Artificial Intelligence-Based Digital Construction Methods and Systems for Marine Ranching

Abstract

This invention relates to a method and system for the digital construction of marine ranches based on artificial intelligence. The method includes real-time monitoring of plankton in the marine ranch, acquiring water images using image recognition technology and establishing a dynamic database to periodically store and update plankton-related data. Based on the monitoring data, a water quality assessment model is established to analyze the interrelationships between plankton species, density, and water quality parameters. A flow change model is established by integrating factors such as water flow velocity and direction to determine the impact of water flow on plankton. By simulating the interaction between farmed organisms and plankton, a primary aquaculture optimization plan is formulated. The output results of the water quality assessment and flow change model are combined to predict aquaculture trends in real time and adjust management strategies accordingly. This solution effectively improves the intelligent management level of marine ranches, achieves dynamic and scientific management of the aquaculture environment, provides strong support for the healthy growth of farmed organisms, and promotes the sustainable development of marine ranches.

Description

Technical Field

[0001] This invention relates to the field of marine ranching, specifically to a method and system for the digital construction of marine ranches based on artificial intelligence. Background Technology

[0002] With the increasing global demand for aquaculture, marine ranching, as a new and sustainable aquaculture model, is receiving increasing attention. However, traditional marine ranching management relies mainly on manual monitoring and experience-based judgment, making it difficult to achieve scientific and systematic management. This method is not only inefficient but also often leads to resource waste and ecological imbalance. With the development of technology, especially the advancement of artificial intelligence and data analysis, marine ranching management urgently needs to transform towards digitalization and intelligence to improve aquaculture efficiency and ecological health.

[0003] Currently, monitoring of marine ranches relies heavily on manual sampling and observation, making real-time data acquisition and analysis difficult. Furthermore, while changes in water quality parameters directly impact the growth and reproduction of farmed organisms, understanding their patterns often depends on experience rather than scientific data. Simultaneously, the influence of water flow patterns on phytoplankton distribution and the aquaculture environment is frequently overlooked, hindering effective adjustments to aquaculture management strategies. Therefore, despite the crucial role of marine ranches in sustainable aquaculture, traditional management methods are insufficient to meet the demands of modern, intelligent development. Summary of the Invention

[0004] This invention addresses the technical problems existing in the prior art by providing a method and system for the digital construction of marine ranches based on artificial intelligence.

[0005] The technical solution of this invention to solve the above-mentioned technical problems is as follows: a method for digital construction of marine ranches based on artificial intelligence, the method comprising:

[0006] Based on image recognition, real-time monitoring of plankton-related data in marine ranches is conducted, and a dynamic database is established to regularly store and update the plankton-related data obtained in the dynamic database.

[0007] Based on the monitored phytoplankton-related data, a water quality assessment model was established to analyze the relationship between phytoplankton species, density and water quality parameters. At the same time, water flow patterns were analyzed to establish a flow change model and determine the impact of water flow on phytoplankton.

[0008] Simulate the interaction between cultured organisms and plankton in a marine ranch, and establish a primary aquaculture optimization scheme that focuses solely on plankton control;

[0009] By integrating the outputs of the water quality assessment model and the flow change model, the current aquaculture trend of the marine ranch is predicted in real time. The primary aquaculture optimization scheme is integrated, the development and changes of the cultured organisms are analyzed, and the primary aquaculture optimization scheme is adjusted based on the results of the development and changes of the cultured organisms to generate the final aquaculture optimization scheme.

[0010] As a further aspect of the present invention, the real-time monitoring of plankton-related data in marine ranches and the establishment of a dynamic database specifically include:

[0011] Regularly acquire water body images and add time stamps to the images based on the acquisition time;

[0012] The acquired images are analyzed to identify plankton and determine their species and density.

[0013] A dynamic database architecture tailored to the needs of marine ranching was established, and the obtained plankton-related data, along with the time stamps of the corresponding water images, were stored in the dynamic database.

[0014] As a further aspect of the present invention, the establishment of a water quality assessment model to analyze the relationship between plankton species, density, and water quality parameters, and to analyze water flow patterns, establish a flow change model, and determine the impact of water flow on plankton, specifically includes:

[0015] Establish a water quality assessment model, analyze the relationship between phytoplankton species, density and water quality parameters, determine how phytoplankton species and density affect water quality parameters, and construct an ecological network model between phytoplankton and water quality parameters;

[0016] By integrating water flow data and combining it with plankton monitoring data, a flow change model was established to assess the impact of water flow on plankton.

[0017] By combining the results of the water quality assessment model with the output of the flow change model, the current trend of water quality change and the changes in plankton species and density are identified, and a water quality status report is generated.

