Early warning regulation method and system for aquaculture based on numerical simulation of groundwater salinity

Abstract

This invention relates to the field of smart agriculture and aquaculture safety monitoring technology, specifically to a method and system for early warning and control in aquaculture based on groundwater salinity numerical simulation. The method includes: collecting geological and hydrogeological data of the aquaculture pond to construct an initial groundwater salinity numerical model; collecting real-time environmental water quality data, including salinity, pH, and water level, through a sensor network deployed inside and outside the aquaculture pond; calibrating the initial groundwater salinity numerical model based on the real-time environmental water quality data; simulating the groundwater flow field and solute transport trends within a future target time period using the calibrated groundwater salinity numerical model, and predicting and outputting predicted water quality parameters for each target point in the aquaculture pond; and then providing risk warnings and control schemes based on the predicted water quality parameters and a dynamic water-salt balance model. This allows for scientific and efficient risk warning, significantly improving the risk resistance capability of aquaculture.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture and aquaculture safety monitoring technology, specifically to an aquaculture early warning and control method and system based on groundwater salinity numerical simulation. Background Technology

[0002] Aquaculture, especially saline-alkali land aquaculture, is an important industry that plays a crucial role in ensuring food security and expanding agricultural production space. However, aquaculture ponds have long faced significant safety risks caused by the unpredictable upwelling of underground saline water. Sudden upwelling of underground saline water can cause drastic fluctuations in key water quality parameters such as salinity and pH in aquaculture ponds. This risk is highly insidious and sudden, often leading to the "pond overflow" and complete crop failure, resulting in heavy economic losses and severely restricting the safe expansion and sustainable development of aquaculture, especially saline-alkali land aquaculture.

[0003] To address the aforementioned risks, existing technologies generally include two main solutions, but both have significant drawbacks: First, traditional experience-based judgment methods rely entirely on the personal practical experience of farmers, lack scientific theory and data support, have extremely low prediction accuracy, and are completely unable to cope with the complex and ever-changing groundwater flow field, making it difficult to predict the risk of sudden changes in water quality in advance; Second, general IoT water quality monitoring systems, although they can achieve real-time monitoring of parameters such as salinity and pH value by deploying sensors, can only issue alarms after the water quality has exceeded the standard, and cannot provide early warnings before the risk occurs, resulting in farmers lacking sufficient time to intervene and only being able to passively bear the losses.

[0004] In addition, due to the lack of accurate forecast data and control methods, aquaculture decisions rely heavily on personal experience, leading to a "trial and error" dilemma: insufficient control results in continued losses, while excessive control wastes precious water and energy resources and may cause new environmental stresses due to frequent water changes.

[0005] In summary, existing technologies have not yet developed a dedicated solution that can provide farmers, especially those in saline-alkali land, with advanced and quantitative risk warnings and decision-making based on real-time monitoring data. Therefore, there is an urgent need for a technical solution that balances scientific rigor, practicality, and ease of use to address the challenges of predicting and accurately controlling sudden changes in water quality in saline-alkali land aquaculture. Summary of the Invention

[0006] In view of this, the purpose of this invention is to provide a method and system for early warning and control of aquaculture based on numerical simulation of groundwater salinity, so as to overcome the current problem that it is impossible to conduct scientific and efficient risk warning and precise control for aquaculture, especially saline-alkali aquaculture.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] Firstly, this application provides a method for early warning and control of aquaculture based on numerical simulation of groundwater salinity, including: Collect geological and hydrogeological data of the aquaculture ponds and construct an initial numerical model of groundwater salinity; Real-time environmental water quality data is collected by a sensor network deployed inside and outside the aquaculture pond. The real-time environmental water quality data includes salinity, pH value and water level. The initial groundwater salinity numerical model was calibrated based on the real-time environmental water quality data. The calibrated groundwater salinity numerical model is used to simulate the groundwater flow field and solute transport trend in the future target period, and to predict the water quality parameters of each target point in the aquaculture pond. Risk warnings and control schemes are provided based on the predicted water quality parameters and the dynamic water-salt balance model.

