A method for regulating aquaculture environment to promote rapid maturation of gonads of Lateolabrax japonicus

Abstract

The present invention provides a method for regulating and controlling an aquaculture environment for promoting rapid maturation of gonads of striped seabass, and relates to the technical field of aquaculture environment regulation of striped seabass. The specific steps include: conducting aquaculture experiments of striped seabass respectively under different aquaculture environment parameter combinations, constructing a prediction model for the development of striped seabass, obtaining growth state parameters and gonad development parameters of striped seabass, constructing a functional relationship between body length, body height, body weight and growth trait coefficients, constructing a functional relationship between gonad weight, gonad index and gonad development coefficient, generating a gonad maturation coefficient, using a genetic algorithm, iteratively optimizing the gonad maturation coefficient, screening out individuals corresponding to stage IV of gonad development, and using the individuals corresponding to the maximum value of the gonad maturation coefficient as the optimal aquaculture environment parameter combination. The present invention finds out the best aquaculture environment parameter combination through iterative optimization of a genetic algorithm to achieve the goal of promoting rapid maturation of gonads of striped seabass, thereby improving the efficiency and benefit of aquaculture.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental regulation for Japanese seabass farming, and specifically provides a method for regulating the farming environment to promote the rapid gonadal maturation of Japanese seabass. Background Art

[0002] Japanese seabass is an important economic fish widely distributed in tropical and subtropical waters. Due to its delicious meat and rich nutrition, the market demand is continuously increasing. Therefore, studying its growth and reproduction characteristics is of great significance for improving farming efficiency and meeting market demand. In recent years, with the progress of aquaculture technology, many environmental regulation technologies have been introduced into Japanese seabass farming, including automated water quality monitoring and regulation equipment, intelligent feed feeding systems, and lighting control systems. The application of these technologies enables farmers to more precisely regulate the farming environment, providing good conditions for the rapid gonadal maturation of Japanese seabass.

[0003] In the prior art, a method for reproductive regulation and breeding of Japanese seabass with the publication number CN105494210B includes the following steps: light regulation, temperature regulation, salinity regulation, and nutrition regulation. When hatching fertilized eggs, a special hatching device is used to regulate southern parent fish by gradually extending the light time, stimulating temperature changes, stimulating salinity changes, etc., to promote the gonadal development of southern parent fish, advancing the sexual maturity time of southern parent fish from November to January to October to December. At the same time, reduce the light and cultivate at low temperature for northern parent fish to delay the gonadal development of parent fish, delaying the sexual maturity time of northern parent fish from September to November to October to December, so that the gonadal development of southern parent fish and northern parent fish is synchronized, and ovulation and sperm production are synchronized.

[0004] However, there are still the following deficiencies. From the above statements, although the prior art regulates light, temperature, salinity, and nutrition, it often considers the influence of a single factor alone and does not comprehensively consider the combined effects of salinity, temperature, light cycle, and nutrient content, resulting in an insufficient comprehensive evaluation of the influence on the gonadal development of Japanese seabass and poor setting of environmental parameters for promoting the rapid gonadal maturation of Japanese seabass, leading to long reproductive cycles and breeding cycles and difficult to achieve the best farming benefits.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and therefore it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for regulating the farming environment to promote the rapid gonadal maturation of Japanese seabass, so as to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A method for regulating the aquaculture environment to promote the rapid gonadal maturation of Japanese seabass, the specific steps include:

[0009] S1. Under different combinations of aquaculture environment parameters, conduct Japanese seabass aquaculture experiments respectively. The aquaculture experiments last for a total of T time periods, and Japanese seabass with gonadal development stage I are used for the aquaculture experiments. After the experiments end, obtain the growth trait parameters and gonadal development parameters of Japanese seabass. The growth trait parameters of Japanese seabass include body length, body height and body weight, and the gonadal development parameters include gonad weight and gonadosomatic index. The aquaculture environment parameters include salinity, temperature, photoperiod and nutrient content. The gonadal development stage is determined based on the gonad weight.

