Reservoir greenhouse effect evaluation method and device based on physical driving neural network

Abstract

The embodiment of the invention discloses a reservoir greenhouse effect evaluation method based on a physical driving neural network. The method comprises the following steps: collecting historical data of a target reservoir monitoring station; establishing a river reservoir one-dimensional nitrogen element transport model based on the nitrogen element transport process of the target reservoir, determining a nitrification and denitrification coefficient calibration neural network in the nitrogen element transport process of the target reservoir according to the river reservoir one-dimensional nitrogen element transport model, and a corresponding to-be-optimized target function, inputting historical data to the to-be-optimized target function, and determining a nitrification and denitrification coefficient calibration neural network in the nitrogen element transport process of the target reservoir according to the to-be-optimized target function. Determining neural network optimization parameters so as to determine nitrification and denitrification optimization coefficients; and evaluating greenhouse gas emission of the target reservoir based on the nitrogen element real-time data of the target reservoir and the nitrification and denitrification optimization coefficient. According to the embodiment of the invention, the one-dimensional nitrogen element transport equation is utilized, the actual aquatic environment of the reservoir is combined, the physical constraint of the nitrification and denitrification coefficient calibration process is increased, and the greenhouse gas emission of the reservoir is accurately evaluated.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of reservoir greenhouse effect assessment, and specifically to a reservoir greenhouse effect assessment method based on a physical driven neural network and a reservoir greenhouse effect assessment device based on a physical driven neural network. Background Art

[0002] The "active" nitrogen added by human activities every year has caused a serious imbalance in the global nitrogen cycle, and has caused a series of environmental problems such as eutrophication of water bodies, acidification of water bodies, and greenhouse gas emissions. As an important nitrogen sink, the nitrogen cycle based on nitrification and denitrification of nitrogen elements in rivers and reservoirs is of great significance to the nitrogen budget of the entire ecosystem, nitrogen pollution in water bodies, and greenhouse gas emissions. The nitrification and denitrification coefficient of the nitrogen element transport process in rivers and reservoirs is an important parameter reflecting the process. It is mainly affected by water temperature, dissolved oxygen, microbial content, flow rate, and solute interaction. It is generally measured in the laboratory after water sampling or obtained by inversion parameters of the transport equation.

[0003] Traditional methods do not take into account the complexity and heterogeneity of nitrogen transport processes in reservoirs, do not evaluate reservoir greenhouse gas emissions through physical constraints, and cannot accurately evaluate reservoir greenhouse gas emissions.

[0004] Therefore, how to improve the accuracy of nitrogen cycle assessment in rivers and reservoirs and thus accurately assess greenhouse gas emissions from reservoirs is a difficult problem that needs to be solved. Summary of the invention

[0005] In view of the above problems, a reservoir greenhouse effect assessment method based on a physical driven neural network and a reservoir greenhouse effect assessment device based on a physical driven neural network are proposed to overcome the above problems or at least partially solve the above problems.

[0006] According to a first aspect of an embodiment of the present invention, a method for evaluating the greenhouse effect of a reservoir based on a physical driven neural network is provided, the method comprising:

[0007] Collect historical data from monitoring sites at target reservoirs;

[0008] Establishing a one-dimensional nitrogen transport model for river reservoirs based on the nitrogen transport process of the target reservoir;

[0009] Determine the nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized;

[0010] Inputting the historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficients;

[0011] The greenhouse gas emission of the target reservoir is predicted based on the real-time data of nitrogen elements of the target reservoir and the nitrification and denitrification optimization coefficient, so as to evaluate the greenhouse effect of the target reservoir.

[0012] Furthermore, the one-dimensional nitrogen transport model of the river reservoir is established based on the nitrogen transport process of the target reservoir, including:

[0013] Establishing a correlation between nitrogen and greenhouse gases in the target reservoir based on the historical data;

[0014] A one-dimensional nitrogen transport model for river reservoirs is established based on the correlation relationship and the nitrogen transport process of the target reservoir.

[0015] Furthermore, after establishing the one-dimensional nitrogen transport model of the river reservoir based on the association relationship and the nitrogen transport process of the target reservoir, it also includes:

[0016] A one-dimensional nitrogen convection-diffusion equation is established based on the one-dimensional nitrogen transport model of the river reservoir;

[0017] Determine the boundary conditions of the nitrogen element convection-diffusion equation.

[0018] Furthermore, the one-dimensional nitrogen element convection-diffusion equation is established based on the one-dimensional nitrogen element transport model of the river reservoir, including:

[0019] Based on the one-dimensional nitrogen transport model of the river reservoir, the one-dimensional nitrogen convection diffusion equation is established according to the following formula 1;

[0020] Formula 1 is:

[0021]

[0022] Among them: t is the current moment; v is the amplitude of variable stress at each level; x is the spatial position; v is the flow parameter; D is the diffusion coefficient, which describes the diffusion capacity of nitrogen in the reservoir; U is the concentration of nitrate in the reservoir river; R is the nitrification and denitrification coefficient of the water body, which represents the nitrification and denitrification rate of the water body, reflects the activity of plankton and microorganisms in the water body, and is affected by the oxygen content of the water body.