[0018] As a further aspect of the present invention, the analysis of the relationship between plankton species, density, and water quality parameters, and the determination of how plankton species and density affect water quality parameters, specifically includes:

[0019] ;

[0020] in, The overall impact score reflects the degree of influence of plankton on water quality parameters. The total number of planktonic species. For the first The density of plankton, For the first The species index of planktonic organisms, with values ​​ranging from 1 to 2. , For the first The basic influence coefficients of planktonic organisms on target water quality parameters The impact index of plankton density, The impact index of plankton species;

[0021] The assessment of the impact of water flow on plankton specifically includes:

[0022] ;

[0023] ;

[0024] in, For the first The rate of change in the density of planktonic organisms For the first The inherent growth rate of the plankton species For the first The environmental carrying capacity of plankton The function representing the effect of water flow on plankton is determined by the speed and direction of the water flow. The constant represents the baseline for the impact of water flow on plankton. The index represents the nonlinear exponent affecting the effect of water flow intensity on phytoplankton growth, and the velocity field of the water flow is represented. This is a symbolic function used to indicate the directionality of water flow, i.e.:

[0025] .

[0026] As a further aspect of the present invention, the simulation of the interaction between cultured organisms and plankton in a marine ranch, establishing a primary aquaculture optimization scheme targeting only plankton control, specifically includes:

[0027] Extract plankton monitoring data, water quality data, and aquaculture data from a dynamic database;

[0028] Several simulation scenarios were established, taking into account different plankton densities, species and water quality conditions, and the growth, reproduction and health status of cultured organisms were recorded under different simulation scenarios.

[0029] The simulation results were extracted to analyze the growth rate, reproduction rate and health index of the cultured organisms, and to identify the effects of different plankton densities on the cultured organisms, including positive and negative effects.

[0030] Based on the identification results, a primary aquaculture optimization scheme was developed to optimize the growth environment of cultured organisms by controlling plankton.

[0031] As a further aspect of the present invention, the analysis of the growth rate, reproductive rate, and health index of cultured organisms, and the identification of the impact of different plankton densities on cultured organisms, specifically includes:

[0032] Calculate growth rate :

[0033] ;

[0034] in, Indicates the inherent growth rate, reflecting the maximum growth potential of cultured organisms under ideal conditions. The current density of farmed organisms, Environmental carrying capacity represents the maximum density of cultured organisms under specific environmental conditions;

[0035] Calculate the reproductive rate :

[0036] ;

[0037] in, The basal reproductive rate coefficient represents the reproductive capacity under optimized conditions. The density of plankton, To optimize plankton density, this represents the optimal plankton density for maximizing the reproductive rate of cultured organisms.

[0038] Calculate the health index :

[0039] ;

[0040] in, The basic health index represents the health status of farmed organisms under ideal conditions. , where is the weighting coefficient, representing the relative contribution of growth rate and reproduction rate to the health index;

[0041] Assessment of the overall impact of plankton density on the growth, reproduction, and health of cultured organisms. :

[0042] ;

[0043] in, The overall impact score reflects the combined effects of plankton on cultured organisms; , where are weighting coefficients, representing the degree of contribution of growth rate, reproduction rate, and health index to the overall impact score, respectively.

[0044] As a further aspect of the present invention, the real-time prediction of the current aquaculture trend in the marine ranch, the comprehensive analysis of the primary aquaculture optimization scheme, the analysis of the development and changes of the cultured organisms, and the adjustment of the primary aquaculture optimization scheme based on the results of the development and changes of the cultured organisms to generate a final aquaculture optimization scheme, specifically includes:

[0045] Extract the latest output results of the water quality assessment model and the flow change model, and extract real-time aquaculture biological monitoring data;

[0046] Establish an aquaculture trend prediction model to capture the relationship between aquaculture organisms and water quality parameters, predict and analyze aquaculture trends in the current and future time periods, and determine changes in the growth and reproductive capacity of aquaculture organisms.

[0047] The prediction results are integrated with the primary aquaculture optimization scheme. Taking into account the interaction between aquaculture organisms, plankton, water flow and water quality parameters, the parts of the primary aquaculture optimization scheme that need to be adjusted are identified, and the final aquaculture optimization scheme is generated.

[0048] As a further aspect of the present invention, the step of predicting and analyzing the aquaculture trends for the current and future time periods to determine the changes in the growth and reproductive capacity of the farmed organisms specifically includes:

[0049] Predicting in time Density of cultured organisms at that time :

[0050] ;

[0051] in, Initial stocking density;

[0052] Calculate in time Reproduction rate of cultured organisms based on plankton density at that time :

[0053] ;

[0054] By combining the growth and reproduction of farmed organisms, a comprehensive predictive model can be formed:

[0055] ;

[0056] in, Indicates the density of cultured organisms over time The rate of change, if This indicates that the reproductive rate is higher than the mortality rate. This indicates that the reproductive rate is lower than the mortality rate.

[0057] As a further aspect of the present invention, the step of comprehensively considering the interrelationships between cultured organisms, plankton, water flow, and water quality parameters to identify the parts in the primary aquaculture optimization scheme that need adjustment specifically includes:

[0058] Analysis time Water quality parameters at any time :

[0059] ;

[0060] in, Basic water quality parameters For parameters related to water flow, These are the water quality impact coefficients corresponding to cultured organisms, plankton, and flow patterns, respectively.