[0009] Furthermore, in some embodiments of this application, the collection of geological and hydrogeological data of the aquaculture ponds and the construction of an initial groundwater salinity numerical model include: Collect geological and hydrogeological data of the aquaculture ponds; The collected geological and hydrogeological data of the aquaculture ponds were used to construct a three-dimensional digital twin model of the aquaculture ponds and the surrounding underground aquifers based on the MODFLOW numerical simulation engine. The three-dimensional digital twin model is used as the initial numerical model for groundwater salt.

[0010] Furthermore, in some embodiments of this application, the sensor network includes a salinity sensor, a pH sensor, and a water level sensor disposed at each target point; The target locations include the inlet, outlet, and center of the aquaculture pond, as well as the observation wells outside the aquaculture pond.

[0011] Furthermore, in some embodiments of this application, the initial groundwater salinity numerical model is calibrated based on the real-time environmental water quality data, including: The real-time environmental water quality data is assimilated using an ensemble Kalman filter algorithm to dynamically calibrate the initial groundwater salinity numerical model.

[0012] Furthermore, in some embodiments of this application, risk warning and control schemes are provided based on the predicted water quality parameters and the dynamic water-salt balance model, including: Based on the predicted water quality parameters, real-time water volume and salinity in the aquaculture pond, and aquaculture management parameters, a dynamic water-salt balance model is used to perform reverse simulation with preset constraints as the objective, generating a risk warning report and calculating feasible control schemes. Based on a preset optimization strategy, a recommended control scheme is determined from the feasible control schemes, and a control decision report is generated. The risk warning report includes the risk location, risk level, and expected occurrence time, and the quantitative parameters in the recommended control plan include water exchange start time, water exchange flow rate, and water exchange duration.

[0013] Furthermore, in some embodiments of this application, the preset optimization strategy is a strategy of lowest cost, strategy of least water consumption, or strategy of simplest operation. The aquaculture management parameters include at least one of the following: planned water exchange rate, available freshwater source quality, evaporation rate, and precipitation replenishment.

[0014] Furthermore, in some embodiments of this application, the method further includes: pushing the risk warning report and the control decision report to the user; wherein the pushing method includes at least one of web page, SMS or application push.

[0015] Furthermore, in some embodiments of this application, it also includes: Before implementing the recommended control scheme, the parameters of the groundwater salinity numerical model are corrected based on real-time environmental water quality data. After implementing the recommended control scheme, the parameters of the dynamic water-salt balance model of groundwater salt number are corrected based on real-time environmental water quality data.

[0016] Secondly, this application provides an aquaculture early warning and control system based on groundwater salinity numerical simulation, used to implement the aforementioned aquaculture early warning and control method based on groundwater salinity numerical simulation, including: The groundwater salinity model module is used to collect geological and hydrogeological data of aquaculture ponds, and based on the geological and hydrogeological data of aquaculture ponds collected by the data collection module, to construct an initial groundwater salinity numerical model; and after calibration, to simulate the groundwater flow field and solute transport trend in future target time periods, and to predict and output the predicted values ​​of water quality parameters at each target point in the aquaculture pond. Sensors deployed inside and outside the aquaculture pond are used to collect real-time environmental water quality data, including salinity, pH value and water level. The data assimilation and calibration module is used to calibrate the initial groundwater salinity numerical model based on the real-time environmental water quality data. The dynamic water-salt balance model module is used to provide risk warnings and control solutions based on the predicted values ​​of the water quality parameters.

[0017] Furthermore, in some embodiments of this application, a wireless communication module is also included; The sensor is communicatively connected to the data assimilation and calibration module, the groundwater model module, and the dynamic water-salt balance model via the wireless communication module. The wireless communication module includes at least one of LoRa, NB-IoT, 4G, or 5G network modules.