[0023] Further, the boundary conditions include upper boundary conditions and lower boundary conditions;

[0024] The boundary conditions for determining the nitrogen element convection-diffusion equation include:

[0025] Determining the upper boundary condition as the inflow nitrogen concentration of the target reservoir;

[0026] The lower boundary condition is determined as the outflow nitrogen concentration of the target reservoir.

[0027] Furthermore, the nitrification and denitrification coefficient calibration neural network and the corresponding objective function to be optimized in the nitrogen transport process of the target reservoir are determined according to the one-dimensional nitrogen transport model of the river reservoir, including:

[0028] According to the one-dimensional nitrogen transport model of the river reservoir, the nitrification and denitrification coefficient calibration neural network of the nitrogen transport process of the target reservoir is determined according to the following formulas 2 and 3;

[0029] Formula 2 is:

[0030]

[0031] Where: e1 is the residual of the one-dimensional nitrogen transport model of the river reservoir; U s is the approximate value of the actual nitrogen concentration; t is the current moment; v is the stress amplitude at each level; x is the spatial position, v is the flow parameter; D is the diffusion coefficient; R s It is an approximate value of the actual nitrification and denitrification coefficient.

[0032] Formula three is:

[0033] e2=U s -U * ;

[0034] Where: e2 is the approximation error of the neural network output to the observed cross-section nitrogen element; U s is the approximate value of the actual nitrogen concentration; U * is the observed nitrogen concentration in the cross section.

[0035] Furthermore, the nitrification and denitrification coefficient calibration neural network and the corresponding objective function to be optimized in the nitrogen transport process of the target reservoir are determined according to the one-dimensional nitrogen transport model of the river reservoir, including:

[0036] The objective function to be optimized is determined according to the following formula 4:

[0037] Formula 4 is:

[0038]

[0039] Where: L(θ u ,θ n ) is the objective function to be optimized; θ u is the approximate value of the true nitrification and denitrification coefficient R s The fitting model parameters of n is the approximate value of the actual nitrogen concentration U sThe fitting model parameters; e1 is the residual of the one-dimensional nitrogen transport model of the river reservoir; e2 is the approximation error of the neural network output to the observed cross-section nitrogen element; is the square of the second norm of the corresponding parameter.

[0040] Furthermore, the historical data is input into the objective function to be optimized, and the neural network optimization parameters are determined, thereby determining the nitrification and denitrification optimization coefficients, including:

[0041] Inputting the historical data into the objective function to be optimized;

[0042] Solving the objective function to be optimized based on a gradient descent method to obtain neural network optimization parameters;

[0043] The nitrification and denitrification optimization coefficient is determined based on the neural network optimization parameters.

[0044] Furthermore, solving the objective function to be optimized based on a gradient descent method to obtain neural network optimization parameters includes:

[0045] Calculating the gradient of each parameter in the objective function to be optimized;

[0046] Updating the parameter value of the neural network according to the gradient information of the gradient;

[0047] It is determined whether the parameter value of the neural network meets the convergence condition. If the update amplitude of the parameter value of the neural network is less than a preset threshold or reaches the maximum number of iterations, the iteration is stopped to obtain the optimization parameters of the neural network.

[0048] Furthermore, the greenhouse gas emissions of the target reservoir are predicted based on the real-time data of nitrogen elements of the target reservoir and the nitrification and denitrification optimization coefficient, so as to evaluate the greenhouse effect of the target reservoir, including:

[0049] Drawing a two-dimensional dot matrix diagram based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient;

[0050] The greenhouse gas emissions of the target reservoir are predicted based on the two-dimensional dot matrix, and the greenhouse effect of the target reservoir is evaluated.

[0051] Furthermore, the method further comprises:

[0052] Inputting the nitrification and denitrification optimization coefficient into a one-dimensional nitrogen element convection diffusion equation;

[0053] Solving the one-dimensional nitrogen convection-diffusion equation based on an implicit difference method to obtain the nitrogen content of the target reservoir after a preset time;

[0054] Determining the loss of nitrogen in the target reservoir based on the nitrogen content in the target reservoir after the preset time and the nitrification and denitrification optimization coefficient;

[0055] Based on the loss amount and the two-dimensional dot matrix, the greenhouse gas emissions of the target reservoir are predicted, and the greenhouse effect of the target reservoir is evaluated.