[0061] Calculate the first Minimum overall loss for each step :

[0062] ;

[0063] in, For the first Water quality parameters during the steps, For the desired target water quality parameters, For the first The density of cultured organisms during the steps, For the desired target culture density, For the first Reproduction rate of cultured organisms during the steps To achieve the desired target reproductive rate of cultured organisms, For the first Plankton density at the time of the step These are the weighting coefficients.

[0064] Set a loss threshold. If it is greater than the loss threshold, then it indicates a step. Adjustments are needed.

[0065] Another object of the present invention is to provide an artificial intelligence-based digital construction system for marine ranching, the system comprising:

[0066] The plankton monitoring module is used to monitor plankton-related data in marine ranches in real time based on image recognition, and to establish a dynamic database, which is regularly stored and updated with the plankton-related data obtained in the dynamic database.

[0067] The water quality analysis and water flow pattern analysis module is used to establish a water quality assessment model based on the monitored plankton-related data, analyze the relationship between plankton species, density and water quality parameters, and at the same time analyze water flow patterns, establish flow change models, and determine the impact of water flow on plankton.

[0068] The primary aquaculture optimization simulation module is used to simulate the interaction between cultured organisms and plankton in marine ranches and to establish a primary aquaculture optimization scheme that focuses solely on plankton control.

[0069] The final optimization scheme adjustment module is used to integrate the output results of the water quality assessment model and the flow change model to predict the current aquaculture trend of the marine ranch in real time. It integrates the primary aquaculture optimization scheme, analyzes the development and changes of the cultured organisms, and adjusts the primary aquaculture optimization scheme based on the results of the development and changes of the cultured organisms to generate the final aquaculture optimization scheme.

[0070] The beneficial effects of this invention are:

[0071] This solution utilizes artificial intelligence and digital technologies to construct a comprehensive marine ranching management system, aiming to achieve dynamic and efficient management of the aquaculture environment. For real-time monitoring, the solution employs image recognition technology to regularly acquire water images and identify phytoplankton, forming a dynamic database. This mechanism ensures the timeliness and accuracy of data, enabling aquaculture managers to make informed decisions based on the latest environmental conditions. Furthermore, by establishing a water quality assessment model, the solution analyzes the impact of phytoplankton species and density on water quality parameters, constructing an ecological network to reveal the relationship between phytoplankton and water quality, providing crucial information for the health of farmed organisms. In addition, integrating the influence of water flow patterns allows managers to understand the role of water flow in phytoplankton distribution, further optimizing the aquaculture environment.

[0072] In terms of interaction simulation, the scheme identifies the positive or negative impact of plankton density on cultured organisms by simulating the relationship between cultured organisms and plankton. This allows managers to formulate specific control strategies to improve culture efficiency while balancing ecological and economic benefits. Combining water quality assessment and flow change model outputs, the scheme enables real-time prediction of culture trends, establishing a culture trend prediction model that allows managers to better understand the growth changes of cultured organisms and the relationships between water quality parameters. This predictive capability helps managers adjust culture strategies in a dynamic environment, ensuring the sustainability and ecological health of culture. Attached Figure Description

[0073] Figure 1 A flowchart illustrating an artificial intelligence-based digital construction method for marine ranching, provided as an embodiment of the present invention.

[0074] Figure 2 A flowchart illustrating real-time monitoring of plankton-related data in marine ranches and the establishment of a dynamic database, as provided in this embodiment of the invention;

[0075] Figure 3 A flowchart for analyzing the relationship between plankton species, density, and water quality parameters, and for determining the impact of water flow on plankton, provided for embodiments of the present invention;

[0076] Figure 4 A flowchart for establishing a primary aquaculture optimization scheme that targets planktonic control only, provided as an embodiment of the present invention;

[0077] Figure 5 A flowchart for generating the final optimized aquaculture scheme provided in an embodiment of the present invention;

[0078] Figure 6 The structural block diagram of the artificial intelligence-based digital construction system for marine ranching provided in the embodiments of the present invention. Detailed Implementation

[0079] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0080] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0081] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0082] Figure 1 A flowchart of an artificial intelligence-based digital construction method for marine ranching provided in an embodiment of the present invention is shown below. Figure 1 As shown, the method includes:

[0083] S100 uses image recognition to monitor plankton-related data in marine ranches in real time and establishes a dynamic database, which is regularly stored and updated to store and update the plankton-related data obtained in the dynamic database.

[0084] This step ensures the timeliness and traceability of monitoring data by periodically acquiring water images and adding time stamps to each image. The automation of this process makes data acquisition more efficient, reduces the possibility of human intervention, and thus lowers the risk of human error. Next, the acquired images are analyzed using advanced image recognition algorithms to accurately identify plankton in the images. Through the application of deep learning technology, the system can continuously improve its recognition accuracy to adapt to changes in different aquatic environments and plankton species.

[0085] Establishing a dynamic database architecture tailored to the needs of marine ranching is a crucial step in this process. The dynamic database stores not only plankton-related data but also corresponding water images and their time stamps, providing multi-dimensional data support. This structured information storage method makes subsequent data analysis and model building more efficient and accurate. The dynamic database's regular storage and update mechanism ensures the timeliness and accuracy of the data, enabling decision-makers to formulate management strategies based on the latest monitoring results.

