Diffusion coefficient calibration method and device for nitrogen element transport process

Abstract

The application provides a diffusion coefficient calibration method and device for a nitrogen element transport process, and the method comprises the following steps: selecting a target reservoir to determine a topological structure; establishing a one-dimensional nitrogen element convection-diffusion equation taking spatial position information of the target reservoir as a variable to obtain a nitrogen element transport model; establishing a neural network model corresponding to a to-be-calibrated diffusion coefficient under a nitrogen element transport process constraint of the target reservoir, and establishing a to-be-optimized objective function; collecting historical reservoir area information of each preset monitoring station in the target reservoir; and optimizing the to-be-optimized objective function based on the historical reservoir area information to obtain a to-be-sought diffusion coefficient. The scheme provided by the application considers the complexity and non-uniformity of the nitrogen element transport process in the reservoir, combines the actual aquatic environment of the reservoir, increases the constraint condition of the diffusion coefficient calibration process, calibrates the nitrogen element diffusion coefficient through the established one-dimensional nitrogen element transport equation and the physically driven neural network inversion model, and improves the accuracy of the nitrogen element transport process evaluation and prediction.

Description

Technical Field

[0001] This application relates to the field of environmental science and technology, and in particular to a method and apparatus for calibrating the diffusion coefficient of nitrogen transport processes. Background Technology

[0002] Reservoirs are important water resource regulation and supply facilities, and can be divided into natural and artificial reservoirs. Due to factors such as wastewater discharge from agriculture, industry, and urban activities, as well as soil erosion, the concentration of nitrogen in reservoirs is often high, posing a potential threat to the aquatic ecosystem and water quality safety. In environmental science, the calibration of water quality model parameters is a crucial step to improve the accuracy and reliability of model predictions. Therefore, accurately assessing and predicting nitrogen transport processes in reservoirs is of great significance for the scientific management and protection of reservoir ecosystems.

[0003] Existing technologies employ various measures to control nitrogen levels in reservoirs, primarily including source control, sediment management, water quality regulation, and ecological restoration. In simulating nitrogen transport processes, existing technologies construct nitrogen transport models incorporating nitrification and denitrification reactions to describe the nitrogen transport process in reservoirs, thereby capturing the distribution characteristics of nitrogen in the reservoir. However, the characteristics of nitrogen in reservoirs make water resource transport processes highly complex, exhibiting non-uniform distribution, time-varying behavior, multiple input sources, and biological interactions. Furthermore, the diffusion coefficient, as a core parameter reflecting the diffusion process of nitrogen in water, is mainly affected by temperature, flow velocity, and solute interactions, making it a non-constant parameter. Existing technologies suffer from multiple solutions during parameter inversion; existing tracer determination methods rely on the selection and stability of the tracer; and computational fluid dynamics numerical simulation methods struggle to address the uncertainties in parameters and assumptions, leading to deviations in simulation results.

[0004] Therefore, there is an urgent need to provide a diffusion coefficient calibration scheme for nitrogen transport processes in order to accurately assess and predict nitrogen levels in reservoir water transport processes. Summary of the Invention

[0005] This application discloses a method and apparatus for calibrating the diffusion coefficient of nitrogen transport processes, so as to accurately assess and predict nitrogen transport processes in reservoirs.

[0006] In a first aspect, this application discloses a method for calibrating the diffusion coefficient of a nitrogen transport process, the method comprising:

[0007] Select a target reservoir and determine its topology.

[0008] Based on the aforementioned topology, a one-dimensional nitrogen convection-diffusion equation is established with the spatial location information of the target reservoir as the variable, thereby obtaining a nitrogen transport model for the target reservoir.

[0009] Based on the nitrogen transport model, a neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen transport process in the target reservoir is established, and an objective function to be optimized corresponding to the neural network model is established. The neural network model is a physics-driven neural network inversion model.

[0010] Collect historical reservoir area information for each preset monitoring station in the target reservoir;

[0011] Based on the historical reservoir information, the objective function to be optimized is optimized to obtain the diffusion coefficient to be determined when the model parameters of the neural network model take the optimal value during the fitting process, thus completing the calibration of the diffusion coefficient of the nitrogen element transport process.

[0012] Optionally, the method further includes:

[0013] Obtain real-time reservoir area information for each preset monitoring station in the target reservoir;

[0014] The real-time nitrogen content of the target reservoir is calculated based on the nitrogen transport model corresponding to the calibrated diffusion coefficient.

