Bay aquaculture capacity evaluation method and system based on digital twinborn technology

Abstract

The invention discloses a bay aquaculture capacity evaluation method and system based on a digital twinborn technology. The method comprises the steps of obtaining multi-source real-time data of a target aquaculture water area; a digital space model corresponding to the target aquaculture water area is established, and the space model configures a simulation engine integrating environment evolution logic and a biological metabolism mechanism; dividing the digital spatial model into a plurality of calculation units, and dynamically coupling the source item, the sink item and the environmental evolution logic on the spatial-temporal scale in the calculation step length of the calculation units; performing state calibration on the digital space model, and performing environment evolution trend simulation in a future time period in combination with prediction driving data; and by taking the ecological health index and the biological survival index as constraint conditions, adjusting the breeding configuration parameters in the digital space model to carry out iterative simulation, and outputting a dynamic breeding capacity meeting the constraint conditions. According to the invention, the method achieves the crossing of the breeding capacity from the static estimation to the dynamic numerical deduction, and effectively improves the perspectiveness of risk early warning and the precision of management decision.

Description

Technical Field

[0001] This invention relates to the fields of aquaculture biology and aquaculture management technology, and in particular to a method and system for assessing the aquaculture capacity of a bay based on digital twin technology. Background Technology

[0002] Aquaculture capacity, as the maximum biomass that a specific body of water can support while maintaining an ecosystem health, is a core parameter for achieving sustainable development in the industry. However, traditional assessment methods mainly rely on static field surveys, empirical formulas, and periodic testing, which have inherent defects such as significant lag, localization, and insufficient predictive ability. Because they cannot reflect the dynamic changes of key factors such as dissolved oxygen and ammonia nitrogen in real time, and are difficult to simulate the impact of extreme weather on the system, traditional models are heavily reliant on human experience. The lack of scientific quantitative decision-making support can easily lead to over-aquaculture, thereby triggering risks such as eutrophication and disease outbreaks.

[0003] While digital twin technology has demonstrated its powerful advantages in integrating the virtual and real worlds in fields such as industrial manufacturing, a technological gap remains in the highly complex and environmentally sensitive field of aquaculture, where the construction of dynamic and predictable assessment models is still lacking. Existing technologies lack a systematic solution capable of integrating multi-source environmental data, deeply coupling hydrodynamics and biological growth models, and achieving full-process virtual-real interaction from perception to modeling to decision-making to control. This makes it difficult to meet the urgent needs of modern smart aquaculture for refined management and risk control. Summary of the Invention

[0004] To address the aforementioned technical problems in the existing technology, this invention proposes a method and system for assessing the aquaculture capacity of bays based on digital twin technology, thereby resolving these technical issues.

[0005] According to a first aspect of the present invention, a method for assessing the aquaculture capacity of a bay based on digital twin technology is proposed, comprising: S1: Acquire multi-source real-time data of the target aquaculture area, including environmental characteristic data and biological activity data; establish a digital spatial model corresponding to the target aquaculture area, and configure a simulation engine that integrates environmental evolution logic and biological metabolic mechanism in the digital spatial model; S2: Divide the digital spatial model into several computational units. Within the computational step of each computational unit, define the material contribution generated by the metabolism of farmed organisms as the source term and the material consumption generated by the activities of farmed organisms as the sink term. Dynamically couple the source term, sink term and environmental evolution logic on a spatiotemporal scale. S3: Perform state calibration on the digital spatial model based on multi-source real-time data, and simulate the environmental evolution trend in future periods by combining predictive driving data; S4: Using ecological health indicators and biological survival indicators as constraints, iterative simulation is performed by adjusting the aquaculture configuration parameters in the digital spatial model to output the dynamic aquaculture capacity that meets the constraints.

[0006] The above technical solution establishes a virtual mapping system that deeply couples the physical environment with biological mechanisms, realizing a leap from "static empirical estimation" to "dynamic numerical extrapolation" of aquaculture capacity, and greatly improving the timeliness and scientificity of capacity assessment.

