Analysis, regulation and control system and analysis, regulation and control method for living environment of sargassum fusiforme male algae

Abstract

The invention relates to the technical field of sargassum fusiforme cultivation, and discloses a sargassum fusiforme male frond living environment analysis regulation and control system and method.The analysis regulation and control system comprises a multi-source data acquisition module, a gender recognition and physiological state analysis module, a dynamic environment regulation and control module, a biological prevention and control module and a risk prediction and feedback module; the analysis regulation and control method comprises the following steps: acquiring environmental parameters and frond physiological data; identifying the gender and the physiological stage of the frond; dynamically regulating and controlling environmental parameters; executing biological prevention and control; and risk prediction and feedback regulation and control are carried out. Through intelligent, dynamic regulation and control, real-time monitoring, biological prevention and control and other technologies, the survival rate of the male algae is increased, the sperm discharge period of the male algae is prolonged, the fertilization rate during manual seedling collection is increased, and sustainable development of ecological environment protection and algae culture is promoted.

Description

Technical Field

[0001] This invention relates to the field of Sargassum aquatic life cultivation technology, and in particular to an analysis and control system and method for the survival environment of male Sargassum fusiforme thallus. Background Technology

[0002] As an important economic seaweed, the reproductive efficiency of male thallus of Sargassum directly affects the genetic diversity of the population and the benefits of large-scale aquaculture. However, existing technologies have the following problems:

[0003] 1. Lack of research on sex-specific environmental requirements: Existing technologies mostly focus on optimizing the overall growth conditions of Sargassum fusiforme, without distinguishing the physiological differences between male and female thalli. The reproductive receptacle structure of male thalli differs significantly from that of females, and their metabolic activities and environmental tolerance may differ. Traditional methods using uniform environmental parameters can easily lead to delayed development of male thalli or reduced reproductive cell activity, thus reducing the reproductive success rate. 2. Static and extensive nature of environmental parameter control: Existing aquaculture systems mostly rely on fixed environmental parameters and lack real-time response mechanisms to dynamic environmental factors. Male algae are more prone to problems under extreme climates, and current environmental monitoring technologies mostly rely on manual sampling, resulting in insufficient data timeliness and accuracy. 3. Lack of intelligent analysis and feedback mechanisms: Current Sargassum fusiforme cultivation systems are mostly based on experience to set environmental parameters, without integrating the correlation model between physiological indicators and environmental factors, and cannot predict the risk of declining survival rate of male thalli through real-time data analysis, resulting in delayed remedial measures; 4. Interference from pathogenic microorganisms and competing organisms: Male algae have active metabolism during the reproductive period, making them more attractive to zooplankton or pathogenic microorganisms. Existing environmental control systems lack targeted biological control modules, leading to increased mortality rates in male algae. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides an analysis and regulation system and method for the survival environment of male Sargassum fusiforme thallus. Through intelligent, dynamic regulation, real-time monitoring, and biocontrol technologies, it comprehensively solves the problems existing in the prior art, such as the lack of gender-specific environmental requirements, the static and extensive nature of environmental parameter regulation, the lack of intelligent analysis and feedback mechanisms, and interference from pathogenic microorganisms. This aims to improve the survival rate of male thallus, extend the sperm release cycle of male thallus, and increase the fertilization rate during artificial seedling collection.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows:

[0006] An analysis and control system for the survival environment of male Sargassum fusiforme thallus is characterized by comprising a multi-source data acquisition module, a sex identification and physiological state analysis module, a dynamic environment control module, a biocontrol module, and a risk prediction and feedback module, wherein the multi-source data acquisition module, the sex identification and physiological state analysis module, the dynamic environment control module, the biocontrol module, and the risk prediction and feedback module are all electrically connected to the main control unit. The multi-source data acquisition module monitors various physical, chemical, and biological parameters in the habitat of Sargassum fusiforme in real time through multiple sensors installed in the environment. All collected data is transmitted to the main control unit in real time for subsequent analysis and control. The gender identification and physiological state analysis module uses image recognition and deep learning technology to identify the gender and analyze the physiological state of Sargassum fusiforme. The dynamic environment control module calculates the ideal environmental parameters required by Sargassum fusiforme based on the multi-source data and gender and physiological state information received by the main control unit, and performs dynamic control. The biocontrol module is responsible for monitoring the microbial situation in the water, using sensors to identify pathogens that may harm Sargassum fusiforme, and initiating control measures if an excessive number of microorganisms or abnormalities are detected. It can also adjust the water flow speed to reduce physical interference with Sargassum fusiforme. The risk prediction and feedback module is based on machine learning algorithms and combines historical environmental data with current environmental conditions to predict the survival status of Sargassum fusiforme in the next 24 hours. If the prediction results show that environmental conditions may lead to a decrease in the survival rate of Sargassum fusiforme, the system will automatically trigger control measures.

[0007] In the above scheme, the multi-source data acquisition module includes: The real-time environmental parameter monitoring unit is used to collect physical, chemical, and biological parameters; the physical parameters include water temperature, salinity, and light intensity; the chemical parameters include dissolved oxygen and nutrient concentration; and the biological parameters include plankton density and abundance of attached microorganisms. The algal physiological data acquisition unit is used to acquire algal images and extract morphological features, and to measure photosynthetic activity using a fluorescence spectrometer; the morphological features include the length and diameter of the reproductive receptacle and the volume of the air sacs. The data fusion unit uses Kalman filtering to fuse sensor data; let the state vector be... Includes water temperature T, salinity S, and light intensity I; the observed values ​​are... The system noise is The observation noise is The state transition matrix is The control input matrix is The observation matrix is ; The state prediction equation is then: ; The observation equation is: .

[0008] In the above scheme, the gender recognition and physiological state analysis module includes: A gender classification model, built on a ResNet-18 convolutional neural network; The physiological stage determination unit determines whether the algae are in the reproductive stage based on the length of the reproductive receptacle and photosynthetic activity. If the length of the reproductive receptacle is greater than 5 mm and the photosynthetic activity is less than 0.6, it is determined to be in the reproductive stage; otherwise, it is determined to be in the vegetative growth stage.

[0009] In the above scheme, the output of the sex classification model is the probability that the algae are male. The calculation formula is: ; Where I is the input algal image, Let be the feature extraction function of the neural network, W be the weight matrix of the neural network, b be the bias vector, and σ be the sigmoid activation function.