[0056] Furthermore, the collection of historical data of the target reservoir monitoring site includes:

[0057] Collecting the target reservoir area information, and obtaining the historical data of the monitoring stations set up on the main and tributary rivers in the target reservoir area;

[0058] The historical data at least include: flow rate, average flow rate, water temperature, nitrogen content, dissolved oxygen, microbial content, and greenhouse gas absorption.

[0059] According to a second aspect of the present invention, a reservoir greenhouse effect assessment device based on a physical driven neural network is provided, the device comprising:

[0060] A data collection module, used to collect historical data from target reservoir monitoring sites;

[0061] A first model building module is used to build a one-dimensional nitrogen transport model for river reservoirs based on the nitrogen transport process of the target reservoir;

[0062] A neural network building module is used to determine the nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized;

[0063] An optimization coefficient determination module is used to input the historical data into the target function to be optimized, determine the neural network optimization parameters, and thus determine the nitrification and denitrification optimization coefficients;

[0064] An evaluation module is used to predict the greenhouse gas emissions of the target reservoir based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient, so as to evaluate the greenhouse effect of the target reservoir.

[0065] According to a third aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0066] A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, is a reservoir greenhouse effect assessment method based on a physics-driven neural network as described in any one of the above items.

[0067] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for assessing the greenhouse effect of a reservoir based on a physically driven neural network as described in any one of the above items is implemented.

[0068] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0069] The embodiment of the present invention discloses a reservoir greenhouse effect assessment method based on a physical driven neural network, the method comprising: collecting historical data of a target reservoir monitoring station; establishing a one-dimensional nitrogen transport model for a river reservoir based on the nitrogen transport process of the target reservoir, determining a nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and a corresponding objective function to be optimized, inputting historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficient; assessing the greenhouse gas emissions of the target reservoir based on the real-time nitrogen data of the target reservoir and the nitrification and denitrification optimization coefficient. The embodiment of the present invention uses a one-dimensional nitrogen transport equation, combined with the actual aquatic environment of the reservoir, to increase the physical constraints of the nitrification and denitrification coefficient calibration process, thereby accurately assessing the greenhouse gas emissions of the reservoir. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0071] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0072] Figure 1 is a flowchart of the steps of a reservoir greenhouse effect assessment method based on a physical driven neural network according to an embodiment of the present invention;

[0073] Figure 2 Schematic diagram of the reservoir nitrogen transport process according to an embodiment of the present invention;

[0074] Figure 3 It is a structural block diagram of a reservoir greenhouse effect assessment device based on a physical driven neural network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] The "active" nitrogen added by human activities every year has caused a serious imbalance in the global nitrogen cycle, and has caused a series of environmental problems such as eutrophication of water bodies, acidification of water bodies, and greenhouse gas emissions. As an important nitrogen sink, the nitrogen cycle based on nitrification and denitrification of nitrogen elements in rivers and reservoirs is of great significance to the nitrogen budget of the entire ecosystem, nitrogen pollution in water bodies, and greenhouse gas emissions. The nitrification and denitrification coefficient of the nitrogen element transport process in rivers and reservoirs is an important parameter reflecting the process. It is mainly affected by water temperature, dissolved oxygen, microbial content, flow rate, and solute interaction. It is generally measured in the laboratory after water sampling or obtained by inversion parameters of the transport equation.

[0077] Traditional methods do not take into account the complexity and heterogeneity of nitrogen transport in reservoirs, do not use physical constraints to evaluate reservoir greenhouse gas emissions, and cannot accurately evaluate reservoir greenhouse gas emissions. Therefore, how to improve the accuracy of nitrogen cycle assessment in rivers and reservoirs and accurately evaluate reservoir greenhouse gas emissions is a difficult problem that needs to be solved.

[0078] In view of the problems existing in the traditional methods, we propose a reservoir greenhouse effect assessment method based on a physical driven neural network and a reservoir greenhouse effect assessment device based on a physical driven neural network, collect historical data of the target reservoir monitoring station; establish a one-dimensional nitrogen element transport model for river reservoirs based on the nitrogen element transport process of the target reservoir, determine the nitrification and denitrification coefficient calibration neural network in the nitrogen element transport process of the target reservoir according to the one-dimensional nitrogen element transport model of the river reservoir, and the corresponding objective function to be optimized, input the historical data into the objective function to be optimized, determine the neural network optimization parameters, and thus determine the nitrification and denitrification optimization coefficient; evaluate the greenhouse gas emissions of the target reservoir based on the real-time nitrogen data of the target reservoir and the nitrification and denitrification optimization coefficient. The embodiment of the present invention uses a one-dimensional nitrogen element transport equation, combined with the actual aquatic environment of the reservoir, to increase the physical constraints of the nitrification and denitrification coefficient calibration process, thereby accurately assessing the greenhouse gas emissions of the reservoir.

