A fish breeding environment optimization method and system based on a cellular automaton

Abstract

The embodiment of the application discloses a fish breeding environment optimization method and system based on a cellular automaton, and the method comprises the following steps: a three-dimensional cellular automaton model is established, wherein a first layer of grids is used to simulate the physical environment state of water, and a second layer of grids is used to simulate the pheromone concentration field of fish breeding; pheromone generation rules, diffusion rules and attenuation rules are set in the second layer of grids, so that pheromone is only generated in the cells where mature female fish or male fish are located, and diffuses in the adjacent cells according to the concentration gradient; according to the breeding trigger rules, the cellular automaton is iteratively run to obtain the breeding success rate distribution of each region under different environment regulation schemes; the breeding trigger rules comprise that only when the pheromone concentration of the target cell continuously exceeds the preset threshold and the physical environment suitable conditions are met at the same time, the cell is allowed to have the fish spawning or fertilization behavior; and the optimal breeding environment parameter combination is determined according to the breeding success rate distribution. The fish breeding success rate is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ecological protection and rare and unique fish breeding in water conservancy and hydropower engineering, and in particular relates to a fish breeding environment optimization method and system based on a cellular automaton. BACKGROUND

[0002] In the related propagation and release station or the conservation station of water conservancy and hydropower engineering, the artificial breeding of rare and unique fish is a key link for restoring and maintaining the population resources. At present, the traditional fish breeding environment optimization mainly relies on the experience to adjust the physical parameters such as water flow, light and dissolved oxygen, or to make a rough prediction through a statistical model, and it is difficult to truly reproduce the chemical behavior coupling mechanism of fish relying on the spawning pheromone for synchronous spawning in clusters, resulting in a low and fluctuating breeding success rate.

[0003] The existing few cellular automaton aquaculture applications are limited to two-dimensional plane and single physical factor simulation, and there is no public technology that takes the fish breeding pheromone concentration field as an independent grid layer and combines it with the water flow, the female and male double-component pheromone, the microbial positive feedback and the closed-loop optimization, which cannot meet the urgent needs of the fine and systematic simulation and regulation of the breeding environment in the conservation of rare fish under the background of water conservancy and hydropower engineering. SUMMARY

[0004] The present application provides a fish breeding environment optimization method and system based on a cellular automaton, which improves the breeding success rate.

[0005] The present application provides the following solutions:

[0006] According to a first aspect, a fish breeding environment optimization method based on a cellular automaton is provided, the method comprising: establishing a three-dimensional cellular automaton model comprising at least two layers of grids, wherein the first layer of grids is used to simulate the physical environment state of the water body, and the second layer of grids is used to simulate the fish breeding pheromone concentration field; setting pheromone generation rules, diffusion rules and attenuation rules in the second layer of grids, so that the pheromone is only generated in the cells where mature female fish or mature male fish are located, and diffuses and attenuates in the neighborhood cells according to the concentration gradient; obtaining the breeding success rate distribution of each region under different environmental regulation schemes by iteratively running the three-dimensional cellular automaton according to a breeding trigger rule, the breeding trigger rule comprising: only when the pheromone concentration of the target cell continuously exceeds a preset threshold and at the same time meets the physical environment suitable condition, the cell is allowed to have fish spawning or fertilization behavior; and determining the optimal combination of breeding environment parameters according to the breeding success rate distribution.

[0007] According to an implementable manner in the embodiments of the present application, the pheromone production rule comprises a gender differentiation mechanism, the gender differentiation mechanism comprises that female fish produces a first type of pheromone, male fish produces a second type of pheromone, and fertilization behavior is triggered only when the concentrations of the first type of pheromone and the second type of pheromone in the same cell or adjacent cells simultaneously exceed respective threshold values.

[0008] According to an implementable manner in the embodiments of the present application, the pheromone diffusion rule is that pheromones propagate in a manner of water flow directional advection combined with concentration gradient diffusion, the pheromone diffusion rule is coupled with the water flow field of the first layer of grids, and pheromones perform asymmetric advection diffusion along the water flow vector at each iteration step.

[0009] According to an implementable manner in the embodiments of the present application, the attenuation rule comprises that the pheromone concentrations of all cells are uniformly multiplied by an attenuation coefficient at the end of each iteration step, and a rate attenuation is additionally applied when the dissolved oxygen concentration of the cell in the first layer of grids is lower than a preset oxygen threshold value.

[0010] According to an implementable manner in the embodiments of the present application, the physical environment suitable condition comprises photoperiod simulation, and a dynamic light attenuation layer changing over time is introduced into the three-dimensional cellular automaton model, and pheromone production is automatically inhibited when the light intensity is lower than a preset value.

[0011] According to an implementable manner in the embodiments of the present application, the cellular automaton further comprises a third layer of microbial grids, each cell of the third layer of microbial grids has a microbial density state; the following mutually coupled update rules are performed in each iteration step: the microorganisms consume the current cell pheromone concentration as a substrate, and produce a secondary metabolite concentration in proportion to the consumption amount; the secondary metabolite concentration is accumulated to the corresponding cell of the second layer of grids, and acts as a multiplicative coefficient on the pheromone attenuation rule of the second layer of grids, so that the pheromone attenuation rate monotonically decreases with the increase of the secondary metabolite concentration.

