Water quality early warning is a key aspect in industrial recirculating aquaculture systems for high-density shrimp farming. The concentrations of ammonia nitrogen and nitrite in the water significantly impact the cultured animals and are challenging to measure in real-time, posing a substantial challenge to water quality early warning technology. This study aims to collect data samples using low-cost water quality sensors during the industrial recirculating aquaculture process and to construct predictive values for ammonia nitrogen and nitrite, which are difficult to obtain through sensors in the aquaculture environment, using data prediction techniques. This study employs various machine learning algorithms, including General Regression Neural Network (GRNN), Deep Belief Network (DBN), Long Short-Term Memory (LSTM), and Support Vector Machine (SVM), to build predictive models for ammonia nitrogen and nitrite. The accuracy of the models is determined by comparing the predicted values with the actual values, and the performance of the models is evaluated using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) metrics. Ultimately, the optimized GRNN-based predictive model for ammonia nitrogen concentration (MAE = 0.5915, MAPE = 28.95%, RMSE = 0.7765) and the nitrite concentration predictive model (MAE = 0.1191, MAPE = 29.65%, RMSE = 0.1904) were selected. The models can be integrated into an Internet of Things system to analyze the changes in ammonia nitrogen and nitrite concentrations over time through aquaculture management and routine water quality conditions, thereby achieving the application of recirculating aquaculture system water environment early warning technology.

The swimming ability of shrimp is important for their survival and growth, which directly affects their avoidance of enemies and uncomfortable environment, search and capture of food, reproductive behavior, and distribution. The knowledge concerning the swimming ability of shrimp can be widely used in the conservation of fishery resources, improving capture efficiency and stock enhancement. As one of the edible marine organisms, Litopenaeus vannamei is a traditional fishery resource and an important economic aquaculture species in China. Dissolved oxygen (DO) concentration and salinity are considered to play crucial roles in the swimming ability of L. vannamei. The tail-flip speed (S_tf) of whiteleg shrimp L. vannamei (79.90 ± 0.41 mm, 5.76 ± 0.10 g) that were exposed to various salinities (20‰, 25‰, 30‰, 35‰, and 40‰) and DO concentrations (1.9, 3.8, 6.8, and 13.6 mg/L) was determined under laboratory conditions. Metabolite concentrations in the hemolymph, hepatopancreas, and abdominal muscles were measured before and after tail-flip fatigue to evaluate the physiologic effects of fatigue in L. vannamei. The results showed that salinity and DO significantly affected the S_tf of L. vannamei. The S_tf increased and subsequently decreased with the increase in salinity from 20‰ to 40‰. The relationship between S_tf and salinity (s, ‰) can be expressed by the quadratic model as S_tf = −0.2386s² + 15.528s − 145.12, R² = 0.9693. The optimum salinity and corresponding maximum S_tf were 32.54‰ and 107.52 cm/s, respectively. The S_tf increased as the DO concentration increased from 1.9 mg/L to 13.6 mg/L. The relationship between S_tf and DO (mg/L) can be expressed by the power model as S_tf = 75.621 DO^0.1753, R² = 0.9981. The different salinities and DO concentrations directly affected the physiology of the shrimp, inducing changes in hepatopancreas total protein, plasma total protein, abdominal muscle lactate, plasma lactate, plasma glucose, hepatopancreas glycogen, and abdominal muscle glycogen concentration. Fatigue from tail-flip led to severe loss of hepatopancreas glycogen under 20‰ salinity and plasma glucose under 25‰, 30‰, and 35‰ salinity. The triglyceride and lactate in the plasma concentration increased significantly in a range of salinities. In the DO concentration experiment, fatigue from tail-flip led to a severe loss of plasma glucose under 1.9 mg/L and 3.8 mg/L DO concentrations. The plasma lactate concentration increased significantly in all DO groups. The results suggested that the inappropriate salinity and DO significantly limited the tail-flip speed of shrimp, which was due to the accumulation of metabolites. The proper salinity and DO accelerated the elimination of metabolites, reduced the energy consumption of shrimp, and thus, improved the exercise ability of shrimp. This conclusion is of particular value in evaluating the swimming ability of shrimp and understanding its ecological processes to improve capture and rearing techniques.

