Netting damage limits the safe development of marine aquaculture. In order to identify and locate damaged netting accurately, we propose a detection method using an improved Mask R-CNN. We create an image dataset of different kinds of damage from a mix of conditions and enhance it by data augmentation. We then introduce the Recursive Feature Pyramid (RFP) and Deformable Convolution Network (DCN) structures into the learning framework to optimize the basic backbone for a marine environment and build a feature map with both high-level semantic and low-level localization information of the network. This modification solves the problem of poor detection performance in damaged nets with small and irregular damage. Experimental results show that these changes improve the average precision of the model significantly, to 94.48%, which is 7.86% higher than the original method. The enhanced model performs rapidly, with a missing rate of about 7.12% and a detection period of 4.74 frames per second. Compared with traditional image processing methods, the proposed netting damage detection model is robust and better balances detection precision and speed. Our method provides an effective solution for detecting netting damage in marine aquaculture environments.

The study aimed to investigate the effects of temperature and dissolved oxygen on juvenile largemouth bass during transportation. The experiment involved four temperature groups: 20, 15, 10, and 5 °C. We analyzed the effects of acute and uniform cooling on fish behavior to determine the optimal approach for cooling. Then, we simulated transport under different temperature conditions while measuring the dissolved oxygen level and metabolic rate until all the fish died. The results showed that acute cooling significantly influenced the tail-beat frequency of fish compared with uniform cooling, while abnormal behaviors such as increased swimming, attempted jumping out of the water, and loss of balance were observed. As the transport temperature reduced, the oxygen consumption rate of fish significantly changed at 10 °C, being 2.6 times lower than at 15 °C, with values of 0.10 ± 0.02 and 0.47 ± 0.07 mg·g⁻¹·h⁻¹, respectively. The critical oxygen threshold (P_crit) of fish were 1.90 ± 0.12, 1.61 ± 0.04, 1.15 ± 0.09, and 1.12 ± 0.25 mg·L⁻¹ at 5, 10, 15, and 20 °C. In addition, below P_crit, hypoxia-led behavior changes and oxygen consumption rate reduction were observed at every transport temperature. The findings suggest that the optimal low temperature can reduce metabolism and improve the hypoxia tolerance of juvenile largemouth bass. We recommend transporting largemouth bass at an optimal low temperature (15 °C), monitoring fish behavior, and maintaining oxygen levels above P_crit during transport to prevent stress.

The optimization of the inlet layout in aquaculture systems is essential to ensure minimal solid waste discharge into the environment and improve fish production efficiency. In the present study, laboratory experiments were carried out to investigate the effects of the jetting position d/a (where d is the distance from the pipe axis to the tank side and a is the side length of the tank wall) and the jetting angle θ (the acute angle between the jetting direction and the nearest tank wall) on the solid waste removal efficiency in single-inlet and dual-inlet octagonal Recirculating Aquaculture System (RAS) tanks. To this end, three jetting positions (d/a) of 1/50, 1/8, and 1/4 and ten jetting angles (θ) of 0° to 80° were considered in the experiments. The Particle Image Velocimetry (PIV) technique was applied to measure the flow characteristics in the tank and analyze the solid waste removal under different working conditions. Residual mass of the solid waste, time of complete removal of solid waste, average velocity (v_avg), and uniformity coefficient of velocity distribution (DU₅₀) were analyzed to evaluate the solid waste removal efficiency. The obtained results indicate that adjustments of the inlet layout significantly affect the solid waste removal efficiency. It was found that a single-inlet tank with a d/a of 1/8 and θ in the range 10° to 40° has a good solid wastes removal performance, and the optimal efficiency occurs at a jetting angle of 30°. Moreover, the optimal solid waste removal efficiency in a dual-inlet tank can be achieved with a d/a ratio of 1/8 and a θ of 20°. The performed analyses reveal that from the aspect of solid waste removal efficiency, a tank with a d/a ratio of 1/8 outperforms a tank with a d/a ratio of 1/4 or 1/50. The results of this article offer novel insights in the layout of octagonal RAS tanks and provide a guideline to improve self-cleaning features of aquaculture tanks.

Anchor piles are widely used in marine aquaculture, and the safety is largely determined by the uplift resistance capacity,especially in harsh ocean environments. However, there are few practical guides to the design and installation of the anchor piles for mooring the body of marine aquaculture equipment. Laboratory experiments were conducted to investigate the effect of the initial tension angle, pile diameter, embedded depth, and pile configuration on the uplift resistance capacity of anchor piles under oblique loads. CCD camera and load cell were utilized to measure the corresponding displacement and load, respectively. The results show that increasing the initial tension angle of circular and square single piles can significantly improve the uplift resistance capacity. The failure load of the square single pile was slightly higher than that of the circular single pile. Increasing the pile diameter can effectively improve the failure load and delay the development speed of the pile top displacement. Increasing the embedded depth can effectively improve the failure load and increase the lateral displacement of the pile top. The uplift resistance capacity of the dual anchor piles was better than that of the single anchor piles. The layout configuration has little effect on the failure load, but has a large effect on the displacement development.

In recent years, the development of China’s marine aquaculture has brought serious challenges to the marine ecological environment. Therefore, it is significant to classify and extract the aquaculture zone and spatial distribution in order to provide a reference for aquaculture management. However, considering the complex marine aquaculture environment, it is difficult for traditional remote sensing technology and deep learning to achieve a breakthrough in the extraction of large-scale aquaculture zones so far. This study proposes a method based on the combination of piecewise linear stretching and R³Det to classify and extract raft aquaculture and cage aquaculture zones. The grayscale value is changed by piecewise linear stretching to reduce the influence of complex aquaculture backgrounds on the extraction accuracy, to effectively highlight the appearance characteristics of the aquaculture zone, and to improve the image contrast. On this basis, the aquaculture zone is classified and extracted by R³Det. Taking the aquaculture zone of Sansha Bay as the research object, the experimental results showed that the accuracy of R³Det in extracting the number of raft aquaculture and cage aquaculture zones was 98.91% and 97.21%, respectively, and the extraction precision of the area of the aquaculture zone reached 92.08%. The proposed method can classify and extract large-scale marine aquaculture zones more simply and efficiently than common remote sensing techniques.

Marine aquaculture facilities have been working in a high salt and humidity marine environment for a long time, which makes them be inevitably affected by seawater corrosion, especially the main structures such as metal mesh and frame. Therefore, studying the corrosion behavior of net and frame steel is of great significance for the selection of materials and corrosion protection of marine aquaculture facilities. The influence of NaCl concentrations and immersion state on self-corrosion behavior and the influence of layer thickness and overlapping area on galvanic corrosion behavior of H62 copper alloy mesh/D36 steel plate was discussed in this study using weight loss and electrochemical measurements. The tensile tests were conducted to observe the influence of different corrosion conditions on maximum force and tensile strength of the net. The corrosion rate of the two materials increased rapidly with the increase of NaCl concentrations; the corrosion rate of both materials showed the decreasing trend with the extension of time, and the corrosion rate of H62 was always lower than D36 steel. When two materials were coupled, the galvanic corrosion rate would decrease with the increase of the layer thickness and overlapping area. The tensile results were consistent with the corrosion results. When these two materials work together, adding layer thickness or increasing the overlapping area is one of the ways to protect the frame steel to a certain extent.