A method and system for regulating water body of new maroon shrimp based on meteorological data

Abstract

The application discloses a meteorological data-based penaeus monodon cultivation water body regulation method and system, and relates to the water quality regulation field.The method comprises the following steps: collecting penaeus monodon samples in different development states, determining corresponding development stages and corresponding water quality parameters, and generating a sample database; collecting the development state parameters of target penaeus monodon in a to-be-regulated cultivation tank, comparing the development state parameters with the sample database, determining the development stage and corresponding water quality requirements of the target penaeus monodon, obtaining cultivation water quality parameters under different meteorological conditions, and establishing a neural network model; inputting real-time meteorological data into the trained neural network model, outputting water quality parameter prediction values, judging whether the water quality meets the water quality requirements of the target penaeus monodon, and adaptively regulating the water quality that does not meet the requirements, so that the water quality parameters are maintained within a target range.The method effectively improves the accuracy and adaptability of penaeus monodon cultivation water quality management.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality control, and in particular to a method and system for controlling water quality in shrimp farming based on meteorological data. Background Art

[0002] New Penaeus lanceolatus ( Metapenaeus ensis Penaeus scutellaria is a marine organism that thrives at the interface between fresh and salt water and is a very important economic shrimp. Its high protein content, unique flavor, and suitability for long-distance transportation have made it highly sought after in the domestic consumer market. Currently, artificial propagation technology for the Penaeus scutellaria is immature, and the level of systematic farming is low, resulting in low production and a failure to meet market demand.

[0003] Due to high market demand, catches are no longer sufficient to meet demand. Extensive bottom trawling in recent years has damaged the genetic resources of the Penaeus razorbackii, significantly reducing its abundance. As a highly economically valuable species, its aquaculture has long been restricted to coastal environments. Existing indoor farms suffer from issues such as low survival rates due to salinity fluctuations, excessive ammonia and nitrogen levels caused by accumulated excrement, and inefficient space utilization due to insufficient three-dimensional stratification.

[0004] At the same time, with the continuous development of meteorological data collection and intelligent control technologies, it is becoming possible to provide more scientific, real-time, and efficient water quality control methods for the cultivation of Penaeus scutellaria. Meteorological conditions such as temperature, humidity, and wind speed have a significant impact on the water quality parameters of the aquaculture water. For example, air temperature fluctuations can change water temperature, and wind speed can affect salinity fluctuations in the water. These external environmental factors affect the cultivation results of Penaeus scutellaria. Therefore, establishing water quality control methods based on meteorological data and combining them with artificial intelligence technology to achieve automated water quality control is a key technical direction for solving the water quality management problems of traditional aquaculture.

[0005] Prior art publication CN116941562A discloses an IoT-based water quality control method and system for shrimp farming. The method includes the following steps: arranging multiple water quality sensors within the shrimp farming pond to detect initial water quality data; constructing an initial water quality model based on the initial water quality data and deriving initial water quality parameters; regulating the shrimp farming pond using an intelligent control system based on the initial pond parameters; training a BP neural network on the regulated water quality data to generate real-time water quality data; and finally, analyzing the real-time water quality data to adjust control instructions for the aerator. The intelligent control system is connected to a monitoring and alarm system. Upon activation of the monitoring and alarm system, the intelligent control system resumes control of the aerator. However, this solution fails to account for the impact of meteorological factors and the effect of salinity fluctuations on shrimp survival rates. Consequently, the practicality and effectiveness of the water control method are reduced.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The object of the present invention is to provide a method and system for regulating water bodies for Penaeus scabra aquaculture based on meteorological data, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for regulating water bodies for Penaeus serratus aquaculture based on meteorological data, comprising the following steps:

[0010] Obtain samples of Neopenaeus edulis at different developmental stages, collect developmental status parameters for each sample, and establish mapping relationships between developmental status parameters and developmental stages, and between developmental stages and water quality parameter requirements;

[0011] Randomly collect multiple Penaeus scutellaria from the culture tank of the target Penaeus scutellaria var. juncea. Determine the primary developmental stage based on the distribution of developmental stages. Combined with the mapping relationship, determine the target water quality parameter requirements. Select the Penaeus scutellaria var. juncea that belong to the primary developmental stage as the target Penaeus scutellaria var.

[0012] Obtain the past meteorological condition parameters and water quality parameters of the new shrimp culture tank to be regulated, and use them to train a water quality prediction model built based on the long short-term memory network. Based on the trained water quality prediction model, the predicted values ​​of future water quality parameters are output;

[0013] Collect the developmental status parameters of the target Penaeus lanceolatus shrimp and, based on the difference between the predicted water quality parameters and the target water quality parameters, determine whether to adjust the water quality of the Penaeus lanceolatus shrimp culture tank to be regulated;

[0014] If the predicted values ​​of the water quality parameters do not meet the water quality requirements, the control device in the breeding tank to be regulated will be adjusted. By adjusting the control device, adaptive regulation of the water quality is achieved, and the breeding water quality parameters are controlled within the water quality requirements of the target new shrimp at the corresponding developmental stage.

[0015] Further, determining the developmental stages of different Penaeus lanceolatus samples and the water quality parameter requirements for the corresponding developmental stages, wherein the developmental stages of the Penaeus lanceolatus samples include embryonic stage, larval stage, postlarval stage and adult stage;

[0016] The water quality parameter requirements during the development stage specifically refer to salinity and uniformity requirements, water temperature requirements, dissolved oxygen requirements, and ammonia nitrogen content requirements;

[0017] The development state parameters of the sample of the Neocaridina denticulata are the body length, the body weight and the expression level of hormones of the Neocaridina denticulata, and the expression level of hormones specifically refers to the animal hyperglycemic hormone level and the molting inhibiting hormone level of the Neocaridina denticulata;

[0018] The data between the development state parameters and the development stages and the water quality parameter requirements are one-to-one mapped to form a corresponding grid, and the formed grid is recorded as a sample data set;

[0019] The logic for determining the main development stage is that a plurality of Neocaridina denticulata are randomly collected from a to-be-controlled Neocaridina denticulata breeding tank as detection samples, the development stages of the detection samples are determined through the development state parameters of the detection samples, a development stage with the largest number of detection samples is screened out and is taken as the main development stage, and the detection samples belonging to the main development stage are taken as target Neocaridina denticulata.