[0086] Through efficient image recognition and data storage mechanisms, comprehensive monitoring of plankton species, quantities, and distribution has been achieved, providing a solid data foundation for subsequent water quality assessment and aquaculture optimization. The establishment of the dynamic database not only provides long-term data accumulation for ecological health assessment but also lays a good foundation for future intelligent analysis and decision-making systems. Simultaneously, real-time monitoring provides timely feedback to aquaculture managers, enabling them to quickly adjust aquaculture strategies in the face of sudden environmental changes to ensure the health and stability of the aquaculture environment, thereby improving aquaculture efficiency and ecological sustainability.

[0087] like Figure 2 As shown, the real-time monitoring of plankton-related data in the marine ranch and the establishment of a dynamic database specifically include:

[0088] S110 periodically acquires water body images and adds time stamps to the water body images according to the acquisition time;

[0089] S120: Analyze the acquired images, identify plankton in the images, and analyze their species and density.

[0090] S130, establish a dynamic database architecture tailored to the needs of marine ranching, and store the obtained plankton-related data along with the time stamps of the corresponding water images in the dynamic database.

[0091] S200, based on the monitored phytoplankton-related data, establishes a water quality assessment model, analyzes the relationship between phytoplankton species, density and water quality parameters, and analyzes water flow patterns to establish a flow change model to determine the impact of water flow on phytoplankton;

[0092] This step establishes an ecological network model to clarify the impact of plankton on water quality parameters (such as nitrogen, phosphorus content, and dissolved oxygen), providing a scientific basis for the subsequent management of aquaculture organisms.

[0093] In practice, the water quality assessment model integrates phytoplankton monitoring data, identifies the types and quantities of various phytoplankton, and quantitatively analyzes how phytoplankton density affects water quality parameters by establishing mathematical models. The core of this model lies in quantifying the interaction between phytoplankton and water quality through a combination of experimental and field data, enabling managers to promptly identify potential risks of water quality changes.

[0094] Furthermore, it integrates water flow data such as flow velocity and direction, and combines this with plankton monitoring data to establish a flow change model. This model can be used to assess the impact of water flow on plankton, especially its influence on plankton distribution and reproduction under different environmental conditions (water temperature, salinity, wind force, etc.). This comprehensive analysis clarifies the relationship between plankton ecological behavior and water quality changes.

[0095] Furthermore, combining the results of the water quality assessment model with the output of the flow change model helps identify current trends in water quality changes and record changes in plankton species and density. Generating detailed water quality reports provides early warnings for the management of aquaculture organisms, ensuring a healthy and stable aquaculture environment.

[0096] The formula proposed in this step is actually a dynamic model used to analyze the relationship between plankton species, density, and water quality parameters. This formula is not merely a mathematical expression, but also a crucial reflection of the interactions between various factors within the ecosystem.

[0097] A key component of this model is the comprehensive impact assessment, which reflects the extent to which phytoplankton influences water quality parameters. Specifically, the formula quantifies phytoplankton species, density, and water quality parameters, enabling managers to clearly understand how phytoplankton affects water quality under different environmental conditions. For example, high-density phytoplankton can lead to eutrophication, affecting water quality stability and the habitat of aquaculture organisms. This analysis not only identifies potential water quality problems but also provides a basis for implementing control measures.

[0098] By adjusting and analyzing the formula parameters, managers can assess changes in water quality in real time. For example, changes in the diversity and density of plankton species directly affect the concentrations of water quality parameters such as nitrogen and phosphorus, thereby impacting the health of the aquaculture environment. The results from the formula help managers promptly detect abnormal fluctuations in water quality and take corresponding aquaculture control measures, such as adjusting feed input and stocking density, to ensure that aquaculture organisms are in a favorable growth environment.

[0099] Furthermore, the integration of flow change models brings a deeper meaning to this analysis. The speed and direction of water flow affect the distribution of phytoplankton and its interaction with water quality. Through this dynamic model, managers can gain a more comprehensive understanding of how water flow influences the survival and reproduction of phytoplankton under different water conditions. This holistic perspective not only enhances sensitivity to the environment but also provides strong support for the formulation of ecological management strategies.

[0100] Through scientific model building and data analysis, managers can monitor the ecological status of marine ranches in real time and take timely measures to address potential ecological crises. This dynamic management approach not only enhances the sustainability of marine ranches but also provides solid data support for decision-making, strengthens adaptability to environmental changes, optimizes aquaculture efficiency, and ensures ecological health. Furthermore, a deep understanding of the relationship between water quality and plankton can guide future aquaculture management and environmental protection, promoting the intelligent development of marine ranches.

[0101] like Figure 3 As shown, the establishment of a water quality assessment model analyzes the relationship between phytoplankton species, density, and water quality parameters, while simultaneously analyzing water flow patterns, establishing a flow change model, and determining the impact of water flow on phytoplankton. Specifically, this includes:

[0102] S210, Establish a water quality assessment model, analyze the relationship between plankton species, density and water quality parameters, determine how plankton species and density affect water quality parameters, and construct an ecological network model between plankton and water quality parameters;

[0103] S220 integrates water flow data and combines it with plankton monitoring data to establish a flow change model and assess the impact of water flow on plankton.