As one of the edible jellyfish species, Rhopilema esculentum (Kishinouye, 1891) is a traditional fishery resource and an important economic aquaculture species in China. However, facing the current situation of natural resources exhaustion and problems of breeding population frequent disease, quantity, and quality of seedlings in artificial breeding cannot satisfy the market demand. Temperature and salinity have been considered to play crucial roles in regulating R. esculentum asexual reproduction. This study examined the combined effects by exposing post-preserved R. esculentum podocysts (preserved at 2 ± 1 °C for more than 12 months) to three variable temperatures (simulated temperatures increasing from different starting dates of 14.5 °C on 1 April, 18 °C on 1 May, and 23.2 °C on 1 July, respective to natural levels) and three salinities (20, 25, and 30). Podocyst excystment, the start time of strobilation, duration of strobilation, and cumulative ephyra numbers were tested for 45 days and transfer rates from podocysts to ephyrae were analyzed to assess the most optimal combination of temperature and salinity. The results showed that podocyst excystment and ephyrae production occurred in all treatments. Higher temperature and lower salinity significantly facilitated the podocyst excystment and accelerated the start time of strobilation (p < 0.05). Significantly greater ephyra numbers were produced with lower salinity (20 and 25) and temperatures increasing from 18 °C on 1 May to natural levels (p < 0.05). There were significant interactions between temperature and salinity on the cumulative ephyra numbers and transfer rates from podocysts to ephyrae (p < 0.05). These results suggested that R. esculentum podocysts for long-term preservation at low temperature could be recycled. Temperature and salinity regulation can affect the number and time of R. esculentum seedlings to achieve high production and satisfy the market demand for real-time seedling supply. This conclusion would provide a scientific basis for the innovative methods of sustainable utilization of the edible jellyfish (R. esculentum) resources.

Swimming ability is an important means for shrimp to survive in a water environment. To investigate the effects of different body lengths (L₁: 6.5 ± 0.25 cm, L₂: 8.8 ± 0.16 cm, and L₃: 11.5 ± 0.28 cm) and different measurement methods on the measured critical swimming speeds (U_crit), this study used experimental ecology methods to determine the U_crit of three body length (BL) groups of whiteleg shrimp (Litopenaeus vannamei) at different time intervals (10, 20, 30, 40, and 50 min) and speed increments (1/2 BL s⁻¹, 3/4 BL s⁻¹, and BL s⁻¹) in a biological swimming channel. The results showed that the time interval and speed increment significantly affected the U_crit. In the small-body-length group (L₁), the U_crit of the shrimp decreased and then increased as the time interval increased, with no significant difference between time intervals or velocity increments. In the medium-body-length group (L₂), at the speed increment of 1/2 BL s⁻¹, the U_crit of the shrimp under the time interval < 40 min was significantly greater than that in the other treatment groups. At the speed increment of 1/2 BL s⁻¹, the U_crit of the shrimp decreased as the time interval increased. At the speed increment of 3/4 BL s⁻¹, the U_crit of the shrimp showed a trend of decreasing and then increasing with increasing time interval, and at a high-speed increment (BL s⁻¹), the time interval had no significant effect on U_crit. In the large-body-length group (L₃), at the speed increment of 1/2 BL s⁻¹, the U_crit of the shrimp under the time interval < 30 min was significantly higher than that in the other treatment groups. The effect of the time interval on U_crit was not significant at high-speed increments, and U_crit decreased with increasing time interval only at the speed increment of 1/2 BL s⁻¹. This study showed that, in the small-body-length group, the time increment has a more significant effect on the critical swimming speed, and, as the body length increases, both the time increment and velocity increment affect the critical swimming speed. When the time interval is 20 min and the speed increment is 1/2 BL s⁻¹, the measured U_crit is the closest to the appropriate value.

Accurate monitoring of polyp attachment density is critical for the efficient culture of the edible jellyfish Rhopilema esculentum , yet quantitative density–growth guidelines remain limited. This study coupled image-based deep learning with conventional morphometry to characterise density-dependent growth of polyps. Polyp calyx diameter was measured manually to establish a density–size relationship. In parallel, standardised photography combined with a U-Net segmentation model was used to obtain individual polyp counts and projected areas. Regression analyses were conducted to derive functional relationships between attachment density and polyp size metrics, and processing times were compared between manual and automated approaches. Manual measurements showed that calyx diameter followed a power-law decay with density ( Calyx diameter = 1.5752Density ^-0.281 , R ² = 0.9614). Automated image analysis yielded an exponential density–polyp area model ( Polyp area = 4.3888e ^-0.202 Density , R ² = 0.9909). Both models revealed a strong inverse relationship: as attachment density increased, average polyp size and relative growth efficiency declined, whereas size variability increased. The U-Net-based segmentation approach achieved processing times of under one second per image, dramatically faster than manual measurements. These results demonstrate that AI-driven image segmentation provides accurate, high-throughput estimation of polyp size and robust quantitative density–growth relationships. The approach offers a practical and efficient tool for precision monitoring and optimisation of nursery conditions in R. esculentum aquaculture.