[0020] Further, based on the data in the training data set, a neural network model is established, and the training data set specifically refers to the past meteorological condition parameters and water quality parameters of the to-be-controlled Neocaridina denticulata breeding tank, and the time stamps of the corresponding meteorological condition parameters and water quality parameters are recorded, and the meteorological condition parameter and water quality parameter data with the aligned time stamps are one-to-one mapped to form a training data set; wherein the neural network model is established based on a long short-term memory network model, the long short-term memory network model is an LSTM model, an activation function and an optimization algorithm are selected, wherein a Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is:

[0021]

[0022] In the formula, Tanh function, independent variable represents the input weighted sum of neurons, that is, the result of the weighted sum of the inputs received by the neurons from the previous layer;

[0023] Meanwhile, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing quantity and the number of hidden layer neurons;

[0024] The number of network layers is set to a three-layer network structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch processing quantity is set to 256, and the number of hidden layer neurons is 32;

[0025] The meteorological condition parameters and water quality parameters corresponding to the first n-1 timestamps in the training data set are used as the input of the model, and the water quality parameters corresponding to the nth timestamp are used as labels to train the neural network model; where n is a positive integer;

[0026] The meteorological condition parameters and water quality parameters corresponding to the current moment and the previous n-2 moments are input into the trained neural network model to obtain the parameter prediction value of the aquaculture water quality at the next moment.

[0027] Furthermore, it is determined whether the predicted water quality parameter and the target water quality parameter meet the following constraints. If so, the water quality is not adjusted. If not, the water quality is determined again based on the developmental status parameters of the target Penaeus lanceolatus.

[0028]

[0029] Where, is the predicted value of water salinity, is the predicted value of water salinity uniformity, is the predicted value of water quality and temperature, is the predicted value of dissolved oxygen in water quality, is the predicted value of ammonia nitrogen content in water quality, and are the minimum and maximum salinity requirements in the target water quality parameter requirements, and are the minimum and maximum values ​​of water temperature requirements in the target water quality parameter requirements, and are the minimum and maximum values ​​of dissolved oxygen in the target water quality parameter requirements, The maximum value of ammonia nitrogen content required in the target water quality parameter requirements;

[0030] If the water quality constraint conditions are not met, the minimum difference between the predicted water quality parameter and the target water quality requirement is calculated. The formula for calculating the minimum salinity difference is:

[0031]

[0032] Where, is the minimum difference in salinity;

[0033] The minimum difference between the predicted water quality parameters and the target water quality requirements was analyzed, and the adjustment judgment coefficient was calculated based on the target developmental state parameters of the new white shrimp. The adjustment judgment coefficient was calculated based on the formula:

[0034]

[0035] Where, To adjust the judgment coefficient, is the development index of target Penaeus scabra, is the minimum difference in salinity uniformity; is the minimum difference in water temperature, is the minimum difference in dissolved oxygen, is the minimum difference in ammonia nitrogen content;

[0036] The target shrimp development index The specific formula for the calculation is:

[0037]

[0038] Where, is the maximum body length corresponding to the main developmental stages, is the maximum weight corresponding to the main developmental stages, is the highest molting frequency corresponding to the main developmental stages, is the average body length of the target Penaeus scabra, is the average weight of target Penaeus scabra shrimp, is the average molting frequency of the target Neopenaeus scutellaria;

[0039] The logic for determining whether to adjust the water quality of the new shrimp farming tank is as follows:

[0040] when When the water quality in the aquarium is judged to need to be adjusted;

[0041] when When the water quality in the culture tank does not need to be adjusted, the water quality meets the current development requirements of the Neopenaeus lanceolatus. To adjust the judgment threshold;

[0042] If it is determined that regulation is necessary, the control device in the breeding tank to be regulated that does not meet the water quality requirements of the corresponding development stage is regulated.

[0043] Furthermore, the control device is controlled, specifically, by controlling the flow rate of the wave maker, the amount of degradation components in the filter tank, and the water temperature, wherein the goal of the adaptive control is to control the aquaculture water quality parameters within the water quality requirements of the corresponding developmental stage of the Neopenaeus lanceolatus.

[0044] The specific formula for regulating the output flow of the wave maker is:

[0045]

[0046] Where, is the flow correction value of the wave maker at the next moment, Real-time flow of the wave maker, is the control coefficient, which is characterized by the error of water quality parameters, where the control coefficient The calculation is based on the formula:

[0047]

[0048] Where, 、 and are the weight coefficients of salinity difference, dissolved oxygen difference and salinity uniformity difference, respectively, where and 、 and are all greater than 0 and their sum is 1.

[0049] Furthermore, the specific formula for regulating the amount of degradation components in the filter tank is:

[0050]

[0051] Where, is the correction value of the amount of degradation components in the filter tank, is the initial value of the amount of degradation components in the filter tank, is the maximum amount of degradation components in the filter tank, is the coefficient of influence of the amount of degradation components; the filter tank adopts a three-dimensional layered form and is isolated from the aquaculture waters.

[0052] The water temperature is regulated by adjusting the operating frequency of the water temperature control device, and the specific formula is as follows:

[0053]

[0054] Where, is the working frequency correction value of the water temperature control device at the next moment, is the real-time operating frequency of the water temperature control device, where is the temperature correction coefficient, where When the water temperature control device acts as a cooler, When the water temperature control device is used as a heater.

[0055] The present invention also provides a water body control system for Penaeus serratus shrimp aquaculture based on meteorological data, wherein the water body control system for Penaeus serratus shrimp aquaculture based on meteorological data is used to execute the above-mentioned water body control method for Penaeus serratus shrimp aquaculture based on meteorological data, comprising:

[0056] The sample data processing module is used to obtain samples of Neopenaeus edulis at different developmental stages, collect developmental status parameters of each sample, and establish mapping relationships between developmental status parameters and developmental stages, and between developmental stages and water quality parameter requirements;

[0057] The developmental stage characterization module is used to randomly collect multiple Penaeus scutellaria from the culture tank of the target Penaeus scutellaria var. ...

[0058] The meteorological impact characterization module is used to obtain the past meteorological condition parameters and water quality parameters of the new shrimp culture tanks to be regulated, and use them to train the water quality prediction model built based on the long short-term memory network. The trained water quality prediction model outputs the predicted values ​​of future water quality parameters based on the completed water quality prediction model;

[0059] The dynamic water quality control judgment module is used to collect the developmental status parameters of the target Penaeus scutellaria var. scutellariae and, based on the difference between the predicted water quality parameters and the target water quality parameters, determine whether to adjust the water quality of the Penaeus scutellariae var. scutellariae breeding tank;

[0060] The water quality requirement control module is used to control the control device in the breeding tank to be regulated if the predicted value of the water quality parameter does not meet the water quality requirements. By adjusting the control device, adaptive control of water quality is achieved, and the breeding water quality parameters are controlled within the water quality requirements range of the target new shrimp at the corresponding development stage.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] First, by establishing a sample database, a number of Penaeus scutellaria samples at different developmental stages were correlated with the water quality requirements of their corresponding developmental stages. This approach provides a scientific reference for water quality regulation at different developmental stages of Penaeus scutellaria. This approach addresses the unclear control standards and reliance on manual experience in traditional aquaculture, ensuring that water quality parameters are closely aligned with the developmental needs of Penaeus scutellaria, thereby optimizing the shrimp's growth environment, reducing disease risks, and increasing yields.

