Shenglong Yang

Most unoccupied aerial systems (UAS) research in cetacean monitoring has shown that drones can acquire high-resolution imagery, but the conditions under which such imagery becomes auditable ecological evidence remain less clearly defined. A structured narrative synthesis (evidence map) was conducted using 242 Web of Science Core Collection records retained from a final export dated 23 June 2026, with search transparency supported by index specification, sentinel-paper recall checking, and predefined evidence and validation maturity coding. Five application domains were identified: morphometrics and health assessment (79 records, 32.6%), behavioral monitoring (76, 31.4%), individual identification (34, 14.0%), abundance and distribution monitoring (33, 13.6%), and multimodal or operational applications (20, 8.3%). Across these domains, the field is shifting from opportunistic visual documentation toward calibrated photogrammetry, computer-vision-assisted detection and re-identification, behavior quantification, and targeted health or molecular sampling. However, ecological inference remains constrained by availability bias, perception bias, group-size error, measurement uncertainty, algorithmic-transfer bias, and disturbance-induced bias. UAS monitoring is therefore evaluated as an observation-to-inference workflow linking platform design, sensor geometry, image preprocessing, annotation, model validation, and uncertainty propagation to management-relevant cetacean evidence.

Fine-scale identification of Spartina alterniflora (S. alterniflora) is essential for coastal wetland conservation. However, in tidal-flat environments, lodged S. alterniflora often occurs together with upright S. alterniflora and native vegetation. The two-dimensional spectral features of S. alterniflora are easily affected by senescence, canopy posture, tidal stage and mixed pixels, leading to unstable classification. The integration of UAV multispectral imagery and LiDAR data can effectively address this problem. The study focused on Shangsha Island within Jiuduansha Wetland in the Yangtze Estuary and constructed multidimensional spectral–structural features by integrating the two data sources. The separability of upright S. alterniflora, lodged S. alterniflora, Phragmites australis (P. australis) and Scirpus mariqueter (S. mariqueter) was characterized using point-cloud elevation distributions, vertical organization and canopy density. The results showed that P. australis had a multilayered point-cloud structure with broad vertical extent, S. mariqueter showed a compact and sparse structure, and S. alterniflora was characterized by a continuous and dense single-layer point-cloud structure. Lodged S. alterniflora further showed a more concentrated, single-layered point-cloud structure and stronger grass-layer continuity. Multisource classification achieved an overall accuracy of 98.15% and a Kappa coefficient of 0.97. In the lodging-area comparison experiment, point-cloud fusion increased overall accuracy from 95.18% to 97.99% and Kappa from 0.89 to 0.95, improving boundary continuity and discrimination stability. Experimental results demonstrate that the fusion of UAV multispectral imagery and LiDAR data can improve the identification of lodged S. alterniflora in complex tidal-flat environments. Accurate identification and spatial delineation of S. alterniflora can help reduce field-survey effort and associated costs while supporting more targeted and efficient removal operations.

Chub Mackerel (Scomber japonicus) is an important pelagic fishery resource in the Northwest Pacific, and its fishing-ground distribution is strongly influenced by dynamic marine environmental conditions. This study aimed to evaluate how environmental information at different temporal scales affects the prediction of high-catch fishing grounds and to identify environmental-variable contributions. Fishery logbook data from Chinese light purse seine vessels during 2014–2022 were combined with marine environmental variables to construct four feature sets: instantaneous features (E1), multi-temporal-scale fusion features (E2), short-term features with 7-day rolling means (E3), and long-term features with 30-day rolling means (E4). Deep Forest, random forest, XGBoost, LightGBM, and CatBoost were evaluated using nested spatial group cross-validation, and SHapley Additive exPlanations (SHAP) was applied to interpret model predictions. The results showed that, after historical environmental information was added, AUC values increased for most models, and the multi-temporal-scale fusion features performed better in metrics related to high-catch sample identification; therefore, the hypothesis proposed in this study was supported in the overall trend. Model comparisons showed that Deep Forest performed relatively stably under E2, E3, and E4, whereas RF performed relatively well under E1. Short-term environmental features helped improve overall fishing-ground discrimination, whereas multi-temporal-scale fusion was more favorable for identifying high-catch samples. Time-lag correlation and SHAP analyses indicated that short-term environmental changes, longer-term background conditions, and seasonal signals jointly provided information for model prediction. This study may provide a reference for real-time fishing-ground prediction and fishery management.