[0010] S2. Construct a Japanese seabass development prediction model, use different combinations of aquaculture environment parameters as inputs, and growth trait parameters and gonadal development parameters as labels to train the model, and train the Japanese seabass development prediction model.

[0011] S3. Establish constraints for aquaculture environment parameters, randomly combine the aquaculture environment parameters, construct individuals of the initial population of aquaculture environment parameters, input the individuals of the initial population of aquaculture environment parameters into the Japanese seabass development prediction model, and obtain growth trait parameters and gonadal development parameters.

[0012] S4. Construct functional relationships between body length, body height, body weight and growth trait coefficients, construct functional relationships between gonad weight, gonadosomatic index and gonadal development coefficients, construct functional relationships between growth trait coefficients, gonadal development coefficients and gonadal maturity coefficients. The gonadal maturity coefficient is used to comprehensively evaluate the gonadal maturity degree of Japanese seabass. Using the genetic algorithm, select, cross and mutate the gonadal maturity coefficient until after reaching the predetermined number of iterations, screen out the individuals corresponding to the gonadal development stage reaching stage IV, and use the individual corresponding to the maximum gonadal maturity coefficient among them as the optimal combination of aquaculture environment parameters.

[0013] Furthermore, randomly combine the aquaculture environment parameters to construct individuals of the initial population of aquaculture environment parameters. The specific process is as follows:

[0014] Set the duration of the T time period to 6 months, and label the initial population as , and the initial population , is the th individual in the initial population, is the index of the individual in the initial population, and , is the number of individuals in the initial population, , where are respectively the salinity, temperature, photoperiod and nutrient content of the th individual.

[0015] Furthermore, the Japanese sea bass development prediction model is composed of a deep learning network based on a multi-layer perceptron. The deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and all use ReLU as the activation function;

[0016] The process of training the Japanese sea bass development prediction model is as follows:

[0017] Using different combinations of aquaculture environment parameters as input quantities, and growth state parameters and gonadal development parameters as output labels for training, using the mean square error as the loss function. When the mean square error is within the range, the training of the Japanese sea bass development prediction model is completed.

[0018] Furthermore, a functional relationship between body length, body height, body weight, and growth trait coefficient is constructed, and the formula is as follows:

[0019]

[0020] Among them, is the growth trait coefficient of the th individual, is the body length of the th individual, is the body height of the th individual, is the body weight of the th individual, is the weight coefficient of the combined parameter of body length and body height of the th individual, is the weight coefficient of the body weight of the th individual, , .

[0021] Furthermore, a functional relationship between gonad weight, gonadosomatic index, and gonadal development coefficient is constructed, and the formula is as follows:

[0022]

[0023]

[0024] Among them, is the gonadal development coefficient of the th individual, is the gonad weight of the th individual, is the gonadosomatic index of the th individual, is the The weight of an individual.

[0025] Furthermore, a functional relationship of the growth trait coefficient, gonadal development coefficient, and gonadal maturity coefficient is constructed, and the basis formula is as follows:

[0026]

[0027] Among them, is the gonadal maturity coefficient of the th individual, is the weight coefficient of the growth trait coefficient of the th individual, is the weight coefficient of the gonadal development coefficient of the th individual, and , The specific values of are determined by the analytic hierarchy process.

[0028] Furthermore, the genetic algorithm is used to select, cross, and mutate the gonadal maturity coefficient. After reaching the predetermined number of iterations, the optimal aquaculture environment parameter combination is determined. The specific process is as follows:

