intestinal immune network for IgA production pathway, which represents an orthology-based mapping of conserved mucosal immune components, alongside the upregulation of IL-6, CXCL12–CXCR4, integrins (α4β7), MHC class II, complement C3, and polymeric immunoglobulin receptor (pIgR). Given that catfish rely primarily on IgM in mucosal immunity, these findings indicate the induction of IgM-mediated mucosal defense rather than classical mammalian IgA responses. Concurrent complement and scavenger receptor signatures suggest a transition toward efficient opsonophagocytic clearance with controlled inflammation at this subacute stage. Conclusions: This study provides the first systems-level view of host transcriptomic responses to a regulated-lysis E. piscicida vaccine in channel catfish. The findings demonstrate that immersion vaccination, although transcriptionally less expansive than injection, effectively activates coordinated mucosal innate and adaptive immune programs, supporting its practical use as a scalable vaccination strategy for aquaculture. Full article

Cadmium (Cd) is a typical heavy metal pollutant in aquatic environments. It enters fish through the gills, digestive tract, and body surface, and accumulates mainly in the liver and kidneys, with species- and tissue-specific distribution. Cadmium triggers apoptosis by inducing oxidative stress, calcium imbalance, and DNA damage. These signals are integrated and amplified by the mitogen-activated protein kinase (MAPK), nuclear factor kappa B (NF-κB), phosphatidylinositol 3-kinase (PI3K)/AKT, and nuclear factor erythroid 2-related factor 2 (Nrf2) pathways, ultimately activating three downstream apoptotic execution pathways: the death receptor, mitochondrial, and endoplasmic reticulum stress pathways. These three pathways form an interactive network through molecular nodes such as BH3 interacting domain death agonist (Bid), Ca²⁺, c-Jun N-terminal kinase (JNK), and C/EBP homologous protein (CHOP), synergistically amplifying the apoptotic effect, with the mitochondrial pathway playing a central role. Cadmium-induced apoptosis is dose-dependent: low concentrations activate protective responses, whereas high concentrations strongly promote apoptosis. Current research gaps remain regarding dynamic pathway crosstalk, chronic low-dose effects, species differences, and fish-specific apoptotic molecules (e.g., caspase-12 homologs). Future studies should focus on constructing multidimensional response maps, clarifying pathway activation thresholds and interaction contributions, and developing composite protective strategies based on Nrf2 activators, metal chelators, and antioxidants, thereby promoting translation into ecological risk assessment and aquaculture pollution control. Full article

Most Portuguese aquaculture farms are located in estuaries and coastal lagoons, which are highly productive, nutrient-rich transition zones that are also among the most vulnerable to anthropogenic pressures and climate change. This study assesses Ria Formosa’s suitability for grooved carpet shell (Ruditapes decussatus) aquaculture, accounting for projected climate change and a potential increase in clam farming production. The methodology involved implementing a numerical modeling system to map key physico-chemical variables under historical (1995–2014) and future (2081–2100) conditions. Model outputs were then used to compute a suitability index (SI), which was converted into aquaculture suitability maps for this species. Results indicate that the hydrodynamic and transport components reproduced tidal propagation and the transport of salinity and heat effectively. In contrast, simulations of water quality variables were less accurate, reflecting the greater complexity and uncertainty in representing biochemical processes. Across both time periods, environmental conditions were generally less favorable in winter and more favorable in spring. Water temperature and chlorophyll-a concentration emerged as the dominant drivers of seasonal suitability. Projections suggest that Ria Formosa may become increasingly suitable for grooved carpet shell aquaculture by the end of the century. However, expanding production could compromise ecological balance, reduce resilience, and constrain the system’s long-term sustainable development. Full article