[0063] Secondly, the present invention incorporates the impact of meteorological conditions on aquaculture water quality into the control system, and establishes a neural network model by collecting water quality parameter data under different meteorological conditions. After training, the changes in aquaculture water quality are predicted based on real-time meteorological data. This prediction method based on meteorological data solves the problem that traditional control methods cannot respond to environmental changes in a timely manner. It can achieve early prediction and rapid control of water quality changes, so that the farm can maintain a stable water quality environment when meteorological conditions fluctuate. In addition, the present invention combines a control device to achieve adaptive control of water quality. When the real-time water quality parameters do not meet the developmental stage requirements of the new blade-headed shrimp, the water temperature, dissolved oxygen concentration and other key parameters are quickly adjusted through the automation system to ensure that the water quality is always within an appropriate range. This adaptive control method significantly improves the accuracy and efficiency of water quality control and reduces the necessity of manual intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 Schematic diagram of the overall method flow of the present invention;

[0065] Figure 2 The dot-line representation diagram of the developmental parameters of different Penaeus lanceolatus;

[0066] Figure 3 This is a bar chart showing the specific developmental stages of different Neopenaeus scabra.

[0067] Figure 4 The dot-line graph represents the accuracy of salinity prediction value and water temperature prediction value;

[0068] Figure 5 A dot-line graph representing the predicted values ​​of dissolved oxygen and ammonia nitrogen;

[0069] Figure 6 This is a schematic diagram of the correction of the wave maker flow rate and degradation component dosage;

[0070] Figure 7 This is a schematic diagram of the working frequency correction of the water temperature control device;

[0071] Figure 8 Schematic diagram of the overall system structure of the present invention;

[0072] Figure 9 This is a right side view of the aquaculture tank structure of the present invention;

[0073] Figure 10 This is a left side view of the aquaculture tank structure of the present invention;

[0074] Figure 11 This is a front view of the aquaculture tank structure of the present invention;

[0075] The attached figure supplements the explanation that in the structural diagram of the breeding tank: 1 is the physical interception area for the protein skimmer; 2 is the second interception module; 3 is the upper water tank; 4 is the water temperature control device; 5 is the emergency oxygen control device; 6 is the water outlet valve; 7 is the wave-making device; and 8 is the water inlet valve. DETAILED DESCRIPTION

[0076] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0077] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0078] Example:

[0079] See also Figure 1-Figure 7 , the present invention provides a technical solution:

[0080] A method for regulating water bodies for Penaeus serratus aquaculture based on meteorological data, comprising the following steps:

[0081] Step 1: Obtain samples of Penaeus edulis at different developmental stages, collect developmental status parameters for each sample, and establish mapping relationships between developmental status parameters and developmental stages, and between developmental stages and water quality parameter requirements.

[0082] Determining the developmental stages of different Penaeus lanceolatus samples and the water quality parameter requirements for the corresponding developmental stages, wherein the developmental stages of the Penaeus lanceolatus samples include embryonic stage, larval stage, postlarval stage and adult stage;

[0083] Neopenaeus razorbackus is a benthic shrimp, active at night and burrowing in the sand. It is found in coastal waters at depths of 20 to 50 meters. It is a euryhaline shrimp that can thrive in both seawater and pure freshwater. Its growth temperature range is 12 to 37°C, with an optimum temperature of 25 to 30°C. The dissolved oxygen asphyxiation point for embryonic shrimp is 0.20 mg / L. Ammonia nitrogen concentration should be below 0.1 mg / L, as juveniles are particularly sensitive to it and excessively high levels can cause toxicity. Salinity: Optimum salinity is 27%-29%, making it highly adaptable, but adjustments must be made to the culture environment.

[0084] The dissolved oxygen asphyxiation point for juvenile shrimp is 1.63 mg / L. High dissolved oxygen levels are required to ensure the juveniles' metabolic needs. Ammonia nitrogen concentrations should be below 0.15 mg / L, as juveniles are particularly sensitive to ammonia nitrogen and excessively high concentrations can cause toxicity. Salinity: The optimal salinity is 25%-30%, which is highly adaptable, but still needs to be adjusted according to the aquaculture environment.

[0085] The dissolved oxygen asphyxiation point for larval shrimp is between 0.50 and 0.73 mg / L. They can survive normally in water with a pH between 7 and 9. Ammonia nitrogen: The concentration should be below 0.15 mg / L, as larvae are particularly sensitive to it and excessively high concentrations can cause poisoning. Salinity: The optimal salinity is 25%-32%.

[0086] The dissolved oxygen asphyxiation point of adult shrimp is between 0.30 and 0.61 mg / L. They can survive normally in water with a pH between 7 and 9. Mature individuals range in length from 80 to 160 mm and weigh from 13 to 35 g. Their optimal salinity is 25% to 32%. Ammonia nitrogen concentrations should be below 0.15 mg / L.

[0087] Neopenaeus razorbackus reaches sexual maturity at 10 cm in length. Adult shrimp breed in water temperatures between 25 and 32°C, with the optimum temperature for spawning being between 29 and 30°C. The ovaries of sexually mature females extend from the cephalothorax to the end of the abdomen, and mature gonads can be observed through the carapace.

[0088] The water quality parameter requirements during the development stage specifically refer to salinity and uniformity requirements, water temperature requirements, dissolved oxygen requirements, and ammonia nitrogen content requirements;

[0089] The salinity and uniformity of water quality are monitored using a salinometer or conductivity meter. Samples are taken at fixed points in the aquaculture water body, and the salinity of the water body is directly measured using a salinometer. Uniformity can be measured multiple times at different depths and locations, such as the four corners and center of the aquaculture pond. The data are recorded and the mean and standard deviation are calculated to evaluate the uniformity of salinity.

[0090] Use a water thermometer or digital thermometer to monitor water temperature. Measure the water temperature directly in the aquaculture water body, paying attention to measuring at different depths (surface and bottom) to obtain comprehensive data.

[0091] Use a dissolved oxygen meter to directly measure dissolved oxygen levels in aquaculture water. Multiple measurements can be taken at different time periods to understand trends in dissolved oxygen levels over the day and night.

[0092] Use an ammonia nitrogen meter or kit, such as a water quality analysis kit. After sampling, use the kit according to the instructions to determine the ammonia nitrogen content, usually by colorimetry or other chemical reaction methods.