[0012] According to an implementable manner in the embodiments of the present application, the determining the optimal combination of breeding environment parameters according to the breeding success rate distribution comprises: directly extracting the physical environment state vector of a region with the highest breeding success rate as a template vector; searching for a set of historical optimal parameter combinations closest to the template vector in a preset parameter space library through cosine similarity; if the cosine similarity exceeds a similarity threshold value, directly calling the historical optimal parameter combination as the final parameter combination; if the cosine similarity is lower than the similarity threshold value, taking the template vector as an initial population, and quickly converging to obtain a set of new water flow velocity fields, illumination gradients and feeding partition layouts as the final parameter combination through a particle swarm optimization algorithm; and automatically writing the final parameter combination to a programmable logic controller of the breeding pond through a communication interface, so that the breeding equipment operates according to the final parameter combination.

[0013] According to a second aspect, a fish reproduction environment optimization system based on a cellular automaton is provided, the system comprising: a model establishing module configured to establish a three-dimensional cellular automaton model comprising at least two layers of grids, wherein a first layer of grids is used to simulate a physical environment state of a water body, and a second layer of grids is used to simulate a pheromone concentration field of fish reproduction; a rule setting module configured to set pheromone production rules, diffusion rules and attenuation rules in the second layer of grids, so that pheromone is only produced in a cell where a mature female fish or a mature male fish is located, and diffuses and attenuates in neighboring cells according to a concentration gradient; an iterative running module configured to obtain a reproduction success rate distribution of each region under different environment regulation schemes by iteratively running the three-dimensional cellular automaton model according to a reproduction trigger rule, the reproduction trigger rule comprising: only when the pheromone concentration of a target cell continuously exceeds a preset threshold and at the same time the physical environment suitable conditions are met, the cell is allowed to have fish spawning or fertilization behavior; and a parameter determining module configured to determine an optimal combination of reproduction environment parameters according to the reproduction success rate distribution.

[0014] According to a third aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method of any one of the above first aspect.

[0015] According to a fourth aspect, an electronic device is provided, comprising: one or more processors; and a memory associated with the one or more processors, the memory being configured to store program instructions, the program instructions being configured to perform the steps of the method of any one of the above first aspect when executed by the one or more processors.

[0016] According to the embodiments provided in the present application, the following technical effects are disclosed:

[0017] The present application introduces the fish reproduction pheromone concentration field as an independent grid layer into the three-dimensional cellular automaton, realizes the precise space-time simulation of the cluster spawning behavior driven by chemical signals, and through the double coupling trigger mechanism of the pheromone threshold and the physical environment suitable conditions, completely gets rid of the limitations of the traditional model relying on the rough prediction of physical factors such as temperature and dissolved oxygen. The reproduction success rate distribution generated thereby can truly reflect the differential influence of different flow, light and other regulation schemes on fish chemical communication and synchronous spawning, thereby guiding the aquaculturist to accurately determine the optimal combination of environmental parameters, significantly improving the fertilization rate and fry quality, reducing the risk of embryo malformation and germplasm degradation, and providing a high-fidelity, low-cost and land-based digital optimization new method for factory breeding.

[0018] Of course, implementing any product of the present application does not necessarily require all the advantages described above to be achieved at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below only illustrate some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0020] Figure 1 The flow chart of the fish breeding environment optimization method based on a cellular automaton provided in the embodiments of the present application;

[0021] Figure 2 The structural block diagram of the fish breeding environment optimization system based on a cellular automaton provided in the embodiments of the present application;

[0022] Figure 3 The schematic block diagram of the electronic device provided in the embodiments of the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0024] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0025] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship.

[0026] Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted as "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0027] Figure 1A flow chart of a fish breeding environment optimization method based on a cellular automaton is provided for the embodiments of the present application. As shown in Figure 1 the method can include the following steps:

[0028] Step 101: Establish a three-dimensional cellular automaton model containing at least two layers of grids, wherein the first layer of grids is used to simulate the physical environment state of the water body, and the second layer of grids is used to simulate the fish breeding pheromone concentration field.

[0029] Step 102: Set pheromone production rules, diffusion rules and decay rules in the second layer of grids, so that pheromones are only produced in cells where mature female fish or male fish are located, and diffuse and decay in neighboring cells according to the concentration gradient.

[0030] Step 103: According to the breeding trigger rule, the breeding success rate distribution of each region under different environmental regulation schemes is obtained by iteratively running the three-dimensional cellular automaton; the breeding trigger rule includes: only when the pheromone concentration of the target cell continuously exceeds the preset threshold and at the same time meets the suitable conditions of the physical environment, the cell is allowed to have fish spawning or fertilization behavior.

[0031] Step 104: Determine the optimal combination of breeding environment parameters according to the breeding success rate distribution.

[0032] As can be seen from the above process, the present application introduces the fish breeding pheromone concentration field as an independent grid layer into the three-dimensional cellular automaton, realizes the precise space-time simulation of the cluster spawning behavior driven by chemical signals, and through the double coupling trigger mechanism of the pheromone threshold and the suitable conditions of the physical environment, completely gets rid of the limitations of the traditional model relying on temperature, dissolved oxygen and other physical factors for rough prediction. The breeding success rate distribution generated thereby can truly reflect the differential influence of different water flow, light and other regulation schemes on fish chemical communication and synchronous spawning, thereby guiding the breeder to accurately determine the optimal combination of environmental parameters, significantly improving the fertilization rate and fry quality, reducing the risk of embryo malformation and germplasm degradation, and providing a high-fidelity, low-cost and land-based digital optimization new method for factory breeding.

[0033] The steps in the above process and the effects that can be further produced will be described in detail below. First, the step 101 of the above process, i.e., "establishing a three-dimensional cellular automaton model containing at least two layers of grids, wherein the first layer of grids is used to simulate the physical environment state of the water body, and the second layer of grids is used to simulate the fish breeding pheromone concentration field", will be described in detail in conjunction with an embodiment.