[0029] Iteratively optimize the individuals in the initial population of aquaculture environment parameters. During the iterative optimization process, the constraint conditions of the aquaculture environment parameters need to be set, that is, the maximum and minimum values of salinity, temperature, light cycle, and nutrient content are set respectively. Within the constraint range of salinity, temperature, light cycle, and nutrient content, the aquaculture environment parameters are iteratively optimized. Specifically, the gonadal maturity coefficient is sorted from large to small, and the individuals with the gonadal maturity coefficient in the front row are selected as the parental generation. Through the operations of crossing and mutation, the genes of the parental generation individuals are exchanged, combined, and mutated to generate new individuals. The growth trait parameters and gonadal development parameters of the newly generated individuals are obtained by using the Japanese seabass development prediction model, and their gonadal maturity coefficients are calculated. The new individuals and the parental generation are used as a new population, and the operations of selection, crossing, and mutation are repeated. After reaching the predetermined number of iterations, the individuals corresponding to the gonadal development stage reaching stage IV are screened out, and the individual corresponding to the maximum gonadal maturity coefficient among them is used as the optimal aquaculture environment parameter combination. The individual corresponding to the maximum gonadal maturity coefficient is labeled as , then the optimal aquaculture environment parameter combination is salinity , temperature , light cycle and nutrient content .

[0030] Compared with the prior art, the beneficial effects of the present invention are:

[0031] The present invention conducts sea bass farming experiments under different combinations of aquaculture environmental parameters, constructs a sea bass development prediction model, uses different combinations of aquaculture environmental parameters as inputs, outputs the growth trait parameters and gonadal development parameters of sea bass, constructs a functional relationship between body length, body height, body weight and growth trait coefficient, constructs a functional relationship between gonad weight, gonadosomatic index and gonadal development coefficient, generates a gonadal maturity coefficient for comprehensively evaluating the gonadal maturity degree of sea bass, and uses a genetic algorithm to select, cross, and mutate the gonadal maturity coefficient until after reaching a predetermined number of iterations, screening out the individuals corresponding to the gonadal development reaching stage IV, and taking the individual corresponding to the maximum value of the gonadal maturity coefficient as the optimal aquaculture environmental parameter combination. The gonadal maturity coefficient provides a clear evaluation criterion for aquaculture managers, and the best aquaculture environmental parameter combination is found through the iterative optimization of the genetic algorithm, so as to achieve the purpose of promoting the rapid gonadal maturity of sea bass, shortening the reproductive cycle and breeding cycle, and improving the efficiency and benefits of aquaculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0034] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not represent any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0035] Example 1:

[0036] Please refer to Figure 1 , the present invention provides a technical solution:

[0037] A method for regulating aquaculture environment to promote the rapid gonadal maturity of sea bass, the specific steps include:

[0038] S1. Conduct sea bass farming experiments under different combinations of farming environment parameters. The farming experiments last for a total of T time periods. Sea bass at gonadal development stage I are used for the farming experiments. After the experiments end, several sea bass are randomly captured, homogenized, and the growth trait parameters and gonadal development parameters of the sea bass are obtained. The sea bass growth trait parameters include body length, body height, and body weight, and the gonadal development parameters include gonad weight and gonad index. The farming environment parameters include salinity, temperature, light cycle, and nutrient content. The gonadal development stage is determined based on the gonad weight.

[0039] S2. Construct a sea bass development prediction model. Use different combinations of farming environment parameters as inputs and growth trait parameters and gonadal development parameters as labels to train the model and train the sea bass development prediction model.

[0040] S3. Establish constraint conditions for farming environment parameters. Randomly combine the farming environment parameters to construct individuals in the initial population of farming environment parameters. Input the individuals in the initial population of farming environment parameters into the sea bass development prediction model to obtain growth trait parameters and gonadal development parameters.

[0041] S4. Construct functional relationships between body length, body height, body weight, and growth trait coefficients, between gonad weight, gonad index, and gonadal development coefficients, and between growth trait coefficients, gonadal development coefficients, and gonadal maturity coefficients. The gonadal maturity coefficient is used to comprehensively evaluate the gonadal maturity degree of sea bass. Use the genetic algorithm to select, cross, and mutate the gonadal maturity coefficient until the predetermined number of iterations is reached, then screen out the individuals corresponding to the gonadal development stage reaching stage IV, and use the individual corresponding to the maximum gonadal maturity coefficient as the optimal combination of farming environment parameters.