[0093] The developmental status parameters of the Penaeus scutellariae sample include the body length, weight and hormone expression levels of the Penaeus scutellariae, wherein the hormone expression levels specifically refer to the levels of animal hyperglycemic hormone and molting-inhibiting hormone of the Penaeus scutellariae;

[0094] When scholars from the University of Hong Kong cloned the crustacean hyperglycemic hormone (CHH) and molt-inhibiting hormone (MIH) of the cuttlefish and injected them, they found that the transcription levels of CHH and MIH increased in the middle and late stages of sexual maturity of the cuttlefish, respectively. This may be because these two hormones play an important role in the gonadal maturation cycle of female cuttlefish; some studies have used recombinant protein and RNA interference technology to confirm that molt-inhibiting hormone (MIH) has the function of stimulating gonads.

[0095] Therefore, crustacean hyperglycemic hormone (CHH) and molt-inhibiting hormone (MIH) of the cuttlefish are used to affect sexual maturity development, and sexual maturity development is closely related to the developmental stage of the shrimp. Therefore, the developmental stage of the cuttlefish can be judged by combining the hormone expression levels.

[0096] According to existing literature, CHH is primarily synthesized and secreted in the optic nerve and abdominal ganglion of shrimp, while MIH is primarily synthesized in the pancreas. These tissues can be selected for hormone level testing. Store frozen in liquid nitrogen or at -80°C until hormone extraction. Homogenize the frozen tissue sample in extraction buffer, typically using a tissue homogenizer or ultrasonicator. Protease inhibitors may be added during homogenization to prevent hormone degradation. After homogenization, centrifuge the mixture at 12,000-15,000 rpm for 10-15 minutes at 4°C to obtain the supernatant, which will be retained for subsequent hormone measurement. Select an ELISA kit suitable for CHH and MIH, ensuring its specificity and sensitivity meet experimental requirements. The specific experimental steps include: Add the standard and diluted sample to a 96-well plate. Add the appropriate amount of enzyme-conjugated antibody, mix thoroughly, and incubate at an appropriate temperature, typically room temperature or 37°C, for the time specified in the kit instructions. Wash the plate to remove unbound antibody. Add the substrate solution and incubate until the color reaction reaches a plateau. Then stop the reaction, usually by adding a stop solution. Read the absorbance using a microplate reader at a specific wavelength, typically 450 nm.

[0097] Map the data between the development state parameters and the development stages, and between the development stages and the water quality parameter requirements one by one to form a corresponding grid, and record the formed grid as a sample data set;

[0098] The logic behind determining the primary developmental stage is as follows: Multiple Penaeus scutellariae shrimp are randomly collected from the target Penaeus scutellariae shrimp culture tanks as test samples. Developmental parameters are then used to determine the developmental stage of each sample. The developmental stage with the largest number of samples is then selected as the primary developmental stage, and samples belonging to this primary developmental stage are designated as the target Penaeus scutellariae shrimp. Table 1 shows selected growth and development data for each developmental stage.

[0099] Table 1: Developmental status parameters and corresponding developmental stage statistics

[0100]

[0101] The length of Penaeus scutellaria specimens is measured using a vernier caliper or specialized fish and shrimp measuring instruments. Ensure the accuracy of the measuring tool. This is typically measured from the head to the end of the tail fin. This is called a "full-length" measurement. Ensure the shrimp is stable during measurement to obtain an accurate reading.

[0102] The method for obtaining weight data is to use a precise electronic balance to ensure the calibration and accuracy of the balance, place the fresh shrimp on the weighing plate, and ensure that the shrimp body is not affected by external forces to avoid errors caused by movement.

[0103] Step 2: Randomly collect multiple Penaeus scutellaria from the culture tank of the target Penaeus scutellaria var. scutellariae. Determine the main developmental stage based on the distribution of developmental stages, and determine the target water quality parameter requirements based on the mapping relationship. The Penaeus scutellariae that belong to the main developmental stage are used as the target Penaeus scutellariae.

[0104] The main developmental stage is determined based on the distribution of developmental stages. The logic for determining the main developmental stage is as follows: multiple Penaeus scutellariae shrimp are randomly collected from the breeding tank of the Penaeus scutellariae shrimp to be regulated as test samples. The developmental stage of each test sample is determined by testing the developmental status parameters of the test samples. The developmental stage with the most occurrence in the test samples is regarded as the main developmental stage, and the Penaeus scutellariae shrimp belonging to the main developmental stage are regarded as the target Penaeus scutellariae shrimp.

[0105] Step 3: Obtain the past meteorological condition parameters and water quality parameters of the new shrimp culture tank to be regulated, and use them to train the water quality prediction model constructed based on the long short-term memory network. Based on the trained water quality prediction model, output the predicted values ​​of future water quality parameters.

[0106] Table 2 shows the condition parameters for the test settings.

[0107] Table 2: Statistics of experimental setting parameters

[0108]

[0109] The neural network model is established based on data in a training data set, and the training data set specifically refers to: past meteorological condition parameters and water quality parameters of the to-be-regulated Marsupenaeus japonicus culture tank, and the corresponding time stamps of the meteorological condition parameters and the water quality parameters are recorded, the meteorological condition parameters and the water quality parameters data aligned with the time stamps are one-to-one mapped to form a training data set; wherein the neural network model is established based on a long short-term memory network model, and the long short-term memory network model is an LSTM model, an activation function and an optimization algorithm are selected, wherein a Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is:

[0110]

[0111] In the formula, Indicates the Tanh function, and the independent variable Indicates the input weight sum of the neuron, that is, the result of the weighted sum of the input received by the neuron from the previous layer;

[0112] Meanwhile, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include: network layer number, iteration number, learning rate, batch size, training number, batch quantity and hidden layer neuron number;

[0113] The network layer number is set to a 3-layer network structure, the iteration number is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the training number is set to 100, the batch quantity is set to 256, and the hidden layer neuron number is 32;

[0114] The meteorological condition parameters and the water quality parameters corresponding to the first n-1 time stamps in the training data set are used as the input of the model, and the water quality parameters corresponding to the nth time stamp are used as the label, and the neural network model is trained; wherein n is a positive integer;

[0115] The meteorological condition parameters and the water quality parameters corresponding to the current time and the previous n-2 time are input into the trained neural network model to obtain the predicted value of the water quality parameters of the next time.

[0116] Table 3: Statistical table of predicted and experimental values of water quality conditions

[0117]

[0118] As shown in Table 3, the experimental and predicted values ​​for salinity, water temperature, dissolved oxygen, and ammonia nitrogen content exhibited some fluctuation and accuracy across different samples. Sample 5 had the smallest difference between the experimental salinity value (29.5) and the predicted value (30.0), achieving a prediction accuracy of 98.31%. In contrast, Sample 8 had the largest difference between the experimental water temperature value (16.5) and the predicted value (23.0), demonstrating the relative instability of the model under specific conditions.