[0034] This step extends the traditional cellular automaton from a single grid to a three-dimensional structure with multiple layers stacked, and strictly separates the physical environment and chemical signals into different layers, thereby realizing the independent evolution and selective coupling of two variables with completely different properties.

[0035] The first layer grid is responsible for simulating the physical environment state of the water body. This layer contains multiple physical fields, such as temperature field, dissolved oxygen concentration field, water flow velocity vector field, light intensity attenuation field with depth, and pH value field, etc. Each cell saves a complete set of physical state vectors at each time, and these physical quantities are updated synchronously according to the real fluid mechanics, heat conduction, convection and diffusion, and light attenuation rules. This layer essentially reproduces the objective physical background of the aquaculture water body, providing basic constraint conditions for the survival and activity of fish.

[0036] The second layer grid is completely independent and is used to simulate the concentration field of fish reproductive pheromone. This layer only records the pheromone concentration scalar (or concentration vector) in each cell, without directly storing any physical variables. As the key chemical communication signal for fish reproductive behavior, the production, diffusion and decay process of pheromone has completely different biological rules from temperature and dissolved oxygen. By placing the pheromone concentration field in the second layer, it can evolve independently according to the specially designed production rules, gradient diffusion rules, water flow advection rules and decay rules, while it can also interact precisely with the physical fields of the first layer when needed, such as pheromone being transported directionally with water flow or being degraded faster in low dissolved oxygen areas.

[0037] The following describes the step 102, i.e., "setting pheromone production rules, diffusion rules and decay rules in the second layer grid, so that pheromone is only produced in the cells where mature female or male fish are located, and diffuses and decays in the adjacent cells according to the concentration gradient", in detail in combination with embodiments.

[0038] This step specially formulates three independent evolution rules for the second layer pheromone concentration field, and accurately restores the real biological generation and propagation mechanism of chemical signals in the fish reproduction process through these rules, so that the model jumps from pure physical simulation to real chemical behavior coupling simulation.

[0039] The pheromone production rule clearly stipulates that only when there is a female or male fish in the estrus state in the cell, the cell will produce a certain amount of reproductive pheromone at each iteration step. The cells where ordinary cells, immature fish or non-estrus fish are located always maintain a production amount of zero. This selective production mechanism directly simulates the biological fact that only sexually mature individuals can secrete reproductive pheromones in reality, avoiding the unrealistic assumption that all fish uniformly release signals in traditional models, thereby greatly improving the fidelity of the model in the simulation of reproductive synchrony.

[0040] In the second layer grid, pheromone concentration is only produced in cells containing mature fish. The specific formula is:

[0041]

[0042] where, representing cells at time step pheromone concentration; is a production constant (e.g. units / step); is an indicator function that is 1 if there is a mature female or male in the cell, and 0 otherwise. This formula ensures that pheromones are locally produced from the source of the organism.

[0043] As an implementable way, the pheromone production rule includes a gender differentiation mechanism: females produce a first type of pheromone, males produce a second type of pheromone, and fertilization behavior is triggered only when the concentrations of both types of pheromones in the same cell or adjacent cells simultaneously exceed their respective thresholds.

[0044] Specifically, in real fish reproduction behavior, females and males usually release completely different chemical signals: females secrete a first type of pheromone (often referred to as attractant or ovulation) to attract males and induce them to release sperm before and after ovulation, and males release a second type of pheromone (often referred to as sperm accompaniment or male recognition) in a state of sexual excitement. The chemical structure, release timing, and biological function of these two types of pheromones are different, and only when female and male individuals simultaneously release and perceive sufficient concentrations of each other within the same spatiotemporal window, will the final synchronous ovulation and spermiation behavior be triggered. The present application first restores this two-component chemical dialogue process in the framework of cellular automata by distinguishing the pheromones into two independent channels of the first type of pheromone and the second type of pheromone in the second layer of grid.

[0045] The specific rule design is: when there is a mature female in the cell, only the concentration of the first type of pheromone channel is increased; when there is a mature male in the cell, only the concentration of the second type of pheromone channel is increased; the two do not interfere with each other, and also cannot occur simultaneously in a single gender cell. This gender-specific production mechanism ensures that the pheromone signal carries clear gender information, enabling the model to distinguish between female and male chemical fingerprints.

[0046] The fertilization trigger condition further requires that, in the same cell or spatially adjacent cells, the concentration of the first type of pheromone must continuously exceed the respective preset threshold for multiple steps, and the concentration of the second type of pheromone must also simultaneously exceed the respective preset threshold, to allow marking the location as a fertilization event. This "double threshold simultaneous satisfaction" logic is equivalent to reproducing the mutual confirmation process in the natural world, where "females ovulate only when they smell male signals, and males release sperm only when they smell female signals", completely avoiding the unrealistic situation of blind fertilization in traditional models as long as the total amount of pheromones is sufficient.

[0047] The diffusion rule makes pheromone naturally spread between neighboring cells according to the concentration gradient. Specifically, in each iteration step, the system first calculates the concentration difference between the current cell and the surrounding neighbor cells, and then transfers a portion of pheromone from the high concentration cell to the low concentration neighbor cell in proportion, forming a typical isotropic diffusion effect. This diffusion method based on local concentration gradient reproduces the process of pheromone molecules gradually expanding through molecular random motion in still water or weak flow environment, enabling fish in the distance to perceive the chemical signals released by upstream or peripheral individuals, thereby achieving information exchange at the cluster level.

[0048] As an implementable way, the pheromone diffusion rule is a combination of water flow directional advection and concentration gradient diffusion, which is coupled with the water flow field of the first layer grid, and the pheromone performs asymmetric advection diffusion along the water flow vector at each iteration step.