[0007] In some specific embodiments, the multi-source real-time data includes velocity field data acquired using an acoustic current profiler, dissolved oxygen gradient data acquired using multi-layer water quality sensors, and wind field forecast data acquired using weather stations. By introducing high-dimensional profile flow fields, dissolved oxygen gradients, and forecast-level meteorological data, the singularity of the model's boundary conditions is eliminated, significantly enhancing the system's perception accuracy of water stratification phenomena and future environmental fluctuations in complex habitats.

[0008] In some specific embodiments, the steps for constructing a digital spatial model include: acquiring geographic mapping data, sediment data, and shoreline data of the target aquaculture area; and constructing a three-dimensional discretized mesh based on computational fluid dynamics logic as the computational unit carrying the simulation engine. Utilizing three-dimensional discretized mesh technology transforms complex marine topography into a mathematically accurate computational carrier, providing a unified spatial benchmark for multi-field coupled simulations and ensuring the convergence of numerical calculations and the spatial continuity of simulation results.

[0009] In some specific embodiments, the environmental evolution logic integrates a three-dimensional hydrodynamic and water quality model. It simulates the physical flow and transport processes of water by solving the Navier-Stokes equations, and combines these with convection-diffusion equations to map the spatiotemporal concentration field distribution of dissolved oxygen, nutrients, and pollutants in each computational unit in real time. By integrating classical hydrodynamic and water quality evolution equations, a logical mapping of the entire process of material migration and transformation within the aquaculture area is achieved, providing a physically consistent evolutionary basis for simulating environmental risks.

[0010] In some specific embodiments, the biological metabolic mechanism integrates a biological growth and metabolism model. By establishing a correlation function with individual biomass, real-time water temperature, and dissolved oxygen concentration as independent variables, the feeding, respiration, and excretion rates of cultured organisms at different growth stages are dynamically quantified. The resulting instantaneous oxygen consumption and metabolic waste release are transformed into dynamic source and sink terms in a digital spatial model. By constructing a multi-factor correlation function, the material and energy exchange patterns between individual cultured organisms and the environment are quantified, enabling the evaluation model to simulate the metabolic effects of "living organisms" and improving the model's biofidelity.

[0011] In some specific embodiments, dynamic coupling includes: loading the nutrient load generated by the metabolism of cultured organisms as a source term into the corresponding computational unit, and loading the oxygen consumption generated by the respiration of cultured organisms as a sink term into the corresponding computational unit; within each computational step, based on the real-time flow field data output by the environmental evolution logic, driving the convection-diffusion equations to simultaneously solve the advection, diffusion, and mixing processes of substances in each computational unit. This achieves real-time coupling of flow field and substance concentration at the computational step level, solves the problem of difficulty in capturing the local instantaneous impact of cultured organisms on the environment, and greatly improves the spatiotemporal accuracy of dissolved oxygen and nutrient calculations.

[0012] In some specific embodiments, the constraints for the ecological health index are: the total nutrient flux in the simulated area is less than or equal to zero within a complete aquaculture cycle; the constraints for the biological survival index are: the real-time dissolved oxygen concentration in all computational units involved in aquaculture activities is not lower than the preset biological survival critical threshold. By setting dual constraints of ecological compensation and survival red lines, a dynamic safety boundary is established for aquaculture production, achieving the optimization of maximizing output potential while protecting the carbon and nitrogen balance of the ecosystem.

[0013] In some specific embodiments, the method further includes: S5: generating decision suggestions based on dynamic aquaculture capacity, including instructions for starting and stopping aeration equipment, instructions for adjusting feeding strategies, or harvesting and sorting plans. This transforms complex simulation data into intuitive production control instructions, shortening the decision-making chain from "risk discovery" to "human intervention," and significantly reducing the risk of mortality in farmed organisms caused by sudden environmental changes.

[0014] According to a second aspect of the invention, a computer-readable storage medium is provided on which one or more computer programs are stored, which, when executed by a computer processor, implement the method described above.

