In computer vision applications, the primary task of object detection is to answer the following question: “What object is present and where is it located?”. However, underwater environments introduce challenges, such as poor lighting, high complexity, and diverse marine organism shapes, leading to missed detections or false positives in deep learning-based algorithms. To improve detection accuracy and robustness, this paper proposes an enhanced YOLOv11-based algorithm for underwater object detection that strengthens the ability to capture both local and global details and global contextual information in complex underwater environments. To better capture local and global features while integrating contextual information, the proposed method introduces several enhancements. The backbone incorporates a DualBottleneck module to enhance feature extraction, replacing the standard bottleneck structure in C3k, thus enhancing the feature extraction and the channel aggregation. The detection head adopts DyHead-GDC, integrating ghost depthwise separable convolution with DyHead for greater efficiency. Furthermore, the ADown module replaces conventional feature extraction and downsampling convolutions, reducing parameters and FLOPs by 14%. The C2PSF module, combining focal modulation and C2, strengthens local feature extraction and global context processing. Additionally, a SCSA module is inserted before the detection head to fully utilize multi-semantic information, improving the detection performance in complex underwater scenes. Experimental results confirm the effectiveness of these improvements. The model achieves 84.2% mAP50 on UTDAC2020, 84.4% on DUO and 86.7% on RUOD, surpassing the baseline by 2.5%, 1.6% and 1.2%, respectively. It remains lightweight, with 6.5 M parameters and a computational cost of 7.1 GFLOPs.

The Yangtze finless porpoises (Neophocaena asiaeorientalis asiaeorientalis) living in different environments display significant differences in behavior and physiology. To compare and analyze gene expression differences between an ex situ population and a controlled environment population of the Yangtze finless porpoise, we sequenced the transcriptome of blood tissues living in a semi-natural reserve and an artificial facility, respectively. We identified 6860 differentially expressed genes (DEGs), of which 6603 were up-regulated and 257 were down-regulated in the controlled environment vs ex situ comparison. GO and KEGG enrichment analysis showed that the up-regulated genes in the controlled environment population were significantly associated with glucose metabolism, amino acid metabolism, and the nervous system, while those up-regulated in the ex situ population were significantly associated with energy supply and biosynthesis. Further analysis showed that metabolic and hearing-related genes were significantly affected by changes in the environment, and key metabolic genes such as HK, PFK, IDH, and GLS and key hearing-related genes such as OTOA, OTOF, SLC38A1, and GABBR2 were identified. These results suggest that the controlled environment population may have enhanced glucose metabolic ability via activation of glycolysis/gluconeogenesis, the TCA cycle, and inositol phosphate metabolism, while the ex situ population may meet higher energy requirements via enhancement of the amino acid metabolism of the liver and muscle and oxidative phosphorylation. Additionally, the acoustic behavior and auditory-related genes of Yangtze finless porpoise may show responsive changes and differential expression under different environment conditions, and thus the auditory sensitivity may also show corresponding adaptive characteristics. This study provides a new perspective for further exploration of the responsive changes of the two populations to various environments and provides a theoretical reference for further improvements in conservation practices for the Yangtze finless porpoise.

The classification of high-frequency marine mammal vocalizations often faces challenges due to the limitations of acoustic features, which are sensitive to mid-to-low frequencies but offer low resolution in high-frequency ranges. Additionally, single-channel networks can restrict overall classification performance. To tackle these challenges, we introduce MT-Resformer, an innovative dual-channel model with a multi-scale framework designed for classifying marine mammal vocalizations. Our approach introduces a feature fusion strategy that combines the constant-Q spectrogram with Mel filter-based spectrogram features, effectively overcoming the low resolution of Mel spectrograms in high frequencies. The MT-Resformer model incorporates two key components: a multi-scale parallel residual network (MResNet) and a Transformer network channel. The model employs a multi-level neural perceptron (MLP) to dynamically regulate the weighting of the two channels, enabling flexible feature fusion. Experimental findings validate the proposed approach, yielding classification accuracies of 99.17% on the Watkins dataset and 95.22% on the ChangLong dataset. These results emphasize its outstanding performance.