[0079] Reference Figure 1 , shows a flow chart of the steps of a reservoir greenhouse effect assessment method based on a physical driven neural network provided by an embodiment of the present invention, and the method may specifically include the following steps:

[0080] Reference Figure 1, shows a schematic diagram of a reservoir greenhouse effect assessment method based on a physical driven neural network provided in an embodiment of the present invention, which may specifically include:

[0081] Step 101, collecting historical data of the target reservoir monitoring site;

[0082] By acquiring monitoring stations set up on the main and tributary rivers of the target reservoir area, historical data on the main and tributary rivers of the target reservoir area where the monitoring stations are located can be collected, which may include: flow rate, average flow rate, water temperature, nitrogen content, dissolved oxygen, microbial content and greenhouse gas absorption data at the current location of the target reservoir.

[0083] Step 102, establishing a one-dimensional nitrogen transport model for a river reservoir based on the nitrogen transport process of the target reservoir;

[0084] Reference Figure 2 , showing a schematic diagram of the reservoir nitrogen transport process.

[0085] The transport of nitrogen in a reservoir is a dynamic process of an ecosystem involving multiple links. First, nitrogen enters the reservoir through atmospheric deposition, surface runoff, groundwater recharge, and biological input. Nitrogen undergoes complex transformation processes in the riverbed of the target reservoir area, the surface of the target reservoir, and the riverbed and surface of the downstream river, including nitrification to convert ammonia nitrogen (NH3 and NH4+) into nitrate, denitrification to convert nitrate into nitrogen gas (N2) under anoxic conditions, and assimilation by aquatic plants and algae to convert inorganic nitrogen into organic nitrogen. These transformation processes are affected by factors such as oxygen supply, temperature, and pH. The migration of nitrogen in a reservoir is mainly achieved through horizontal and vertical diffusion through the movement of water flow. Finally, nitrogen is exported from the reservoir through water output at the outlet, adsorption by sediments, and migration or death and decomposition of organisms. These export pathways are affected by factors such as reservoir management, human activities, and climate change.

[0086] The management and control of nitrogen transport in reservoirs is crucial to protecting water quality and maintaining ecological balance. Through reasonable water resource management, improved agricultural practices, sewage treatment and ecological restoration, nitrogen input can be effectively reduced and nitrogen output can be increased, thereby reducing the nitrogen load of reservoirs.

[0087] Establishing a one-dimensional chlorine transport model in rivers and reservoirs based on topological structure can simulate the migration and transformation process of nitrogen in rivers and reservoirs.

[0088] Step 103, determining a nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir and a corresponding objective function to be optimized according to the one-dimensional nitrogen transport model of the river reservoir;

[0089] Nitrification-denitrification coefficients are parameters used to describe the rates of nitrification and denitrification in water or soil. These coefficients are very important in environmental science and ecology because they affect the nitrogen cycle and nitrogen biogeochemical processes.

[0090] Nitrification refers to the process in which ammonia nitrogen (NH3 and NH4+) is oxidized to nitrite nitrogen (NO2-) and further oxidized to nitrate nitrogen (NO3-) under the action of microorganisms. The nitrification coefficient is usually expressed as the rate at which ammonia nitrogen is converted to nitrate nitrogen per unit time. This coefficient is affected by many factors such as temperature, pH value, oxygen concentration, microbial community structure and activity.

[0091] Denitrification refers to the process in which microorganisms reduce nitrate nitrogen to nitrogen gas (N2) and release it into the atmosphere under anoxic conditions. The denitrification coefficient is usually expressed as the rate at which nitrate fluoride is converted into nitrogen gas per unit time. This coefficient is also affected by factors such as temperature, pH value, oxygen concentration, microbial community structure and activity.

[0092] In practical applications, nitrification and denitrification coefficients can be determined through laboratory cultivation experiments, field monitoring, and mathematical models. These coefficients are important for evaluating nitrogen cycles in water and soil, designing sewage treatment systems, predicting the migration and transformation of nitrogen pollutants, and formulating environmental management strategies.

[0093] For example, in wastewater treatment, understanding the nitrification-denitrification coefficient can help engineers design more efficient denitrification processes, such as biological denitrification systems, to reduce nitrogen emissions and protect the water environment. In agricultural management, understanding these coefficients can help farmers optimize fertilization strategies, reduce nitrogen fertilizer losses, and improve nitrogen utilization efficiency while reducing negative impacts on the environment.

[0094] In this embodiment, the nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir is determined based on the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized. Compared with the traditional method, this embodiment requires less data volume and adds physical constraints, thereby improving the accuracy of the nitrogen cycle assessment of the river reservoir, and then accurately assessing the greenhouse gas emissions of the reservoir.

[0095] Step 104, inputting the historical data into the target function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficients;

[0096] Step 105: predicting the greenhouse gas emissions of the target reservoir based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient, thereby evaluating the greenhouse effect of the target reservoir.