[0015] According to a third aspect of the present invention, a bay aquaculture capacity assessment system based on digital twin technology is proposed, comprising: The digital spatial modeling module is configured to acquire multi-source real-time data of the target aquaculture area, including environmental characteristic data and biological activity data; and to establish a digital spatial model corresponding to the target aquaculture area. The digital spatial model is configured with a simulation engine that integrates environmental evolution logic and biological metabolic mechanisms. The dynamic coupling module is configured to divide the digital spatial model into several computational units. Within the computational step of the computational unit, the material contribution generated by the metabolism of farmed organisms is defined as the source term, and the material consumption generated by the activities of farmed organisms is defined as the sink term. The source term, sink term and environmental evolution logic are dynamically coupled in the spatiotemporal scale. The trend simulation module is configured to perform state calibration of the digital spatial model based on multi-source real-time data, and to simulate the environmental evolution trend in future periods by combining predictive driving data. The iterative evaluation module is configured to perform iterative simulations by adjusting the aquaculture configuration parameters in the digital spatial model, using ecological health indicators and biological survival indicators as constraints, and output dynamic aquaculture capacity that meets the constraints.

[0016] The above technical solution provides a complete digital twin closed-loop architecture, which realizes digital management of all elements of aquaculture and improves the intelligent operation efficiency and data resource integration of the bay aquaculture system in complex environments.

[0017] In some specific embodiments, the system further includes: The decision execution module is configured to generate decision suggestions based on dynamic aquaculture capacity. These suggestions include commands to start / stop aeration equipment, commands to adjust feeding strategies, and harvesting and sorting plans. A reverse control logic of "perception-analysis-execution" has been established, enabling intelligent intervention from virtual space to physical entities, ensuring the precise implementation and refined management of aquaculture control plans.

[0018] This invention proposes a method and system for assessing the aquaculture capacity of a bay based on digital twin technology, which has the following technical advantages: First, this invention constructs a simulation engine that integrates environmental evolution logic and biological metabolic mechanisms, coupling physical environmental fluctuations with the instantaneous state of biological activity at the computational unit level. Compared with traditional estimation methods that rely on static formulas or historical experience, this scheme can reflect the dynamic balance between the water body's self-purification capacity and biological load in real time, transforming aquaculture capacity from a fixed reference value into a dynamic indicator that evolves in real time with environmental characteristics. This effectively overcomes the resource waste or ecological overload problems caused by empiricism.

[0019] Secondly, this invention introduces predictive data to conduct scenario simulations for future time periods, using external stimuli such as weather forecasts and astronomical tide levels to drive the digital spatial model forward. This enables the system to anticipate potential risks in aquaculture areas under extreme conditions such as weakened wind fields and water stratification, including decreased dissolved oxygen and ammonia nitrogen accumulation. This forward-looking simulation capability provides a scientific basis for the advance allocation of dynamic aquaculture capacity, realizing a shift from a "passive post-disaster remediation" to a "proactive pre-disaster early warning and control" production model.

[0020] Furthermore, this invention constructs a three-dimensional discretized grid based on computational fluid dynamics logic. By solving the Navier-Stokes equations and convection-diffusion equations, it quantifies the complex nonlinear relationship between the metabolic source-sink terms of aquaculture organisms and the hydrodynamic transport field. This highly faithful digital modeling method can not only accurately capture the local material contribution and consumption gradients of aquaculture grid points, but also simulate the long-term impact of different aquaculture configuration parameters on the overall ecological flux of the bay, providing scientific, intuitive, and physically consistent decision support for optimizing aquaculture layout and density control.

[0021] Finally, this invention goes beyond capacity assessment; by outputting control recommendations that meet constraints, it directly impacts physical execution equipment, forming a complete digital twin management closed loop. Presenting complex physical and biochemical processes and capacity assessment models through three-dimensional visualization significantly lowers the operational threshold for users. This automated and refined closed-loop control logic significantly reduces the intensity of manual inspections and management risks, providing a solid technological foundation for achieving unmanned or minimally manned high-end intelligent aquaculture. Attached Figure Description