[0010] In the above scheme, the dynamic environment control module includes: The environmental quality index calculation unit is used to calculate the environmental suitability index of male thalli. The parameter optimization unit uses an improved genetic algorithm to solve for the optimal combination of environmental parameters, with the objective being to minimize... Furthermore, the water temperature T satisfies 18℃≤T≤24℃, and the salinity S satisfies... Crossover probability Probability of mutation EQI target EQI is the target environmental suitability index. current This represents the current environmental suitability index.

[0011] In a further technical solution, the formula for calculating the environmental suitability index is: EQI=α·T′+β·S′+γ·I′+δ·DO′; Wherein, EQI is the environmental suitability index, T′, S′, I′, and DO′ are the normalized water temperature, salinity, light intensity, and dissolved oxygen parameters, respectively, and α, β, γ, and δ are the corresponding weights, with α+β+γ+δ=1, and during the reproductive period, α=0.3, β=0.2, γ=0.4, and δ=0.1.

[0012] In the above scheme, the biosecurity module includes: The microbial risk classification unit initiates ultraviolet sterilization or releases bacteriostatic agents based on the abundance M of attached microorganisms. Then the ultraviolet sterilization device will be activated; if Then it releases a slow-release antibacterial agent; The competitive biological inhibition unit uses a fuzzy control algorithm to adjust the water flow speed to drive away zooplankton.

[0013] In the above scheme, the formula for calculating the water flow velocity v is: ; in, e(t) is the error function. For the target planktonic density, The current plankton density, , , These are the proportional, integral, and differential coefficients, respectively.

[0014] In the above scheme, the risk prediction and feedback module includes: The survival rate prediction model is based on an LSTM neural network, with time-series environmental data as input. It contains water temperature, salinity, light intensity, and dissolved oxygen at different times; the hidden layer dimension is set to 64; the hidden state is obtained through LSTM unit calculation. The output layer weight matrix is The bias vector is ; Output the survival rate Y for the next 24 hours; The feedback control trigger mechanism activates emergency control measures when the predicted survival rate is lower than a set threshold. These emergency control measures include reducing light intensity, increasing water flow rate, and injecting nitrates.

[0015] A method for regulating the survival environment of male Sargassum fusiforme thallus based on the above system includes the following steps: S1. Collect environmental parameters and algal physiological data: Physical, chemical, and biological parameters are collected by deploying a distributed sensor array, and algal images are acquired using an underwater high-definition camera to extract algal morphological features. Photosynthetic activity is measured by fluorescence spectroscopy. The physical parameters include water temperature, salinity, and light intensity; the chemical parameters include dissolved oxygen and nutrient concentration; and the biological parameters include plankton density and abundance of attached microorganisms. S2. Identify the sex and physiological stage of algae: Based on the algal images obtained in S1, sex is identified using a convolutional neural network model; and further, the physiological stage of the algae is determined by combining the algal morphological features and photosynthetic activity data obtained in S1. S3. Dynamically regulate environmental parameters: Based on the physiological stage determined in S2, calculate the environmental suitability index of the male thallus, and then use an optimization algorithm to solve for the optimal combination of environmental parameters based on the environmental suitability index, and perform regulation. S4. Implement biocontrol: Based on the abundance of attached microorganisms collected in S1, classify the microbial risk and initiate corresponding control measures; at the same time, based on the plankton density collected in S1, adjust the water flow speed to suppress competing organisms. S5. Predicting Risks and Feedback Control: Based on the physical and chemical parameters collected in S1, predict the future survival rate of male Sargassum fusiforme thallus; when the predicted survival rate is lower than the set threshold, trigger emergency control measures.

[0016] Through the above technical solution, the analytical and regulatory system and method for the survival environment of male Sargassum fusiforme provided by the present invention have the following beneficial effects: 1. This system can distinguish the physiological differences between male and female algae, and precisely regulate the environment based on the reproductive structure, metabolic activity, and environmental tolerance characteristics of male algae. By real-time monitoring of physiological indicators of male algae (such as metabolic rate and photosynthetic efficiency) and dynamic adjustment of environmental parameters (such as light intensity, nutrient supply, and temperature), it meets the specific needs of male algae. This reduces the problem of delayed development or decreased reproductive cell activity in male algae due to uniform environmental conditions in traditional methods, significantly improving the reproductive success rate of male algae. It also enhances the genetic diversity of the population and promotes the improvement of large-scale aquaculture efficiency. 2. The system employs dynamic monitoring technology to collect various environmental parameters in real time (such as water temperature, light intensity, water flow velocity, and oxygen content), and adjusts environmental settings based on data changes to ensure the environment remains suitable for male algae growth. Through automated sensors and feedback mechanisms, the system can quickly respond to environmental changes, especially emergency adjustments under extreme weather conditions. This eliminates the drawbacks of traditional static and extensive control modes, improving the flexibility and accuracy of environmental control. Under extreme weather and sudden environmental changes, male algae can receive timely and effective protection, preventing growth and development from being hindered. 3. This system establishes a correlation model between male thalli and environmental factors, utilizing big data analysis and intelligent algorithms to analyze and predict the survival status and reproductive health of male thalli in real time. Based on the analysis results, the system can predict the risk of declining survival rates and adjust environmental parameters or initiate remedial measures through an automated feedback mechanism. Intelligent analysis and prediction avoid the blindness of traditional experience-based environmental parameter settings, improving the accuracy and predictability of the cultivation process. Timely identification of potential survival risks avoids delays in remedial measures due to information lag, thus improving the survival rate of male thalli. 4. The system incorporates a targeted biocontrol module, which, combined with environmental data analysis and the growth of male algae, effectively prevents and controls the invasion of pathogenic microorganisms. By regularly monitoring plankton and microbial populations in the water, the system automatically adjusts the aquatic environment, reducing interference with male algae. Through biocontrol measures, the system effectively reduces interference from zooplankton and pathogenic microorganisms, lowering the mortality rate of male algae. This improves the aquatic ecological environment, reduces the proliferation of pathogens and harmful organisms, and ensures that male algae can grow in a relatively healthy and stable environment. 5. This system integrates multiple technologies, including environmental monitoring, data analysis, intelligent feedback, and biosecurity modules, forming an integrated aquaculture management platform. Through a unified management interface, farmers can view and adjust various parameters in real time, simplifying the aquaculture management process. This improves the efficiency and accuracy of aquaculture management, reducing manual intervention and errors. The system has a high degree of automation, enabling rapid responses to real-time monitoring and control, thereby optimizing the aquaculture process and improving aquaculture efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0018] Figure 1 This is a schematic diagram of an analysis and regulation system for the survival environment of male Sargassum fusiforme thallus disclosed in an embodiment of the present invention; Figure 2 This is a schematic flowchart of a method for analyzing and regulating the survival environment of male Sargassum fusiforme thallus, as disclosed in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0020] This invention provides an analysis and regulation system for the survival environment of male Sargassum fusiforme thallus, such as... Figure 1 As shown, the system includes a multi-source data acquisition module, a gender recognition and physiological state analysis module, a dynamic environment control module, a biosecurity module, and a risk prediction and feedback module. All of these modules are electrically connected to the main control unit. The functions of each module are as follows:

[0021] 1. Multi-source data acquisition module The multi-source data acquisition module monitors various physical, chemical, and biological parameters in the habitat of Sargassum fusiforme in real time using multiple sensors installed in the environment (such as temperature, salinity, light, and dissolved oxygen sensors). All collected data is transmitted to the main control unit in real time for subsequent analysis and control. This module has high acquisition accuracy, ensuring that environmental changes are promptly reflected in the system, guaranteeing timely control.

[0022] The multi-source data acquisition module includes: (1) Real-time environmental parameter monitoring unit, used to collect physical, chemical and biological parameters; Physical parameters include water temperature (denoted by T, in °C), which reflects the temperature conditions of the living environment of male Sargassum fusiforme thallus. The physiological activities of the thallus are significantly affected by water temperature. The water temperature directly affects the metabolic rate, growth rate, and reproductive capacity of the thallus. Salinity (denoted by S, unit: psu) measures seawater salinity. This indicator affects physiological processes such as osmotic pressure balance in algae. Changes in salinity affect the water balance inside and outside algal cells, thus influencing algal growth and metabolism. When salinity is too high, water may seep out of the algal cells, leading to cell dehydration and impairing normal physiological functions. Conversely, when salinity is too low, excessive water absorption may cause cell rupture. Light intensity (denoted by I, in μmol / m²) 2 Light is the energy source for algal photosynthesis, and different light intensities have different effects on algal growth and development. Appropriate light intensity can promote algal photosynthesis, providing energy and material for algal growth and reproduction. However, excessive light may lead to algal photoinhibition, affecting the efficiency of photosynthesis and even causing photodamage; while insufficient light will limit algal photosynthesis, affecting its growth and development. Chemical parameters include dissolved oxygen (DO, in mg / L). Dissolved oxygen is essential for algal respiration, and its concentration affects the algal metabolism. Algae consume dissolved oxygen through respiration, oxidizing and decomposing organic matter to release energy for life activities. The level of dissolved oxygen directly affects the algal respiration and growth status. When dissolved oxygen is sufficient, algae can carry out respiration normally and maintain normal physiological functions; while when dissolved oxygen is insufficient, algae will experience respiratory difficulties, growth will be inhibited, and death may even occur. Nutrient concentration (represented by N, unit: μmol / L) is crucial for algal growth. Nitrogen and phosphorus are essential macroelements that participate in important physiological processes such as protein synthesis and nucleic acid metabolism. A suitable nutrient concentration can meet the needs of algal growth and reproduction, promoting algal growth and biomass accumulation. However, excessive nutrient concentration may lead to excessive algal growth and cause ecological problems such as red tides; while insufficient nutrient concentration will limit algal growth and development. Biological parameters include plankton density (denoted by D, in cells / mL), and a competitive or symbiotic relationship exists between plankton and the male Sargassum fusiforme thallus. Plankton and thallus may compete for resources such as light and nutrients, thus affecting the growth and survival of the thallus. Abundance of attached microorganisms (denoted by M, in units of CFU / cm³) 2 Microbial attachment may affect algal health;

[0023] (2) The algal physiological data acquisition unit uses an underwater high-definition camera to acquire algal images and extract morphological features; Morphological characteristics include: Length of genital support (using) The length of the receptacle (in mm) is part of the reproductive structure of Sargassum fusiforme, and its changes reflect the reproductive status of the algae. By measuring the length of the receptacle, one can understand the reproductive progress of the algae, determine whether the algae are in the reproductive stage, and the intensity of reproductive activity. For example, an increase in the length of the receptacle usually indicates that the reproductive activity of the algae is increasing, and the algae may be preparing to release gametes for reproduction.

[0024] Diameter (using) The diameter of the receptacle (in mm) is an important morphological indicator related to algal reproduction. Changes in the diameter of the receptacle can reflect the developmental level of the algal reproductive structure and are closely related to the algal's reproductive capacity. For example, an increase in the diameter of the receptacle may mean that the algal reproductive structure is more complete, capable of producing more gametes, thereby increasing the algal's reproductive success rate.

[0025] Airbag volume (in V) 气囊 The unit is cm. 3 Air sacs affect the buoyancy and other physiological functions of algae in seawater. The size of the air sacs influences the buoyancy of the algae in the water, thus affecting their distribution and movement. For example, increasing the air sac volume increases the buoyancy of the algae, allowing them to float more easily near the surface and obtain more sunlight, which is beneficial for photosynthesis and growth. Conversely, decreasing the air sac volume reduces the buoyancy of the algae, causing them to sink, which may affect their photosynthesis and survival. Photosynthetic activity was determined using a fluorescence spectrometer. (This ratio reflects the efficiency of photosynthesis in algae.) It is an indicator of the maximum photosynthetic efficiency of the algae, reflecting the functional state of the algal photosystem II. Under normal circumstances, The value is usually between 0.65 and 0.85. When algae are subjected to environmental stresses, such as high temperature, strong light, or nutrient deficiency... A decrease in the value indicates that photosynthesis in the algae is inhibited and the function of photosystem II is impaired. This can be achieved by monitoring... Changes in the algae can provide timely information about their photosynthetic status, offering a basis for regulating the aquaculture environment.

[0026] The data fusion unit uses Kalman filtering to fuse sensor data.

[0027] The various data collected by the multi-source data acquisition module (such as physicochemical parameters like water temperature, salinity, light intensity, and dissolved oxygen) are typically acquired by different types of sensors at different locations. These sensors may have different sources of error, such as sensor calibration errors, the effects of environmental changes, and device drift. The core task of data fusion using Kalman filtering is to fuse these scattered, noisy measurement results into a final estimate with higher accuracy.