[0097] In this embodiment, historical data of the target reservoir monitoring station is collected; a one-dimensional nitrogen transport model of the river reservoir is established based on the nitrogen transport process of the target reservoir; a nitrification and denitrification coefficient calibration neural network and a corresponding objective function to be optimized are determined according to the one-dimensional nitrogen transport model of the river reservoir; historical data are input into the objective function to be optimized, and the neural network optimization parameters are determined, thereby determining the nitrification and denitrification optimization coefficient; greenhouse gas emissions of the target reservoir are evaluated based on the real-time nitrogen data of the target reservoir and the nitrification and denitrification optimization coefficient. The embodiment of the present invention uses a one-dimensional nitrogen transport equation, combined with the actual aquatic environment of the reservoir, to increase the physical constraints of the nitrification and denitrification coefficient calibration process, thereby accurately evaluating the greenhouse gas emissions of the reservoir.

[0098] In one embodiment of the present invention, the collecting of historical data of the target reservoir monitoring site includes:

[0099] Collecting the target reservoir area information, and obtaining the historical data of the monitoring stations set up on the main and tributary rivers in the target reservoir area;

[0100] The historical data at least include: flow rate, average flow rate, water temperature, nitrogen content, dissolved oxygen, microbial content, and greenhouse gas absorption.

[0101] In one embodiment of the present invention, the one-dimensional nitrogen transport model of a river reservoir is established based on the nitrogen transport process of the target reservoir, including:

[0102] Establishing a correlation relationship between nitrogen element and greenhouse gas absorption in the target reservoir based on the historical data;

[0103] A one-dimensional nitrogen transport model for river reservoirs is established based on the correlation relationship and the nitrogen transport process of the target reservoir.

[0104] In an embodiment of the present invention, after establishing the one-dimensional nitrogen transport model of the river reservoir based on the association relationship and the nitrogen transport process of the target reservoir, the method further includes:

[0105] After the one-dimensional nitrogen transport model of the river reservoir is established based on the association relationship and the nitrogen transport process of the target reservoir, the method further includes:

[0106] A one-dimensional nitrogen convection-diffusion equation is established based on the one-dimensional nitrogen transport model of the river reservoir;

[0107] Determine the boundary conditions of the nitrogen element convection-diffusion equation.

[0108] In this embodiment, existing data can be collected in advance to preliminarily establish the correlation between nitrogen elements in the target reservoir and greenhouse gas absorption. Figure 2The topological structure of the reservoir nitrogen transport process shown in Figure 1 establishes a one-dimensional nitrogen transport model for river reservoirs. The one-dimensional nitrogen transport model based on the topological structure can help scientists and engineers understand the nitrogen cycle process, evaluate the sources and impacts of nitrogen pollution, and design effective pollution control and ecological restoration programs.

[0109] Taking into account that the nitrification and denitrification coefficients vary with space, in this embodiment, after a one-dimensional nitrogen element transport model for a river reservoir is established based on the correlation between the nitrogen element in the target reservoir and the absorption of greenhouse gases and the nitrogen element transport process of the target reservoir, which is a step function in space, a one-dimensional nitrogen element convection-diffusion equation is established, and the boundary conditions of the one-dimensional nitrogen element convection-diffusion equation are determined.

[0110] In one embodiment of the present invention, the one-dimensional nitrogen element convection-diffusion equation is established based on the one-dimensional nitrogen element transport model of the river reservoir, including:

[0111] Based on the one-dimensional nitrogen transport model of the river reservoir, the one-dimensional nitrogen convection diffusion equation is established according to the following formula 1;

[0112] Formula 1 is:

[0113]

[0114] Among them: t is the current moment; v is the amplitude of variable stress at each level; x is the spatial position; v is the flow parameter; D is the diffusion coefficient, which describes the diffusion capacity of nitrogen in the reservoir; U is the concentration of nitrate in the reservoir river; R is the nitrification and denitrification coefficient of the water body, which represents the nitrification and denitrification rate of the water body, reflects the activity of plankton and microorganisms in the water body, and is affected by the oxygen content of the water body.

[0115] By establishing a one-dimensional nitrogen convection-diffusion equation, the space is divided into several intervals, and the nitrification and denitrification coefficients in each interval are kept constant, so as to more accurately simulate and predict the transport and transformation process of nitrogen in the reservoir.

[0116] In one embodiment of the present invention, the boundary conditions include an upper boundary condition and a lower boundary condition;

[0117] The boundary conditions for determining the nitrogen element convection-diffusion equation include:

[0118] Determining the upper boundary condition as the inflow nitrogen concentration of the target reservoir;

[0119] The lower boundary condition is determined as the outflow nitrogen concentration of the target reservoir.

[0120] In flow-diffusion equations, boundary conditions play a crucial role. They define the behavior of the system at the boundary and directly affect the solution of the equation.