[0022] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments and, together with the description, serve to explain the principles of the invention. Many anticipated advantages of the embodiments and other embodiments of the invention will be readily recognized as they become better understood through reference to the following detailed description. Other features, objects, and advantages of this application will become more apparent from reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart of a method for assessing the aquaculture capacity of a bay based on digital twin technology, according to one embodiment of this application; Figure 2 This is a framework diagram of a bay aquaculture capacity assessment system based on digital twin technology, which is a specific embodiment of this application; Figure 3 This is a schematic diagram of the structure of a computer system used to implement the electronic device of the present application. Detailed Implementation

[0023] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] Figure 1 A flowchart illustrating a method for assessing bay aquaculture capacity based on digital twin technology, according to an embodiment of this application, is shown. Figure 1 As shown, the method includes the following steps: S1: Acquire multi-source real-time data of the target aquaculture area, including environmental characteristic data and biological activity data; establish a digital spatial model corresponding to the target aquaculture area, and configure a simulation engine that integrates environmental evolution logic and biological metabolic mechanism into the digital spatial model.

[0026] In some specific embodiments, a physical entity layer for aquaculture, namely a sensing layer, is constructed. A multi-dimensional sensing network is deployed in the target aquaculture area. Water quality sensor arrays are deployed at different depths in the water to monitor dissolved oxygen, temperature, pH, ammonia nitrogen, and nitrite parameters in real time. Underwater imaging units are used to acquire image data of biological activity. Full-element automatic weather stations are used to monitor wind speed, wind direction, light intensity, and rainfall. Acoustic Doppler Current Profilers (ADCPs) are used to monitor water flow and acquire profile velocity data of the dynamic flow field of the water body, realizing the synchronous acquisition of spatiotemporal data of physical environmental characteristics and biological behavior.

[0027] In some specific embodiments, a virtual twin of aquaculture is constructed. Three-dimensional geographic environment spatial modeling is performed by acquiring geographic mapping data, bottom sediment data, and shoreline data of the target aquaculture area. Using UAV aerial photogrammetry data and sonar multibeam topographic survey data, a high-precision three-dimensional digital base model is constructed, encompassing water space, bottom sediment characteristics, shoreline geometry, and aquaculture facilities. Based on this, a three-dimensional discretized mesh is constructed using computational fluid dynamics logic, serving as the computational unit to support the simulation engine. This provides a unified spatial benchmark and numerical computation carrier for the coupled analysis of hydrodynamics, water quality, and biological metabolism.

[0028] Specifically, computational fluid dynamics (CFD) logic refers to an algorithmic system that uses physical conservation laws to numerically solve for fluid motion and mass transport in target water bodies. This includes using the finite volume method or finite element method to spatiotemporally discretize the continuity equation, Navier-Stokes equations, and mass convection-diffusion equations describing fluid motion. By executing iterative algorithms on a three-dimensional discretized grid, the velocity, pressure, and concentration fields of each computational unit are solved in real-time within each computational step, thereby achieving quantitative simulation of the dynamic evolution of water bodies and the migration of habitat elements in complex bay environments. By introducing mature CFD logic as the simulation foundation and utilizing its rigorous physical conservation calculations, a physically consistent computational carrier is provided for the proposed dynamic coupling of biological metabolism, ensuring the scientific validity and high accuracy of the dynamic aquaculture capacity assessment results.

[0029] In some specific embodiments, the environmental evolution logic integrates a three-dimensional hydrodynamic water quality model, which simulates the physical flow, mixing and transport processes of water by solving the Navier-Stokes equations, and combines the convection-diffusion equations to simulate the spatial concentration field evolution of dissolved oxygen, nutrients and pollutants. The environmental evolution logic can respond in real time to external meteorological drives and changes in water flow boundaries, and realize the digital mapping of the physical and biochemical processes of the aquaculture environment.

[0030] In some specific embodiments, the biological metabolic mechanism integrates biological growth and metabolism models. By establishing a correlation function with individual biomass, real-time water temperature and dissolved oxygen concentration as independent variables, the feeding, respiration and excretion processes of cultured organisms at different growth stages are simulated. The mechanism is used to quantify the immediate oxygen consumption of individual organisms and the total amount of nitrogen- and phosphorus-containing metabolic waste discharged into the water body, and to transform it into dynamic source and sink terms in virtual space.

