Search Results (106)

Accurate monitoring of fish movement is essential for understanding behavioral patterns and group dynamics in aquaculture systems. Underwater scenes—characterized by dense populations, frequent occlusions, non-rigid body motion, and visually similar appearances—present substantial challenges for conventional multi-object tracking methods. We propose an improved CenterTrack-based framework tailored for multi-fish tracking in such environments. The framework integrates three complementary components: a multi-branch feature extractor that enhances discrimination among visually similar individuals, occlusion-aware output heads that estimate visibility states, and a three-stage cascade association module that improves trajectory continuity under abrupt motion and occlusions. To support systematic evaluation, we introduce a self-built dataset named Multi-Fish 25 (MF25), continuous video sequences of 75 individually annotated fish recorded in aquaculture tanks. The experimental results on MF25 show that the proposed method achieves an IDF1 of 82.5%, MOTA of 85.8%, and IDP of 84.7%. Although this study focuses on tracking performance rather than biological analysis, the produced high-quality trajectories form a solid basis for subsequent behavioral studies. The framework’s modular design and computational efficiency make it suitable for practical, online tracking in aquaculture scenarios. Full article

In freshwater fish, group behavior is ecologically critical for daily activities such as predator avoidance. However, species with varying shoaling preferences exhibit divergent behavioral responses under different environmental conditions. This study investigated the behavioral responses of three shoaling species (Moenkhausia costae, Puntius tetrazona, and Myxocyprinus asiaticus) and three non-shoaling species (Trichogaster trichopterus, Micropterus salmoides, and Cichlasoma managuense) to simulated predation in either an open arena or a six-arm maze with shelter available. Our findings reveal that, in open water, shoaling species employ a dual strategy against predators: maintaining high group cohesion while increasing swimming speed and acceleration. This exploits the confusion effect to mitigate individual predation risk. In contrast, non-shoaling species do not engage in evasive maneuvers; instead, they adopt a cryptic strategy by minimizing activity and often freezing in place to avoid detection. In the six-arm maze, shoaling species consistently employed group coordination strategies, whereas non-shoaling species primarily relied on shelter concealment or reduced activity. Notably, shoaling species maintained high cohesion, synchronization, and activity levels across both open and complex habitats, using coordinated movement to facilitate collective escape. Together, our findings demonstrate that habitat complexity and social tendencies jointly determine how fishes trade off risk and safety. This work provides new insights into the adaptive evolution of social behavior in dynamic aquatic ecosystems. Full article

The Neptunea cumingii (N. cumingii) fishing industry has long relied on expensive and perishable skate (Raja porosa) meat as bait. The unknown chemical attraction mechanism has hindered the development of artificial alternatives. This study employed untargeted metabolomics to analyze the chemical composition of skate meat and combined quantitative behavioral analysis to identify four key attractant compounds. These compounds were taurine, glutamate (Glu), inositol, and lactate. A standardized behavioral assessment system was established using the three parameters of response time, displacement distance, and movement velocity. This system enabled precise quantification of attraction efficacy. Concentration-gradient experiments determined the optimal concentration for all four compounds as 0.1 M. Taurine exhibited the strongest single-compound activity. It reduced response time by 50% and increased displacement distance by 164.5%. The mixture of four compounds at 0.1 M produced significant synergistic effects. The mixture achieved a comprehensive score of 93.6. This score approached that of natural skate meat at 94.8. All behavioral parameters improved by over 69% compared to the best single compound. These findings reveal the key attractant components in skate meat. They provide a scientific basis for developing efficient and stable artificial attractants. This research holds substantial value for promoting sustainable development of the N. cumingii fishing industry. Full article

The optimization of fishway design relies on a deep understanding of fish swimming performance and behavioral traits. Traditional methods often underestimate fish swimming performance and overlook their behavior under high-flow conditions, particularly in the context of high-altitude species. This study, based on an open-channel flume system and combined with high-speed video tracking and Acoustic Doppler Velocity (ADV) measurements, constructs a Resource Selection Function-Generalized Additive Mixed Models (RSF-GAMMs) to quantify the swimming performance and behavior mechanisms of the high-altitude species, Schizothorax oconnori Lloyd, 1908 (S. oconnori), in high-velocity environments. The results show that S. oconnori significantly outperforms traditional swimming tests and exhibits strong dependence on movement modes. Endurance analysis reveals the breakpoints of endurance models, indicating the species’ high sensitivity to variations in exercise intensity, showcasing the unique physiological and behavioral characteristics of high-altitude fish. In high-velocity conditions, adult S. oconnori primarily aims to optimize energy conservation and stability, selectively choosing water bodies with varying disturbance levels depending on its movement mode and endurance state, thus optimizing path selection. This study presents a systematic method for quantifying the extreme swimming abilities and nonlinear behavioral responses of adult S. oconnori under complex flow conditions, providing scientific guidance for setting hydraulic thresholds and developing protection strategies for fishways. Full article