[0018] This invention relates to the field of smart agriculture and aquaculture safety monitoring technology, specifically to an aquaculture early warning and control method and system based on groundwater salinity numerical simulation. The method includes: collecting geological and hydrogeological data of the aquaculture pond to construct an initial groundwater salinity numerical model; collecting real-time environmental water quality data, including salinity, pH value, and water level, through a sensor network deployed inside and outside the aquaculture pond; calibrating the initial groundwater salinity numerical model based on the real-time environmental water quality data; simulating the groundwater flow field and solute transport trend within a future target time period using the calibrated groundwater salinity numerical model, and predicting and outputting predicted water quality parameters for each target point in the aquaculture pond; and issuing a risk warning based on the predicted water quality parameters and a preset safety threshold. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this embodiment of the invention. Figure 2 This is a flowchart illustrating the principle of the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this embodiment of the invention. Figure 3 This is a schematic diagram of the layout of target points in the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in the embodiments of the present invention; Figure 4 This is a schematic diagram of the structure of an aquaculture early warning and control system based on groundwater salt numerical simulation provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0022] Figure 1 This is a schematic flowchart of the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this embodiment of the invention. Figure 2 This is a flowchart illustrating the principle of the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this invention. Please refer to the following: Figure 1 and Figure 2 In this embodiment, the risk warning section may specifically include the following steps: S101. Collect geological and hydrogeological data of the aquaculture ponds and construct an initial numerical model of groundwater salinity.

[0023] Specifically, geological and hydrogeological data of the aquaculture ponds are collected. Based on the MODFLOW numerical simulation engine, a three-dimensional digital twin model of the aquaculture ponds and the surrounding underground aquifers is constructed using the collected geological and hydrogeological data of the aquaculture ponds. The three-dimensional digital twin model is then used as the initial numerical model of groundwater salinity.

[0024] In practical applications, the system used in this application to implement the aquaculture early warning and control method based on groundwater salinity numerical simulation, namely the aquaculture early warning and control system based on groundwater salinity numerical simulation, can be divided into a perception layer, a model layer, and an application layer.

[0025] The model layer, which can be deployed on a cloud server or a local server, is the core computing unit of the entire system. Specifically, it can include: a groundwater salt numerical model module, a data assimilation and calibration module, and a dynamic water-salt balance model module.

[0026] Among them, the groundwater salinity numerical model module is used to realize the above-mentioned geological exploration data and hydrogeological parameters based on the aquaculture pond and numerical simulation engines such as MODFLOW to construct a three-dimensional digital twin model of the aquaculture pond and the surrounding underground aquifer, and obtain the initial groundwater salinity numerical model.

[0027] S102. Real-time environmental water quality data are collected through a sensor network deployed inside and outside the aquaculture pond.

[0028] Real-time environmental water quality data includes salinity, pH value, and water level.

[0029] Specifically, the aforementioned sensor network constitutes the perception layer, which includes a multi-parameter sensor network deployed in and around key locations of the aquaculture pond for real-time collection of environmental water quality data, including water quality data and environmental data such as salinity, pH value and water level. The sensor network includes multiple sensor nodes, equipped with salinity sensors, pH sensors and water level sensors (a single node can be equipped with all of the above types of sensors).

[0030] In practical applications, the aforementioned sensors continuously collect data from the aquaculture pond and its surroundings in real time. The collected data is transmitted via wireless networks such as LoRa and NB-IoT (of course, in some other embodiments of this application, 4G or 5G networks can also be used) and uploaded to the model layer for calibration of the groundwater salinity numerical model, which is then used for prediction (at the same time, it can also be used to determine the real-time water volume and salinity of the aquaculture pond, so as to input the dynamic water and salinity balance model in the dynamic water and salinity balance model module for risk prediction and determination of control schemes).

[0031] S103. The initial groundwater salinity numerical model is calibrated based on real-time environmental water quality data.

[0032] S104. Using the calibrated groundwater salinity numerical model, simulate the groundwater flow field and solute transport trend in the future target period, and predict the water quality parameters of each target point in the aquaculture pond.