[0119] Overall, the differences between the experimental and predicted salinity values ​​are small. For example, the difference between the experimental value (25.8) and the predicted value (26.0) for the second sample is only 0.2, while the difference for the fourth sample is 0.5. These fluctuations are within a reasonable range, indicating that the model is relatively adaptable to different salinity conditions.

[0120] The prediction accuracy for water temperature was generally high, with the difference between the predicted and actual values ​​for the vast majority of samples not exceeding 1.5°C, demonstrating the model's strong ability to predict water temperature fluctuations. Notably, the difference between the experimental and predicted dissolved oxygen values ​​for sample 3 (0.3) remained relatively consistent across all samples, demonstrating that the model effectively captured the varying characteristics of dissolved oxygen. For ammonia nitrogen content, the prediction accuracy for the vast majority of samples exceeded 90%. For example, the difference between the experimental ammonia nitrogen value (0.065) and the predicted value (0.06) for sample 1 was 0.005, demonstrating the model's reliability in predicting ammonia nitrogen content.

[0121] LSTM, through its unique gating mechanism—forget gate, input gate, and output gate—can effectively capture long-term dependencies, enabling it to better process and predict time series data. For example, aquaculture water quality parameters and meteorological conditions often change over time. LSTM can remember past state information, enabling more accurate predictions of future states.

[0122] Multiple input features: LSTM models can process multiple input features, such as real-time meteorological data, and can adapt to different input modes and dimensions. This is crucial for real-time monitoring of aquaculture water quality, as factors affecting water quality can vary, such as temperature, humidity, and wind speed.

[0123] Step 4: Collect the developmental status parameters of the target Penaeus razorfin shrimp and, based on the difference between the predicted water quality parameters and the target water quality parameter requirements, determine whether to adjust the water quality of the Penaeus razorfin shrimp culture tank to be regulated.

[0124] Determine whether the predicted water quality parameter values ​​and target water quality parameter requirements meet the following constraints. If so, do not adjust the water quality. If not, re-determine based on the developmental status parameters of the target Penaeus lanceolatus.

[0125]

[0126] Where, is the predicted value of water salinity, is the predicted value of water salinity uniformity, is the predicted value of water quality and temperature, is the predicted value of dissolved oxygen in water quality, is the predicted value of ammonia nitrogen content in water quality, and are the minimum and maximum salinity requirements in the target water quality parameter requirements, and are the minimum and maximum values ​​of water temperature requirements in the target water quality parameter requirements, and are the minimum and maximum values ​​of dissolved oxygen in the target water quality parameter requirements, The maximum value of ammonia nitrogen content required in the target water quality parameter requirements;

[0127] If the water quality constraint conditions are not met, the minimum difference between the predicted water quality parameter and the target water quality requirement is calculated. The formula for calculating the minimum salinity difference is:

[0128]

[0129] Where, is the minimum difference in salinity;

[0130] The larger the minimum salinity difference value, the greater the deviation from the salinity requirement of the target water quality, and the less suitable it is for the growth and development of Penaeus lanceolatus.

[0131] The formula for calculating the minimum difference in salinity uniformity is:

[0132]

[0133] in is the minimum difference in salinity uniformity; the larger the minimum difference in salinity uniformity, the greater the deviation from the salinity uniformity required by the target water quality, and the less suitable it is for the growth and development of Penaeus lanceolatus.

[0134] The calculation methods for the minimum difference in water temperature and the minimum difference in dissolved oxygen are similar and will not be elaborated here.

[0135] The formula for calculating the minimum difference in ammonia nitrogen content is:

[0136]

[0137] Where, The minimum difference in ammonia nitrogen content. A larger minimum difference in ammonia nitrogen content indicates a higher ammonia nitrogen content, which may cause disease and death in the shrimp, making it unsuitable for the shrimp's growth and development.

[0138] The minimum difference between the predicted water quality parameters and the target water quality requirements was analyzed, and the adjustment judgment coefficient was calculated based on the target developmental state parameters of the new white shrimp. The adjustment judgment coefficient was calculated based on the formula:

[0139]

[0140] Where, To adjust the judgment coefficient, is the development index of target Penaeus scabra, is the minimum difference in salinity uniformity; is the minimum difference in water temperature, is the minimum difference in dissolved oxygen, is the minimum difference in ammonia nitrogen content;

[0141] It should be noted that through the form of square root , avoid excessive influence caused by water temperature difference, make calculation smoother, and adjust the judgment coefficient Larger values ​​indicate a lower probability of requiring adjustment. The introduction of the target Penaeus lanceolatus development index indicates that when the target Penaeus lanceolatus is well developed (i.e., its length and weight are above the average for that developmental stage), and when water quality variations are small, no water quality adjustment is necessary. Larger minimum differences between water quality requirements indicate a greater deviation from the target water quality parameters, making the water less suitable for Penaeus lanceolatus growth and development, and increasing the probability that water quality adjustment is necessary. Therefore, the adjustment judgment coefficient is inversely proportional to the minimum difference between water quality requirements.

[0142] The target shrimp development index The specific formula for the calculation is:

[0143]

[0144] Where, is the maximum body length corresponding to the main developmental stages, is the maximum weight corresponding to the main developmental stages, is the highest molting frequency corresponding to the main developmental stages, is the average body length of the target Penaeus scabra, is the average weight of target Penaeus scabra shrimp, is the average molting frequency of the target Neopenaeus scutellaria;

[0145] Molting is an essential physiological process for the growth of shrimp and other crustaceans. Introducing molting frequency provides a more comprehensive reflection of the growth and health of Penaeus scaphos. Molting frequency is closely related to the shrimp's growth rate and ability to adapt to the environment. Frequent molting generally indicates favorable growth conditions and adequate nutrient supply.

[0146] The molting frequency can reflect the effect of water quality on the growth of shrimp. Changes in water quality will directly affect the molting frequency of shrimp. By monitoring the molting frequency, the suitability of water quality can be indirectly judged. When the water quality is poor, the molting frequency may decrease, reflecting that the growth of shrimp is inhibited. Therefore, the introduction of molting frequency makes More sensitive in water quality adaptability assessment. 、 and It can be set by referring to the materials and combining expert experience.

[0147] It should be noted that the target development index of Penaeus serratus The larger the value, the better the development of the target Penaeus lanceolatus, indicating that the current water quality is suitable for breeding. Therefore, when there are slight differences in water quality requirements, if the target Penaeus lanceolatus development index is Large enough to avoid water quality control.