The overexploitation of wild populations for the marine ornamental trade necessitates optimized captive breeding, particularly for iconic species like the clownfish Amphiprion ocellaris. This study investigated the social behavior and cognitive abilities of juvenile clownfish in relation to artificial rearing practices. Using modified three-tank tests, we assessed social preference and cognition ability in two size groups: Small-bodied Group (SG: 2.0–2.5 cm) and Large-bodied Group (LG: 3.5–4 cm). The results indicated that clownfish have the following: (a) Strong Social Preference: Both SG and LG exhibited significant preference for areas near conspecifics (SPI > 0), with SG showing significantly higher SPI values than LG. (b) Developmental Stage Differences: SG demonstrated a stronger tendency to cluster tightly near conspecifics. LG showed wider exploration patterns and greater movement. (c) Cognition Ability: SG showed renewed interest towards a novel fish after habituation to a familiar fish, while LG displayed a stronger preference for the familiar fish. These findings suggest that clownfish juveniles possess advanced sociality and basic cognition ability. Furthermore, the observed shift in social interaction preference with developmental stages informs optimal timing for grading practices to minimize artificial rearing stress. This study provides some behavioral insights for optimizing large-scale artificial rearing protocols for clownfish, reducing pressure on wild populations. Full article

Downstream migration of salmonid smolts through regulated rivers remains a major ecological and engineering challenge, with high mortality and delay rates despite mitigation measures like bypasses and guidance systems. This study integrates Computational Fluid Dynamics (CFD) with fish telemetry to analyze how salmon smolts respond to local hydraulic conditions in a real riverine environment. By coupling detailed CFD flow models with two-dimensional smolt track data from a hydropower facility in northern Sweden, we identified behavioral tendencies linked to specific flow velocities. The analysis of fish movement patterns indicates a general tendency to follow the main current during migration, with occasional variations influenced by initial velocity and local flow conditions. This behaviorally informed CFD–telemetry approach provides a method for identifying behavioral patterns based on velocities and demonstrates its potential to improve fish passage models, supporting more ecologically effective hydropower design. This study highlights the need for broader datasets to fully capture smolt behavior and to develop standardized, transferable modeling frameworks for fish–flow interactions. Full article

The welfare of farmed hybrid striped bass remains largely unaddressed in U.S. aquaculture, despite the species’ economic significance and the scale of production. Physical handling during grading and inspection not only causes stress and increased incidence of injury, but also results in unmarketable fish and significant financial loss for producers. To address these issues, we present a prototype system that uses directed water currents to leverage the fish’s natural rheotactic behavior, enabling directed movement between tank regions without the need for direct physical contact. Our design allows for early identification of malformed individuals, who otherwise face prolonged suffering and starvation, so they can be humanely culled. In a small pilot study, we observed that fish moved into the destination region more frequently and with less behavioral variability when exposed to a directed current, suggesting this method as a viable alternative to traditional handling. While the system requires further refinement and testing at scale, these preliminary results offer a promising step toward ethical, commercially viable, and low-stress fish sorting systems in commercial aquaculture. Full article

The climbing perch, Anabas testudineus, is one of the most widely distributed freshwater amphibious fishes in South and Southeast Asia, inhabiting both natural and artificial water bodies polluted by plastic waste. Current mesocosm experimental study aimed to investigate behavioral responses of wild fish to floating expanded polystyrene (EPS) pellets, with a focus on the biofilm developing on their surface. For biofilm formation, the pellets (diameter 3–4 mm) were exposed for two, six, and fourteen days in an irrigation canal inhabited by climbing perch. Development of an intensive biofilm was observed on days 6 and 14 of exposure, characterized by a high diversity of organisms, including protozoa, cyanobacteria, algae, amoebae, and fungi. Fish feeding behavior was observed in the presence of feed pellets, clean EPS pellets, and three variants of EPS pellets with biofilm developed on their surfaces in the freshwater environment. The fish rapidly grasped and ingested feed pellets compared to all variants of plastic pellets. Climbing perch grasped all types of EPS pellets but always rejected them after oral cavity testing. The time to the first grasp was significantly longer for both clean EPS and EPS exposed for two days compared to feed pellets. Biofilm appeared to function as a taste deterrent for the fish: the duration of oral cavity testing was negatively correlated with the EPS pellet exposure timings in natural conditions. We suggest that floating plastic stimulates foraging behavior in the fish, and the duration of this behavior was significantly longer than that observed with feed pellets. The similarity of positive buoyant EPS pellets to natural food objects may stimulate the fish movements towards the water surface, which likely results in greater energy expenditure and increased risk of predation, without any apparent benefit to the individual. Full article