[0049] Specifically, the diffusion of pheromone is no longer simply isotropic molecular diffusion, but is divided into two sequentially executed sub-steps. First, water flow directional advection is performed, that is, at the beginning of each iteration step, the system reads the current water flow velocity vector of each cell in the first layer grid, and then the pheromone concentration at this position of the second layer grid is translated and transported as a whole according to the water flow direction and speed. This advection process makes pheromone like floating dye be transported downstream in blocks by water flow, thereby forming a clear main transmission direction and a high concentration tail downstream.

[0050] The pheromone diffuses in the neighborhood according to the concentration gradient. The specific formula is:

[0051]

[0052] wherein, is the diffusion coefficient (for example, , control the diffusion intensity); indicates the neighborhood cells (such as Moore 26 neighborhood); is the number of neighborhood cells. This formula simulates the gradient transmission from high to low concentration, realizing spatial diffusion.

[0053] After advection, the traditional concentration gradient diffusion is performed, that is, isotropic exchange according to the concentration difference in the local neighborhood. This sub-step simulates the local mixing effect caused by molecular thermal motion. Since advection has caused asymmetric concentration distribution on a macroscopic scale, the subsequent gradient diffusion only plays a smoothing role locally and does not offset the overall directional transmission brought by water flow, thereby finally forming an asymmetric diffusion pattern, which conforms to the propagation rule of odor or pheromone in actual water bodies.

[0054] The attenuation rule is responsible for simulating the natural deactivation and degradation process of pheromone in water bodies. At the end of each iteration step, the pheromone concentration of all cells is multiplied by a decay coefficient less than 1, or directly subtracted by a fixed amount, to reflect the reality that pheromone gradually disappears due to photolysis, oxidation, microbial degradation, etc. This rule ensures that the pheromone signal has clear temporal validity and spatial finiteness, preventing signal accumulation from distorting the model, while also forcing fish to gather in high concentration areas within a limited time to complete spawning, avoiding unnatural breeding behavior caused by permanent signal in traditional models.

[0055] Preferably, the attenuation rule is that at the end of each iteration step, the pheromone concentration of all cells is uniformly multiplied by a decay coefficient, and when the dissolved oxygen concentration in the first layer of the grid is below the preset oxygen threshold, an additional rate attenuation is applied.

[0056] Specifically, when the dissolved oxygen concentration at the same location in the first layer of the grid is below the preset oxygen threshold, the system applies an additional rate attenuation to the pheromone concentration of the cell, i.e., it is multiplied by a smaller coefficient again or directly reduced significantly. This rule is directly derived from the biochemical rules in real water bodies: in a low-dissolved oxygen environment, the redox potential of the water body decreases rapidly, reducing substances increase, and pheromone molecules are more easily chemically reduced or rapidly decomposed by anaerobic microorganisms, resulting in a dramatic shortening of their half-life. At the same time, low oxygen itself is an important signal of fish stress, and fish will reduce or even stop breeding behavior in hypoxic areas. At this time, if the pheromone remains at a high concentration for a long time, it will deviate significantly from biological reality.

[0057] The above step 103, i.e., "obtaining the spawning success rate distribution of each region under different environmental regulation schemes by iteratively running the cellular automaton according to the spawning trigger rule; the spawning trigger rule includes: only when the pheromone concentration of the target cell continuously exceeds the preset threshold and at the same time meets the physical environment suitable condition, the cell is allowed to have fish spawning or fertilization behavior", is described in detail below in conjunction with embodiments.

[0058] Iterative running is the core execution mechanism of cellular automata. In each iteration step, the system first updates all state variables of the first layer of the physical environment grid, such as temperature, dissolved oxygen, and water flow, etc., and then updates the second layer of the pheromone concentration field, including the execution of rules such as generation, diffusion, and attenuation. Next, for each cell, it checks whether the spawning trigger condition is met. If so, a spawning or fertilization event is recorded in the cell. Through multiple complete iteration cycles, usually hundreds to thousands of steps, the model simulates the entire dynamic process of fish from sensing the signal to completing the spawning.

[0059] The core logic of the spawning trigger rule is that only when a cell meets two independent and indispensable conditions simultaneously, a real spawning or fertilization event is allowed to be marked at that location. The first condition is that the pheromone concentration must exceed a preset threshold for several consecutive iteration steps, which simulates the fact that fish will only enter the irreversible state of final ovulation or ejaculation after receiving a stable and strong enough chemical signal, preventing false triggers caused by transient high concentration noise. The second condition is that the physical environment of the same location must fall entirely within the optimal range for fish reproduction, such as temperature 22 to 28 degrees Celsius, dissolved oxygen higher than 5 milligrams per liter, pH value 6.8 to 8.2, light intensity in the appropriate range, etc. Only when both chemical signals and physical conditions are met, the cell is determined as a successful reproduction event.

[0060] As an implementable way, the physical environment suitable conditions of the present application include photoperiod simulation, a dynamic light attenuation layer is introduced into the model, which automatically inhibits pheromone production when the light intensity is lower than the preset value.

[0061] Specifically, photoperiod simulation refers to the built-in light intensity distribution field in the model that changes periodically with time to reproduce the natural light cycle of sunrise, sunset and day-night alternation in real water bodies. Specifically, this layer can be regarded as an extended sublayer of the first layer of physical environment grid, whose light intensity value is dynamically adjusted according to the simulation time stamp at each iteration step, for example, gradually increasing from morning to noon peak, and then gradually decreasing to the lowest value at night. This time-varying design is directly derived from fish physiology, and the secretion of reproductive hormones of many economic fish species such as salmon or tilapia is highly dependent on photoperiod, and only under suitable light duration and intensity will enter the estrus state.