[0104] S230 combines the results of the water quality assessment model with the output of the flow change model to identify the current trend of water quality changes and changes in the species and density of plankton, and generates a water quality status report.

[0105] In this step, the analysis of the relationship between plankton species, density, and water quality parameters, and the determination of how plankton species and density affect water quality parameters, specifically involves:

[0106] ;

[0107] in, The overall impact score reflects the degree of influence of plankton on water quality parameters. The total number of planktonic species. For the first The density of plankton, For the first The species index of planktonic organisms, with values ​​ranging from 1 to 2. , For the first The basic influence coefficients of planktonic organisms on target water quality parameters The impact index of plankton density, The impact index of plankton species;

[0108] The assessment of the impact of water flow on plankton specifically includes:

[0109] ;

[0110] ;

[0111] in, For the first The rate of change in the density of planktonic organisms For the first The inherent growth rate of the plankton species For the first The environmental carrying capacity of plankton The function representing the effect of water flow on plankton is determined by the speed and direction of the water flow. The constant represents the baseline for the impact of water flow on plankton. The index represents the nonlinear exponent affecting the effect of water flow intensity on phytoplankton growth, and the velocity field of the water flow is represented. This is a symbolic function used to indicate the directionality of water flow, i.e.:

[0112] .

[0113] S300 simulates the interaction between cultured organisms and plankton in marine ranching, and establishes a primary aquaculture optimization scheme that focuses solely on plankton control.

[0114] The core of this step lies in the analysis of growth rate, reproductive rate, and health index, using formulas to quantitatively evaluate these key parameters.

[0115] By considering different plankton densities, species, and water quality conditions, the system can effectively simulate the growth, reproduction, and health status of cultured organisms under various environments. This simulation is not limited to the analysis of static data, but also allows for the consideration of dynamically changing factors (such as water temperature and salinity), thus more realistically reflecting the complexity of actual aquaculture environments.

[0116] After extracting the simulation results, analyzing the growth rate, reproduction rate, and health index of the cultured organisms is crucial. By comparing the growth performance of cultured organisms under different plankton densities, managers can identify the positive or negative impacts of plankton on the cultured organisms. For example, high plankton density may promote nutrient supply to the water, while low density may lead to increased competition and affect the health of the cultured organisms. This detailed analysis helps managers make more scientific decisions in aquaculture to ensure that cultured organisms can grow in optimal environments.

[0117] Based on the identification results, through in-depth analysis of the simulation results, managers can formulate specific control strategies for different environmental conditions, such as adjusting the quantity and type of plankton or applying specific nutrients to optimize aquaculture conditions. This approach not only helps improve aquaculture efficiency but also reduces environmental risks and ensures the sustainability of the ecosystem.

[0118] By establishing dynamic simulation models, managers can quickly respond to environmental changes and adjust aquaculture strategies. This real-time decision support system enables managers to take necessary measures promptly based on the latest data and simulation results, thereby reducing environmental risks and improving the growth efficiency of farmed organisms. Furthermore, dynamic management strategies for plankton can effectively reduce potential ecological problems during aquaculture, achieving both ecological and economic optimization and injecting new vitality into the intelligent management of marine ranches.

[0119] like Figure 4 As shown, the simulation of the interaction between cultured organisms and plankton in a marine ranch establishes a primary aquaculture optimization scheme targeting only plankton control, specifically including:

[0120] S310, extracts plankton monitoring data, water quality data and aquaculture data from a dynamic database;

[0121] S320: Establish several simulation scenarios, consider different plankton densities, species and water quality conditions, and record the growth, reproduction and health status of cultured organisms under different simulation scenarios;

[0122] S330: Extract simulation results, analyze the growth rate, reproduction rate and health index of cultured organisms, and identify the effects of different plankton densities on cultured organisms, including positive and negative effects.

[0123] S340, based on the identification results, formulate a primary aquaculture optimization plan to optimize the growth environment of cultured organisms by controlling plankton.

[0124] In this step, the analysis of the growth rate, reproductive rate, and health index of the cultured organisms, and the identification of the impact of different plankton densities on the cultured organisms, specifically includes:

[0125] Calculate growth rate :

[0126] ;

[0127] in, Indicates the inherent growth rate, reflecting the maximum growth potential of cultured organisms under ideal conditions. The current density of farmed organisms, Environmental carrying capacity represents the maximum density of cultured organisms under specific environmental conditions;

[0128] Calculate the reproductive rate :

[0129] ;

[0130] in, The basal reproductive rate coefficient represents the reproductive capacity under optimized conditions. The density of plankton, To optimize plankton density, this represents the optimal plankton density for maximizing the reproductive rate of cultured organisms.