[0148] The logic for determining whether to adjust the water quality of the new shrimp farming tank is as follows:

[0149] when When the water quality in the aquarium is judged to need to be adjusted;

[0150] when When the water quality in the culture tank does not need to be adjusted, the water quality meets the current development requirements of the Neopenaeus lanceolatus. To adjust the judgment threshold;

[0151] If it is determined that regulation is necessary, the control device in the breeding tank to be regulated that does not meet the water quality requirements of the corresponding development stage is regulated.

[0152] Step 5: If the predicted values ​​of the water quality parameters do not meet the water quality requirements, the control device in the breeding tank to be regulated is regulated. By regulating the control device, adaptive regulation of the water quality is achieved, and the breeding water quality parameters are controlled within the water quality requirements of the target new shrimp at the corresponding developmental stage.

[0153] The regulating of the control device specifically refers to regulating the flow rate of the wave maker, the amount of degradation components in the filter tank, and the water temperature, wherein the goal of the adaptive regulation is to control the aquaculture water quality parameters within the water quality requirements of the corresponding developmental stage of the Neopenaeus lanceolatus;

[0154] The specific formula for regulating the output flow of the wave maker is:

[0155]

[0156] Where, is the flow correction value of the wave maker at the next moment, Real-time traffic for the wave maker.

[0157] It should be noted that the flow correction value of the wave maker at the next moment Correction is made through the control coefficient. When the salinity is too high, the salinity fluctuates greatly, or the dissolved oxygen content is low, the output flow of the wave maker is regulated. When the water level drops below 50, an early warning of low salinity is issued, prompting the user to adjust the salinity. Increasing the output flow of the wave maker can improve the uniformity of salinity and the dissolved oxygen content. When the output flow of the wave maker increases, the speed of the water flow will also increase accordingly, which will lead to a stronger water stirring effect. Strong water flow can accelerate the mixing inside the water body, so that water layers with different salinity and dissolved oxygen content can be mixed quickly, thereby improving the uniformity of salinity and the distribution of dissolved oxygen. Increasing the output flow can also increase the contact area between the water surface and the air. When flowing water comes into contact with air, oxygen dissolves more easily in water. When the flow rate increases, the water surface fluctuations intensify, forming more surface bubbles, thereby enhancing the oxygen dissolution process. Therefore, when the salinity requirements, dissolved oxygen, and salinity uniformity requirements of the water quality do not meet the target water quality requirements, the salinity requirements, dissolved oxygen, and salinity uniformity of the water quality can be changed by regulating the flow of the wave maker. The specific regulation range is determined by the difference with the target water quality requirements, that is, the regulation coefficient. Sure.

[0158] is the control coefficient, which is characterized by the error of water quality parameters, where the control coefficient The calculation is based on the formula:

[0159]

[0160] Where, 、 and are the weight coefficients of salinity difference, dissolved oxygen difference and salinity uniformity difference, respectively, where and 、 and are all greater than 0 and their sum is 1.

[0161] It should be noted that the control coefficient The larger the value, the greater the difference between the current water quality and the target water quality requirements, and the greater the degree of regulation required.

[0162] Salinity is the concentration of dissolved salts in water. Large variations in salinity between different areas may indicate poor mixing of the water, possibly due to stratification or the presence of pollution. Excessive salinity differences can affect the survival of aquatic life, leading to ecological imbalance and reduced survival rates for Penaeus scutellaria. The less suitable the water is for Penaeus scutellaria, the more water quality needs to be regulated.

[0163] Dissolved oxygen (DO), the amount of oxygen in water, is crucial for the survival of aquatic life. Large variations in DO levels within a body of water may indicate a lack of oxygen in certain areas. This is often linked to the decomposition of organic matter, pollution, or eutrophication, which in turn impacts water quality and biodiversity. Lower DO levels make it less suitable for the growth of Penaeus scutellaria, necessitating water quality control. The lower the DO level, the greater the degree of control required to meet the growth needs of Penaeus scutellaria.

[0164] Differences in salinity uniformity reflect the degree of mixing in the water. Uneven salinity distribution in a given area may indicate stratification and poor water flow. This can lead to ecological degradation in certain areas, impacting the habitat and reproduction of Neopenaeus scabra. Therefore, greater differences in salinity, dissolved oxygen, and salinity uniformity indicate a greater control coefficient, indicating the need for greater water quality control.

[0165] It should be noted that the control coefficient is characterized by salinity difference, dissolved oxygen difference and salinity uniformity difference. Among them, salinity is an important environmental factor for the growth of Neopenaeus razorbackii, and has a direct impact on its physiological state and growth rate. Therefore, in the control coefficient, it is reasonable to set the weight of salinity difference to the highest. The appropriate salinity range is essential for the health and growth of shrimp. Exceeding this range may cause physiological stress or death. Dissolved oxygen is a key factor in maintaining the life activities of aquatic organisms and affects the respiration and metabolism of Neopenaeus razorbackii. Although dissolved oxygen is also important, its changes usually have a slightly smaller impact on organisms than salinity and salinity fluctuations, so it is set and 、 and All values ​​are greater than 0 and their sum is 1. Adjusting the predicted value of aquaculture water salinity uniformity using a square root function prevents overcorrection. Directly processing the aquaculture water salinity uniformity using a linear relationship can even lead to equipment overload or damage. Using a square root function can reduce the workload of the equipment.

[0166] The specific formula for regulating the amount of degradation components in the filter tank is:

[0167]

[0168] Where, is the correction value of the amount of degradation components in the filter tank, is the initial value of the amount of degradation components in the filter tank, is the maximum amount of degradation components in the filter tank, The coefficient of influence of the amount of degradation components is: the filter tank adopts a three-dimensional layered form to isolate it from the aquaculture waters. It is determined through expert experience and reference literature, and the general value range is between 0.1 and 0.2.

[0169] It should be noted that The larger the value, the greater the ammonia nitrogen content, and the less suitable it is for the growth and development of Penaeus lanceolatus. The larger the value, the more degradation components are needed to reduce the ammonia nitrogen content to the target water quality requirements. Therefore, the correction value of the degradation component dosage in the filter tank is The amount of degradation components in the filter tank specifically refers to the amount of sodium bicarbonate. Sodium bicarbonate can reduce the ammonia nitrogen content in the water through chemical balance. Therefore, the correction value of the amount of degradation components in the filter tank is The difference in ammonia nitrogen content Proportional, and the content of sodium bicarbonate cannot exceed the amount of degradation components in the filter tank Maximum value.

[0170] The water temperature is regulated by adjusting the operating frequency of the water temperature control device, and the specific formula is:

[0171]

[0172] Where, is the working frequency correction value of the water temperature control device at the next moment, is the real-time operating frequency of the water temperature control device, where is the temperature correction coefficient, where When the water temperature control device acts as a cooler, When the water temperature control device acts as a heater. The temperature correction coefficient It is determined through expert experience and reference literature, and the general value range is between 0.1 and 0.3.