[0015] Optionally, the step of collecting historical reservoir area information for each preset monitoring station in the target reservoir includes:

[0016] Historical reservoir area data are obtained from multiple monitoring stations established on the main stream and / or tributaries of the target reservoir. The historical reservoir area data includes at least cross-sectional flow, flow parameters, water temperature, nitrogen content, and total length of the reservoir area.

[0017] Optionally, the step of establishing a one-dimensional nitrogen convection-diffusion equation based on the topology, using the spatial location information of the target reservoir as a variable, to obtain a nitrogen transport model for the target reservoir, includes:

[0018] The one-dimensional nitrogen convection-diffusion equation is established according to the following expression, and a nitrogen transport model for the target reservoir is generated.

[0019]

[0020] Where x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, D is the diffusion coefficient, U represents the nitrogen concentration in the target reservoir, R1 represents the nitrogen fixation rate of the water body, and R2 represents the denitrification rate of the water body.

[0021] Optionally, the step of establishing a neural network model corresponding to the diffusion coefficient to be calibrated under the constraints of the nitrogen transport process in the target reservoir based on the nitrogen transport model includes:

[0022] The neural network model is constructed according to the following expression.

[0023]

[0024] e2 = U S -U* (3)

[0025] Where e1 represents the residual of the one-dimensional nitrogen transport model of the target reservoir, e2 represents the residual of the nitrogen concentration in the target reservoir, x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, and D s U is the predicted diffusion coefficient output by the neural network model. s U represents the predicted nitrogen concentration in the target reservoir output by the neural network model. * R1 represents the actual nitrogen concentration in the target reservoir, R2 represents the nitrogen fixation rate in the water, and R2 represents the denitrification rate in the water.

[0026] Optionally, the step of establishing the objective function to be optimized corresponding to the neural network model includes:

[0027] The objective function to be optimized is established according to the following expression.

[0028]

[0029] D s =D s (x;θ u )

[0030] U s =U s (x, t; θ) n )

[0031] Where, θ u D represents the predicted diffusion coefficient output after fitting the neural network model. s The corresponding model parameters, θ n U represents the predicted diffusion coefficient output after the neural network model is fitted. s The corresponding model parameters.

[0032] Optionally, the step of optimizing the objective function based on the historical reservoir information to obtain the diffusion coefficient corresponding to the optimal value of the model parameters during the fitting process of the neural network model includes:

[0033] Input the historical reservoir information into the objective function to be optimized;

[0034] The gradient descent method is used to solve the objective function to be optimized until the model parameters of the optimal neural network model are obtained;

[0035] After the objective function is optimized, θ is determined. n The diffusion coefficient corresponding to the optimal value is the calibrated diffusion coefficient.

[0036] Secondly, this application discloses a diffusion coefficient calibration device for a nitrogen element transport process, the device comprising:

[0037] The reservoir determination module is used to select a target reservoir and determine the topology of the target reservoir.

[0038] The nitrogen transport model establishment module is used to establish a one-dimensional nitrogen convection and diffusion equation based on the topology, with the spatial location information of the target reservoir as the variable, to obtain the nitrogen transport model of the target reservoir;

[0039] The neural network model building module is used to build a neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen element transport process in the target reservoir based on the nitrogen element transport model, and to build the objective function to be optimized corresponding to the neural network model, wherein the neural network model is a physics-driven neural network inversion model;

[0040] The historical information collection module is used to collect historical reservoir area information for each preset monitoring station in the target reservoir;

[0041] The diffusion coefficient calibration module is used to optimize the objective function to be optimized based on the historical reservoir information, and obtain the diffusion coefficient to be determined when the model parameters of the neural network model take the optimal value during the fitting process, thereby completing the calibration of the diffusion coefficient of the nitrogen element transport process.

[0042] Optionally, the device further includes a nitrogen content monitoring module, used to acquire real-time reservoir area information of each preset monitoring station in the target reservoir; and to calculate the real-time nitrogen content of the target reservoir based on the nitrogen transport model corresponding to the calibrated diffusion coefficient.

[0043] Optionally, the historical information collection module is specifically used to acquire historical reservoir area data from multiple monitoring stations established on the main stream and / or tributaries of the target reservoir. The historical reservoir area data includes at least cross-sectional flow, flow parameters, water temperature, nitrogen content, and total length of the reservoir area.

[0044] Optionally, the nitrogen transport model building module is specifically used to establish the one-dimensional nitrogen convection-diffusion equation according to the following expression, thereby generating the nitrogen transport model of the target reservoir.

[0045]

[0046] Where x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, D is the diffusion coefficient, U represents the nitrogen concentration in the target reservoir, R1 represents the nitrogen fixation rate of the water body, and R2 represents the denitrification rate of the water body.