[0042] Based on the above embodiments, randomly combine the farming environment parameters to construct individuals in the initial population of farming environment parameters. The specific process is as follows:

[0043] Set the duration of T time periods to 6 months, and label the initial population as , and the initial population , is the th individual in the initial population, is the index of the individual in the initial population, and , is the number of individuals in the initial population, , where are the salinity, temperature, light cycle, and nutrient content of the th individual, respectively.

[0044] Based on the above embodiments, the Japanese seabass development prediction model is composed of a deep learning network based on a multi-layer perceptron. The deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and all use ReLU as the activation function;

[0045] In this embodiment, the input features of the deep learning network of the multi-layer perceptron include: salinity, temperature, light cycle, and nutrient content, a total of 4 features.

[0046] The structure of the deep learning network of the multi-layer perceptron is as follows:

[0047] Input layer: Receives the input of 4 features;

[0048] First hidden layer: Has 64 neurons and uses ReLU as the activation function;

[0049] Second hidden layer: Has 32 neurons and also uses the ReLU activation function;

[0050] Third hidden layer: Has 16 neurons and uses the ReLU activation function;

[0051] Output layer: Has 2 neurons, the growth trait parameters and the gonad development parameters.

[0052] The process of training the Japanese seabass development prediction model is as follows:

[0053] Using different combinations of aquaculture environment parameters as the input, and the growth trait parameters and the gonad development parameters as the output labels for training, using the mean squared error as the loss function. When the mean squared error is within the specified range, the training of the Japanese seabass development prediction model is completed.

[0054] Based on the above embodiments, the correlations between the body length, body height, body weight of the Japanese seabass and the excellent growth degree of the Japanese seabass are as follows:

[0055] The body length of the Japanese seabass is positively correlated with the excellent growth degree of the Japanese seabass. Because an increase in body length usually means a fast growth rate, which reflects that the Japanese seabass can effectively absorb nutrients in the aquaculture environment. Good nutrient intake can not only promote the growth of body length but also contribute to improving the overall excellent growth degree.

[0056] The body height of the Japanese seabass is positively correlated with the excellent growth degree of the Japanese seabass. Because an increase in body height usually means an increase in the volume of the Japanese seabass. Larger Japanese seabass are beneficial for better storing energy and nutrients, thus improving the excellent growth degree.

[0057] The weight of Japanese seabass is positively correlated with the excellent growth degree of Japanese seabass. Since the increase in weight usually reflects the growth rate of Japanese seabass, a Japanese seabass with a larger weight generally indicates that it has accumulated more biomass within a specific period, which shows that its growth state is good and the excellent growth degree has improved.

[0058] According to the correlations between the body length, body height, weight of Japanese seabass and the excellent growth degree of Japanese seabass, a functional relationship between the body length, body height, weight and the growth trait coefficient is constructed, and the formula is as follows:

[0059]

[0060] Among them, is the growth trait coefficient of the th individual, is the body length of the th individual, is the body height of the th individual, is the weight of the th individual, is the weight coefficient of the combined parameter of the body length and body height of the th individual, is the weight coefficient of the weight of the th individual;

[0061] The growth trait coefficient of the th individual has a value range of ;

[0062] When is close to , it indicates that the growth performance of the individual is poor, suggesting that the breeding environment of the individual is not suitable;

[0063] When is close to , it indicates that the growth performance of the individual is excellent, suggesting that the breeding environment of the individual is suitable;

[0064] Therefore, the larger the growth trait coefficient , the better the growth of the individual.

[0065] The reasons for adopting the above functional form to express the functional relationship between the body length, body height, weight of Japanese seabass and the growth trait coefficient are as follows:

[0066] First, since the functional relationship between the body length , body height , weight of Japanese seabass and the growth trait coefficient is not linear, that is, as the body length , body height or weight With the increase of , the change of the growth trait coefficient does not occur at a fixed rate, so an exponential function with a non-linear relationship is used to express it.

[0067] Second, body length and body height The product of reflects the interaction between these two parameters. The growth of Japanese seabass is not the result of a single parameter, but the combined action of multiple parameters. By multiplying, the combination of body length and body height can more effectively characterize how they jointly affect the growth traits of Japanese seabass.