[0173] It should be noted that the greater the difference between the water temperature and the required water temperature, the less suitable the current environment is for the growth and development of the shrimp. Therefore, the operating frequency of the water temperature control device is adjusted according to the difference between the water temperature and the required water temperature. The greater the difference between the water temperature and the required water temperature, the higher the operating frequency of the water temperature control device. The square root function The temperature difference changes relatively smoothly. Assuming that the temperature deviation is small, the square root change is not large, which helps to maintain the stable operation of the control device and avoid excessive reaction to cause the equipment to frequently switch on and off. If the temperature deviation is large, the square root will increase, and the system can react faster, which is necessary for rapid water temperature adjustment.

[0174] Referring to Figure 8 The application also provides a meteorological data-based water body regulation and control system for farming of Neocaridina denticulata, which is used to execute the above-mentioned meteorological data-based water body regulation and control method for farming of Neocaridina denticulata, and comprises:

[0175] A sample data processing module is configured to obtain Neocaridina denticulata samples at different development stages, collect development state parameters of each sample, and establish a mapping relationship between the development state parameters and the development stages and between the development stages and water quality parameter requirements.

[0176] A development stage representation module is configured to randomly collect a plurality of Neocaridina denticulata from a to-be-regulated Neocaridina denticulata farming tank, determine a main development stage based on the development stage distribution, determine target water quality parameter requirements in combination with the mapping relationship, and take Neocaridina denticulata belonging to the main development stage as target Neocaridina denticulata.

[0177] A meteorological influence representation module is configured to obtain past meteorological condition parameters and water quality parameters of the to-be-regulated Neocaridina denticulata farming tank, and train a water quality prediction model based on a long short-term memory network based on the same, and output a future water quality parameter prediction value based on the trained water quality prediction model.

[0178] A dynamic water quality regulation and control judgment module is configured to collect development state parameters of the target Neocaridina denticulata, and judge whether to regulate the water quality of the to-be-regulated Neocaridina denticulata farming tank in combination with the difference between the water quality parameter prediction value and the target water quality parameter requirements.

[0179] A water quality requirement regulation and control module is configured to regulate the control device in the to-be-regulated farming tank if the water quality parameter prediction value does not meet the water quality requirements, to realize self-adaptive regulation of the water quality by regulating the control device, and to control the farming water quality parameters within the water quality requirement range corresponding to the development stage of the target Neocaridina denticulata.

[0180] Referring to Figures 9-11 The farming tank of the Neocaridina denticulata adopts a three-dimensional farming structure, specifically an interleaved and stacked shrimp nest, and each layer is designed at an angle to At the same time, the filter tank adopts a three-dimensional layered form to isolate it from the aquaculture waters. The aquaculture waters of the new-style shrimp include a wave-making device 7, which simulates dynamic feed. The water temperature control device 4 is used to control the water temperature. The inlet valve 8 and the outlet valve 6 are used to control the water volume and change the water. When feeding, the inlet valve 8 and the outlet valve 6 are closed, and a valve for the fixed water level of water change is set to ensure the consistent amount of water change. The filter tank specifically includes three parts: the protein skimmer physical interception area 1, which is used to physically filter the water quality; the second interception module 2, which is used to store the degradation component sodium bicarbonate to achieve chemical balance; after passing through the first two water quality filter modules, it enters the upper water tank 3, which is used to change the water in the aquaculture waters. The emergency oxygen control device 5 is used to start the emergency oxygen control device 5 and apply oxygen urgently when the current water quality dissolved oxygen is lower than 2 times the minimum dissolved oxygen data.

[0181] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0182] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0183] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0184] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for regulating water bodies for Penaeus serrata aquaculture based on meteorological data, characterized in that: The specific steps include: Obtain samples of Neopenaeus edulis at different developmental stages, collect developmental status parameters for each sample, and establish mapping relationships between developmental status parameters and developmental stages, and between developmental stages and water quality parameter requirements; Randomly collect multiple Penaeus scutellaria from the culture tank of the target Penaeus scutellaria var. juncea. Determine the primary developmental stage based on the distribution of developmental stages. Combined with the mapping relationship, determine the target water quality parameter requirements. Select the Penaeus scutellaria var. juncea that belong to the primary developmental stage as the target Penaeus scutellaria var. Obtain the past meteorological condition parameters and water quality parameters of the new shrimp culture tank to be regulated, and use them to train a water quality prediction model built based on the long short-term memory network. Based on the trained water quality prediction model, the predicted values ​​of future water quality parameters are output; Collect the developmental status parameters of the target Penaeus lanceolatus shrimp and, based on the difference between the predicted water quality parameters and the target water quality parameters, determine whether to adjust the water quality of the Penaeus lanceolatus shrimp culture tank to be regulated; If the predicted values ​​of the water quality parameters do not meet the water quality requirements, the control device in the breeding tank to be regulated is regulated, and the adaptive regulation of the water quality is achieved by regulating the control device, so that the breeding water quality parameters are controlled within the water quality requirements of the corresponding development stage of the target Penaeus lanceolatus shrimp; Determining the developmental stages of different Penaeus lanceolatus samples and the water quality parameter requirements for the corresponding developmental stages, wherein the developmental stages of the Penaeus lanceolatus samples include embryonic stage, larval stage, postlarval stage and adult stage; The water quality parameter requirements during the development stage specifically refer to salinity and uniformity requirements, water temperature requirements, dissolved oxygen requirements, and ammonia nitrogen content requirements; The developmental status parameters of the Penaeus scutellariae sample include the body length, weight and hormone expression levels of the Penaeus scutellariae, wherein the hormone expression levels specifically refer to the levels of animal hyperglycemic hormone and molting-inhibiting hormone of the Penaeus scutellariae; Map the data between the development state parameters and the development stages, and between the development stages and the water quality parameter requirements one by one to form a corresponding grid, and record the formed grid as a sample data set; The logic for determining the main developmental stage is as follows: randomly collect multiple Penaeus razorback shrimp from the breeding tank of the Penaeus razorback shrimp to be regulated as test samples, determine the developmental stage of each test sample by measuring the developmental status parameters of the test samples, screen out the developmental stage with the largest number of test samples and take it as the main developmental stage, and take the test samples belonging to the main developmental stage as the target Penaeus razorback shrimp.