[0047] Optionally, the neural network model building module is specifically used to build the neural network model according to the following expression:

[0048]

[0049] e2 = U S -U* (3)

[0050] Where e1 represents the residual of the one-dimensional nitrogen transport model of the target reservoir, e2 represents the residual of the nitrogen concentration in the target reservoir, x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, and D s U is the predicted diffusion coefficient output by the neural network model. s U represents the predicted nitrogen concentration in the target reservoir output by the neural network model. * R1 represents the actual nitrogen concentration in the target reservoir, R2 represents the nitrogen fixation rate in the water, and R2 represents the denitrification rate in the water.

[0051] Optionally, the neural network model building module is specifically used to build the objective function to be optimized according to the following expression:

[0052]

[0053] D s =D s (x;θ u )

[0054] U s =U s (x, t; θ) n )

[0055] Where, θ u D represents the predicted diffusion coefficient output after fitting the neural network model. s The corresponding model parameters, θ n U represents the predicted diffusion coefficient output after the neural network model is fitted. s The corresponding model parameters.

[0056] Optionally, the diffusion coefficient calibration module is specifically used to input the historical reservoir area information into the objective function to be optimized; solve the objective function to be optimized using the gradient descent method until the optimal neural network model parameters are obtained; and determine θ after the objective function is optimized. n The diffusion coefficient corresponding to the optimal value is the calibrated diffusion coefficient.

[0057] Thirdly, this application discloses an electronic device comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to perform the method as described in any of the preceding aspects.

[0058] Fourthly, this application discloses a non-transitory computer-readable storage medium in which, when the instructions in the storage medium are executed by a processor of an electronic device, enable the electronic device to perform the methods described in any of the preceding aspects.

[0059] Fifthly, this application discloses a computer program product in which, when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to perform the method described in any of the preceding aspects.

[0060] The technical solution provided in this application may include the following beneficial effects:

[0061] First, a target reservoir is selected, and its topology is determined. Then, based on the topology, a one-dimensional nitrogen convection-diffusion equation is established, using the spatial location information of the target reservoir as a variable, to obtain a nitrogen transport model for the target reservoir. Next, a neural network model corresponding to the diffusion coefficient to be calibrated under the constraints of the nitrogen transport process in the target reservoir is established according to the nitrogen transport model, and an objective function to be optimized is established for the neural network model. Historical reservoir area information from each preset monitoring station in the target reservoir is collected. Finally, the objective function to be optimized is optimized based on the historical reservoir area information to obtain the diffusion coefficient to be determined when the model parameters of the neural network model reach their optimal values ​​during the fitting process, thus completing the calibration of the diffusion coefficient of the nitrogen transport process.

[0062] It can be seen that the scheme provided in this application also takes into account the complexity and non-uniformity of nitrogen transport process in reservoir during the diffusion coefficient calibration process. Combined with the actual aquatic environment of the reservoir, the constraints of the diffusion coefficient calibration process are increased. The nitrogen diffusion coefficient is calibrated by establishing a one-dimensional nitrogen transport equation and a physical-driven neural network inversion model, which improves the accuracy and precision of the assessment and prediction of nitrogen transport process. Attached Figure Description

[0063] Figure 1This is a flowchart of a method for calibrating the diffusion coefficient of nitrogen transport processes provided in this application.

[0064] Figure 2 This is a schematic diagram of the nitrogen transport process in the reservoir provided in this application.

[0065] Figure 3 This is another flowchart of the diffusion coefficient calibration method for nitrogen transport processes provided in this application.

[0066] Figure 4 This is a structural diagram of a diffusion coefficient calibration device for nitrogen element transport process provided in this application.

[0067] Figure 5 This is another structural diagram of the diffusion coefficient calibration device for the nitrogen transport process provided in this application.

[0068] Figure 6 This is a structural block diagram of the electronic device provided in this application.

[0069] Figure 7 This is another structural block diagram of the electronic device provided in this application. Detailed Implementation

[0070] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0071] It should be noted that the diffusion coefficient reflects the diffusion capacity of nitrogen in a reservoir. In order to accurately assess and predict the nitrogen transport process in a reservoir, this application provides a method and apparatus for calibrating the diffusion coefficient of nitrogen transport. The method for calibrating the diffusion coefficient of nitrogen transport provided in this application will be described below.

[0072] Example 1

[0073] Reference Figure 1 This is a flowchart of a method for calibrating the diffusion coefficient of nitrogen transport processes provided in this application. This method can be applied to electronic devices, and specifically includes the following steps:

[0074] Step S101: Select a target reservoir and determine its topology.