The Mediterranean Sea is both a global biodiversity hotspot and the world’s most heavily invaded marine region, where non-indigenous species arrivals are accelerating under intensifying shipping, Suez Canal traffic, aquaculture, and climate warming. Yet, despite rapidly growing research activity, a comprehensive synthesis of the scientific literature on Mediterranean marine invasions has been lacking. This study provides the first Mediterranean-wide combined bibliometric and topic-modeling analysis of invasive marine species research, using 3521 unique documents retrieved from Scopus and Web of Science. We quantify temporal growth in publications and citations, map the conceptual structure of the field through co-citation, co-word, and topic modeling, and reveal pronounced regional and thematic biases. Latent Dirichlet Allocation resolves 13 coherent topics, dominated by first records of non-native species, invasive macroalgae, alien species diversity, and ecological impacts, with strong signals for Lessepsian migration and climate-driven range shifts, particularly in the Eastern Mediterranean. Spatial and thematic analyses reveal pronounced regional biases, with invasion hotspots in the Aegean and Levantine seas contrasted by comparatively sparse coverage of western and central sub-basins, and notable gaps in predictive modeling and socioeconomic assessments. The results underscore the need to rebalance effort toward under-studied regions and themes, while leveraging existing collaboration networks and methodological advances to support MSFD (Marine Strategy Framework Directive) implementation, International Maritime Organization (IMO) instruments, and broader ecosystem-based management. The reproducible framework presented here offers a baseline for periodically tracking research evolution and guiding adaptive, transboundary governance of Mediterranean marine bio-invasions. Full article

Madagascar’s expanding blue economy is largely underpinned by seaweed aquaculture, particularly Kappaphycus alvarezii (Cottonii), which offers an alternative to declining small-scale fisheries and strengthens the resilience of coastal socio-ecosystems. Ensuring the sustainability of this economic activity requires effective ecological monitoring of aquaculture sites and surrounding habitats. This study examines and compares the performance of two imaging configurations—an RGB composite derived from a subset of multispectral images capturing red (650 nm), green (560 nm), and blue (450 nm) bands; and a five-band multispectral (MS) image encompassing blue, green, red, red-edge (730 nm), and near-infrared (840 nm) bands—combined with a Random Forest (RF) classification model, for benthic habitat mapping in a seaweed cultivation context. High-resolution orthomosaics (2 cm/pixel) enabled the discrimination of Kappaphycus cultivation plots from three shallow-water habitats: (i) ‘benthic macrophytes’, which comprise: seagrass meadows and benthic macroalgal; (ii) ‘sandy bottom’ and (iii) ‘green algae’. The RF classification achieved an overall accuracy of 87% (Kappa = 0.82) across ~10 hectares. Producer’s accuracy exceeded 80% for Kappaphycus cultivation, green algae, and sandy bottom for both the RGB and MS datasets, indicating strong classification performance. However, early-stage seaweed was occasionally misclassified as benthic macrophytes, likely due to its low biomass and weak spectral signature. This UAS-based approach provided a robust and cost-effective framework for monitoring off-bottom seaweed farms and associated natural habitats. This approach supports sustainable aquaculture development and integrated coastal management in Madagascar and comparable tropical reef socio-ecosystems. Full article

Shrimp aquaculture increasingly depends on precise water quality management, yet most farms still rely on fragmented measurements and qualitative assessments. This study aimed to evaluate whether routine physicochemical data from commercial ponds can reliably discriminate between operational categories of acceptable and residual water and thus support early warning systems. We compiled water quality records from shrimp ponds in several coastal provinces, focusing on a reduced set of variables related to salinity, alkalinity, hardness and inorganic nitrogen. Supervised and unsupervised machine learning models were trained and compared using standard classification metrics. Tree-based ensembles and margin-based models achieved high accuracy and F1 scores when predicting water status from routine variables, while clustering methods only reproduced similar patterns after an ex post mapping of clusters to classes. These results indicate that latent nitrogen loads and subtle shifts in water chemistry are systematically captured by basic monitoring data and can be translated into operational signals of risk. The study demonstrates the feasibility of integrating data-driven classification into shrimp farm monitoring and outlines a pathway toward low-cost, scalable decision support tools for aquaculture 4.0 in data-limited settings. Full article