2. The method for regulating water bodies for breeding Penaeus lanceolatus shrimp based on meteorological data according to claim 1, characterized in that: A neural network model is established based on the data in the training data set, wherein the training data set specifically refers to: the previous meteorological condition parameters and water quality parameters of the new shrimp culture tank to be regulated, and the timestamps of the corresponding meteorological condition parameters and water quality parameters are recorded, and the meteorological condition parameters and water quality parameter data with aligned timestamps are mapped one by one to form a training data set; wherein the neural network model is established based on the long short-term memory network model, wherein the long short-term memory network model is an LSTM model, and an activation function and an optimization algorithm are selected, wherein the Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is: ； Where, Represents the Tanh function, independent variable Represents the weighted sum of the neuron's input, that is, the result of weighted summation of the input received by the neuron from the previous layer; At the same time, the hyperparameters of the LSTM model are set, including the number of network layers, number of iterations, learning rate, batch size, number of training times, batch size, and number of hidden layer neurons; The number of network layers is set to 3 layers, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32; The meteorological condition parameters and water quality parameters corresponding to the first n-1 timestamps in the training data set are used as the input of the model, and the water quality parameters corresponding to the nth timestamp are used as labels to train the neural network model; where n is a positive integer; The meteorological condition parameters and water quality parameters corresponding to the current moment and the previous n-2 moments are input into the trained neural network model to obtain the parameter prediction value of the aquaculture water quality at the next moment.

3. The method for regulating water bodies for breeding Penaeus lanceolatus shrimp based on meteorological data according to claim 2, characterized in that: Determine whether the predicted water quality parameter values ​​and target water quality parameter requirements meet the following constraints. If so, do not adjust the water quality. If not, re-determine based on the developmental status parameters of the target Penaeus lanceolatus. ； Where, is the predicted value of water salinity, is the predicted value of water salinity uniformity, is the predicted value of water quality and temperature, is the predicted value of dissolved oxygen in water quality, is the predicted value of ammonia nitrogen content in water quality, and are the minimum and maximum salinity requirements in the target water quality parameter requirements, and are the minimum and maximum values ​​of water temperature requirements in the target water quality parameter requirements, and are the minimum and maximum values ​​of dissolved oxygen in the target water quality parameter requirements, The maximum value of ammonia nitrogen content required in the target water quality parameter requirements; If the water quality constraint conditions are not met, the minimum difference between the predicted water quality parameter and the target water quality requirement is calculated. The formula for calculating the minimum salinity difference is: ； Where, is the minimum difference in salinity; The minimum difference between the predicted water quality parameters and the target water quality requirements was analyzed, and the adjustment judgment coefficient was calculated based on the target developmental state parameters of the new white shrimp. The adjustment judgment coefficient was calculated based on the formula: ； Where, To adjust the judgment coefficient, is the development index of target Penaeus scabra, is the minimum difference in salinity uniformity; is the minimum difference in water temperature, is the minimum difference in dissolved oxygen, is the minimum difference in ammonia nitrogen content; The target shrimp development index The specific formula for the calculation is: ； Where, is the maximum body length corresponding to the main developmental stages, is the maximum weight corresponding to the main developmental stages, is the highest molting frequency corresponding to the main developmental stages, is the average body length of the target Penaeus scabra, is the average weight of target Penaeus scabra shrimp, is the average molting frequency of the target Neopenaeus scutellaria; The logic for determining whether to adjust the water quality of the new shrimp farming tank is as follows: when When the water quality in the aquarium is judged to need to be adjusted; when When the water quality in the culture tank does not need to be adjusted, the water quality meets the current development requirements of the Neopenaeus lanceolatus. To adjust the judgment threshold; If it is determined that regulation is necessary, the control device in the breeding tank to be regulated that does not meet the water quality requirements of the corresponding development stage is regulated.

4. The method for regulating water bodies for Penaeus serrata aquaculture based on meteorological data according to claim 3, characterized in that: The regulating of the control device specifically refers to regulating the flow rate of the wave maker, the amount of degradation components in the filter tank, and the water temperature, wherein the goal of the adaptive regulation is to control the aquaculture water quality parameters within the water quality requirements of the corresponding developmental stage of the Neopenaeus lanceolatus; The specific formula for regulating the output flow of the wave maker is: ； Where, is the flow correction value of the wave maker at the next moment, For the real-time flow of the wave maker, is the control coefficient, which is characterized by the error of water quality parameters, where the control coefficient The calculation is based on the formula: ； Where, 、 and are the weight coefficients of salinity difference, dissolved oxygen difference and salinity uniformity difference, respectively, where and 、 and are all greater than 0 and their sum is 1.

5. The method for regulating water bodies for breeding Penaeus lanceolatus shrimp based on meteorological data according to claim 4, characterized in that: The specific formula for regulating the amount of degradation components in the filter tank is: ； Where, is the correction value of the amount of degradation components in the filter tank, is the initial value of the amount of degradation components in the filter tank, is the maximum amount of degradation components in the filter tank, is the coefficient of influence of the amount of degradation components; the filter tank adopts a three-dimensional layered form to isolate it from the aquaculture waters; The water temperature is regulated by adjusting the operating frequency of the water temperature control device, and the specific formula is: ； Where, is the working frequency correction value of the water temperature control device at the next moment, is the real-time operating frequency of the water temperature control device, where is the temperature correction coefficient, where When the water temperature control device acts as a cooler, When the water temperature control device is used as a heater.

6. A water control system for Penaeus serrata aquaculture based on meteorological data, characterized by: The meteorological data-based water body control system for Penaeus serratus shrimp aquaculture is used to execute the meteorological data-based water body control method for Penaeus serratus shrimp aquaculture according to any one of claims 1 to 5, comprising: The sample data processing module is used to obtain samples of Neopenaeus edulis at different developmental stages, collect developmental status parameters of each sample, and establish mapping relationships between developmental status parameters and developmental stages, and between developmental stages and water quality parameter requirements; The developmental stage characterization module is used to randomly collect multiple Penaeus scutellaria from the culture tank of the target Penaeus scutellaria var. ... The meteorological impact characterization module is used to obtain the past meteorological condition parameters and water quality parameters of the new shrimp culture tanks to be regulated, and use them to train the water quality prediction model built based on the long short-term memory network. The trained water quality prediction model outputs the predicted values ​​of future water quality parameters based on the completed water quality prediction model; The dynamic water quality control judgment module is used to collect the developmental status parameters of the target Penaeus scutellaria var. scutellariae and, based on the difference between the predicted water quality parameters and the target water quality parameters, determine whether to adjust the water quality of the Penaeus scutellariae var. scutellariae breeding tank; The water quality requirement control module is used to control the control device in the breeding tank to be regulated if the predicted value of the water quality parameter does not meet the water quality requirements. By adjusting the control device, adaptive control of water quality is achieved, and the breeding water quality parameters are controlled within the water quality requirements range of the target new shrimp at the corresponding development stage.

Images