[0075] The application scenarios for this application include reservoirs, such as artificial reservoirs and natural lakes, and it is especially suitable for large reservoirs. Figure 2This is a schematic diagram of the nitrogen transport process in a reservoir provided in this application. Figure 2 The topological structure of the target reservoir can be clearly seen, specifically... Figure 2 The middle section is the reservoir dam. To the left of the dam is the upstream river channel, and to the right is the downstream river channel. For ease of description, the direction along the reservoir water surface from the upstream river channel to the downstream river channel is defined as the x-direction. The total length of the reservoir along the x-direction selected in this application is represented by h.

[0076] Step S102: Based on the topology, establish a one-dimensional nitrogen convection-diffusion equation with the spatial location information of the target reservoir as the variable, and obtain the nitrogen transport model of the target reservoir.

[0077] In one implementation, the one-dimensional nitrogen convection-diffusion equation can be established according to expression (1) to generate a nitrogen transport model for the target reservoir.

[0078]

[0079] Where x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, D is the diffusion coefficient, U represents the nitrogen concentration in the target reservoir, R1 represents the nitrogen fixation rate of the water body, and R2 represents the denitrification rate of the water body.

[0080] In one implementation, the boundary conditions of the one-dimensional nitrogen convection-diffusion equation corresponding to expression (1) can be determined as follows: the upper boundary condition is a fixed boundary condition, i.e., the inflow nitrogen concentration; the lower boundary is a free boundary condition. Preferably, the nitrogen change rate is a constant value, generally taken as 0.

[0081] In one scenario, the flow parameters of the target reservoir can be the average flow velocity of the target reservoir in the selected reservoir area. It should be noted that the specific calculation method of the flow parameters will not be elaborated here, but can be calculated by referring to the relevant methods in the prior art.

[0082] It should be noted that R1 represents the nitrogen fixation rate of the water body, and R2 represents the denitrification rate of the water body. These can be used to reflect the activity of plankton and microorganisms in the water body. They are affected by the adsorption of oxygen content in the bottom sediment of the reservoir. They can be measured by collecting water and bottom sediment samples from the target reservoir in the laboratory. The existing measurement methods for reservoir water and bottom sediment can be referred to, and will not be elaborated here.

[0083] Step S103: Based on the nitrogen transport model, establish a neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen transport process in the target reservoir, and establish the objective function to be optimized corresponding to the neural network model.

[0084] In one implementation of this application, the neural network model can be established according to expressions (2) and (3).

[0085]

[0086] e2 = U S -U* (3)

[0087] Where e1 represents the residual of the one-dimensional nitrogen transport model of the target reservoir, e2 represents the residual of the nitrogen concentration in the target reservoir, x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, and D s U is the predicted diffusion coefficient output by the neural network model. s U represents the predicted nitrogen concentration in the target reservoir output by the neural network model. * R1 represents the actual nitrogen concentration in the target reservoir, R2 represents the nitrogen fixation rate in the water, and R2 represents the denitrification rate in the water.

[0088] It should be noted that in expression (2), e1 represents the residual of the one-dimensional nitrogen transport model of the target reservoir, which is the physical-driven neural network model corresponding to the diffusion coefficient D. The output D of this neural network model is... s =D s (x;θ u θ is an approximation of the true diffusion coefficient, and the corresponding model parameters to be fitted are denoted as θ. u , that is, θ u The output diffusion coefficient prediction value D after fitting the neural network model. s The corresponding model parameters. The network output U. s =U s (x, t; θ) n Let θ be an approximation of the true nitrogen concentration, and let θ be the corresponding model parameter to be fitted. n , that is, θ n The output of the neural network model after fitting is the predicted diffusion coefficient U. s The corresponding model parameters. In expression (3), e2 represents the residual of nitrogen concentration in the target reservoir, reflecting the approximation error of the neural network model output relative to the observed cross-sectional nitrogen concentration.

[0089] Furthermore, the objective function to be optimized is established according to the following expression (4).

[0090]

[0091] D s =D s (x;θ u )

[0092] U s =U s (x, t; θ) n)

[0093] Where, θ u D represents the predicted diffusion coefficient output after fitting the neural network model. s The corresponding model parameters, θ n U represents the predicted diffusion coefficient output after the neural network model is fitted. s The corresponding model parameters.

[0094] It should be emphasized that the neural network model established in the nitrogen transport process diffusion coefficient calibration method provided in this application is a physical-driven neural network inversion model. That is, the residual of the physical equation is added to the loss function of the neural network model. Its advantage is that by adding physical constraints to the neural network model, the fitting result of the model in the inversion process has physical meaning and is more likely to approach the actual value.