Particle Swarm Optimization (PSO) is a metaheuristic optimization technique based on population behavior, inspired by the movement of a flock of birds or a school of fish. In this method, particles move in a search space to find the global minimum of an objective function. In this work, a modified PSO algorithm written in Fortran 90 is proposed. The optimized structures obtained with this algorithm are compared with those obtained using the basin-hopping (BH) method written in Python (3.10), and complemented with density functional theory (DFT) calculations using the Gaussian 09 software. Additionally, the results are compared with the structural parameters reported from single crystal X-ray diffraction data for carbon clusters ${\mathrm{C}}_n$(n = 3–5), and tungsten–oxygen clusters, ${\mathrm{WO}}_n^{m-}$(n = 4–6, $m=2,4,6$). The PSO algorithm performs the search for the minimum energy of a harmonic potential function in a hyperdimensional space $\in {\mathbb{R}}^{3N}$ (where N is the number of atoms in the system), updating the global best position ( $g_{best}$) and local best position ( $p_{best}$), as well as the velocity and position vectors for each swarm cluster. A good approximation of the optimized structures and energies of these clusters was obtained, compared to the geometric optimization and single-point electronic energies calculated with the BH and DFT methods in the Gaussian 09 software. These results suggest that the PSO method, due to its low computational cost, could be useful for approximating a molecular structure associated with the global minimum of potential energy, accelerating the prediction of the most stable configuration or conformation, prior to ab initio electronic structure calculation. Full article

To ensure sustainable marine resource utilization, advanced monitoring methods are urgently needed to mitigate overfishing and ecological imbalances. Conventional fishing activity detection methods, including speed threshold-based approaches and Gaussian Mixture Models, often fail to accurately handle complex vessel trajectories, resulting in imprecise quantification of fishing effort and hindering effective monitoring of illegal, unreported, and unregulated (IUU) fishing activities. To address these limitations, we propose a spatiotemporal adaptive clustering and segmentation (STACS) framework for recognizing fishing activities. First, ST-DBSCAN clustering distinguishes concentrated fishing operations from transit movements. Second, an adaptive segmentation algorithm that incorporates heading stability and local density dynamically partitions trajectories into coherent segments, using spatiotemporal clusters as the basic units. Third, multiple features capturing temporal dynamics and spatial patterns are extracted to characterize fishing behaviors. Finally, an XGBoost classifier with run-length encoding post-processing converts point-level predictions to continuous fishing episodes. Experiments on fishing vessel trajectory datasets demonstrate that STACS outperforms conventional methods and advanced segmentation approaches, improving both point-level classification and segment-level coherence across diverse fishing scenarios. By enhancing IUU fishing detection and reducing classification inconsistencies, STACS provides valuable insights for marine conservation, policymaking, and fisheries management, bridging local behavioral dynamics with global trajectory analysis. Full article

The placement of hydraulic elements in existing pool-type fishways to make them more suitable for Cyprinid fish is an issue of increasing interest in fishway research. Hydrodynamic characteristics and fish behavior at the representative pool of the fishway with bottom orifices and notches were assessed at the Dagdelen hydropower plant in the Ceyhan River Basin, Türkiye. Three-dimensional velocity measurements were taken in the pool of the fishway using an Acoustic Doppler velocimeter. The measurements were taken with and without a brush block at two different vertical distances from the bottom, which were below and above the level of bristles tips. A computational fluid dynamics (CFD) analysis was conducted for the studied fishway. The numerical model utilized Large Eddy Simulation (LES) combined with the Darcy–Forchheimer law, wherein brush blocks were represented as homogenous porous media. Our results revealed that the relative submergence of bristles in the brush block plays a very important role in velocity and Reynolds shear stress (RSS) distributions. After the placement of the submerged brush block, flow velocity and the lateral RSS component were reduced, and a resting area was created behind the brush block below the bristles’ tips. Fish movements in the pool were recorded by underwater cameras under real-time operation conditions. The heatmap analysis, which is a 2-dimensional fish spatial presence visualization technique for a specific time period, showed that Capoeta damascina avoided the areas with high turbulent fluctuations during the tests, and 61.5% of the fish presence intensity was found to be in the low Reynolds shear regions in the pool. This provides a clear case for the real-world ecological benefits of retrofitting existing pool-weir fishways with such flexible hydraulic elements. Full article