[0131] Calculate the health index :

[0132] ;

[0133] in, The basic health index represents the health status of farmed organisms under ideal conditions. , where is the weighting coefficient, representing the relative contribution of growth rate and reproduction rate to the health index;

[0134] Assessment of the overall impact of plankton density on the growth, reproduction, and health of cultured organisms. :

[0135] ;

[0136] in, The overall impact score reflects the combined effects of plankton on cultured organisms; , where are weighting coefficients, representing the degree of contribution of growth rate, reproduction rate, and health index to the overall impact score, respectively.

[0137] S400 integrates the outputs of the water quality assessment model and the flow change model to predict the current aquaculture trend of the marine ranch in real time. It integrates the primary aquaculture optimization scheme, analyzes the development and changes of aquaculture organisms, and adjusts the primary aquaculture optimization scheme based on the results of the development and changes of aquaculture organisms to generate the final aquaculture optimization scheme.

[0138] This step extracts the latest outputs from the water quality assessment model and the flow change model to obtain real-time monitoring data of aquaculture organisms. This data will provide the foundation for establishing aquaculture trend prediction models. The establishment of prediction models means that future aquaculture environments, the growth and reproductive capacity of aquaculture organisms can be proactively analyzed, thereby enabling better management strategies. The dynamic relationship between aquaculture organism density and time in the formula, combined with the influence of flow and water quality parameters, can accurately predict the performance of aquaculture organisms under different environmental conditions.

[0139] Predictive models enable managers to clearly understand the growth potential of farmed organisms and the carrying capacity of the environment. This model-based prediction not only helps identify potential overfarming risks but also guides managers to make timely adjustments in practice.

[0140] By controlling the density of farmed organisms, managers can clearly understand their growth potential under different environmental conditions, and thus determine whether adjustments to the farming scale are necessary. This dynamic predictive capability allows managers to identify potential risks early in the farming process, such as overcrowding leading to resource competition and ecological imbalance.

[0141] Furthermore, the model's analysis of the interaction between flow and water quality parameters enables managers to identify optimal aquaculture strategies under different environmental conditions. By calculating the loss function, managers can quantify the deviation between the performance of farmed organisms and the target state, thereby enabling dynamic adjustments in aquaculture management. This quantitative analysis not only improves the scientific rigor of decision-making but also allows for a more effective response to the challenges posed by environmental changes.

[0142] The loss function quantifies the deviation between the actual performance of farmed organisms and the target state. By systematically comparing the actual growth of farmed organisms with the target growth, managers can accurately identify areas requiring adjustment. This feedback mechanism makes aquaculture management more targeted and improves the scientific rigor and timeliness of decision-making.

[0143] This step, by integrating multiple data sources and models, enables managers to adjust aquaculture strategies in real time within a dynamically changing environment, ensuring the health of farmed organisms and the sustainability of the ecosystem. The construction of a predictive scheduling system allows managers to utilize resources more efficiently, reduce costs, and improve overall aquaculture effectiveness. Simultaneously, this data-driven decision-making mechanism provides strong support for the intelligent management of marine ranches, promoting the process of digital transformation.

[0144] like Figure 5 As shown, the real-time prediction of current marine ranching trends, the comprehensive analysis of primary aquaculture optimization schemes, the analysis of the development and changes of farmed organisms, and the adjustment of the primary aquaculture optimization schemes based on the results of these changes, generate a final aquaculture optimization scheme, specifically including:

[0145] S410 extracts the latest output results of the water quality assessment model and the flow change model, and extracts real-time aquaculture biological monitoring data;

[0146] S420, establish an aquaculture trend prediction model, capture the relationship between aquaculture organisms and water quality parameters, predict and analyze aquaculture trends in the current and future time periods, and judge the growth changes and reproductive capacity changes of aquaculture organisms.

[0147] S430 integrates the prediction results with the primary aquaculture optimization scheme, comprehensively considers the interaction between aquaculture organisms, plankton, water flow and water quality parameters, identifies the parts of the primary aquaculture optimization scheme that need to be adjusted, and generates the final aquaculture optimization scheme.

[0148] In this step, the prediction and analysis of the aquaculture trends for the current and future time periods, and the determination of changes in the growth and reproductive capacity of the farmed organisms, specifically involves:

[0149] Predicting in time Density of cultured organisms at that time :

[0150] ;

[0151] in, Initial stocking density;

[0152] Calculate in time Reproduction rate of cultured organisms based on plankton density at that time :

[0153] ;

[0154] By combining the growth and reproduction of farmed organisms, a comprehensive predictive model can be formed:

[0155] ;

[0156] in, Indicates the density of cultured organisms over time The rate of change, if This indicates that the reproductive rate is higher than the mortality rate. This indicates that the reproductive rate is lower than the mortality rate.

[0157] In this step, the interaction between cultured organisms, plankton, water flow, and water quality parameters is comprehensively considered to identify the parts of the primary aquaculture optimization scheme that need adjustment, specifically:

[0158] Analysis time Water quality parameters at any time :

[0159] ;

[0160] in, Basic water quality parameters For parameters related to water flow, These are the water quality impact coefficients corresponding to cultured organisms, plankton, and flow patterns, respectively.