[0095] Step S104: Collect historical reservoir area information for each preset monitoring station in the target reservoir.

[0096] In one scenario, historical reservoir area information for each pre-set monitoring station in the target reservoir can be collected in the following manner:

[0097] Historical reservoir area data are obtained from multiple monitoring stations established on the main stream and / or tributaries of the target reservoir. The historical reservoir area data includes at least cross-sectional flow, flow parameters, water temperature, nitrogen content, and total reservoir length h.

[0098] Step S105: Optimize the objective function to be optimized based on the historical reservoir information to obtain the diffusion coefficient to be determined when the model parameters of the neural network model take the optimal value during the fitting process, and complete the calibration of the diffusion coefficient of the nitrogen element transport process.

[0099] In one scenario, the objective function to be optimized is optimized in the following manner, and the diffusion coefficient to be determined is obtained when the model parameters of the neural network model take the optimal values ​​during the fitting process:

[0100] i. Input the historical database information into the objective function to be optimized;

[0101] ii. Solve the objective function to be optimized using the gradient descent method until the model parameters of the optimal neural network model are obtained;

[0102] iii. Determine θ after the objective function is optimized. n The diffusion coefficient corresponding to the optimal value is the calibrated diffusion coefficient.

[0103] It should be noted that optimizing the objective function in this way can make the output of the neural network model satisfy the control equation as much as possible and approximate the observation data as closely as possible, thereby improving the accuracy of the diffusion coefficient calibration for nitrogen transport processes.

[0104] In summary, the scheme provided in this application also considers the complexity and non-uniformity of nitrogen transport processes in reservoirs during the diffusion coefficient calibration process. Combined with the actual aquatic environment of the reservoir, it adds constraints to the diffusion coefficient calibration process. By establishing a one-dimensional nitrogen transport equation and a physical-driven neural network inversion model, the diffusion coefficient of nitrogen can be calibrated. This comprehensively considers the influence of temperature, flow rate, and solute interaction on the diffusion coefficient calibration, thereby obtaining optimal parameters for the neural network model and improving the accuracy and precision of the assessment and prediction of nitrogen transport processes.

[0105] Example 2

[0106] Reference Figure 3 This is a flowchart of a method for calibrating the diffusion coefficient of nitrogen transport processes provided in this application. This method can be applied to electronic devices, and specifically includes the following steps:

[0107] Step S201: Select a target reservoir and determine its topology.

[0108] Step S202: Based on the topology, establish a one-dimensional nitrogen convection-diffusion equation with the spatial location information of the target reservoir as the variable, and obtain the nitrogen transport model of the target reservoir.

[0109] Step S203: Based on the nitrogen transport model, establish a neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen transport process in the target reservoir, and establish the objective function to be optimized corresponding to the neural network model, wherein the neural network model is a physics-driven neural network inversion model.

[0110] Step S204: Collect historical reservoir area information for each preset monitoring station in the target reservoir.

[0111] Step S205: Optimize the objective function to be optimized based on the historical reservoir information to obtain the diffusion coefficient to be determined when the model parameters of the neural network model take the optimal value during the fitting process, and complete the calibration of the diffusion coefficient of the nitrogen element transport process.

[0112] It should be noted that steps S201 to S205 in Embodiment 2 are similar to steps S101 to S105 in Embodiment 1. For relevant details, please refer to Embodiment 1. They will not be repeated here.

[0113] Step S206: Obtain real-time reservoir area information for each preset monitoring station in the target reservoir;

[0114] Step S207: Calculate the real-time nitrogen content of the target reservoir based on the nitrogen transport model corresponding to the calibrated diffusion coefficient.

[0115] It should be noted that, Figure 3 The second embodiment shown has Figure 1 In addition to all the beneficial effects of Embodiment 1, after the diffusion coefficient of the nitrogen transport process in the target reservoir is calibrated, the real-time reservoir information, i.e., real-time data, of each preset monitoring point can be obtained to further realize real-time monitoring of the nitrogen content in the target reservoir, thereby enabling dynamic analysis of the change process of nitrogen content in the reservoir.

[0116] The diffusion coefficient calibration apparatus for the nitrogen transport process provided in this application will be described below.