[0121] The upper boundary condition is usually used to describe the material input or output of the system at the highest point. For example, if there is a fixed nitrogen input at the highest point of the reservoir, it can be set as a Dirichlet boundary condition and a fixed concentration value can be specified; if there is no material exchange at the highest point, it can be set as a Neumann boundary condition and the flux can be specified as zero.

[0122] The lower boundary condition is used to describe the material behavior of the system at the lowest point. For example, if the lowest point of the reservoir is completely closed and matter cannot pass through, it can be set as a no-flux boundary condition; if there is material exchange at the lowest point, it can be set as a Robin boundary condition, combining concentration values ​​and flux to describe the exchange process.

[0123] Correctly selecting and setting the upper and lower boundary conditions can ensure that the solution to the equation accurately reflects the behavior of the system at the spatial boundary and provide a reliable basis for the simulation and prediction of the system.

[0124] In this embodiment, the upper boundary condition can be a fixed boundary condition - the nitrogen concentration of the inflow, and the lower boundary of the reservoir is a free boundary condition with a nitrogen change rate of a constant value, generally 0. For natural rivers, the lower boundary condition is generally also a fixed boundary condition - the nitrogen concentration of the outflow.

[0125] In one embodiment of the present invention, the nitrification and denitrification coefficient calibration neural network and the corresponding objective function to be optimized in the nitrogen transport process of the target reservoir are determined according to the one-dimensional nitrogen transport model of the river reservoir, including:

[0126] According to the one-dimensional nitrogen transport model of the river reservoir, the nitrification and denitrification coefficient calibration neural network of the nitrogen transport process of the target reservoir is determined according to the following formulas 2 and 3;

[0127] Formula 2 is:

[0128]

[0129] Where: e1 is the residual of the one-dimensional nitrogen transport model of the river reservoir; U s is the approximate value of the actual nitrogen concentration; t is the current moment; v is the stress amplitude at each level; x is the spatial position, v is the flow parameter; D is the diffusion coefficient; R s It is an approximate value of the actual nitrification and denitrification coefficient.

[0130] Formula three is:

[0131] e2=U s -U * ;

[0132] Where: e2 is the approximation error of the neural network output to the observed cross-section nitrogen element; U s is the approximate value of the actual nitrogen concentration; U * is the observed nitrogen concentration in the cross section.

[0133] According to the one-dimensional nitrogen transport model of the target reservoir, a neural network for nitrification and denitrification coefficient calibration under the constraints of the reservoir nitrogen transport process is established. The complex nonlinear relationship of the nitrification and denitrification process is learned from a large amount of historical data through a machine learning algorithm, thereby improving the accuracy and efficiency of parameter estimation.

[0134] Formula 2 is the residual of the one-dimensional nitrogen transport model of the target reservoir, which is the physically driven neural network model corresponding to the nitrification and denitrification coefficient. The output R of the network is s＝ R s (x,θ u ) is the approximate value of the true nitrification and denitrification coefficient, and the model parameter we need to fit is denoted as θ u The output of the network is U s =U s (x,t,θ n ) is the approximate value of the actual nitrogen concentration, and the model parameter we need to fit is denoted by θ n .

[0135] Formula 3 is the output of the neural network for the observed cross-section nitrogen element U * The approximation error.

[0136] In one embodiment of the present invention, the nitrification and denitrification coefficient calibration neural network and the corresponding objective function to be optimized in the nitrogen transport process of the target reservoir are determined according to the one-dimensional nitrogen transport model of the river reservoir, including:

[0137] The objective function to be optimized is determined according to the following formula 3:

[0138] Formula 4 is:

[0139]

[0140] Where: L(θ u ,θ n ) is the objective function to be optimized; θ u is the approximate value of the true nitrification and denitrification coefficient R s The fitting model parameters of n is the approximate value of the actual nitrogen concentration U s The fitting model parameters; e1 is the residual of the one-dimensional nitrogen transport model of the river reservoir; e2 is the approximation error of the neural network output to the observed cross-section nitrogen element; is the square of the second norm of the corresponding parameter.

[0141] Formula 4 is used to establish the corresponding objective function to be optimized, providing a clear quantitative standard for the optimization process, so as to minimize or maximize the objective function by adjusting the model parameters or decision variables, thereby achieving the optimal solution or satisfactory solution.

[0142] In this embodiment, by fitting the model parameters θ u and θ n , so that its output matches the actual observed data, thereby improving the accuracy of the model, revealing system laws, optimizing system performance, and assisting in decision support.

[0143] In one embodiment of the present invention, the inputting of the historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficients, comprises:

[0144] Inputting the historical data into the objective function to be optimized;

[0145] Solving the objective function to be optimized based on a gradient descent method to obtain neural network optimization parameters;

[0146] The nitrification and denitrification optimization coefficient is determined based on the neural network optimization parameters.