[0033] Specifically, in this application, the data assimilation and calibration module mentioned above receives data from the perception layer, dynamically drives and calibrates the initial groundwater salinity numerical model, such as through data assimilation algorithms like ensemble Kalman filtering, to dynamically calibrate the initial groundwater salinity numerical model, update model parameters, and make its simulated state closer to the real situation. In practical applications, calibration can be performed once before prediction based on newly acquired data in each prediction cycle (e.g., 1 day) after model generation. Of course, in other embodiments, calibration can also be performed at longer intervals, which can be set based on actual accuracy requirements.

[0034] S105. Conduct risk warnings and provide control solutions based on predicted water quality parameters and dynamic water-salt balance models.

[0035] Specifically, in this application, the dynamic water-salt balance model in the dynamic water-salt balance model module simulates the predicted water quality parameters of each target point in the aquaculture pond (such as the location where the sensor is set) based on the groundwater-salt numerical model after operation and calibration, which simulates the groundwater flow and solute (such as salt) migration trend in future target periods such as 24-72 hours. Combined with real-time water volume and salinity of the aquaculture pond and aquaculture management parameters, risk warning and control schemes are achieved.

[0036] Based on this, the application layer mentioned above in this application is used to provide users with an interactive interface, which may specifically include a visual data dashboard and a push module.

[0037] The system includes a visual data dashboard that displays real-time data collected by sensors, results of groundwater salinity numerical model simulations and historical trends, as well as risk warnings and control measures provided by the dynamic water-salt balance model. A push module delivers risk warnings and control measures information from the dynamic water-salt balance model to users. Risk warnings can be risk warning reports, including the risk location, risk level, and expected occurrence time. Control measures information can be control decision reports including recommended control measures, with quantitative parameters such as water exchange start time, water exchange flow rate, and water exchange duration. Push notifications can be delivered via at least one of the following methods: webpage, SMS, or application push.

[0038] Furthermore, in this application, risk warning and control schemes are provided based on predicted water quality parameters and a dynamic water-salt balance model, including: based on predicted water quality parameters, real-time water volume and salinity of groundwater aquaculture ponds, and aquaculture management parameters, a reverse simulation is performed using a dynamic water-salt balance model with preset constraints as the objective, generating a risk warning report and calculating feasible control schemes; and based on preset optimization strategies, a recommended control scheme is determined from the feasible control schemes and a control decision report is generated.

[0039] Specifically, the dynamic water-salt balance model is first constructed based on the law of conservation of mass using the dynamic water-salt balance model module.

[0040] After constructing the dynamic water-salt balance model, based on the predicted water quality parameters output by the aforementioned groundwater-salt numerical model for the future target period, the predicted total salt content (solute input flux) that groundwater will input into the aquaculture pond within the future target hour (e.g., 40 hours determined based on actual needs) is determined. Simultaneously, the current real-time water volume (e.g., water volume), current salinity, and aquaculture management parameters (e.g., planned water exchange rate, available freshwater source quality (i.e., available freshwater salinity), evaporation rate, precipitation replenishment, and maximum flow rate of the water exchange pump, etc., obtained from real-time monitoring, are acquired and input into the dynamic water-salt balance model to determine if any risks exist. If no risks are identified, predictions continue using the groundwater-salt numerical model.

[0041] If a risk exists, a risk warning report containing information such as the location of the risk, the risk level, and the expected time of occurrence is generated using a dynamic water-salt balance model. Simultaneously, using a preset rigid constraint target, such as "salinity of pool water ≤ 8‰ at 40 hours," reverse simulation calculations are performed on decision variables such as "water exchange start-up time (Ts)," "water exchange flow rate (Q)," and "duration (T)" to directly solve for all (Ts, Q, T) parameter combinations that can meet the target. Each combination is considered a feasible control scheme.

[0042] Based on this, a recommended control scheme is determined from the aforementioned feasible control schemes according to the preset optimization strategy, and a control decision report is generated.

[0043] Specifically, the system selects from all feasible control schemes based on preset optimization strategies (such as the lowest cost strategy, the least water consumption strategy, or the simplest operation strategy). For example, from the two feasible control schemes "Scheme A: immediately replace water at 50 m3 / h for 6.5 hours" and "Scheme B: replace water at 65 m3 / h for 5 hours after 2 hours", the scheme with the least water consumption is selected as the recommended control scheme.