[0028] Let the state vector be... Includes water temperature T, salinity S, and light intensity I; the observed values ​​are... The system noise is The observation noise is The state transition matrix is The control input matrix is The observation matrix is ; The state prediction equation is then: ; The observation equation is: .

[0029] 2. Gender Recognition and Physiological State Analysis Module The sex identification and physiological state analysis module utilizes image recognition and deep learning technologies to identify the sex and analyze the physiological state of Sargassum fusiforme. By collecting image data, algorithms (such as convolutional neural networks) are used to classify sex and assess physiological state, thereby determining whether male Sargassum fusiforme are in their optimal growth or reproductive period. This information is transmitted to the main control unit via electrical signals to guide subsequent environmental control operations.

[0030] The gender recognition and physiological state analysis module includes: (1) Gender classification model, constructed based on ResNet-18 convolutional neural network; ResNet-18 is a deep residual neural network with an 18-layer structure that can automatically extract high-level features from algal images. Through training, this network can learn feature patterns that distinguish between male and female Sargassum fusiforme algae. ResNet-18 effectively solves the vanishing gradient problem in deep neural networks by introducing residual connections. Its architecture consists of multiple convolutional layers, batch normalization layers, and fully connected layers, enabling it to automatically extract spatial features from input data (such as images or other biological features).

[0031] Specifically, first, the input data is standardized to fit the requirements of the neural network. This includes image normalization or standardization of biometric data. Further, using biometric data with gender labels (such as images or other morphological features), the model weights are optimized through forward and backpropagation to reduce errors. After training, the model's performance is evaluated using validation and test sets to ensure it can accurately distinguish between individuals of different genders.

[0032] By using a ResNet-18-based convolutional neural network, the model can efficiently learn and extract complex biological sex features, and is especially suitable for identifying the sex of target individuals under complex environmental conditions. It has strong generalization ability and robustness.

[0033] In this system, the input algal image I undergoes operations such as convolutional layers, pooling layers, and fully connected layers in a ResNet-18 network to extract discriminative feature vectors. Then, the Sigmoid activation function maps the feature vectors to a probability range of 0-1, outputting the probability that the algae is male. This sex classification model can accurately identify male Sargassum fusiforme thallus, providing a foundation for subsequent sex-specific regulation.

[0034] Let the input algal image be I, the weight matrix of the neural network be W, the bias vector be b, and the feature extraction function after passing through the convolutional neural network be... Then, the Sigmoid activation function is used. Output gender probability The formula is as follows: ; (2) Physiological stage determination unit: the algae are determined to be in the reproductive stage based on the length of the reproductive receptacle and photosynthetic activity; if >5mm and If the value is less than 0.6, it is considered to be in the reproductive period; otherwise, it is considered to be in the vegetative growth period.

[0035] This rule is based on threshold judgment using characteristic measurement data of organisms, and incorporates relevant research findings in the field of biology, ensuring the accuracy of the judgment rule.

[0036] Specifically, firstly, real-time acquisition of individual... Data is obtained by acquiring relevant parameters of an organism through sensors or other measurement methods. Furthermore, the acquired data... The data is compared with the judgment rules to determine whether an individual has entered the reproductive period. Finally, by outputting physiological stage information, support is provided for subsequent analysis, especially for the monitoring and management of reproductive behavior.

[0037] By employing simple yet effective threshold rules, the physiological stage determination module can accurately and in real time identify the physiological state of an individual, facilitating the tracking and management of biological population dynamics. Furthermore, this method does not rely on complex model calculations and can operate efficiently in low-resource environments.

[0038] Although the sex classification and physiological stage determination modules are independent, through proper integration, they can provide comprehensive analytical results for the physiological state and sex identification of the target organism. The sex classification model provides the sex information of the target organism, while the physiological stage determination module... The data provides information on the physiological stages of an individual. Combining these two aspects allows for a comprehensive and accurate analysis of the physiological characteristics of the target organism, thereby providing strong data support for fields such as ecological monitoring and reproductive management.

[0039] By seamlessly connecting these two modules, the system can not only accurately identify sex, but also dynamically adjust and respond based on the individual's physiological state during real-time monitoring. For example, if an organism is detected to be in its reproductive period, special management measures (such as reproduction control and resource allocation) can be implemented.

[0040] After these operations, the algal image is transformed into a vector with high-dimensional feature information, which contains high-level features that can distinguish between male and female algal cells.

[0041] 3. Dynamic Environment Control Module The dynamic environmental control module calculates the ideal environmental parameters required by Sargassum fusiforme based on multi-source data and information on sex and physiological status received by the main control unit, and then dynamically controls these parameters. For example, water temperature, salinity, light intensity, and dissolved oxygen concentration can all be adjusted in real time using regulating devices (such as heaters, brine pumps, and light regulators). This module, through a closed-loop control system, ensures that environmental conditions are continuously maintained within the optimal range, promoting the growth and reproduction of male Sargassum fusiforme.

[0042] The dynamic environment control module includes: (1) Environmental Quality Index Calculation Unit, used to calculate the environmental suitability index of male thalli; the environmental suitability index (EQI) is a key indicator for assessing the suitability of the aquaculture environment. By normalizing multiple environmental factors such as water temperature, salinity, light intensity and dissolved oxygen, and combining the weight coefficients of each factor, a dimensionless quantitative value is calculated to represent the current environmental suitability for male Sargassum fusiforme thalli.

[0043] The formula for calculating the environmental suitability index is: EQI=α·T′+β·S′+γ·I′+δ·DO′; Wherein, EQI is the environmental suitability index, T′, S′, I′, and DO′ are the normalized water temperature, salinity, light intensity, and dissolved oxygen parameters, respectively, and α, β, γ, and δ are the corresponding weights, with α+β+γ+δ=1, and during the reproductive period, α=0.3, β=0.2, γ=0.4, and δ=0.1.

[0044] (2) The parameter optimization unit uses an improved genetic algorithm to solve for the optimal combination of environmental parameters, with the objective being to minimize Furthermore, the water temperature T satisfies 18℃≤T≤24℃, and the salinity S satisfies... Crossover probability Probability of mutation EQI target EQI is the target environmental suitability index. current This represents the current environmental suitability index. Genetic algorithms, by simulating natural selection and evolution, continuously iterate and optimize the combination of environmental parameters to obtain the optimal environmental regulation scheme.