To address the common challenges in fish recognition tasks under complex backgrounds, such as target overlap, occlusion, and chaotic spatial distribution, an improved YOLOv11 recognition model based on the Vision Transformer (ViT) is proposed. Traditional Convolutional Neural Networks (CNNs) and the YOLO series models are limited by their local receptive fields, making it difficult to capture global semantic correlations in dense and heavily occluded fish target detection, which often leads to feature confusion and false detections. By embedding ViT modules at the beginning of the Head and at the end of the Backbone of YOLOv11, the self-attention mechanism of ViT is leveraged to capture global dependencies in the image, re-integrate and enhance multi-scale features from the Backbone and Neck, thus constructing two improved ViT models. Comparative experiments are conducted on the FishRecognition-2025 dataset, which contains 955 high-resolution RGB images covering nine common coastal fish species across four categories: single fish species, multiple classes separated, slight overlap of multiple fish species, and severe overlap of multiple fish species. Under identical training strategies and evaluation metrics, the four models—original YOLOv11, traditional CNN, ViT-Head, and ViT-Backbone—are compared. The results show that the second improved ViT model (with ViT placed at the end of the Backbone) outperformed the first improved model (with ViT placed at the beginning of the Head) in terms of mAP50 and mAP50-95. Moreover, its overall accuracy across the four test data categories (single fish species, multiple classes separated, slight overlap of multiple fish species, and severe overlap of multiple fish species) surpassed that of YOLOv11, CNN, and the first ViT model. Although its accuracy in single fish species and multiple classes separated scenarios was slightly lower than that of the CNN model, it demonstrated significant advantages in scenarios with slight overlap of multiple fish species and severe overlap of multiple fish species. These findings validate the effectiveness of the ViT module in global feature modeling and adaptability to complex backgrounds, suggesting a promising technical direction for future real-time recognition in fishery field operations.

A comprehensive understanding of the spatial dynamics and operational characteristics of fishing activities in the Arabian Sea is critical for effective marine management and regional resource conservation. Based on VIIRS/DNB nighttime light imagery from 2017 to 2022 and the YOLOv11 model, this study presents an applied observational pipeline for the spatial extraction of fishing vessel positions. Spatial statistical methods were employed to analyze the operational patterns of light-fishing fleets, and habitat niches were identified by integrating marine environmental data. The results indicate that: (1) The YOLOv11 model achieved a precision (P) of 0.966, a recall (R) of 0.954, and a mean average precision (mAP) of 0.969. Under clear-sky and thin-cloud conditions, it demonstrated superior detection accuracy compared to existing VBD (VIIRS Boat Detection) products. (2) Through Kernel Density Hotspot Analysis (KDHSA), the primary spatial distribution of the light-fishing fleet was delineated. Fishing Operation Areas (FOAs) exhibited a pronounced seasonal “clustering–diffusion–re-clustering” pattern. The Center of Effort (CoE) generally followed a counter-clockwise migration trajectory, though a clockwise shift was observed during the 2019–2020 fishing season. (3) Random Forest analysis identified dissolved oxygen at 200 m (DO200), sea surface height (SSH), and temperature at 200 m (T200) as the primary predictive environmental features associated with vessel distribution. The core spatial ranges associated with high vessel density were 9.5–14.9 mmol⋅m⁻³ for DO200, 0.24–0.36 m for SSH, and 17.3–18.0 °C for T200. Notably, the statistical contribution of subsurface factors significantly exceeded that of sea surface temperature (SST). Future research should integrate ship position data with fishery biological data to further explore the drivers of FOA variations. This study provides a scientific basis for the sustainable management and rational development of marine resources in the Northwest Indian Ocean.

To accurately predict the fishing intensity of the Northwest Pacific squid fishing grounds and address the limitations of traditional models in capturing long-term temporal and spatial correlations and neglecting the coupling relationships of deep environmental factors, this study constructs a 3DCNN model and three fusion models incorporating residual, attention, and Transformer mechanisms. Using the 2017–2024 AIS fishing data and ocean environmental variables from the North Pacific squid fishing industry, the models’ performance is compared at 12 different temporal and spatial scales, and key core environmental variables are identified. The results show that the ResNet3D model exhibits the best overall performance, achieving an F1 score of 0.7909 at the 1.0°-7 days temporal–spatial scale. The residual connections effectively mitigate the gradient vanishing problem, balancing prediction accuracy and stability. The optimal spatial resolution is 1.0°, and the key environmental variables include S₁₀₀, Chl-a₁₀₀, PP₁₀₀, and DO₁₀₀. S₁₀₀ is the core driving variable, consistently exhibiting the highest feature importance value at all time scales. It should be noted that Chl-a is considered an indirect indicator of primary productivity, which may influence squid distribution through trophic transfer processes rather than direct biological effects. This study demonstrates the prediction accuracy and applicability of the multi-mechanism fusion 3DCNN model, reveals the temporal and spatial distribution patterns of fishing intensity in the Northwest Pacific squid fishing grounds, and provides scientific methods and technical support for dynamic monitoring, intelligent management, and sustainable utilization of squid resources.