[0044] Based on this, a structured decision report for intelligent regulation, namely a regulation decision report, can be output based on the above information. An example of its content is: "[Regulation Decision Instruction for Pond No. 3] Objective: Prevent salinity from exceeding the standard (safety threshold ≤ 8‰). Recommended solution: Delay water exchange for 2 hours, flow rate 65 m³ / h, continuous for 5 hours, total water consumption 325 tons. Expected effect: Salinity will drop to 7.8‰ in the 38th hour and remain stable. Please confirm execution." (It is understood that in some embodiments of this application, the risk warning report and the regulation decision report can also be merged to generate a comprehensive report.)

[0045] Furthermore, in some embodiments of this application, the parameters of the groundwater salinity numerical model are corrected based on real-time environmental water quality data before the recommended control scheme is implemented; and the parameters of the groundwater salinity dynamic water-salt balance model are corrected based on real-time environmental water quality data after the recommended control scheme is implemented.

[0046] For example, without user intervention, the groundwater salinity numerical model can be optimized directly using newly collected real-time environmental water quality data.

[0047] The system records user intervention measures and actual water quality changes before and after intervention (e.g., determined by real-time environmental water quality data detected by the aforementioned sensors). Based on these recorded actual water quality changes after user intervention, the system optimizes the dynamic water-salt balance model. For example, after a user executes a recommended control plan, the system continuously compares the actual salinity decrease curve determined by the actual water quality changes with the predicted salinity decrease curve. If there is a systematic deviation, the system can automatically correct local parameters (such as the mixing efficiency coefficient) in the dynamic water-salt balance model using a preset self-learning unit, thereby achieving continuous accuracy and personalized adaptation of the dynamic water-salt balance model (similarly, the groundwater salinity numerical model can also be optimized using this principle).

[0048] Figure 3 This is a schematic diagram of the target point layout in the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this embodiment of the invention, as shown in the figure. Figure 3As shown in some embodiments of this application, the target locations include inside and outside the aquaculture pond. The inside of the aquaculture pond may include the inlet, outlet, and center of the pond, while the outside of the aquaculture pond may include various observation wells in the surrounding area of ​​the aquaculture pond.

[0049] The following is a practical application example illustrating the specific application of the aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this application: For a standard aquaculture base (including multiple aquaculture ponds) covering approximately 10 acres in a certain region, the hardware deployment (corresponding to the aforementioned sensing layer) includes: Based on Figure 3 As shown, three target points are planned within each aquaculture pond: the inlet, the center of the pond, and the outlet. (All aquaculture ponds can be numbered, and the sensors under each pond can be mapped to the pond itself, allowing for rapid identification of at-risk ponds based on the sensor data at the target points during subsequent alarms.) Each point is equipped with a salinity and pH composite sensor (or two separate sensors can be installed). Two groundwater level observation wells are planned around the aquaculture ponds, each containing a water level sensor and a salinity and pH composite sensor for simultaneous monitoring of groundwater level changes, salinity, and pH. Wireless communication modules are also installed to enable all sensors to transmit data to the gateway via communication methods such as LoRa or 4G / NB-IoT, and then the gateway uploads the data to the cloud server.

[0050] The operations in software and model building (corresponding to the model layer mentioned above) include: A system platform is built on a cloud server, such as using the open-source MODFLOW6 engine. Based on the geological and hydrogeological data of the aquaculture farm, a three-dimensional digital twin model is constructed, including the aquaculture pond (as the boundary of the surface water body) and the aquifer within a 200-meter radius around it, and then discretized and meshed. At the application layer, the aforementioned groundwater-salt numerical model module, data assimilation and calibration module, and dynamic water-salt balance model module are developed.

[0051] In this way, the system can be put into actual operation.