[0045] In genetic algorithms, individuals in the population are represented by chromosomes, and each chromosome corresponds to a set of environmental parameter combinations. The fitness function is: The population is continuously optimized through selection, crossover, mutation, and other operations until the optimal solution is found.

[0046] 4. Biocontrol Module The biocontrol module monitors the microbial population in the water, using sensors to identify pathogens that may harm Sargassum fusiforme. If an excessive number of microorganisms or abnormalities are detected, it activates control measures such as ultraviolet lamps, sterilization devices, or the administration of biological antibacterial agents to promptly reduce the threat of pathogens. Furthermore, this module can regulate water flow speed to minimize physical disturbance to Sargassum fusiforme and ensure its healthy growth.

[0047] The biosecurity module includes: (1) Microbial risk classification unit, based on the abundance M of attached microorganisms, initiates ultraviolet sterilization or releases bacteriostatic agents, if Then the ultraviolet sterilization device will be activated; if Then, a slow-release antibacterial agent (at a concentration of 0.1 mg / L) is released to inhibit microbial growth. This measure effectively controls microbial damage and maintains the health of the algae.

[0048] Monitoring the abundance (M) of attached microorganisms can assess the potential risk of microorganisms to the male thallus of Sargassum fusiforme. When the abundance of attached microorganisms exceeds [a certain threshold], [the risk is assessed]. When the abundance of attached microorganisms reaches a certain level, it indicates a high number of microorganisms that may pose a serious threat to the algae. At this point, activating the ultraviolet sterilization device utilizes the bactericidal effect of ultraviolet light to kill the microorganisms attached to the algae surface, reducing their impact on the algae. When the abundance of attached microorganisms is within a certain range... At this stage, the number of microorganisms is relatively small, but they can still have a certain impact on the algae. In this case, releasing a slow-release antibacterial agent can inhibit the growth and reproduction of microorganisms by slowly releasing antibacterial components, thereby protecting the health of the algae. This microbial risk classification and control measure can effectively control the harm of microorganisms to the male algae of Sargassum fusiforme and maintain the microbial balance of the cultivation environment.

[0049] (2) Competitive biological inhibition unit: fuzzy control algorithm is used to adjust the water flow speed to drive away zooplankton and reduce their competition for algae.

[0050] The formula for calculating the water flow velocity v is: ; in, e(t) is the error function. For the target planktonic density, The current plankton density, , , These are the proportional, integral, and differential coefficients, respectively.

[0051] Fuzzy control algorithms are control methods based on fuzzy logic, suitable for handling complex systems with uncertainty and fuzziness. In this system, a target plankton density is set. The concentration is 50 cells / mL, and the current planktonic density is... The error function e(t) is obtained by comparing it with the target value. Based on the magnitude and trend of the error function e(t), the water flow velocity v is adjusted using a fuzzy control algorithm to drive away zooplankton and reduce their competition and harm to the male algae of Sargassum fusiforme. (Proportional coefficient) Integral coefficient used to adjust the water flow velocity based on the current error. Differential coefficients are used to eliminate the cumulative effect of errors. This is used to predict the changing trend of errors, thereby achieving precise control of water flow velocity. By adjusting the water flow velocity through fuzzy control algorithms, zooplankton can be effectively driven away, reducing their competition and damage to algae, and protecting the growth and reproduction of male Sargassum fusiforme algae.

[0052] 5. Risk Prediction and Feedback Module The risk prediction and feedback module, based on machine learning algorithms and combining historical environmental data with current environmental conditions, predicts the survival status of Sargassum fusiforme within the next 24 hours. It uses techniques such as Long Short-Term Memory (LSTM) neural networks to analyze time-series data and predict the impact of environmental changes on Sargassum fusiforme survival rates. Once the prediction results indicate that environmental conditions may lead to a decrease in Sargassum fusiforme survival rates, the system automatically triggers control measures, such as adjusting environmental factors like light and temperature, and provides real-time feedback to other modules for collaborative adjustments.

[0053] LSTM neural networks are deep learning models suitable for time series forecasting, capable of capturing long-term dependencies in time series data. In this step, the model's input is historical growth data of male Sargassum fusiforme thalassioides, including environmental factors such as light intensity, water flow velocity, microbial abundance, and plankton density, as well as their impact on thalassioide survival. After training, the LSTM model can predict the thalassioide survival rate over a future period based on this input data. The predicted survival rate is output as a real-time updated value, reflecting the impact of current environmental conditions on thalassioide health.

[0054] The risk prediction and feedback module includes: (1) Survival prediction model, based on LSTM neural network, with time series environmental data as input to the neural network. It contains water temperature, salinity, light intensity, and dissolved oxygen at different times; the hidden layer dimension is set to 64; the hidden state is obtained through LSTM unit calculation. The output layer weight matrix is The bias vector is Output the survival rate Y for the next 24 hours; Building an LSTM neural network involves the following steps: Step 5.1: Input timing environment data. The input data is timing environment data. It contains environmental parameters such as water temperature, salinity, light intensity, and dissolved oxygen at different times. These parameters are key factors affecting the growth and survival of male Sargassum fusiforme thalassemblages. By monitoring and recording these parameters in real time, a complete time-series dataset can be constructed for training an LSTM model.

[0055] Step 5.2: Set the hidden layer dimension to 64. The hidden layer is the part of the LSTM network responsible for processing and storing information. Its dimension determines the complexity and expressive power of the network. In this system, 64 is chosen as the hidden layer dimension based on a comprehensive consideration of model performance and computing resources. A larger hidden layer dimension can improve the expressive power of the model, but it will also increase the amount of computation and training time; a smaller hidden layer dimension may lead to insufficient expressive power of the model and affect the prediction accuracy.

[0056] Step 5.3: Obtain the hidden state through LSTM unit calculation. The LSTM unit is the core component of the LSTM network. It controls the flow and storage of information through input gates, forget gates, and output gates. Specifically, the input gate determines how much new information is written into the cell state at the current time step; the forget gate determines how much information in the cell state is retained or forgotten; and the output gate determines how much information in the cell state is output as the hidden state at the current time step. Through these gating mechanisms, the LSTM unit can effectively handle long-term dependencies in long sequence data.