In disease control and precision management in aquaculture, rapid and accurate identification of common fish diseases is pivotal to mitigating economic losses and ensuring aquaculture profitability. However, fish diseases are characterized by subtle symptoms, polymorphic lesions, and high susceptibility to environmental perturbations such as water turbidity and illumination fluctuations. Existing detection models generally suffer from inadequate lightweight design, poor fine-grained lesion feature extraction, and deficient adaptability to class imbalance, failing to meet the stringent requirements of precise diagnosis in real-world aquaculture scenarios. To address these challenges, this study proposes FDR-Net: a fine-grained lesion detection model for tilapia via multi-scale feature enhancement and spatial attention fusion. Using image data of Nile tilapia (Oreochromis niloticus) covering 6 common diseases and healthy individuals (from the NTD-1 dataset), the model incorporates symmetry-aware design logic, leveraging the morphological and textural symmetry of healthy tilapia tissues to capture lesion-induced symmetry-breaking features, thereby improving fine-grained lesion detection accuracy. Through depth-width scaling coefficients, FDR-Net achieves lightweight optimization while integrating three core modules and a task-specific loss function for full-chain optimization: specifically, a Micro-lesion Feature Enhancement Module (MLFEM) is embedded in key feature layers of the backbone network to accurately extract edge and texture features of incipient fine-grained lesions via multi-scale frequency decomposition and residual fusion; subsequently, a Lightweight Multi-scale Position Attention Module (MS_PSA) and a Single-modal Intra-feature Contrastive Fusion Module (SMICFM) are collaboratively deployed—the former focusing on spatial localization of lesion features, and the latter enhancing lesion-background discriminability through channel-spatial feature recalibration and contrastive fusion; finally, a Class-Aware Weighted Hybrid Loss (CAWHL) function is combined with customized small-target anchor boxes to alleviate class imbalance and further improve localization and classification accuracy of fine-grained lesions. Empirical evaluations on the NTD-1 dataset demonstrate that compared with mainstream state-of-the-art baseline models, FDR-Net achieves a peak recognition accuracy of 90.1% with substantially enhanced mAP_50-95 performance. Retaining lightweight characteristics, it exhibits superior performance in identifying incipient fine-grained lesions and strong adaptability to simulated complex aquaculture scenarios. Collectively, this study provides an efficient technical backbone for the rapid and precise detection of tilapia fine-grained lesions, offering a potential solution for precise disease management in tilapia farming. Full article

Background: Fish skin mucus contains proteins involved in diverse biological pathways, representing a valuable non-invasive diagnostic of fish health. Methods: Skin mucus from three male and three female barramundi was analysed using liquid chromatography-tandem mass spectrometry (LC-MS/MS) following protein extraction and S-Trap digestion. Results and Discussion: A total of 1801 protein groups were matched to the L. calcarifer reference proteome and functionally annotated using Gene Ontology (GO) terms via UniProt ID mapping, with representation across Biological Process, Cellular Component, and Molecular Function categories. Functional classification using eggNOG-mapper further associated leading protein group sequences with Clusters of Orthologous Groups (COGs) and Kyoto Encyclopaedia of Genes and Genomes (KEGG) pathways. GO-based screening prioritised 352 putatively immune-relevant protein groups and 24 protein groups associated with sex- and reproduction-related processes, highlighting the functional complexity of the skin mucus proteome. Comparative analysis revealed sex-associated patterns in protein group detection and relative abundance, with differential abundance analysis identifying 244 protein groups exhibiting statistically significant differences between male and female samples. Conclusions: This study provides the first comprehensive discovery-based characterisation of the barramundi skin mucus proteome and establishes a baseline reference dataset for this aquaculture-relevant species. The findings support the utility of skin mucus proteomics for exploring immune and sex-associated molecular patterns and provide a baseline dataset for future validation studies investigating non-invasive health and reproductive monitoring. Full article

The environmental and social problems caused by overfishing and unsustainable aquaculture practices make it necessary to implement the principles of the circular economy to steer the sector towards sustainability and responsible use of resources. The objective of this study was to assess the sustainability of the aquaculture sector in the context of current environmental and social concerns in the fisheries sector and to understand the state of research in terms of implementing circular practices, providing a comprehensive mapping of scientific articles focusing on circular practices adopted in the aquaculture sector over the last ten years, describing them and identifying their potential advantages and disadvantages. A bibliometric analysis was conducted using the Scopus database to obtain a clear picture of the sustainable innovations carried out in the aquaculture sector over the last ten years. The analysis focused on the terms ‘aquaculture’ and ‘circular economy’. The results indicate a rising trend in the number of studies on the circular economy in aquaculture from 2020 onwards, which can be attributed to an escalating awareness of environmental concerns. Subsequently, the analysis carried out by the VOSviewer software allowed the articles to be classified in four clusters, according to the relevance of the different adopted circularity practices. A particular focus was placed on the significance of practices minimising environmental impact, optimising resources and pursuing innovative strategies to ensure sustainability. Full article