[0068] Third, body weight is related to energy intake and consumption. A larger body weight requires more energy to maintain physiological processes and growth. Therefore, the product of body weight and body length and body height can emphasize the important role of body weight during the growth process. By multiplication, combining body weight with body length and body height makes the growth trait coefficient more comprehensively reflect the growth potential of an individual.

[0069] Fourth, weight coefficient is a scalar used to adjust the contribution degree of the product of body length and body height to the growth trait coefficient . Multiplying by serves to adjust the overall contribution of body length and body height in the growth traits. By introducing , the relative importance of body length and body height to growth performance can be flexibly adjusted according to the needs of different individuals or different environments;

[0070] There are significant differences in body weight among different Japanese seabass individuals. Some individuals show outstanding growth in body length and body height , but the body weight increases slowly. In this case, by an appropriate value, the influence of body weight in the growth traits can be enhanced to more comprehensively reflect the growth characteristics of Japanese seabass individuals.

[0071] The weight coefficient of the combined parameters of body length and body height of an individual and the weight coefficient of an individual's body weight The size relationship is set as follows:

[0072] First, since the body length and body height of Japanese seabass are considered key factors determining growth potential, their product can reflect the space occupancy and growth ability of Japanese seabass individuals. A larger body length and body height mean that the individual has certain advantages in resource competition. Therefore, these two indicators play a dominant role in growth performance. The combined effect of body length and body height will significantly affect the growth performance of the individual;

[0073] Second, the growth priority of Japanese seabass individuals tends to be towards the increase of body length and body height , especially in the initial growth stage, because individuals need to enhance their survival competitiveness and adaptability by increasing body length and body height during their juvenile period.

[0074] In the above situation, the product of body length and body height has a relatively large correlation with the growth trait coefficient , and body weight has a relatively small correlation with the growth trait coefficient . Therefore, is set to be larger, is set to be smaller, that is, on the basis of , set .

[0075] As an implementation method, ranges from 0.5 - 0.6, ranges from 0.3 - 0.45. The specific values are set by technicians according to the actual situation and are not limited here.

[0076] On the basis of the above embodiments, the correlations between the gonad weight, gonadosomatic index and excellent gonad development degree of Japanese seabass are as follows:

[0077] The gonad weight of Japanese seabass is positively correlated with the excellent gonad development degree. Because the gonad is the main organ that produces germ cells (sperm or eggs), the increase in gonad weight corresponds to the increase in the number of mature germ cells. And the increase in the number of mature germ cells means that more mature germ cells can improve the individual's reproductive potential, ensure more eggs or sperm available for mating and fertilization, and the physiological function is more active, which can effectively respond to environmental and endocrine stimuli and promote reproductive behavior.

[0078] The gonadosomatic index of Japanese sea bass is positively correlated with the excellent degree of gonadal development. Since the gonadosomatic index is the ratio of gonad weight to body weight and can effectively reflect the reproductive ability of an individual, an increase in the gonadosomatic index means that the individual can produce more mature germ cells (such as sperm or eggs), which not only enhances the reproductive ability of the individual but also increases the success rate of reproduction. With the good development of the gonads, the reproductive ability is further enhanced, thus forming a positive feedback loop, making the gonadal development better and better.

[0079] According to the correlation between the gonad weight, gonadosomatic index and excellent degree of gonadal development of Japanese sea bass, a functional relationship between the gonad weight, gonadosomatic index and gonadal development coefficient is constructed, and the formula is as follows:

[0080]

[0081]

[0082] Among them, is the gonadal development coefficient of the th individual, is the gonad weight of the th individual, is the gonadosomatic index of the th individual, is the body weight of the th individual;

[0083] The th individual's gonadal development coefficient ranges from ;

[0084] When is close to , it indicates that the gonadal development of the individual is poor, meaning that the reproductive ability of the individual is poor;

[0085] When is close to , it indicates that the gonadal development of the individual is good, meaning that the reproductive ability of the individual is strong and can show a good reproductive state during the breeding season.