[0057] Step 5.4: Let the output layer weight matrix be... The bias vector is The output layer is the last layer of the LSTM network; it contains the hidden state. This is converted into the final predicted output. Weight matrix. and bias vector These are the trainable parameters of the output layer, which are optimized during training using the backpropagation algorithm to minimize the error between the predicted output and the actual label.

[0058] Step 5.5: Output the survival rate Y for the next 24 hours. Through training and optimization of the LSTM network, the model can learn the complex relationship between environmental parameters and the survival rate of male Sargassum fusiforme thalassioides. In practical applications, the current time-series environmental data is input. The LSTM network can predict the survival rate Y of male Sargassum fusiforme thallus within the next 24 hours, providing an important basis for aquaculture management decisions.

[0059] (2) Feedback control triggering mechanism: when the predicted survival rate is lower than the set threshold, emergency control measures are initiated. Emergency control measures include reducing light intensity, increasing water flow speed, and injecting nitrates.

[0060] In this embodiment, when predicting survival rate When this occurs, an emergency control protocol is activated. Setting 85% as the predicted survival rate threshold is based on a comprehensive consideration of the growth characteristics of male Sargassum fusiforme thallus and cultivation experience. When the predicted survival rate is below 85%, it indicates that the cultivation environment may be putting significant stress on the thallus's survival, requiring timely control measures to prevent mass mortality and ensure cultivation efficiency.

[0061] In emergency control measures, reducing light intensity specifically means reducing the light intensity to 200 μmol / m². 2 Light intensity is a crucial factor affecting the photosynthesis and growth of male Sargassum fusiforme thalassemblages. When the predicted survival rate is low, reducing light intensity can alleviate photosynthetic stress on the thalassemblages, preventing photoinhibition and photodamage, and promoting recovery and growth. When the predicted survival rate falls below a threshold, it may be due to excessive or damaged photosynthesis caused by excessive light. In this case, the system will adjust the light intensity to reduce light exposure and prevent damage to the thalassemblages caused by excessive light.

[0062] Increasing the water flow velocity specifically involves raising it to 0.8 m / s. This increased velocity improves oxygen supply and nutrient exchange in the aquaculture water, while also dispersing potentially harmful plankton and microorganisms, thus providing a more suitable growth environment for the algae. By optimizing the water flow velocity, the algal growth environment is improved, thereby increasing the survival rate.

[0063] The injected nitrate concentration was 0.05 mg / L. Nitrate is one of the essential nutrients for the growth of male Sargassum fusiforme thallus. It participates in the metabolic processes of the thallus, promoting its growth and recovery. Injecting nitrate during emergency regulation can enhance the thallus's stress resistance and prolong the sperm release cycle of male algae. When the growth status of male algae declines, the thallus may experience decreased stress resistance and reduced protein synthesis due to nitrogen deficiency. In such cases, injecting nitrate helps promote the thallus's metabolism and extend the sperm release cycle.

[0064] All modules collaborate closely with the main control unit via electrical connections and data transmission. The main control unit aggregates information from each module, performs comprehensive analysis using intelligent algorithms, makes rapid decisions, and sends instructions to various control devices. This structure ensures that the system can simultaneously monitor and regulate the survival environment of Sargassum fusiforme across multiple dimensions, exhibiting high efficiency and rapid response. Each module plays a crucial role in data sharing and collaborative operation, guaranteeing the system's high stability and adaptability under complex environmental changes. By adjusting environmental parameters in real time, the system effectively improves the growth rate, survival rate, and reproductive efficiency of Sargassum fusiforme, while also reducing disease risks and ensuring the sustainability of the ecological environment.

[0065] A method for regulating the survival environment of male Sargassum fusiforme thallus based on the above system, such as... Figure 2 As shown, it includes the following steps: S1. Collect environmental parameters and algal physiological data: Collect physical, chemical and biological parameters by deploying a distributed sensor array, and acquire algal images through an underwater high-definition camera device to extract algal morphological characteristics. Measure photosynthetic activity through fluorescence spectroscopy. Physical parameters include water temperature, salinity and light intensity; chemical parameters include dissolved oxygen and nutrient concentration; biological parameters include plankton density and abundance of attached microorganisms.

[0066] The various data collected by the multi-source data acquisition module (such as physicochemical parameters like water temperature, salinity, light intensity, and dissolved oxygen) are typically acquired by different types of sensors at different locations. These sensors may have different sources of error, such as sensor calibration errors, the effects of environmental changes, and device drift. The core task of data fusion using Kalman filtering is to fuse these scattered, noisy measurement results into a final estimate with higher accuracy.

[0067] S2. Identify the sex and physiological stage of algae: Based on the algal images obtained in S1, sex is identified using a convolutional neural network model; and further, the physiological stage of the algae is determined by combining the algal morphological features and photosynthetic activity data obtained in S1.

[0068] Furthermore, the extracted feature vector is passed through a fully connected layer to obtain a new representation. Next, the network linearly combines this feature vector with the weight matrix and bias vector to obtain a new value, which is then mapped using the Sigmoid activation function. The specific formula is as follows: ; in, It represents the probability that the algae are male. It is the feature vector of the algal body image extracted by the ResNet-18 network. It is the weight matrix of the fully connected layer, which contains the parameters learned during training. It is a bias vector used to adjust the network's output. It is the Sigmoid activation function, defined as: The sigmoid function maps the result of a linear combination to a probability range of 0 to 1, representing the probability that the algae are male. If... A value close to 1 indicates that the algae is male; a value close to 0 indicates that the algae is female.

[0069] During training, the network is trained using a large amount of labeled algal images. The backpropagation algorithm is used to continuously adjust the weight matrix and bias vector, thus improving the model's output. The gender value is close to the actual label value. Commonly used optimization algorithms include stochastic gradient descent (SGD) and the Adam optimizer.

[0070] Through the above steps, the sex classification model transforms the input algal image into a sex probability. The ResNet-18 network automatically extracts high-level features from the image, capturing complex visual patterns, while the Sigmoid activation function provides a concise probability output, aiding in determining the sex of the algae. This structure efficiently processes image data and, through deep learning methods, can not only identify significant sex differences but also extract meaningful features from subtle, biologically specific differences.

[0071] S3. Dynamically regulate environmental parameters: Based on the physiological stage determined in S2, calculate the environmental suitability index of the male thallus, and then use an optimization algorithm to solve for the optimal combination of environmental parameters based on the environmental suitability index, and implement regulation.