[0031] S2: Divide the digital spatial model into several computational units. Within the computational step of each unit, define the material contribution generated by the metabolism of farmed organisms as the source term and the material consumption generated by the activities of farmed organisms as the sink term. Dynamically couple the source term, sink term and environmental evolution logic on a spatiotemporal scale.

[0032] In some specific embodiments, the virtual simulation engine adopts a non-equilibrium dynamic calculation mode to calculate the nutrient (N, P) balance and biological oxygen consumption processes based on different aquaculture densities and layouts. Within each model calculation step, the advection and diffusion processes of nutrients released by feeding aquaculture organisms within the model area are quantitatively calculated, and the oxygen consumption rate related to the individual organism mass and ambient temperature is calculated simultaneously. Nutrient release and oxygen consumption are loaded as dynamic source and sink terms into the NORWECOM computing grid based on the current aquaculture layout. After completing the source and sink term integration calculation, the mixing, advection and diffusion of water flow processes are numerically solved.

[0033] In some specific embodiments, the construction of the dynamic coupling model includes integrating and coupling a hydrodynamic water quality model and a biological growth and metabolism model on the basis of a three-dimensional digital base model. The hydrodynamic water quality model uses numerical solutions to simulate the advection, diffusion, and mixing processes of water bodies, mapping the spatiotemporal evolution and distribution of key water quality indicators such as dissolved oxygen, nutrients, and pollutants in real time. The biological growth and metabolism model constructs correlation equations between the growth rate of cultured organisms and environmental factors (including temperature, dissolved oxygen, and salinity), dynamically simulating the feeding, respiration, and excretion processes of organisms, and quantifying the generation rate of metabolic wastes such as ammonia nitrogen.

[0034] S3: Perform state calibration on the digital spatial model based on multi-source real-time data, and simulate the environmental evolution trend in future periods by combining predictive driving data.

[0035] In some specific embodiments, state calibration and trend simulation acquire water quality and hydrodynamic parameters fed back from the sensing layer in real time through a data interface. Assimilation algorithms are used to dynamically calibrate the boundary conditions and initial field of the digital spatial model, ensuring high fidelity between the virtual twin and the physical entity. Combined with forecast-driven data (such as weather forecasts and astronomical tide forecasts), the simulation simulates the environmental evolution trend under different meteorological conditions, feeding strategies, and aquaculture loads over the next 24 to 72 hours. The forecast-driven data refers to boundary parameters acquired from external forecasting systems or preset manually, used to constrain the future evolution trend of the digital spatial model. Specifically, this includes hourly weather forecasts (such as wind field, air pressure, and illumination) for the next 24 to 72 hours, astronomical tide forecasts, and preset aquaculture management plans (such as feeding plans and oxygenation strategies).

[0036] S4: Using ecological health indicators and biological survival indicators as constraints, iterative simulation is performed by adjusting the aquaculture configuration parameters in the digital spatial model to output the dynamic aquaculture capacity that meets the constraints.

[0037] In some specific embodiments, within a complete aquaculture cycle, the spatial impact weights of nutrient release and absorption in each computational unit (i.e., aquaculture unit) are calculated to quantitatively assess environmental carrying capacity pressure. By adjusting the cage layout parameters, aquaculture density parameters, and number of cages in the virtual scenario, the nutrient load and oxygen consumption distribution are recalculated iteratively to simulate and explore changes in environmental impact under reduced aquaculture or optimized layout schemes. Among these, the ecological health indicator is the maximum aquaculture biomass that the water body's self-purification capacity can support under current environmental conditions, calculated in real-time and used as the dynamic aquaculture capacity. This comprehensively considers the absorption capacity of aquaculture algae for dissolved nutrients, ensuring that aquaculture activities do not exacerbate eutrophication, i.e., the total nitrogen and total phosphorus fluxes in the simulated area within the calculation step are less than or equal to zero. Simultaneously, the biological survival indicator is the risk period and area where the dissolved oxygen concentration in the fish aquaculture area is not less than the survival threshold of 4 mg / L in real-time. In some specific embodiments, the capacity assessment model iterative steps include adding a biomass-based oxygen consumption rate function to the aquaculture calculation grid locations, loading corresponding oxygen consumption sinks according to different growth stages of the cultured organisms; within each calculation step, numerically solving for the advection and diffusion effects caused by coupled hydrodynamics, and checking whether there is a dissolved oxygen concentration less than 4 mg / L during the simulation process; if there is a risk, adjusting the aquaculture layout by reducing the number of aquaculture cages or changing the aquaculture grids in specific areas to non-aquaculture status, repeating the simulation calculation until the maximum total biomass that meets the above-mentioned ecological health indicators and biological survival indicators constraints is found, and outputting optimal cage number and layout control suggestions based on the result.