[0062] The dynamic light attenuation layer emphasizes the gradient attenuation of light with depth in water. According to the Beer-Lambert law, light intensity decays exponentially with water depth, so the light value of the upper cells in the model is higher, and the lower cells are significantly reduced due to scattering and absorption. This layer not only changes with time, but also is coupled with variables such as water turbidity or algal density, further enhancing the realism of the simulation.

[0063] When the light intensity of a cell in the dynamic light attenuation layer is lower than the preset value, the system automatically inhibits the pheromone production of the cell. The specific rule is that if the light intensity is lower than the threshold, the increment coefficient in the production rule is reduced to zero or greatly reduced, thereby preventing mature fish from releasing reproductive signals in dark or low light environment. This directly simulates the biological fact that most fish will suspend reproductive activity at night or in low light to avoid exposing the embryo to an environment that is not conducive to development.

[0064] With this feature, the model can automatically avoid triggering false spawning events in low-light areas, making the spawning success rate distribution more accurately reflect reality, such as preferring to lay eggs in the surface layer or well-lit areas. At the same time, this mechanism guides breeding optimization, such as simulating natural light cycles through LED lamps, extending the suitable light period, ultimately improving overall fertilization efficiency and fry survival rate.

[0065] This dual-gating mechanism completely changes the prediction method of traditional fish breeding models. Most past models considered spawning possible as long as physical factors such as temperature and dissolved oxygen were suitable, completely ignoring the decisive role of chemical signals; or conversely, considered breeding possible as long as pheromone concentration was high, ignoring the biological fact that low temperature, high ammonia nitrogen, or hypoxia can directly block the final maturation of the gonad. The invention forces the two to be bound together, truly restoring the real decision-making process in nature and in aquaculture ponds: "fish will only finally reproduce when they both smell the signal of their own kind and feel comfortable in the environment."

[0066] By repeatedly iterating the cellular automaton under a large number of different environmental control schemes, the system automatically counts how many times a spawning event is triggered in each region under each parameter combination, ultimately forming a high-resolution spawning success rate distribution map.

[0067] The specific formula is:

[0068]

[0069] where, is the success rate of the region under scheme ; is the number of cells in the region; is the total number of iterations; indicates different environmental control schemes (such as different water flow rates). This formula quantifies the region probability of each scheme to determine the optimal parameter combination.

[0070] The spawning success rate distribution is essentially a three-dimensional probability field or heat map that aggregates the results of the cellular automaton under different environmental control schemes. Specifically, this distribution records the frequency of spawning or fertilization events in each region or cell within the simulation period, for example, high success rate regions may correspond to locations with moderate water flow, adequate dissolved oxygen, and stable pheromone concentration, while low success rate regions often reflect defects such as hypoxia, insufficient light, or rapid pheromone decay. Through this distribution, the system can intuitively quantify the overall impact of various parameter combinations on breeding efficiency, avoiding the rough evaluation of traditional methods relying on a single indicator such as average egg production.

[0071] ​Preferably, the cellular automaton of the present application further comprises a third layer of microbial grid, each cell of the microbial grid having a microbial density state; the following inter-coupled update rules are performed in each iteration step: the microorganism consumes the current pheromone concentration as substrate and produces a secondary metabolite concentration proportional to the consumption; the secondary metabolite concentration is accumulated to the corresponding cell of the second layer grid and acts as a multiplicative coefficient on the pheromone decay rule of the second layer grid, making the pheromone decay rate monotonically decrease with the increase of the secondary metabolite concentration.

[0072] The third layer of microbial grid exists in parallel with the first two layers of physical environment grid and pheromone concentration field grid, and each cell independently maintains a microbial density state variable. This state represents the microbial biomass or activity level at this location, such as the concentration distribution of bacteria or microalgae. The microbial density is updated with each iteration step and can respond to external inputs such as pheromone concentration, water quality parameters, etc., forming a self-organizing microbial ecological layer.

[0073] In each iteration step, the system performs a series of inter-coupled update rules, starting with the microbial consumption process of pheromone. The microorganism treats the current cell's pheromone concentration as a substrate, i.e. a source of nutrition, for metabolic consumption. Specifically, the consumption is proportional to the pheromone concentration, for example, each unit of pheromone is absorbed by the microorganism and reduced by a corresponding proportion, while the microbial density may slightly increase due to the intake of nutrients. This consumption simulates the biological degradation behavior of microorganisms such as bacteria on fish pheromones in real water bodies, preventing excessive accumulation of pheromones.

[0074] After the consumption process, the microorganism produces a secondary metabolite concentration proportional to the consumption. These secondary metabolites can be enzymes, hormones, or organic acids secreted by microorganisms, and their production is directly based on the amount of consumed pheromone, forming a proportional conversion relationship. This step reproduces the phenomenon of secondary metabolite release by microorganisms when metabolizing fish signals, and these metabolites often have biological activity, which can further affect the surrounding environment.

[0075] The produced secondary metabolite concentration is accumulated to the corresponding cell of the second layer grid, i.e. the pheromone concentration field layer. This accumulation operation realizes cross-layer interaction, making the output of the microbial layer directly feedback to the pheromone dynamics. Specifically, the secondary metabolite, as an auxiliary variable, accumulates and participates in the subsequent evolution rules of pheromone.