[0147] In this embodiment, the objective function to be optimized is solved by adopting a gradient descent method, wherein the basic idea of ​​the gradient descent method is to gradually adjust the parameters along the negative gradient direction of the objective function to be optimized in an iterative manner to achieve the purpose of minimizing the objective function to be optimized.

[0148] In one embodiment of the present invention, solving the objective function to be optimized based on a gradient descent method to obtain a neural network optimization parameter includes:

[0149] Calculating the gradient of each parameter in the objective function to be optimized;

[0150] Updating the parameter value of the neural network according to the gradient information of the gradient;

[0151] It is determined whether the parameter value of the neural network meets the convergence condition. If the update amplitude of the parameter value of the neural network is less than a preset threshold or reaches the maximum number of iterations, the iteration is stopped to obtain the optimization parameters of the neural network.

[0152] The objective function to be optimized is solved by using a gradient descent method, wherein the basic idea of ​​the gradient descent method is to gradually adjust the parameters along the negative gradient direction of the objective function to be optimized in an iterative manner, specifically including:

[0153] Step 1: Initialize parameters: Randomly select a set of initial parameter values ​​as the starting point of the optimization process;

[0154] Step 2: Calculate the gradient: At the current parameter value, calculate the gradient (i.e. partial derivative) of the objective function to be optimized with respect to each parameter. The gradient indicates the direction in which the function has the largest rate of change at the current point.

[0155] Step 3: Update parameters: Update parameter values ​​according to gradient information and learning rate;

[0156] Step 4: Check convergence conditions: Determine whether the convergence conditions are met, such as whether the parameter update amplitude is less than a certain threshold or the maximum number of iterations is reached. If the conditions are met, stop the iteration; otherwise, return to step 2 to continue the iteration.

[0157] By inputting the flow data of nitrogen content in the collected historical data into the established objective function to be optimized, and using the gradient descent method to solve the objective function, until the optimal neural network optimization parameters are found, the output of the neural network can satisfy the control equation as much as possible and be as close to the observed data as possible. After the optimization is completed, the optimal parameter θ is found. n * , then the nitrification and denitrification coefficient is R s (x,θ n * ), which is the desired optimization coefficient of nitrification and denitrification.

[0158] In one embodiment of the present invention, the greenhouse gas emissions of the target reservoir are predicted based on the real-time data of nitrogen elements of the target reservoir and the nitrification and denitrification optimization coefficient, thereby evaluating the greenhouse effect of the target reservoir, including:

[0159] Drawing a two-dimensional dot matrix diagram based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient;

[0160] The greenhouse gas emissions of the target reservoir are predicted based on the two-dimensional dot matrix, and the greenhouse effect of the target reservoir is evaluated.

[0161] In this embodiment, the real-time data of nitrogen observed at the target reservoir monitoring station and the calibrated nitrification and denitrification optimization coefficient can be plotted into a two-dimensional dot matrix diagram, wherein the real-time data of nitrogen includes at least: nitrogen content data and greenhouse gas monitoring quantity records.

[0162] After the two-dimensional dot matrix is ​​obtained, the greenhouse gas emissions of the target reservoir are predicted based on the two-dimensional dot matrix, and the greenhouse effect of the target reservoir is evaluated.

[0163] In one embodiment of the present invention, the method further comprises:

[0164] Inputting the nitrification and denitrification optimization coefficient into a one-dimensional nitrogen element convection diffusion equation;

[0165] Solving the one-dimensional nitrogen convection-diffusion equation based on an implicit difference method to obtain the nitrogen content of the target reservoir after a preset time;

[0166] Determining the loss of nitrogen in the target reservoir based on the nitrogen content in the target reservoir after the preset time and the nitrification and denitrification optimization coefficient;

[0167] Based on the loss amount and the two-dimensional dot matrix diagram, the greenhouse gas emission of the target reservoir is predicted, and the greenhouse effect of the target reservoir is evaluated.

[0168] In this embodiment, the nitrification and denitrification optimization coefficients may be input into a one-dimensional nitrogen advection diffusion equation, and the one-dimensional nitrogen advection diffusion equation may be solved based on an implicit difference method, which includes the following steps:

[0169] Step S1, establish the difference equation: For the time derivative, use the backward difference format:

[0170]

[0171] For spatial derivatives, the central difference scheme or other appropriate difference schemes can be used;

[0172] Step S2, Substitute into the original equation: Substitute the difference format into the original partial differential equation to obtain a i n+1 algebraic equations;

[0173] Step S3, establishing a linear equation system: Since backward difference is used, the obtained algebraic equation is usually nonlinear, and a linear equation system is obtained through linearization processing; this linear equation system can be in the form of a tridiagonal matrix, or can be processed by matrix decomposition technology (such as LU decomposition);

[0174] Step S4, solving the linear equations: using numerical methods (such as TDMA, iteration method, etc.) to solve the linear equations and obtain t n+1 The solution of the moment n+1 ;

[0175] Step S5, iterative calculation: starting from the initial time t0, iterative calculation is performed step by step until the preset time t is reached. M .