[0086] Therefore, the larger the gonadal development coefficient , the better the gonadal development of the individual.

[0087] The reasons for adopting the above functional form to express the functional relationship between the gonad weight, gonadosomatic index and gonadal development coefficient of Japanese sea bass are as follows:

[0088] First, the gonad weight The increase is related to the change in hormone levels. During the development of the gonads (such as testes or ovaries), more sex hormones (such as testosterone, estrogen) are secreted, and these hormones have important effects on the development, maturation, and function of the reproductive system. The increase in hormone levels further promotes reproductive ability, resulting in a relatively rapid increase in the gonad development coefficient. In addition, the development of the gonads undergoes several important stages. During the critical period of gonad development, the gonad weight increases, triggering a series of physiological changes. These changes are the result of cumulative effects, leading to an exponential growth in the gonad development coefficient. Therefore, an exponential function is used to express the functional relationship between the gonad weight and the gonad development coefficient.

[0089] Second, the gonad index is the ratio of the gonad weight to the individual body weight . This ratio can eliminate the influence of body weight on the performance of gonad development, making the comparison between individuals with different body weights more reasonable. A higher gonad index means that the gonad development of the individual is better relative to the body weight . By introducing the ratio of the gonad weight to the individual body weight into the formula, the gonad index realizes the correction of the individual growth state. When the individual body weight increases, the gonad development coefficient will only increase significantly when the gonad weight increases faster.

[0090] Third, the gonad development coefficient is a comprehensive index that combines the gonad weight and the gonad index . These two factors together reflect the gonad development state of the individual and can be used to evaluate the reproductive ability and health level of the organism. The function in this formula ensures that even when the gonad index and gonad weight are extremely large, the output value will not exceed 1, preventing the results from losing comparability and interpretability due to extreme values.

[0091] Based on the above embodiments, the growth trait coefficient and the gonad development coefficient are processed to generate a gonad maturity coefficient for comprehensively evaluating the gonad maturity degree of Japanese seabass. The formula is as follows:

[0092]

[0093] Among them, is the gonad maturity coefficient of the th individual. The gonad maturity coefficient of the individual is used to combine the growth trait coefficient of the individual and gonad development coefficient , to comprehensively evaluate the gonad maturity degree of Japanese seabass, and the gonad maturity coefficient The larger it is, the higher the gonad maturity degree of Japanese seabass, and the more conducive to reproduction;

[0094] It should be noted that from the above description, the growth trait coefficient of an individual The larger it is, the better the growth. The gonad development coefficient of an individual The larger it is, the better the gonad development. Therefore, the gonad maturity coefficient is positively correlated with the growth trait coefficient and the gonad development coefficient Both are positively correlated. Therefore, the above-mentioned gonad maturity coefficient in the form of weighted summation is set Calculation formula;

[0095] In the formula, is the weight coefficient of the growth trait coefficient of the th individual, is the weight coefficient of the gonad development coefficient of the th individual, and , The specific values of are determined by the analytic hierarchy process. The specific logic is as follows:

[0096] Mark the two indexes of the growth trait coefficient and the gonad development coefficient of the individual, and determine the relative importance values between them through the nine-scale method to construct a judgment matrix. Among them, mark the index of the growth trait coefficient as 1 and the index of the gonad development coefficient as 2. The constructed judgment matrix is:

[0097]

[0098] Among them, , Both represent the indexes of the coefficients, and , , indicating that the coefficient with the index of is more important for the gonad maturity coefficient than the coefficient with the index of v, The specific value of is determined by relevant experts using the 1-9 scoring method, indicating that the coefficient with the index of is extremely important for the gonad maturity coefficient compared with the coefficient with the index of v, indicating that the coefficient with the index of is extremely unimportant for the gonad maturity coefficient compared with the coefficient with the index of v;

[0099] Divide each element value in the judgment matrix by the sum of its column to obtain a normalized judgment matrix. Calculate the mean value of each row element value in the normalized judgment matrix, and take the mean value of the first row element value as the weight coefficient of the growth trait coefficient of the individual, and take the mean value of the second row element value as the weight coefficient of the gonad development coefficient of the individual. With the constraint that the sum of the scaled values equals 1, scale the two weight coefficients proportionally, and take the scaled values as the weights of the corresponding coefficients.