[0076] The concentration of secondary metabolites acts as a multiplicative coefficient on the pheromone decay rule of the second layer grid. The specific mechanism is that the higher the concentration of secondary metabolites, the lower the pheromone decay rate of the cell, forming a monotonous decreasing relationship. For example, the decay coefficient is originally a fixed value, but after being multiplied by a factor that decreases with the concentration of metabolites, the pheromone will decay more slowly in the active area of the microorganism, thereby extending its effective life. This design simulates the protective effect of some microbial secretions on pheromones, such as inhibiting oxidation or providing a stable medium.

[0077] Through these update rules, the entire system forms a positive feedback loop: high pheromone concentration promotes microbial consumption and metabolite production, metabolites in turn slow down pheromone decay, further maintaining high concentration areas, thereby enhancing the stability of synchronous spawning of fish clusters. This positive feedback mechanism highly mimics natural ecology, amplifying the breeding signal in high microbial density areas (such as sediment or algal bloom areas), and accelerating the disappearance of the signal in low density areas, avoiding the aggregation of fish to unsuitable areas.

[0078] The following describes the step 104, i.e., "determining the optimal breeding environment parameter combination according to the breeding success rate distribution", in detail in combination with an embodiment.

[0079] First, the system extracts key indicators from the distribution, such as selecting the scheme with the highest average success rate in the entire field, or prioritizing local optimization in specific areas such as the center of the pond. Then, by comparing the distribution differences of multiple schemes, such as simulation results with water flow speed gradually changing from low to high, the algorithm identifies the core parameter combination that leads to the success rate peak, including the water flow speed field, light intensity gradient, feeding location zoning, and dissolved oxygen maintenance level, etc.

[0080] As an implementable way, determining the optimal breeding environment parameter combination according to the breeding success rate distribution comprises: directly extracting the physical environment state vector of a number of regions with the highest breeding success rate as a template vector; retrieving a set of historical optimal parameter combinations closest to the template vector in a preset parameter space library through cosine similarity; if the similarity exceeds a preset threshold, directly calling the historical combination; if the cosine similarity exceeds a similarity threshold, directly calling the historical optimal parameter combination as the final parameter combination; if the cosine similarity is lower than the similarity threshold, taking the template vector as an initial population, and quickly converging to obtain a new water flow speed field, light gradient, and feeding zoning layout through a particle swarm optimization algorithm as the final parameter combination; and automatically writing the final parameter combination to the programmable logic controller of the breeding pond through a communication interface, so that the breeding equipment operates according to the final parameter combination.

[0081] First, the system identifies and extracts the physical environment state vectors of several regions with the highest success rate from the reproduction success rate distribution as template vectors. These vectors usually include multiple dimensions, such as local water flow speed, dissolved oxygen concentration, temperature, light intensity, and other key indicators. By selecting the state of the top region, the template vector represents a quantitative image of the "ideal breeding conditions" in model simulation, avoiding the local hotspot information that may be ignored by the global average value.

[0082] Next, cosine similarity is used to search in the pre-set parameter space library. This library pre-stores historically verified parameter combinations, such as optimal water flow fields, light gradients, etc. in previous experiments or simulations. Cosine similarity calculates the cosine value of the included angle between the template vector and each entry in the library. The closer the value is to 1, the more similar it is, so that the closest matching item can be quickly found. This step efficiently utilizes historical data and reduces the computational burden of zero optimization.

[0083] If the highest similarity retrieved exceeds the similarity threshold, the historically optimal parameter combination is directly called as the final parameter combination. This ensures the reuse of reliable solutions under similar conditions, avoids unnecessary computational overhead, and improves response speed. If the similarity is below the similarity threshold, indicating that there are not enough matching items in the historical library, the template vector is used as the initial population, and the particle swarm optimization algorithm is started for fast iterative convergence. This algorithm simulates the foraging behavior of bird flocks, with each particle representing a parameter combination. By updating the position and velocity, it converges to the global optimum within a limited number of generations, finally generating a new set of water flow velocity fields, light gradients, and feeding partition layouts as the final parameter combination.

[0084] Finally, the final parameter combination is automatically written to the programmable logic controller of the aquaculture pond through the communication interface, so that the aquaculture equipment operates according to the final parameter combination. This interface realizes seamless connection from simulation optimization to physical devices, such as adjusting the water pump speed, LED light intensity, and feeding machine position, so that the simulation results of the day are directly converted into actual environment reconstruction the next day, forming a truly unmanned intervention closed-loop system.

[0085] The above method provided by the embodiments of the present application can be applied to various application scenarios, including but not limited to, for example, in a large tilapia or carp breeding farm, by simulating the coupling of pheromone diffusion and water flow, the speed of the pond water pump and the layout of the LED light are adjusted in real time, the fertilization success rate is improved, the fry loss is reduced and the economic benefit is improved; secondly, in a scientific research laboratory, the method can be used to simulate the reproductive behavior response of different fish species such as salmon to climate change, combined with the positive feedback mechanism of microorganisms, the influence of environmental disturbance on population dynamics is predicted, and biological experiment design and data-driven academic research are supported; in addition, in an ecological protection project, it can be applied to river or lake habitat restoration engineering, the optimal water quality parameter combination is generated by the particle swarm optimization algorithm, guiding artificial intervention measures such as probiotic bacteria release or water level regulation, helping endangered fish to restore natural reproductive capacity, and promoting biodiversity sustainability.

[0086] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the drawings do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multi-task processing and parallel processing are possible or can be advantageous.

[0087] According to another aspect, embodiments of a fish reproduction environment optimization system based on cellular automata are provided. Figure 2 A schematic block diagram of the fish reproduction environment optimization system based on cellular automata according to one embodiment is shown. As Figure 2 The device 200 includes, as shown,

[0088] The model establishing module 201 is configured to establish a three-dimensional cellular automaton model containing at least two layers of grids, wherein the first layer of grids is used to simulate the physical environment state of the water body, and the second layer of grids is used to simulate the pheromone concentration field of fish reproduction.