[0117] Example 3

[0118] Reference Figure 4 This is a structural diagram of a diffusion coefficient calibration device for nitrogen transport processes provided in this application, the device comprising:

[0119] The reservoir determination module 310 is used to select a target reservoir and determine the topology of the target reservoir;

[0120] The nitrogen element transport model establishment module 320 is used to establish a one-dimensional nitrogen element convection and diffusion equation based on the topology and with the spatial location information of the target reservoir as the variable, so as to obtain the nitrogen element transport model of the target reservoir.

[0121] The neural network model building module 330 is used to build a neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen element transport process in the target reservoir according to the nitrogen element transport model, and to build the objective function to be optimized corresponding to the neural network model, wherein the neural network model is a physics-driven neural network inversion model;

[0122] Historical information collection module 340 is used to collect historical reservoir area information of each preset monitoring station in the target reservoir;

[0123] The diffusion coefficient calibration module 350 is used to optimize the objective function to be optimized based on the historical reservoir information, and obtain the diffusion coefficient to be determined when the model parameters of the neural network model take the optimal value during the fitting process, thereby completing the calibration of the diffusion coefficient of the nitrogen element transport process.

[0124] In one scenario, the historical information collection module 340 is specifically used to acquire historical reservoir area data from multiple monitoring stations established on the main stream and / or tributaries of the target reservoir. The historical reservoir area data includes at least cross-sectional flow rate, flow parameters, water temperature, nitrogen content, and total length of the reservoir area.

[0125] In one scenario, the nitrogen transport model building module 320 is specifically used to build the one-dimensional nitrogen convection-diffusion equation according to the following expression, thereby generating the nitrogen transport model for the target reservoir.

[0126]

[0127] Where x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, D is the diffusion coefficient, U represents the nitrogen concentration in the target reservoir, R1 represents the nitrogen fixation rate of the water body, and R2 represents the denitrification rate of the water body.

[0128] In one scenario, the neural network model building module 330 is specifically used to build the neural network model according to the following expression:

[0129]

[0130] e2 = U S -U* (3)

[0131] Where e1 represents the residual of the one-dimensional nitrogen transport model of the target reservoir, e2 represents the residual of the nitrogen concentration in the target reservoir, x represents the spatial location of the target reservoir, t represents the current time, v represents the flow parameters of the target reservoir, and D s U is the predicted diffusion coefficient output by the neural network model. s U represents the predicted nitrogen concentration in the target reservoir output by the neural network model. * R1 represents the actual nitrogen concentration in the target reservoir, R2 represents the nitrogen fixation rate in the water, and R2 represents the denitrification rate in the water.

[0132] In one scenario, the neural network model building module 330 is specifically used to build the objective function to be optimized according to the following expression:

[0133]

[0134] D s =D s (x;θ u )

[0135] U s =U s (x, t; θ) n )

[0136] Where, θ u D represents the predicted diffusion coefficient output after fitting the neural network model. s The corresponding model parameters, θ n U represents the predicted diffusion coefficient output after the neural network model is fitted. s The corresponding model parameters.

[0137] In one scenario, the diffusion coefficient calibration module 350 is specifically used to input the historical reservoir information into the objective function to be optimized; solve the objective function to be optimized using the gradient descent method until the optimal neural network model parameters are obtained; and determine θ after the objective function optimization is complete. n The diffusion coefficient corresponding to the optimal value is the calibrated diffusion coefficient.

[0138] In summary, the scheme provided in this application also takes into account the complexity and non-uniformity of nitrogen transport processes in reservoirs during the diffusion coefficient calibration process. Combined with the actual aquatic environment of the reservoir, it increases the constraints on the diffusion coefficient calibration process. By establishing a one-dimensional nitrogen transport equation and a physical-driven neural network inversion model, the nitrogen diffusion coefficient is calibrated, which improves the accuracy and precision of the assessment and prediction of nitrogen transport processes.

[0139] Furthermore, such as Figure 5 The diagram shown is another structural diagram of the diffusion coefficient calibration device for nitrogen transport process provided in this application. The device also includes a nitrogen content monitoring module 360, which is used to obtain real-time reservoir area information of each preset monitoring station in the target reservoir; and to calculate the real-time nitrogen content of the target reservoir based on the nitrogen transport model corresponding to the calibrated diffusion coefficient.

[0140] It should be noted that, Figure 5 After the diffusion coefficient of the nitrogen transport process in the target reservoir is calibrated, the device shown can further monitor the nitrogen content of the target reservoir in real time by acquiring real-time reservoir information, i.e., real-time data, from each preset monitoring point, thereby enabling dynamic analysis of the changes in the nitrogen content of the reservoir.