[0052] Specifically, after system initialization, the groundwater salinity numerical model begins operation. In practical applications, it can be set to automatically perform a complete data collection process via sensors, calibration of the groundwater salinity numerical model, and prediction of water quality parameters at a predetermined time each morning. After the groundwater salinity numerical model completes its predictions, the predicted water quality parameters are used to provide risk warnings and control solutions through a dynamic water-salt balance model.

[0053] The aquaculture early warning and control method based on groundwater salinity numerical simulation provided in this application has the following significant advantages compared with the prior art: 1. Upgrade post-event alarms to pre-event warnings. By setting target time periods, users can be provided with a valuable 24-72 hours or even longer intervention window to ensure that users have sufficient time to deal with the situation. This can effectively avoid major aquaculture losses caused by sudden changes in water quality and maximize aquaculture safety.

[0054] 2. By deeply integrating multiple sensors and low-cost IoT technologies such as LoRa and NB-IoT with a professional-grade groundwater salinity numerical simulation model in the specific scenario of saline-alkali land aquaculture, an integrated solution of "monitoring-simulation-prediction" has been created, which greatly improves the accuracy of early warning.

[0055] 3. Through the "digital twin" based model and dynamic calibration mechanism, the complex groundwater model can be adapted to specific sites. Furthermore, by developing a software as a service (SaaS) interface with relevant visualization, the user threshold can be lowered, making it easy to replicate and promote in similar areas. It is highly practical and has high scalability.

[0056] 4. This invention creatively couples groundwater salt numerical simulation with dynamic water-salt balance analysis, and directly outputs quantitative and optimal control schemes (such as precise water exchange volume and timing) through reverse simulation technology. This solves the core decision-making problem of "how to do it and how much to do it" after early warning, and upgrades the experience-based trial-and-error aquaculture to data-driven precision intelligent aquaculture, realizing a fundamental leap from "risk early warning" to "quantitative decision-making".

[0057] 5. By automatically iterating and optimizing model parameters based on actual results, the accuracy of prediction and decision-making continues to improve with use, giving it adaptive and self-learning capabilities. This greatly enhances the long-term applicability and reliability of the system, forming an autonomous evolutionary closed loop of "monitoring-prediction-decision-feedback-optimization".

[0058] Based on the same inventive concept, this application also provides an aquaculture early warning and control system based on groundwater salinity numerical simulation, used to implement the above-described method embodiments. Figure 4 This is a schematic diagram of the structure of an aquaculture early warning and control system based on groundwater salinity numerical simulation provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the system includes: The groundwater salinity model module 11 is used to collect geological and hydrogeological data of the aquaculture pond, and based on the geological and hydrogeological data of the aquaculture pond collected by the data collection module, to construct an initial groundwater salinity numerical model; and after calibration, to simulate the groundwater flow field and solute transport trend in the future target period, and to predict the water quality parameters of each target point in the aquaculture pond.

[0059] Sensors 12, installed inside and outside the aquaculture pond, are used to collect real-time environmental water quality data, including salinity, pH value, and water level.

[0060] The data assimilation and calibration module 13 is used to calibrate the initial groundwater salinity numerical model based on real-time environmental water quality data.

[0061] The dynamic water-salt balance model module 14 is used to provide risk warnings and control solutions based on predicted water quality parameters.

[0062] Furthermore, in some embodiments of this application, a wireless communication module is also included. The sensor is communicatively connected to the data assimilation and model calibration module and the groundwater model module through the wireless communication module. The wireless communication module includes at least one of LoRa, NB-IoT, 4G or 5G network modules.

[0063] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0064] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0065] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0066] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0067] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0068] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0069] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0070] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0071] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0072] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for early warning and control of aquaculture based on numerical simulation of groundwater salinity, characterized in that, include: Collect geological and hydrogeological data of the aquaculture ponds and construct an initial numerical model of groundwater salinity; Real-time environmental water quality data is collected by a sensor network deployed inside and outside the aquaculture pond. The real-time environmental water quality data includes salinity, pH value and water level. The initial groundwater salinity numerical model was calibrated based on the real-time environmental water quality data. The calibrated groundwater salinity numerical model is used to simulate the groundwater flow field and solute transport trend in the future target period, and to predict the water quality parameters of each target point in the aquaculture pond. Risk warnings and control schemes are provided based on the predicted water quality parameters and the dynamic water-salt balance model.

2. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 1, characterized in that, The collection of geological and hydrogeological data from the aquaculture ponds, and the construction of an initial groundwater salinity numerical model, include: Collect geological and hydrogeological data of the aquaculture ponds; The collected geological and hydrogeological data of the aquaculture ponds were used to construct a three-dimensional digital twin model of the aquaculture ponds and the surrounding underground aquifers based on the MODFLOW numerical simulation engine. The three-dimensional digital twin model is used as the initial numerical model for groundwater salt.

3. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 1, characterized in that, The sensor network includes salinity sensors, pH sensors, and water level sensors installed at each target point; The target locations include the inlet, outlet, and center of the aquaculture pond, as well as the observation wells outside the aquaculture pond.

4. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 1, characterized in that, The initial groundwater salinity numerical model is calibrated based on the real-time environmental water quality data, including: The real-time environmental water quality data is assimilated using an ensemble Kalman filter algorithm to dynamically calibrate the initial groundwater salinity numerical model.

5. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 1, characterized in that, Risk warning and control schemes are provided based on the predicted water quality parameters and dynamic water-salt balance model, including: Based on the predicted water quality parameters, real-time water volume and salinity in the aquaculture pond, and aquaculture management parameters, a dynamic water-salt balance model is used to perform reverse simulation with preset constraints as the objective, generating a risk warning report and calculating feasible control schemes. Based on a preset optimization strategy, a recommended control scheme is determined from the feasible control schemes, and a control decision report is generated. The risk warning report includes the risk location, risk level, and expected occurrence time, and the quantitative parameters in the recommended control plan include water exchange start time, water exchange flow rate, and water exchange duration.

6. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 5, characterized in that, The preset optimization strategy is the lowest cost strategy, the least water consumption strategy, or the simplest operation strategy. The aquaculture management parameters include at least one of the following: planned water exchange rate, available freshwater source quality, evaporation rate, and precipitation replenishment.

7. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 6, characterized in that, Also includes: The risk warning report and the regulation decision report are pushed to the user; wherein the push method includes at least one of web page, SMS or application push.

8. The aquaculture early warning and control method based on groundwater salinity numerical simulation according to claim 6, characterized in that, Also includes: Before implementing the recommended control scheme, the parameters of the groundwater salinity numerical model are corrected based on real-time environmental water quality data. After implementing the recommended control scheme, the parameters of the dynamic water-salt balance model of groundwater salt number are corrected based on real-time environmental water quality data.

9. An aquaculture early warning and control system based on groundwater salinity numerical simulation, used to implement the aquaculture early warning and control method based on groundwater salinity numerical simulation as described in any one of claims 1 to 8, characterized in that, include: The groundwater salinity model module is used to collect geological and hydrogeological data of aquaculture ponds, and to construct an initial groundwater salinity numerical model based on the geological and hydrogeological data of aquaculture ponds collected by the data collection module. After calibration, the groundwater flow field and solute transport trend are simulated in the future target period, and the predicted water quality parameters of each target point in the aquaculture pond are predicted. Sensors deployed inside and outside the aquaculture pond are used to collect real-time environmental water quality data, including salinity, pH value and water level. The data assimilation and calibration module is used to calibrate the initial groundwater salinity numerical model based on the real-time environmental water quality data. The dynamic water-salt balance model module is used to provide risk warnings and control solutions based on the predicted values ​​of the water quality parameters.

10. The aquaculture early warning and control system based on groundwater salinity numerical simulation according to claim 9, characterized in that, It also includes a wireless communication module; The sensor is communicatively connected to the data assimilation and calibration module, the groundwater model module, and the dynamic water-salt balance model via the wireless communication module. The wireless communication module includes at least one of LoRa, NB-IoT, 4G, or 5G network modules.

Images