[0072] EQI is an index that quantitatively assesses the suitability of the living environment for male Sargassum fusiforme thallus, taking into account multiple environmental parameters such as water temperature, salinity, light intensity, and dissolved oxygen. Each environmental parameter is normalized and converted into a dimensionless value. Then, each parameter is assigned a weight according to its influence on thallus growth and reproduction, and finally, the weighted sum is obtained to obtain the EQI. During the reproductive period, light intensity has a significant impact on thallus reproduction, so it is assigned a high weight γ=0.4; water temperature and salinity also have an important impact on thallus physiological activities, assigned weights α=0.3 and β=0.2 respectively; dissolved oxygen is crucial for thallus respiration, assigned a weight δ=0.1. By calculating the EQI, the suitability of the current cultivation environment for male Sargassum fusiforme thallus can be intuitively understood, providing a quantitative indicator for environmental control.

[0073] An improved genetic algorithm is a global optimization algorithm that simulates the biological evolution process and is used to solve complex optimization problems. In this system, the objective of the improved genetic algorithm is to minimize the current environmental fitness index. With the target environment suitability index The difference between them, i.e., minimizing By setting constraints on water temperature (T) and salinity (S), the optimized combination of environmental parameters is ensured to remain within a suitable range. Crossover probability. This indicates that in the crossover operation of a genetic algorithm, there is an 80% probability of crossover occurring, and the mutation probability... This indicates a 5% probability of mutation. Through operations such as selection, crossover, and mutation, the genetic algorithm can continuously explore and optimize within the search space, ultimately finding the optimal combination of environmental parameters that makes the environmental quality index closest to the target value, thus achieving precise control of the aquaculture environment.

[0074] S4. Implement biocontrol: Based on the abundance of attached microorganisms collected in S1, classify the microbial risk and initiate corresponding control measures; at the same time, based on the plankton density collected in S1, adjust the water flow speed to suppress competing organisms.

[0075] Microbial risk grading and competitive biotic inhibition work synergistically to influence the growth environment of male Sargassum fusiforme thalli. Microbial risk grading reduces microbial harm to the thalli by controlling microbial abundance, while competitive biotic inhibition reduces competition and damage from plankton by adjusting water flow velocity. Although the control methods for microorganisms and zooplankton differ, the ultimate goal is to maintain the growth and reproduction environment of male Sargassum fusiforme thalli free from external threats. Through their respective control mechanisms, they work together to ensure the health of the thalli and enhance the stability of the aquaculture environment.

[0076] S5. Predicting Risks and Feedback Control: Based on the physical and chemical parameters collected in S1, predict the future survival rate of male Sargassum fusiforme thallus; when the predicted survival rate is lower than the set threshold, trigger emergency control measures.

[0077] In one possible implementation, time-series environmental data is first input into the LSTM network. This data includes environmental parameters such as water temperature, salinity, light intensity, and dissolved oxygen at different times, typically monitored and recorded in real time by sensors. Ensuring the temporal sequence of the data is crucial for constructing a complete time-series dataset. Each set of input data represents the environmental state at the current moment, directly affecting the growth and survival of male Sargassum fusiforme thalassemblages. This dataset requires preprocessing, such as standardization or normalization, to ensure scale consistency of the input data and improve the stability of model training.

[0078] Furthermore, after training and optimization, the LSTM model can predict the survival rate (Y) of male Sargassum fusiforme thalassioides over the next 24 hours, given the current environmental data. Because LSTM can learn the time dependencies in the data, the model can accurately predict future survival rates based on historical environmental parameters. This prediction result is of great significance for aquaculture management, helping managers to take appropriate measures based on the predicted survival rate, such as adjusting environmental parameters and optimizing aquaculture conditions.

[0079] In one possible implementation, if the predicted survival rate is below 85%, the light intensity is promptly reduced to 200 μmol / m². 2Light intensity is a key factor affecting algal photosynthesis. When light intensity is too high, male Sargassum fusiforme thalassemblages may experience photoinhibition, leading to reduced photosynthetic efficiency and even photodamage to cells. Therefore, reducing light intensity can alleviate this problem. Reducing light intensity can be achieved by adjusting the lighting system or covering with shade netting.

[0080] When the predicted survival rate is below 85%, increase the water flow velocity to 0.8 m / s. This can be achieved by adjusting the water pump or adding a water flow guiding device. Increasing the water flow velocity helps optimize the oxygen supply and nutrient exchange in the water, improving the metabolic efficiency of the algae. At the same time, accelerating the water flow helps to remove plankton and microorganisms around the algae, reducing the accumulation of these harmful substances and alleviating the growth stress on the algae.

[0081] In emergency control measures, nitrates are injected into the water at a concentration of 0.05 mg / L. Nitrates play a crucial role in the metabolism of algae, particularly in male algae, promoting energy metabolism, enhancing stress resistance, increasing sperm cell synthesis, and helping the algae recover vitality. This step can be implemented using a nutrient solution injection device or by dissolving the nitrate directly in the aquaculture water.

[0082] All these measures are complementary and synergistic. For example, reducing light intensity can decrease photoinhibition, increasing water flow velocity can increase oxygen supply and nutrient exchange, and injecting nitrates can physiologically improve the metabolic rate and recovery capacity of the algae, promoting the synthesis and release of sperm cells. By adjusting environmental conditions and providing necessary nutritional support, these measures help the male Sargassum fusiforme algae overcome the current unfavorable environment, thereby extending the sperm release cycle.

[0083] Although these regulatory measures mainly involve environmental and nutritional adjustments, to quantify their impact, we can use the following formula to describe the changes in survival rates before and after the regulation: ; in, Indicates the survival rate after regulation; To predict survival rate; This indicates the gain in survival rate due to light regulation; This indicates the gain of flow rate regulation on survival rate; This indicates that supplementing with nitrates improves the survival rate.

[0084] This formula allows us to estimate the actual impact of each control measure on the survival rate, thereby optimizing breeding conditions to improve the survival rate.