[0141] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0142] Example 4

[0143] Optionally, this application also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0144] Example 5

[0145] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0146] Figure 6 This is a block diagram illustrating an electronic device 800. For example, the electronic device 800 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0147] Reference Figure 6 The electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0148] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0149] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of this data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, images, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0150] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0151] Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0152] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0153] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0154] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of electronic device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or a component of electronic device 800, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0155] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast operation information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0156] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0157] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0158] Figure 7This is a structural block diagram of the electronic device 1900 provided in this application. For example, the electronic device 1900 can be provided as a server.

[0159] Reference Figure 7 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0160] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output (I / O) interface 1958. Electronic device 1900 can operate on an operating system stored in memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0161] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0163] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0164] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0165] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0166] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0167] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0169] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0170] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of calibrating a diffusion coefficient of a nitrogen element transport process, characterized by, The method comprises: selecting a target reservoir, determining the topological structure of the target reservoir; based on the topological structure, a one-dimensional nitrogen element convection-diffusion equation with the spatial position information of the target reservoir as a variable is established, and a nitrogen element transport model of the target reservoir is obtained; according to the nitrogen element transport model, a neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen element transport process of the target reservoir is established, and a to-be-optimized objective function corresponding to the neural network model is established, wherein the neural network model is a physically driven neural network inversion model; collecting historical reservoir area information of each preset monitoring station in the target reservoir; based on the historical reservoir area information, the to-be-optimized objective function is optimized, and the diffusion coefficient to be solved corresponding to the optimal value of the model parameter of the neural network model in the fitting process is obtained, and the calibration of the diffusion coefficient of the nitrogen element transport process is completed; the step of establishing the neural network model corresponding to the diffusion coefficient to be calibrated under the constraint of the nitrogen element transport process of the target reservoir according to the nitrogen element transport model comprises: the neural network model is established according to the following expression, wherein, e 1 denotes a residual of a one-dimensional nitrogen element transport model of a target reservoir, e 2 denotes a residual of a nitrogen element concentration in the target reservoir, x denotes a spatial position of the target reservoir, t denotes a current time, v denotes a flow parameter of the target reservoir, D s is a predicted value of a diffusion coefficient output by a neural network model, U s denotes a predicted value of a nitrogen element concentration in the target reservoir output by the neural network model, U * denotes a true value of the nitrogen element concentration in the target reservoir, R 1 denotes a nitrogen fixation rate of a water body, R 2 denotes a denitrification rate of the water body.

2. The method of diffusivity calibration of nitrogen transport processes according to claim 1, characterized in that, the method further comprises: obtaining real-time reservoir area information of each preset monitoring station in the target reservoir; based on the nitrogen element transport model corresponding to the calibrated diffusion coefficient, the real-time nitrogen element content of the target reservoir is calculated.

3. The method of diffusivity calibration of a nitrogen transport process according to claim 1 or 2, characterized in that, the step of collecting historical reservoir area information of each preset monitoring station in the target reservoir comprises: obtaining historical reservoir area data of a plurality of monitoring stations set up on the main stream and / or tributaries of the target reservoir, wherein the historical reservoir area data at least includes cross-section flow, flow parameter, water temperature, nitrogen element content and total length of the reservoir area.

4. The method of diffusivity calibration of a nitrogen transport process according to claim 1 or 2, characterized in that, the step of establishing the one-dimensional nitrogen element convection-diffusion equation with the spatial position information of the target reservoir as a variable based on the topological structure, and obtaining the nitrogen element transport model of the target reservoir comprises: the one-dimensional nitrogen element convection-diffusion equation is established according to the following expression, and the nitrogen element transport model of the target reservoir is generated, wherein, x represents the spatial position of the target water reservoir, t represents the current time, v represents the flow parameter of the target water reservoir, D is the diffusion coefficient, U represents the concentration of nitrogen elements in the target water reservoir, R 1 represents the nitrogen fixation rate of the water body, R 2 represents the denitrification rate of the water body.

5. The method of diffusivity calibration of nitrogen transport processes according to claim 1, wherein, the step of establishing the to-be-optimized objective function corresponding to the neural network model comprises: the to-be-optimized objective function is established according to the following expression, wherein, θ u representing the output of the neural network model after fitting to output a predicted value of the diffusion coefficient D s the corresponding model parameters, θ n representing the output of the neural network model after fitting to output a predicted value of the diffusion coefficient U s the corresponding model parameters.