[0161] Calculate the first Minimum overall loss for each step :

[0162] ;

[0163] in, For the first Water quality parameters during the steps, For the desired target water quality parameters, For the first The density of cultured organisms during the steps, For the desired target culture density, For the first Reproduction rate of cultured organisms during the steps To achieve the desired target reproductive rate of cultured organisms, For the first Plankton density at the time of the step These are the weighting coefficients.

[0164] Set a loss threshold. If it is greater than the loss threshold, then it indicates a step. Adjustments are needed.

[0165] Figure 6 A structural block diagram of an artificial intelligence-based digital construction system for marine ranching provided in an embodiment of the present invention is shown below. Figure 6 As shown, the system includes:

[0166] The plankton monitoring module 100 is used to monitor plankton-related data in marine ranches in real time based on image recognition, and to establish a dynamic database, which is regularly stored and updated with the plankton-related data obtained in the dynamic database.

[0167] The water quality analysis and water flow pattern analysis module 200 is used to establish a water quality assessment model based on the monitored plankton-related data, analyze the relationship between plankton species, density and water quality parameters, and at the same time analyze water flow patterns, establish a flow change model, and determine the impact of water flow on plankton.

[0168] The primary aquaculture optimization simulation module 300 is used to simulate the interaction between cultured organisms and plankton in marine ranches and to establish a primary aquaculture optimization scheme that focuses solely on plankton control.

[0169] The final optimization scheme adjustment module 400 is used to integrate the output results of the water quality assessment model and the flow change model, predict the current aquaculture trend of the marine ranch in real time, integrate the primary aquaculture optimization scheme, analyze the development and changes of aquaculture organisms, and adjust the primary aquaculture optimization scheme based on the development and changes of aquaculture organisms to generate the final aquaculture optimization scheme.

[0170] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0171] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0173] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0174] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0175] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0176] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for digital construction of marine ranches based on artificial intelligence, characterized in that, The method includes: Based on image recognition, real-time monitoring of plankton-related data in marine ranches is conducted, and a dynamic database is established to regularly store and update the plankton-related data obtained in the dynamic database. Based on the monitored phytoplankton-related data, a water quality assessment model was established to analyze the relationship between phytoplankton species, density and water quality parameters. At the same time, water flow patterns were analyzed to establish a flow change model and determine the impact of water flow on phytoplankton. Simulate the interaction between cultured organisms and plankton in a marine ranch, and establish a primary aquaculture optimization scheme that focuses solely on plankton control; By combining the outputs of the water quality assessment model and the flow change model, the current aquaculture trend of the marine ranch is predicted in real time. The primary aquaculture optimization scheme is integrated, the development and changes of the cultured organisms are analyzed, and the primary aquaculture optimization scheme is adjusted based on the results of the development and changes of the cultured organisms to generate the final aquaculture optimization scheme. The aforementioned water quality assessment model is established to analyze the relationship between phytoplankton species, density, and water quality parameters. Simultaneously, water flow patterns are analyzed, a flow change model is established, and the impact of water flow on phytoplankton is determined. Specifically, this includes: Establish a water quality assessment model, analyze the relationship between phytoplankton species, density and water quality parameters, determine how phytoplankton species and density affect water quality parameters, and construct an ecological network model between phytoplankton and water quality parameters; By integrating water flow data and combining it with plankton monitoring data, a flow change model was established to assess the impact of water flow on plankton. By combining the results of the water quality assessment model with the output of the flow change model, the current trend of water quality change and the changes in plankton species and density are identified, and a water quality status report is generated. The simulation of the interaction between cultured organisms and plankton in a marine ranch establishes a primary aquaculture optimization scheme focusing solely on plankton control, specifically including: Extract plankton monitoring data, water quality data, and aquaculture data from a dynamic database; Several simulation scenarios were established, taking into account different plankton densities, species and water quality conditions, and the growth, reproduction and health status of cultured organisms were recorded under different simulation scenarios. The simulation results were extracted to analyze the growth rate, reproduction rate and health index of the cultured organisms, and to identify the effects of different plankton densities on the cultured organisms, including positive and negative effects. Based on the identification results, a primary aquaculture optimization program was developed to optimize the growth environment of cultured organisms by controlling plankton. The process involves real-time prediction of current marine ranching trends, comprehensive analysis of primary aquaculture optimization schemes, and adjustment of the primary aquaculture optimization schemes based on these changes, ultimately generating a final optimized aquaculture scheme. Specifically, this includes: Extract the latest output results of the water quality assessment model and the flow change model, and extract real-time aquaculture biological monitoring data; Establish an aquaculture trend prediction model to capture the relationship between aquaculture organisms and water quality parameters, predict and analyze aquaculture trends in the current and future time periods, and judge the changes in growth and reproductive capacity of aquaculture organisms. The prediction results are integrated with the primary aquaculture optimization scheme. Taking into account the interaction between aquaculture organisms, plankton, water flow and water quality parameters, the parts of the primary aquaculture optimization scheme that need to be adjusted are identified, and the final aquaculture optimization scheme is generated.