Hydropower infrastructure has profoundly altered riverine connectivity, posing challenges to the migratory behavior of aquatic species. This study examined the post-passage migration efficiency of Schizothorax wangchiachii in a regulated river system, focusing on upstream and downstream reaches of the Songxin Hydropower Station on the Heishui River, a tributary of the Jinsha River. We used radio-frequency identification (RFID) tagging to track individuals after fishway passage and coupled this with environmental monitoring data. A Cox proportional hazards model was applied to identify key abiotic drivers of migration success and to develop a predictive framework. The upstream success rate was notably low (15.6%), with a mean passage time of 438 h, while downstream success reached 81.1%, with an average of 142 h. Fish exhibited distinct diel migration patterns; upstream movements were largely nocturnal, whereas downstream migration mainly occurred during daylight. Water temperature (HR = 0.535, p = 0.028), discharge (HR = 0.801, p = 0.050), water level (HR = 0.922, p = 0.040), and diel timing (HR = 0.445, p = 0.088) emerged as significant factors shaping the upstream movement. Our findings highlight that fishways alone may not ensure functional connectivity restoration. Instead, coordinated habitat interventions in upstream tributaries, alongside improved passage infrastructure, are crucial. A combined telemetry and modeling approach offers valuable insights for river management in fragmented systems. Full article

Understanding individual movement patterns in stream-resident salmonids is critical for conservation and river management, particularly in Mediterranean streams characterized by high environmental variability. We tagged 997 Mediterranean brown trout (Salmo trutta complex) and conducted an 11-month mark–recapture study using Passive Integrated Transponder (PIT) technology to assess movement behavior in the Flamisell River (Ebro Basin, northeastern Iberian Peninsula). Movements followed a leptokurtic distribution, with 81.8% of the individuals classified as sedentary (median movement = 24.9 m) and 18.2% as mobile (median movement = 376.2 m). Generalized linear models revealed distinct drivers of fish movement for each group. In sedentary trout, movement was mainly influenced by mesohabitat type, season, sex, and body size, with males and larger individuals moving farther. In mobile trout, mesohabitat type, density, and body size were key predictors. Movement patterns were repeatable over time, indicating consistent behavioral tendencies. These results support a bimodal movement strategy and highlight the importance of individual variation. Conservation planning should account for both sedentary and mobile groups to preserve functional and genetic connectivity and improve resilience of Mediterranean streams. 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

This study examined the behavioral responses of Nile Tilapia (Oreochromis niloticus), a key aquaculture species, to ammonia stress using non-invasive image processing techniques. The experiment was conducted under controlled laboratory conditions and involved four groups exposed to ammonium chloride concentrations (0, 100, 200, and 400 mg·lt⁻¹). Movement trajectories of individual fish were recorded over 10 h using high-resolution cameras positioned above and beside glass tanks. Images were processed with the Optical Flow Farneback algorithm in Python, implemented in Visual Studio Code with OpenCV and NumPy libraries, achieving a 91.40% accuracy rate in tracking fish positions. The results revealed that increasing ammonia levels restricted movement areas while elevating movement irregularity and activity. The 0 mg·lt⁻¹ group utilized the glass tank homogeneously, covering 477 m. In contrast, the 100 mg·lt⁻¹ group showed clustering in specific areas (796 m). At 200 mg·lt⁻¹, clustering intensified, particularly along the glass tank’s left edge (744 m), and at 400 mg·lt⁻¹, fish exhibited severe restriction near the water surface with markedly increased activity (928 m). Statistical analyses using Kruskal–Wallis and Dunn tests confirmed significant differences between the 400 mg·lt⁻¹ group and others. No difference was observed between the 0 mg·lt⁻¹ and 100 mg·lt⁻¹ group, indicating tolerance to lower concentrations. The study highlights the importance of ammonia levels in water quality management and reveals the potential of image processing techniques for automation and stress monitoring in aquaculture. Full article