6. The method of diffusivity calibration of a nitrogen transport process according to claim 5, wherein, the step of optimizing the to-be-optimized objective function based on the historical reservoir area information, and obtaining the diffusion coefficient to be solved corresponding to the optimal value of the model parameter of the neural network model in the fitting process comprises: inputting the historical reservoir area information into the to-be-optimized objective function; the gradient descent method is used to solve the to-be-optimized objective function until the optimal model parameter of the neural network model is obtained; determining that the optimization of the objective function is complete θ n The diffusion coefficient corresponding to the optimal value is the calibrated diffusion coefficient.

7. A device for calibrating a diffusion coefficient of a nitrogen element transport process, characterized by, the device comprises: a reservoir determination module for selecting a target reservoir and determining the topological structure of the target reservoir; a nitrogen element transport model establishment module for establishing a one-dimensional nitrogen element convection-diffusion equation with the spatial position information of the target water reservoir as a variable based on the topological structure, and obtaining the nitrogen element transport model of a target reservoir; The neural network model establishing module is configured to establish a neural network model corresponding to the to-be-calibrated diffusion coefficient under the constraint of the nitrogen element transport process of the target reservoir, and establish a to-be-optimized objective function corresponding to the neural network model, wherein the neural network model is a physically driven neural network inversion model. The historical information collecting module is configured to collect historical reservoir area information of each preset monitoring station in the target reservoir. The diffusion coefficient calibrating module is configured to optimize the to-be-optimized objective function based on the historical reservoir area information, obtain a to-be-solved diffusion coefficient corresponding to the neural network model when the model parameter takes an optimal value in a fitting process, and complete calibration of the diffusion coefficient of the nitrogen element transport process. The neural network model establishing module is specifically configured to establish the neural network model according to the following expression, wherein, e 1 represents the residual of the target reservoir one-dimensional nitrogen element transport model, e 2 represents the residual of the nitrogen element concentration in the target reservoir, x represents the spatial position of the target reservoir, t represents the current time, v represents the flow parameter of the target reservoir, D s is the predicted value of the diffusion coefficient output by the neural network model, U s represents the predicted value of the nitrogen element concentration in the target reservoir output by the neural network model, U * represents the true value of the nitrogen element concentration in the target reservoir, R 1 represents the nitrogen fixation rate of the water body, R 2 represents the denitrification rate of the water body.

8. The apparatus of claim 7, wherein, The device further includes a nitrogen element content monitoring module configured to obtain real-time reservoir area information of each preset monitoring station in the target reservoir, and calculate real-time nitrogen element content of the target reservoir based on the nitrogen element transport model corresponding to the calibrated diffusion coefficient.

9. A diffusion coefficient calibration apparatus for a nitrogen transport process according to claim 7 or 8, characterized in that, The historical information collecting module is specifically configured to obtain historical reservoir area data of a plurality of monitoring stations set on the main stream and / or tributaries of the target reservoir, wherein the historical reservoir area data at least includes cross-section flow, flow parameter, water temperature, nitrogen element content, and total length of the reservoir area.

10. The apparatus for calibrating the diffusion coefficient of a nitrogen transport process according to claim 7 or 8, characterized in that, The nitrogen element transport model establishing module is specifically configured to establish the one-dimensional nitrogen element convection-diffusion equation according to the following expression, and generate the nitrogen element transport model of the target reservoir, wherein, x represents the spatial position of the target water reservoir, t represents the current time, v represents the flow parameter of the target water reservoir, D is the diffusion coefficient, U represents the concentration of nitrogen elements in the target water reservoir, R 1 represents the nitrogen fixation rate of the water body, R 2 represents the denitrification rate of the water body.

11. The apparatus of claim 10, wherein, The neural network model establishing module is specifically configured to establish the to-be-optimized objective function according to the following expression, wherein, The processor, the memory, and the computer program stored on the memory and executable on the processor, when the computer program is executed by the processor, implement the method in any one of claims 1 to 6. u representing the output of the neural network model after fitting to output a predicted value of the diffusion coefficient D s the corresponding model parameters, The computer program is stored on the computer readable storage medium and is executable by the processor to implement the method in any one of claims 1 to 6. n representing the output of the neural network model after fitting to output a predicted value of the diffusion coefficient U s the corresponding model parameters.

12. The apparatus of claim 11, wherein, The diffusion coefficient calibration module is specifically configured to input the historical reservoir area information into the target function to be optimized, solve the target function to be optimized by using a gradient descent method, and determine the model parameters of the optimal neural network model until the target function optimization is completed When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is enabled to perform the method in any one of claims 1 to 6. n The diffusion coefficient corresponding to the optimal value is the calibrated diffusion coefficient.

13. An electronic device, comprising: ​ ​ 14. A computer-readable storage medium, characterized in that, ​ 15. A computer program product, characterised in that, ​

Images