[0038] In some specific embodiments, real-time and predicted aquaculture capacity, key water quality parameters, and risk areas are visualized on a large dashboard screen or mobile terminal. An automatic warning is issued when the predicted aquaculture capacity is close to or lower than the current actual aquaculture volume, or when key water quality indicators exceed thresholds. Based on simulation results, intelligent optimization and control suggestions are generated, such as: suggesting the timing and duration of aerator activation, adjusting feed quantity and timing, and suggesting bin separation or harvesting plans. Preferably, the generated control commands (such as activating aerators in specific locations) can be sent to the physical layer execution devices via a control network to achieve automated and precise control, forming a closed loop of "perception-modeling-decision-control".

[0039] Example A physical entity layer for aquaculture is constructed by deploying a multi-dimensional sensing network in nearshore cage aquaculture areas. By deploying sensor buoys with surface, middle, and bottom monitoring capabilities inside and outside the cages, multi-depth real-time monitoring of environmental characteristics such as dissolved oxygen and temperature is achieved. At the same time, acoustic Doppler current profilers are deployed in the area surrounding the cages to monitor the flow field, and wind direction and speed forecast data provided by meteorological stations are connected in real time. This enables holographic perception and spatiotemporal synchronous acquisition of multi-source heterogeneous data in the physical space.

[0040] A virtual twin of aquaculture was constructed, and a sonar detection device mounted on an unmanned vessel was used to conduct precise mapping of the bottom sediment and surrounding seabed topography of the aquaculture area. Combined with remote sensing image data, a high-precision three-dimensional digital spatial model was constructed, including the cage structure, reef landform, ocean current path and water body boundary. The digital spatial model was integrated and coupled with the growth and metabolic equations of a specific aquaculture species (such as large yellow croaker). Based on biological survival indicators, the dissolved oxygen concentration of not less than 4 mg / L and the total ammonia nitrogen concentration of ecological health indicators of not exceeding the safety threshold were set as the core constraints for operation.

[0041] During operation, the digital spatial model receives dissolved oxygen and temperature data from the sensing layer in real time through a data interface. It uses an assimilation algorithm to dynamically correct the initial field of the model, achieving real-time synchronization between the virtual mapping and the physical entity state. After receiving wind field forecast data for the next 48 hours, the digital twin engine starts predictive simulation. When the simulation reveals that the dissolved oxygen at the bottom of the cage will drop to 3.5 mg / L due to weakened wind speed and increased water stratification in the early morning of the next day, and the calculated dynamic aquaculture capacity is lower than the current actual fish stock, it immediately identifies the capacity gap and habitat risk.

[0042] The system executes decisions and implements closed-loop control, issuing low-oxygen risk warnings and displaying highlighted risk points on the digital management interface. Simultaneously, it uses a simulation engine to iteratively calculate the optimal control strategy, recommending that the oxygenation equipment at the bottom of the cage be turned on at a preset time before the risk occurs (e.g., 8:00 PM that evening) and continue to run until the environmental recovery period the next day (e.g., 8:00 AM the next day). The control commands are sent to the execution end of the physical layer through the control interface, and the oxygenation equipment is either confirmed by the management personnel or automatically driven by the system. This completes the digital management closed loop from "real-time perception - predictive simulation - intelligent decision-making - reverse control", effectively preventing oxygen deficiency accidents in aquaculture organisms.