[0100] Based on the above embodiments, use the genetic algorithm to select, cross, and mutate the gonad maturity coefficient until the predetermined number of iterations is reached, and then determine the optimal combination of aquaculture environment parameters. The specific process is as follows:

[0101] Iteratively optimize the individuals in the initial population of aquaculture environment parameters. During the iterative optimization process, set the constraint conditions of the aquaculture environment parameters, that is, set the maximum and minimum values of salinity, temperature, light cycle, and nutrient content respectively. Within the constraint range of salinity, temperature, light cycle, and nutrient content, iteratively optimize the aquaculture environment parameters. Specifically, sort the gonad maturity coefficients from large to small, and select the individuals with gonad maturity coefficients in the front row as the parental generation. The front row refers to the individuals in the first 50% of the gonad maturity coefficients. Through the cross and mutation operations, exchange and combine and mutate the genes of the parental generation individuals to generate new individuals. Use the Japanese seabass development prediction model to obtain the growth trait parameters and gonad development parameters of the newly generated individuals, and calculate their gonad maturity coefficients. Take the new individuals and the parental generation as the new population, and repeat the selection, cross, and mutation operations until the predetermined number of iterations is reached. Since the gonad development degree of Japanese seabass is divided into four development stages: stage I, stage II, stage III, and stage IV, when the gonad development degree reaches stage IV, the gonad weight of males is 5 - 15 grams, and the gonad weight of females is 7 - 20 grams. From stage I to stage IV, as the gonad develops, the gonad weight gradually increases. Screen out the individuals whose gonad weight reaches the stage IV standard, and take the individual corresponding to the maximum gonad maturity coefficient as the optimal combination of aquaculture environment parameters. Mark the individual corresponding to the maximum gonad maturity coefficient as . Then the optimal combination of aquaculture environment parameters is salinity , temperature , light cycle , and nutrient content . .

[0102] The above formulas are all calculated by taking the numerical values without considering the dimension. The formulas are obtained by collecting a large amount of data and performing software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0103] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any 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 realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] As described above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A method for regulating the aquaculture environment for promoting rapid maturation of the gonads of Lateolabrax japonicus, characterized in that: The specific steps include: S1. Under different combinations of aquaculture environment parameters, a culture experiment of striped seabass was conducted, the culture experiment lasted for a total of T time period, and the striped seabass with gonad development degree at stage I was used for the culture experiment, and the growth trait parameters and gonad development parameters of the striped seabass were obtained after the experiment. The growth trait parameters of the striped seabass included body length, body height and body weight, the gonad development parameters included gonad weight and gonad index, the culture environment parameters included salinity, temperature, photoperiod and nutrient content, and the gonad development degree was determined based on the gonad weight; S2, constructing a development prediction model for japonica seabass, taking different combinations of culture environment parameters as input, and growth trait parameters and gonad development parameters as label training models, and training the development prediction model for japonica seabass; S3. Establishing constraints on aquaculture environment parameters, randomly combining aquaculture environment parameters, constructing individuals of an initial population of aquaculture environment parameters, inputting individuals of the initial population of aquaculture environment parameters into a development prediction model for sea bass, and obtaining growth trait parameters and gonad development parameters; S4. Construct the functional relationship between body length, height, body weight and growth trait coefficient, construct the functional relationship between gonad weight, gonad index and gonad development coefficient, construct the functional relationship between growth trait coefficient, gonad development coefficient and gonad maturity coefficient. The gonad maturity coefficient is used to comprehensively evaluate the degree of gonad maturity of Lateolabrax japonicus. A genetic algorithm is used to select, crossover and mutate the gonad maturity coefficient until the predetermined number of iterations is reached. The individuals corresponding to the gonad development level reaching stage IV are screened out, and the individuals corresponding to the maximum value of the gonad maturity coefficient are used as the optimal breeding environment parameter combination.