[0089] The rule setting module 202 is configured to set pheromone production rules, diffusion rules and decay rules in the second layer of grids, so that pheromones are only produced in cells where mature female fish or mature male fish are located, and diffuse and decay in neighboring cells according to a concentration gradient.

[0090] The iterative running module 203 is configured to obtain the reproduction success rate distribution of each region under different environmental regulation schemes by iteratively running the three-dimensional cellular automaton according to a reproduction trigger rule; the reproduction trigger rule includes: only when the pheromone concentration of the target cell continuously exceeds a preset threshold and at the same time meets the physical environment suitable condition, the cell is allowed to have fish spawning or fertilization behavior.

[0091] The parameter determining module 204 is configured to determine the optimal combination of the breeding environment parameters according to the breeding success rate distribution.

[0092] As an implementable manner, the pheromone generation rule in the rule setting module 202 includes a gender differentiation mechanism: female fish generates a first type of pheromone, male fish generates a second type of pheromone, and fertilization behavior is triggered only when the concentrations of the first type of pheromone and the second type of pheromone in the same cell or adjacent cells simultaneously exceed the respective thresholds.

[0093] As an implementable manner, the pheromone diffusion rule in the rule setting module 202 is a combination of water flow directional advection and concentration gradient diffusion, and the pheromone diffusion rule is coupled with the water flow field of the first layer of grids. The pheromone performs asymmetric advection diffusion along the water flow vector at each iteration step.

[0094] As an implementable manner, the decay rule in the rule setting module 202 includes that the pheromone concentration of all cells is uniformly multiplied by a decay coefficient at the end of each iteration step, and when the dissolved oxygen concentration of the cell in the first layer of grids is lower than the preset oxygen threshold, an additional rate decay is applied.

[0095] As an implementable manner, the physical environment suitable condition in the iteration running module 203 includes photoperiod simulation, and a dynamic light attenuation layer varying with time is introduced into the model, and pheromone generation is automatically inhibited when the light intensity is lower than the preset value.

[0096] As an implementable manner, the cellular automaton further comprises a third layer of microbial grids, each cell of the third layer of microbial grids having a microbial density state; the following mutually coupled update rules are performed at each iteration step: the microorganisms consume the current cell pheromone concentration as a substrate, and generate a secondary metabolite concentration in proportion to the consumption amount; the secondary metabolite concentration is accumulated to the corresponding cell of the second layer of grids, and acts as a multiplicative coefficient on the pheromone decay rule of the second layer of grids, so that the pheromone decay rate monotonically decreases with the increase of the secondary metabolite concentration.

[0097] As an implementable manner, the parameter determination module 204 can be configured to, when determining the optimal breeding environment parameter combination according to the breeding success rate distribution, directly extract the physical environment state vector of the region with the highest breeding success rate as a template vector; search for a set of historical optimal parameter combinations closest to the template vector in a preset parameter space library through cosine similarity; if the cosine similarity exceeds a similarity threshold, directly call the historical optimal parameter combination as the final parameter combination; if the cosine similarity is below the similarity threshold, take the template vector as an initial population, and quickly converge to obtain a set of new water flow velocity fields, light gradients and feeding partition layouts as the final parameter combination through a particle swarm optimization algorithm; and automatically write the final parameter combination to a programmable logic controller of the breeding pond through a communication interface, so that the breeding equipment operates according to the final parameter combination.

[0098] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant part can be referred to the part of the method embodiment. The system embodiment described above is only illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0099] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0100] In addition, the embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the method in any one of the preceding method embodiments.

[0101] and an electronic device, comprising:

[0102] one or more processors; and a memory associated with the one or more processors, the memory for storing program instructions that, when read and executed by the one or more processors, perform the steps of the method of any of the preceding method embodiments.

[0103] The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any of the preceding method embodiments.

[0104] wherein, Figure 3 An exemplary architecture of the electronic device is shown, which can specifically include a processor 310, a video display adapter 311, a disk drive 312, an input / output interface 313, a network interface 314, and a memory 320. The processor 310, the video display adapter 311, the disk drive 312, the input / output interface 313, the network interface 314, and the memory 320 can be communicatively connected through a communication bus 330.

[0105] The processor 310 can be implemented in the form of a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided by the present application.

[0106] The memory 320 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 320 can store an operating system 321 for controlling the operation of the electronic device 300, a basic input / output system (BIOS) 322 for controlling the low-level operation of the electronic device 300. In addition, a web browser 323, a data storage management system 324, and a fish breeding environment optimization system based on cellular automata 325, etc. can also be stored. The fish breeding environment optimization system based on cellular automata 325 can be an application program that specifically implements the above steps in the embodiments of the present application. In summary, when the technical solutions provided by the present application are implemented by software or firmware, the relevant program codes are stored in the memory 320 and executed by the processor 310.

[0107] The input / output interface 313 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0108] The network interface 314 is configured to connect a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0109] The bus 330 includes a channel to transmit information between various components (for example, the processor 310, the video display adapter 311, the disk drive 312, the input / output interface 313, the network interface 314, and the memory 320) of the device.

[0110] It should be noted that although the above device only shows the processor 310, the video display adapter 311, the disk drive 312, the input / output interface 313, the network interface 314, the memory 320, and the bus 330, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain the components necessary to implement the scheme of the present application, and does not have to contain all the components shown in the figure.

[0111] From the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and a general hardware platform. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer program product, which can be stored in a storage medium such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the present application.