[0085] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A system for analyzing and regulating the survival environment of male Sargassum fusiforme thallus, characterized in that, It includes a multi-source data acquisition module, a gender recognition and physiological state analysis module, a dynamic environment control module, a biocontrol module, and a risk prediction and feedback module. The multi-source data acquisition module, gender recognition and physiological state analysis module, dynamic environment control module, biocontrol module, and risk prediction and feedback module are all electrically connected to the main control unit. The multi-source data acquisition module monitors various physical, chemical, and biological parameters in the habitat of Sargassum fusiforme in real time through multiple sensors installed in the environment. All collected data is transmitted to the main control unit in real time for subsequent analysis and control. The gender identification and physiological state analysis module uses image recognition and deep learning technology to identify the gender and analyze the physiological state of Sargassum fusiforme. The dynamic environment control module calculates the ideal environmental parameters required by Sargassum fusiforme based on the multi-source data and gender and physiological state information received by the main control unit, and performs dynamic control. The biocontrol module is responsible for monitoring the microbial situation in the water, using sensors to identify pathogens that may harm Sargassum fusiforme, and initiating control measures if an excessive number of microorganisms or abnormalities are detected. It can also adjust the water flow speed to reduce physical interference with Sargassum fusiforme. The risk prediction and feedback module is based on machine learning algorithms and combines historical environmental data with current environmental conditions to predict the survival status of Sargassum fusiforme in the next 24 hours. If the prediction results show that environmental conditions may lead to a decrease in the survival rate of Sargassum fusiforme, the system will automatically trigger control measures.

2. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 1, characterized in that, The multi-source data acquisition module includes: The real-time environmental parameter monitoring unit is used to collect physical, chemical, and biological parameters; the physical parameters include water temperature, salinity, and light intensity; the chemical parameters include dissolved oxygen and nutrient concentration; and the biological parameters include plankton density and abundance of attached microorganisms. The algal physiological data acquisition unit is used to acquire algal images and extract morphological features, and to measure photosynthetic activity using a fluorescence spectrometer; the morphological features include the length and diameter of the reproductive receptacle and the volume of the air sacs. The data fusion unit uses Kalman filtering to fuse sensor data; let the state vector be... Includes water temperature T, salinity S, and light intensity I; the observed values ​​are... The system noise is The observation noise is The state transition matrix is The control input matrix is The observation matrix is ; The state prediction equation is then: ; The observation equation is: .

3. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 1, characterized in that, The gender recognition and physiological state analysis module includes: A gender classification model, built on a ResNet-18 convolutional neural network; The physiological stage determination unit determines whether the algae are in the reproductive stage based on the length of the reproductive receptacle and photosynthetic activity. If the length of the reproductive receptacle is greater than 5 mm and the photosynthetic activity is less than 0.6, it is determined to be in the reproductive stage; otherwise, it is determined to be in the vegetative growth stage.

4. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 3, characterized in that, The output of the sex classification model is the probability that the algae are male. The calculation formula is: ； Where I is the input algal image, Let be the feature extraction function of the neural network, W be the weight matrix of the neural network, b be the bias vector, and σ be the sigmoid activation function.

5. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 1, characterized in that, The dynamic environment control module includes: The environmental quality index calculation unit is used to calculate the environmental suitability index of male thalli. The parameter optimization unit uses an improved genetic algorithm to solve for the optimal combination of environmental parameters, with the objective being to minimize... Furthermore, the water temperature T satisfies 18℃≤T≤24℃, and the salinity S satisfies... Crossover probability Probability of mutation EQI target EQI is the target environmental suitability index. current This represents the current environmental suitability index.

6. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 5, characterized in that, The formula for calculating the environmental suitability index is as follows: EQI=α·T′+β·S′+γ·I′+δ·DO′; Wherein, EQI is the environmental suitability index, T′, S′, I′, and DO′ are the normalized water temperature, salinity, light intensity, and dissolved oxygen parameters, respectively, and α, β, γ, and δ are the corresponding weights, with α+β+γ+δ=1, and during the reproductive period, α=0.3, β=0.2, γ=0.4, and δ=0.

1.

7. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 1, characterized in that, The biosecurity module includes: The microbial risk classification unit initiates ultraviolet sterilization or releases bacteriostatic agents based on the abundance M of attached microorganisms. Then the ultraviolet sterilization device will be activated; if Then it releases a slow-release antibacterial agent; The competitive biological inhibition unit uses a fuzzy control algorithm to adjust the water flow speed to drive away zooplankton.

8. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 7, characterized in that, The formula for calculating the water flow velocity v is: ； in, e(t) is the error function. For the target planktonic density, The current plankton density, , , These are the proportional, integral, and differential coefficients, respectively.

9. The analysis and regulation system for the survival environment of male Sargassum fusiforme thallus according to claim 1, characterized in that, The risk prediction and feedback module includes: The survival rate prediction model is based on an LSTM neural network, with time-series environmental data as input. It contains water temperature, salinity, light intensity, and dissolved oxygen at different times; the hidden layer dimension is set to 64; the hidden state is obtained through LSTM unit calculation. The output layer weight matrix is The bias vector is ; Output the survival rate Y for the next 24 hours; The feedback control trigger mechanism activates emergency control measures when the predicted survival rate is lower than a set threshold. These emergency control measures include reducing light intensity, increasing water flow rate, and injecting nitrates.

10. A method for regulating the survival environment of male Sargassum fusiforme thallus according to any one of claims 1 to 9, characterized in that, Includes the following steps: S1. Collect environmental parameters and algal physiological data: Physical, chemical, and biological parameters are collected by deploying a distributed sensor array, and algal images are acquired using an underwater high-definition camera to extract algal morphological features. Photosynthetic activity is measured by fluorescence spectroscopy. The physical parameters include water temperature, salinity, and light intensity; the chemical parameters include dissolved oxygen and nutrient concentration; and the biological parameters include plankton density and abundance of attached microorganisms. S2. Identify the sex and physiological stage of algae: Based on the algal images obtained in S1, sex is identified using a convolutional neural network model; and further, the physiological stage of the algae is determined by combining the algal morphological features and photosynthetic activity data obtained in S1. S3. Dynamically regulate environmental parameters: Based on the physiological stage determined in S2, calculate the environmental suitability index of the male thallus, and then use an optimization algorithm to solve for the optimal combination of environmental parameters based on the environmental suitability index, and perform regulation. S4. Implement biocontrol: Based on the abundance of attached microorganisms collected in S1, classify the microbial risk and initiate corresponding control measures; at the same time, based on the plankton density collected in S1, adjust the water flow speed to suppress competing organisms. S5. Predicting Risks and Feedback Control: Based on the physical and chemical parameters collected in S1, predict the future survival rate of male Sargassum fusiforme thallus; when the predicted survival rate is lower than the set threshold, trigger emergency control measures.

Images