[0043] Continue to refer to Figure 2 As an implementation of the above method, this application provides an embodiment of a framework diagram 200 for a bay aquaculture capacity assessment system based on digital twin technology. This system embodiment is similar to... Figure 1Corresponding to the illustrated method embodiment, this system can be specifically applied to various electronic devices. The system 200 includes a digital space modeling module 201, a dynamic coupling module 202, a trend simulation module 203, an iterative evaluation module 204, and a decision execution module 205, all interconnected, wherein: The digital spatial modeling module 201 is configured to acquire multi-source real-time data of the target aquaculture water area, including environmental characteristic data and biological activity data; and to establish a digital spatial model corresponding to the target aquaculture water area. The digital spatial model is configured with a simulation engine that integrates environmental evolution logic and biological metabolic mechanism. The dynamic coupling module 202 is configured to divide the digital spatial model into several computing units. Within the computing step of the computing unit, the material contribution generated by the metabolism of farmed organisms is defined as the source term, the material consumption generated by the activities of farmed organisms is defined as the sink term, and the source term, sink term and environmental evolution logic are dynamically coupled in the spatiotemporal scale. The trend simulation module 203 is configured to perform state calibration of the digital spatial model based on multi-source real-time data, and to simulate the environmental evolution trend in future periods by combining predictive driving data. The iterative evaluation module 204 is configured to perform iterative simulations by adjusting the aquaculture configuration parameters in the digital spatial model, using ecological health indicators and biological survival indicators as constraints, and output dynamic aquaculture capacity that meets the constraints.

[0044] The decision execution module 205 is configured to generate decision suggestions based on dynamic aquaculture capacity. The decision suggestions include instructions for starting and stopping aeration equipment, instructions for adjusting feeding strategies, or harvesting and sorting schemes.

[0045] The following is for reference. Figure 3 It shows a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0046] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 308 into random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the system 300. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0047] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a liquid crystal display (LCD) and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card and a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to I / O interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 310 as needed so that computer programs read from it can be installed into storage section 308 as needed.

[0048] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the methods of this application. It should be noted that the computer-readable storage medium of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0049] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0050] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0051] The modules described in the embodiments of this application can be implemented in software or in hardware.

[0052] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire multi-source real-time data of the target aquaculture area, including environmental characteristic data and biological activity data; establish a digital spatial model corresponding to the target aquaculture area, the digital spatial model being configured with a simulation engine integrating environmental evolution logic and biological metabolic mechanisms; divide the digital spatial model into several computational units, defining the material contribution generated by the metabolism of aquaculture organisms as source terms and the material consumption generated by the activities of aquaculture organisms as sink terms within the computational step size of the computational units, and dynamically coupling the source terms, sink terms, and environmental evolution logic on a spatiotemporal scale; perform state calibration of the digital spatial model based on multi-source real-time data, and simulate the environmental evolution trend in future periods by combining predictive driving data; and perform iterative simulation by adjusting the aquaculture configuration parameters in the digital spatial model using ecological health indicators and biological survival indicators as constraints, outputting a dynamic aquaculture capacity that meets the constraints.

[0053] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for assessing the aquaculture capacity of a bay based on digital twin technology, characterized in that, include: S1: Acquire multi-source real-time data of the target aquaculture area, including environmental characteristic data and biological activity data; establish a digital spatial model corresponding to the target aquaculture area, wherein the digital spatial model is configured with a simulation engine that integrates environmental evolution logic and biological metabolic mechanism; S2: Divide the digital spatial model into several computing units. Within the computing step of the computing unit, define the material contribution generated by the metabolism of farmed organisms as the source term and the material consumption generated by the activities of farmed organisms as the sink term. Dynamically couple the source term, the sink term and the environmental evolution logic on a spatiotemporal scale. S3: Based on the multi-source real-time data, perform state calibration on the digital spatial model, and combine it with predictive driving data to simulate the environmental evolution trend in future time periods; S4: Using ecological health indicators and biological survival indicators as constraints, iterative simulation is performed by adjusting the aquaculture configuration parameters in the digital spatial model to output a dynamic aquaculture capacity that meets the constraints.

2. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 1, characterized in that, The multi-source real-time data includes velocity field data obtained using an acoustic velocity profiler, dissolved oxygen gradient data obtained using a multi-layer water quality sensor, and wind field forecast data obtained using a weather station.

3. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 1, characterized in that, The steps for constructing the digital spatial model include: acquiring geographic mapping data, bottom sediment data, and shoreline data of the target aquaculture area; and constructing a three-dimensional discretized mesh based on computational fluid dynamics logic as the computing unit carrying the simulation engine.

4. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 1, characterized in that, The environmental evolution logic integrates a three-dimensional hydrodynamic water quality model, which simulates the physical flow and transport processes of water bodies by solving the Navier-Stokes equations, and combines the convection-diffusion equations to map the spatiotemporal concentration field distribution of dissolved oxygen, nutrients and pollutants in each computational unit in real time.

5. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 1, characterized in that, The biological metabolic mechanism integrates a biological growth and metabolism model. By establishing a correlation function with individual biomass, real-time water temperature, and dissolved oxygen concentration as independent variables, the feeding, respiration, and excretion rates of cultured organisms at different growth stages are dynamically quantified. The resulting instantaneous oxygen consumption and metabolic waste release are then converted into dynamic source and sink terms in a digital spatial model.

6. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 4, characterized in that, The dynamic coupling specifically includes: loading the nutrient load generated by the metabolism of cultured organisms as the source term into the corresponding computing unit, and loading the oxygen consumption generated by the respiration of cultured organisms as the sink term into the corresponding computing unit; within each computing step, based on the real-time flow field data output by the environmental evolution logic, driving the convection-diffusion equation to simultaneously solve the advection, diffusion and mixing processes of substances in each computing unit.

7. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 1, characterized in that, The constraints for the ecological health indicators are: the total nutrient flux in the simulated area is less than or equal to zero within a complete aquaculture cycle; the constraints for the biological survival indicators are: the real-time dissolved oxygen concentration in all calculation units involved in aquaculture activities is not lower than the preset critical threshold for biological survival.

8. The method for assessing bay aquaculture capacity based on digital twin technology according to claim 1, characterized in that, The method further includes: S5: Generate decision suggestions based on dynamic aquaculture capacity, including instructions for starting and stopping aeration equipment, instructions for adjusting feeding strategies, or harvesting and sorting schemes.

9. A bay aquaculture capacity assessment system based on digital twin technology, characterized in that, include: The digital spatial modeling module is configured to acquire multi-source real-time data of the target aquaculture area, including environmental characteristic data and biological activity data; and to establish a digital spatial model corresponding to the target aquaculture area, wherein the digital spatial model is configured with a simulation engine that integrates environmental evolution logic and biological metabolic mechanism. The dynamic coupling module is configured to divide the digital spatial model into several computing units. Within the computing step of the computing unit, the material contribution generated by the metabolism of farmed organisms is defined as the source term, the material consumption generated by the activities of farmed organisms is defined as the sink term, and the source term, the sink term, and the environmental evolution logic are dynamically coupled in the spatiotemporal scale. The trend simulation module is configured to perform state calibration on the digital spatial model based on the multi-source real-time data, and to simulate the environmental evolution trend in future time periods in combination with predictive driving data. The iterative evaluation module is configured to perform iterative simulations by adjusting the aquaculture configuration parameters in the digital spatial model, using ecological health indicators and biological survival indicators as constraints, and output dynamic aquaculture capacity that meets the constraints.

10. A bay aquaculture capacity assessment system based on digital twin technology according to claim 9, characterized in that, The system also includes: The decision execution module is configured to generate decision suggestions based on dynamic aquaculture capacity. These suggestions include instructions to start / stop aeration equipment, instructions to adjust feeding strategies, or harvesting and sorting schemes.

Images