[0112] The technical solutions provided by the present application are described in detail above, and specific examples are applied to the principle and implementation of the present application. The above description of the embodiments is only to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for optimizing a fish breeding environment based on a cellular automaton, characterized by, The method comprises: establishing a three-dimensional cellular automaton model comprising at least two layers of grids, wherein the first layer of grids is used to simulate the physical environment state of the water body, and the second layer of grids is used to simulate the pheromone concentration field of fish reproduction; setting pheromone production rules, diffusion rules and decay rules in the second layer of grids, so that pheromone is only produced in cells where mature female fish or mature male fish are located, and diffuses and decays in adjacent cells according to the concentration gradient; obtaining the reproduction success rate distribution of each region under different environmental regulation schemes by iteratively running the three-dimensional cellular automaton model according to the reproduction trigger rule, wherein the reproduction trigger rule comprises: only when the pheromone concentration of the target cell continuously exceeds the preset threshold and at the same time meets the physical environment suitable condition, the fish spawning or fertilization behavior is allowed to occur in the target cell; determining the optimal combination of reproduction environmental parameters according to the reproduction success rate distribution; the production rule comprises a gender differentiation mechanism, and the gender differentiation mechanism comprises: female fish produce a first type of pheromone, and male fish produce a second type of pheromone; only when the concentrations of the first type of pheromone and the second type of pheromone in the same cell or adjacent cells simultaneously exceed their respective thresholds, the fertilization behavior is triggered; the diffusion rule comprises that the pheromone propagates in a combination of water flow directional advection and concentration gradient diffusion, the diffusion rule is coupled with the water flow field of the first layer of grids, and the pheromone performs asymmetric advection diffusion along the water flow vector at each iteration step; the decay rule comprises that at the end of each iteration step, the pheromone concentration of all cells is uniformly multiplied by a decay coefficient, and when the dissolved oxygen concentration of the cell in the first layer of grids is lower than the preset oxygen threshold, an additional rate of decay is applied.

2. The method of claim 1, wherein, The physical environment suitable condition comprises photoperiod simulation, and a dynamic light attenuation layer varying with time is introduced into the three-dimensional cellular automaton model, and the pheromone production is automatically inhibited when the light intensity is lower than the preset value.

3. The method of claim 1, wherein, The cellular automaton model further comprises a third layer of microbial grids, each cell of the third layer of microbial grids has a microbial density state; an update rule is executed in each iteration step, and the update rule comprises: microorganisms consume the current cell pheromone concentration as a substrate and produce a secondary metabolite concentration in proportion to the consumption amount; the secondary metabolite concentration is accumulated in the corresponding cell of the second layer of grids and acts as a multiplicative coefficient on the pheromone decay rule of the second layer of grids, so that the pheromone decay rate monotonically decreases with the increase of the secondary metabolite concentration.

4. The method of claim 1, wherein, The determination of the optimal combination of reproduction environmental parameters according to the reproduction success rate distribution comprises: extracting the physical environment state vector of several regions with high reproduction success rate as a template vector; retrieve the set of historical optimal parameter combinations closest to the template vector in the preset parameter space library by cosine similarity; if the cosine similarity exceeds the similarity threshold, the historical optimal parameter combination is directly called as the final parameter combination; if it is lower than the similarity threshold, the template vector is taken as the initial population, and a new set of water flow velocity field, light gradient and feeding partition layout is obtained as the final parameter combination through the particle swarm optimization algorithm. The final parameter combination is automatically written to a programmable logic controller of the breeding pond through a communication interface, so that the breeding equipment operates according to the final parameter combination.

5. A fish breeding environment optimization system based on a cellular automaton, characterized by, The system comprises: The model establishing module is configured to establish a three-dimensional cellular automaton model comprising at least two layers of grids, wherein the first layer of grids is used to simulate the physical environment state of the water body, and the second layer of grids is used to simulate the pheromone concentration field of fish reproduction; The rule setting module is configured to set pheromone production rules, diffusion rules and decay rules in the second layer of grids, so that pheromone is only produced in cells where mature female fish or mature male fish are located, and diffuses and decays in neighboring cells according to a concentration gradient; The iterative running module is configured to obtain the reproduction success rate distribution of each region under different environmental regulation schemes by iteratively running the three-dimensional cellular automaton model according to a reproduction trigger rule, wherein the reproduction trigger rule comprises: only when the pheromone concentration of a target cell continuously exceeds a preset threshold and at the same time the physical environment is suitable, the target cell is allowed to have fish spawning or fertilization behavior; The parameter determining module is configured to determine an optimal reproduction environment parameter combination according to the reproduction success rate distribution; The production rule comprises a gender differentiation mechanism, and the gender differentiation mechanism comprises: female fish produce a first type of pheromone, and male fish produce a second type of pheromone; only when the concentrations of the first type of pheromone and the second type of pheromone in the same cell or adjacent cells simultaneously exceed their respective thresholds, fertilization behavior is triggered; The diffusion rule comprises a combination of pheromone directional advection with concentration gradient diffusion, and the diffusion rule is coupled with the water flow field of the first layer of grids; pheromone performs asymmetric advection diffusion along the water flow vector at each iteration step; The decay rule comprises that at the end of each iteration step, the pheromone concentration of all cells is uniformly multiplied by a decay coefficient, and when the dissolved oxygen concentration of the cell in the first layer of grids is lower than a preset oxygen threshold, an additional rate decay is applied.

6. An electronic device, comprising: Comprise: One or more processors; And a memory associated with the one or more processors, the memory is used to store program instructions, the program instructions are read and executed by the one or more processors, and the steps of the method in any one of claims 1 to 4 are executed.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the steps of the method in any one of claims 1 to 4.

Images