To explore a method of improving the reproductive performance of the striped bamboo shark, three groups (D0, D1, and D2) of mature individuals were fed squid with (D1 and D2) or without (D0) a nutritional fortifier during the breeding seasons of 2022 and 2023. Compared with the D0 group, the D1 and D2 groups had an increase of 20.90% and 31.34% in total eggs, increases of 32.73% and 41.82% in the proportion of lecithal eggs, and a total 119.07% increase in hatching rate, respectively, in 2022. In 2023, the corresponding increase was 17.12% and 9.91% in total eggs, 19.63% and 12.15% in the proportion of lecithal eggs, 43.37% and 43.94% in fertilization rate, 23.94% and 22.22% in hatchability rate, and 66.70% and 8.70% in the survival rate of fry. Moreover, the levels of serum estradiol, testosterone, progesterone, albumin, and total antioxidant capacity and the levels of ARA, EPA, DHA, n-3 PUFA, and n-6 PUFA in both serum and lecithal eggs significantly increased, while the levels of serum triglyceride and total cholesterol were the opposite (p < 0.05). The results demonstrate that feeding the sharks with a nutritional fortifier can increase spawn production and the quality of eggs, regulate the production of sex steroids, and improve the nutrition of eggs and the health of broodstocks.

The Yangtze finless porpoise (Neophocaena asiaeorientalis asiaeorientalis, YFP) is an endangered species endemic to the Yangtze River in China, and it is the only freshwater whale in the genus Neophocaena. In terms of protection, three effective conservation strategies exist: in situ conservation, ex situ conservation, and artificial breeding, all of which have been implemented by the Chinese government. Of these, ex situ conservation involves the relocation of Yangtze finless porpoises to semi-natural waters with less human interference, and artificial breeding involves the relocation of Yangtze finless porpoises to a controlled environment that is more strictly managed. To compare and analyze the responsive changes in gene expression of the YFPs between the ex situ and controlled environments, we performed the RNA sequencing of blood tissues from these YFPs. A total of 1201 differentially expressed genes (DEGs) were identified, of which 423 were up-regulated in the ex situ population and 778 were up-regulated in the controlled-environment population. Gene enrichment analysis showed that 1201 DEGs between the ex situ and controlled-environment populations were generally enriched for vision-, digestion- and immune-system-related pathways. Further analysis revealed that several key immune system pathways, such as the chemokine signaling pathway and B cell receptor signal pathway, were activated in the ex situ population. In addition, the key pathways related to vision, including phototransduction and the inflammatory mediator regulation of TRP channels, as well as the pathways related to the digestive system, such as protein digestion and absorption and salivary secretion, were activated in the controlled-environment population. These results suggest that the ex situ populations may respond to complex environmental conditions in semi-natural waters by enhancing their immune function through the increased expression of immune-related genes and that the visual function and protein digestion of the YFPs were improved compared to those of the ex situ population based on the conditions of artificial feeding, such as the higher transparency of the water and regular feeding. This study provides clues for evaluating the adaptability of YFPs to different environments and is a useful reference for future ex situ conservation and artificial breeding.

In order to optimize diets for Bengal tiger cubs and improve their health condition and survival rates, we conducted microbiota and metabolomics analyses on fecal samples from Bengal tiger cubs fed goat and dog milk replacer formulae. The results showed that there were significant differences in fecal microorganisms and metabolites between the two groups. At the phylum level, the major components of the microbial composition in the feces of cubs were Firmicutes, Actinobacteriota, Proteobacteria, Bacteroidota and Fusobacteriota. In addition, the abundance of gut microbiota varied significantly between the two groups of tiger cubs. The fecal microbiota of the tiger cubs fed dog milk replacer powder exhibited an increase in probiotic bacteria (Anaerostipes and Clostridium_scindens) (p < 0.05), and the microbial community tended to be more balanced. Metabolomics data further elucidated that feeding different milk formulae significantly affected the fecal metabolites and metabolic pathways in the Bengal tiger cubs. In the dog milk replacer powder group, 76 metabolites were up-regulated (p < 0.05), and 278 metabolites were down-regulated (p < 0.05), particularly affecting the metabolism of vitamin D3, vitamin B5, isoleucine, valine, phenylalanine and oleic acid. At the same time, 19 metabolic pathways were affected (p < 0.05), including the amino acid metabolism, lipid metabolism and nucleotide metabolism pathways. In conclusion, this study confirms that milk formula composition affects the gut microbiota and metabolism of Bengal tiger cubs. These findings may provide new insights into how different milk powder formulae and dietary strategies influence the regulation of gut microbiota and overall health in Bengal tiger cubs.