2. The method according to claim 1, characterized in that, The real-time monitoring of plankton-related data in marine ranches and the establishment of a dynamic database specifically include: Regularly acquire water body images and add time stamps to the images based on the acquisition time; The acquired images are analyzed to identify plankton and determine their species and density. A dynamic database architecture tailored to the needs of marine ranching was established, and the obtained plankton-related data, along with the time stamps of the corresponding water images, were stored in the dynamic database.

3. The method according to claim 1, characterized in that, The analysis examines the relationship between plankton species, density, and water quality parameters, determining how plankton species and density affect water quality parameters. Specifically: ； in, The overall impact score reflects the degree of influence of plankton on water quality parameters. The total number of planktonic species. For the first The density of plankton, For the first The species index of planktonic organisms, with values ​​ranging from 1 to 2. , For the first The basic influence coefficients of planktonic organisms on target water quality parameters The impact index of plankton density, The impact index of plankton species; The assessment of the impact of water flow on plankton specifically includes: ； ； in, For the first The rate of change in the density of planktonic organisms For the first The inherent growth rate of the plankton species For the first The environmental carrying capacity of plankton The function representing the effect of water flow on plankton is determined by the speed and direction of the water flow. The constant represents the baseline for the impact of water flow on plankton. The index represents the nonlinear exponent affecting the effect of water flow intensity on phytoplankton growth, and the velocity field of the water flow is represented. This is a symbolic function used to indicate the directionality of water flow, i.e.: 。 4. The method according to claim 1, characterized in that, The analysis examined the growth rate, reproductive rate, and health index of the cultured organisms, identifying the impact of different plankton densities on the cultured organisms, specifically as follows: Calculate growth rate : ； in, Indicates the inherent growth rate, reflecting the maximum growth potential of cultured organisms under ideal conditions. The current density of farmed organisms, Environmental carrying capacity represents the maximum density of cultured organisms under specific environmental conditions; Calculate the reproductive rate : ； in, The basal reproductive rate coefficient represents the reproductive capacity under optimized conditions. For the density of plankton, To optimize plankton density, this represents the optimal plankton density for maximizing the reproductive rate of cultured organisms. Calculate the health index : ； in, The basic health index represents the health status of farmed organisms under ideal conditions. , where is the weighting coefficient, representing the relative contribution of growth rate and reproduction rate to the health index; Assessment of the overall impact of plankton density on the growth, reproduction, and health of cultured organisms. : ； in, The overall impact score reflects the combined effects of plankton on cultured organisms; , where are weighting coefficients, representing the degree of contribution of growth rate, reproduction rate, and health index to the overall impact score, respectively.

5. The method according to claim 1, characterized in that, The aforementioned prediction and analysis of aquaculture trends for the current and future periods, and the assessment of changes in the growth and reproductive capacity of farmed organisms, specifically includes: Predicting in time Density of cultured organisms at that time : ； in, Initial stocking density; Calculate in time Reproduction rate of cultured organisms based on plankton density at that time : ； By combining the growth and reproduction of farmed organisms, a comprehensive predictive model can be formed: ； in, Indicates the density of cultured organisms over time The rate of change, if This indicates that the reproductive rate is higher than the mortality rate. This indicates that the reproductive rate is lower than the mortality rate.

6. The method according to claim 1, characterized in that, The process comprehensively considers the interactions between cultured organisms, plankton, water flow, and water quality parameters, identifying the parts of the primary aquaculture optimization scheme that need adjustment, specifically: Analysis time Water quality parameters at any time : ； in, Basic water quality parameters For parameters related to water flow, These are the water quality impact coefficients corresponding to cultured organisms, plankton, and flow patterns, respectively. Calculate the first Minimum overall loss for each step : ； in, For the first Water quality parameters during the steps, For the desired target water quality parameters, For the first The density of cultured organisms during the steps, To achieve the desired target stock density, For the first Reproduction rate of cultured organisms during the steps To achieve the desired target reproductive rate of cultured organisms, For the first Plankton density at the time of the step These are the weighting coefficients; Set a loss threshold. If it is greater than the loss threshold, then it indicates a step. Adjustments are needed.

7. The method according to claim 1, characterized in that, The system for implementing the AI-based digital construction method for marine ranching includes: The plankton monitoring module is used to monitor plankton-related data in marine ranches in real time based on image recognition, and to establish a dynamic database, which is regularly stored and updated with the plankton-related data obtained in the dynamic database. The water quality analysis and water flow pattern analysis module is used to establish a water quality assessment model based on the monitored plankton-related data, analyze the relationship between plankton species, density and water quality parameters, and at the same time analyze water flow patterns, establish flow change models, and determine the impact of water flow on plankton. The primary aquaculture optimization simulation module is used to simulate the interaction between cultured organisms and plankton in marine ranches and to establish a primary aquaculture optimization scheme that focuses solely on plankton control. The final optimization scheme adjustment module is used to integrate the output results of the water quality assessment model and the flow change model to predict the current aquaculture trend of the marine ranch in real time. It integrates the primary aquaculture optimization scheme, analyzes the development and changes of the cultured organisms, and adjusts the primary aquaculture optimization scheme based on the results of the development and changes of the cultured organisms to generate the final aquaculture optimization scheme.

Images