In aquaculture production, manual or fixed-schedule feeding often fails to match the real-time feeding level of fish schools, and overfeeding can lead to feed wastage and water-quality deterioration, which has become a major bottleneck for both large-scale farming efficiency and environmental sustainability. During feeding, intense competition and jumping behaviors generate splashes of varying magnitudes, which can serve as an indirect visual proxy for hunger intensity. In this study, we constructed a frame-level splash-annotated dataset and performed data preprocessing. Building upon YOLO11 pretrained weights, we introduced a P2–P5 four-scale detection head to enhance small-splash recognition, injected EGMA into the backbone C3k2 blocks, and replaced stride-2 downsampling convolutions with a three-branch ADown operator. On the validation set, the proposed YOLO11-PEGA achieved a precision of 0.86 and a recall of 0.80, with mAP@0.5 exceeding 0.80 and mAP@0.5–0.95 exceeding 0.30. Compared with the baseline model, the parameter count was reduced by 72.3%. The results demonstrate that the proposed model maintains stable detection and evaluation performance under complex environmental conditions, providing actionable decision support for feeding-threshold setting, feeding-time determination, and feed-amount adjustment.

The dynamic monitoring of fishing activities is fundamental to fishery management. Leveraging multi-year (2020–2023) AIS data from squid jigging vessels, this study employed a multi-level data mining and spatial statistical approach to decode the spatiotemporal patterns of fishing effort in the Southeast Pacific Ocean. Our analysis reveals a highly concentrated and cyclical operation model: temporally, 20% of days contributed 46% of the total effort; spatially, 30% of the fishing grounds accounted for 80% of the effort, forming four persistent hotspots. Vessels exhibited a distinct bimodal speed distribution, enabling clear behavioral differentiation. While no fishing was detected inside the seasonal no-take zone, activities were observed near its boundaries and Exclusive Economic Zones, highlighting compliance and potential risks. The significant spatial aggregation, strongest in June, underscores the tight linkage between fleet operations and resource distribution. These findings provide a scientific basis for spatially explicit management strategies to ensure the sustainable harvesting of squid resources.

Siniperca chuatsi, commonly known as mandarin fish, is one of the most economically valuable freshwater species in China. In 2022, the national aquaculture production of mandarin fish reached approximately 401,000 tons, accounting for a significant share of freshwater aquaculture in China and nearly dominating the global commercial farming landscape. With the rapid development of recirculating aquaculture systems (RASs), higher requirements have been raised for feeding efficiency and fish health monitoring. Traditional on-site visual observation methods are highly subjective, inefficient, difficult to quantify, and prone to misjudgment under conditions such as insufficient illumination, turbid water, or high stocking density. To address these challenges, this study proposes FishSegNet-PRL, an instance segmentation-based model designed to quantify the feeding intensity of mandarin fish. The model is built upon the YOLOv11-seg framework, enhanced with a P2 detection layer (P), a residual cross-stage spatial–channel attention module (RCSOSA, R), and a lightweight semantic-detail-enhanced cascaded decoder (LSDECD, L). These improvements collectively enhance small-target detection capability, boundary segmentation accuracy, and real-time inference performance. Experimental results demonstrate that FishSegNet-PRL achieves superior performance in mandarin fish instance segmentation, with a Box mAP50 of 85.7% and a Mask mAP50 of 79.4%, representing improvements of approximately 4.6% and 13.2%, respectively, compared with the baseline YOLOv11-seg model. At the application level, multiple feeding intensity quantification indices were constructed based on the segmentation results and evaluated, achieving a temporal intersection-over-union (IoU_time) of 95.9%. Overall, this approach enables objective and fine-grained assessment of mandarin fish feeding behavior, striking an effective balance between accuracy and real-time performance. It provides a feasible and efficient technical solution for intelligent feeding and behavioral monitoring in aquaculture.