2. The method for regulating the aquaculture environment for promoting rapid gonadal maturation of Lateolabrax japonicus according to claim 1, characterized in that: The aquaculture environment parameters are randomly combined to construct individuals of the initial population of aquaculture environment parameters. The specific process is as follows: Set the duration of time period T to 6 months and mark the initial population as , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively salinity, temperature, photoperiod and nutrient content of each individual.

3. The method for regulating the aquaculture environment for promoting rapid maturation of the gonads of Lateolabrax japonicus according to claim 2, characterized in that: The development prediction model of the striped sea bass is composed of a deep learning network based on a multi-layer perceptron, wherein the deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, wherein the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function; The process of training the Lateolabrax development prediction model is as follows: Different combinations of breeding environment parameters are used as input, growth trait parameters and gonad development parameters are used as output labels for training, and mean square error is used as the loss function. When the range is within the range, the training of the development prediction model of striped seabass is completed.

4. The method for regulating the aquaculture environment for promoting rapid maturation of the gonads of Lateolabrax japonicus according to claim 3, characterized in that: The functional relationship between body length, body height, body weight and growth trait coefficients is constructed as follows: in, For the The growth trait coefficient of each individual, For the The body length of each individual, For the The height of each individual, For the The weight of an individual, For the The weight coefficient of the combined parameters of body length and height of each individual, For the The weight coefficient of each individual's weight, , .

5. The method for regulating the aquaculture environment for promoting rapid maturation of the gonads of Lateolabrax japonicus according to claim 4, characterized in that: The functional relationship between gonad weight, gonad index and gonad development coefficient was constructed as follows: in, For the The gonadal development coefficient of each individual, For the The gonad weight of each individual, For the The gonadal index of each individual, For the The weight of an individual.

6. The method for regulating the aquaculture environment for promoting rapid maturation of the gonads of Lateolabrax japonicus according to claim 5, characterized in that: The functional relationship between growth trait coefficient, gonad development coefficient and gonad maturity coefficient is constructed based on the following formula: in, For the The gonadal maturity coefficient of each individual, For the The weight coefficient of the growth trait coefficient of each individual, For the The weight coefficient of the gonadal development coefficient of each individual, and , The specific value of is determined by the hierarchical analysis method.

7. The method for regulating the aquaculture environment for promoting rapid maturation of the gonads of Lateolabrax japonicus according to claim 6, characterized in that: The genetic algorithm is used to select, cross and mutate the gonadal maturity coefficient until the predetermined number of iterations is reached to determine the optimal combination of breeding environment parameters. The specific process is as follows: Iterative optimization is performed on the individuals of the initial population of aquaculture environment parameters. During the iterative optimization process, the constraints of the aquaculture environment parameters should be set, that is, the maximum and minimum values ​​of salinity, temperature, photoperiod, and nutrient content should be set respectively. Within the constraints of salinity, temperature, photoperiod, and nutrient content, the aquaculture environment parameters are iteratively optimized. Specifically, the gonad maturity coefficient Sort from large to small, select gland maturation coefficient The individuals in the front row are taken as the parents. Through crossover and mutation operations, the genes of the parent individuals are exchanged, combined and mutated to generate new individuals. The growth trait parameters and gonad development parameters of the newly generated individuals are obtained by using the development prediction model of striped sea bass, and the gonad maturity coefficient is calculated. The new individuals and the parents are taken as the new population, and the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached. The individuals corresponding to the gonad development stage IV are screened out, and the individuals corresponding to the maximum gonad maturity coefficient among them are used as the optimal breeding environment parameter combination, and the individuals corresponding to the maximum gonad maturity coefficient are calibrated as , then the optimal aquaculture environment parameter combination is salinity ,temperature , photoperiod and nutritional content .

Images