[0176] Implicit difference methods usually have unconditional stability and can maintain the stability of numerical solutions even for larger time steps. Therefore, solving the one-dimensional nitrogen convection-diffusion equation based on implicit difference method can make it have better numerical stability when dealing with convection and diffusion problems, thereby improving the accuracy of assessing greenhouse gas emissions from reservoirs.

[0177] After solving the one-dimensional nitrogen convection-diffusion equation based on the implicit difference method, the nitrogen content U(x, t) of the target reservoir after a preset time can be obtained. Based on this data and the nitrification and denitrification optimization coefficient, the nitrogen loss of the target reservoir is determined according to the formula R*U(x, t). Finally, based on the nitrogen loss of the target reservoir and the two-dimensional dot matrix, the greenhouse gas emissions of the target reservoir in the future are predicted, and the greenhouse effect of the target reservoir is evaluated.

[0178] The embodiment of the present invention discloses a reservoir greenhouse effect assessment method based on a physical driven neural network, the method comprising: collecting historical data of a target reservoir monitoring station; establishing a one-dimensional nitrogen transport model for a river reservoir based on the nitrogen transport process of the target reservoir, determining a nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and a corresponding objective function to be optimized, inputting historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficient; assessing the greenhouse gas emissions of the target reservoir based on the real-time nitrogen data of the target reservoir and the nitrification and denitrification optimization coefficient. The embodiment of the present invention uses a one-dimensional nitrogen transport equation, combined with the actual aquatic environment of the reservoir, to increase the physical constraints of the nitrification and denitrification coefficient calibration process, thereby accurately assessing the greenhouse gas emissions of the reservoir.

[0179] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0180] Reference Figure 3 , shows a structural block diagram of a reservoir greenhouse effect assessment device based on a physical driven neural network provided by an embodiment of the present invention, which may specifically include the following modules:

[0181] A data collection module 301 is used to collect historical data of a target reservoir monitoring site;

[0182] A first model building module 302 is used to build a one-dimensional nitrogen transport model for a river reservoir based on the nitrogen transport process of the target reservoir;

[0183] A neural network building module 303 is used to determine the nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized;

[0184] The optimization coefficient determination module 304 is used to input the historical data into the target function to be optimized, determine the neural network optimization parameters, and thus determine the nitrification and denitrification optimization coefficients;

[0185] The evaluation module 305 is used to predict the greenhouse gas emission of the target reservoir based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient, so as to evaluate the greenhouse effect of the target reservoir.

[0186] The embodiment of the present invention discloses a reservoir greenhouse effect assessment method based on a physical driven neural network, the method comprising: collecting historical data of a target reservoir monitoring station; establishing a one-dimensional nitrogen transport model for a river reservoir based on the nitrogen transport process of the target reservoir, determining a nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and a corresponding objective function to be optimized, inputting historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficient; assessing the greenhouse gas emissions of the target reservoir based on the real-time nitrogen data of the target reservoir and the nitrification and denitrification optimization coefficient. The embodiment of the present invention uses a one-dimensional nitrogen transport equation, combined with the actual aquatic environment of the reservoir, to increase the physical constraints of the nitrification and denitrification coefficient calibration process, thereby accurately assessing the greenhouse gas emissions of the reservoir.

[0187] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0188] An embodiment of the present invention further provides an electronic device, including:

[0189] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, each process of the embodiment of the reservoir greenhouse effect assessment method based on the physical driven neural network is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0190] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the embodiment of the reservoir greenhouse effect assessment method based on a physical-driven neural network is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0191] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0192] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0193] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0194] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0196] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0197] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0198] The above is a detailed introduction to a reservoir greenhouse effect assessment method based on a physical-driven neural network and a reservoir greenhouse effect assessment device based on a physical-driven neural network provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technicians in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A reservoir greenhouse effect assessment method based on physical driven neural network, characterized in that: The method comprises: Collect historical data from monitoring sites at target reservoirs; Establishing a one-dimensional nitrogen transport model for river reservoirs based on the nitrogen transport process of the target reservoir; Determine the nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized; Inputting the historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficients; The greenhouse gas emission of the target reservoir is predicted based on the real-time data of nitrogen elements of the target reservoir and the nitrification and denitrification optimization coefficient, so as to evaluate the greenhouse effect of the target reservoir.

2. The method according to claim 1, characterized in that: The one-dimensional nitrogen transport model of a river reservoir is established based on the nitrogen transport process of the target reservoir, including: Establishing a correlation between nitrogen and greenhouse gases in the target reservoir based on the historical data; A one-dimensional nitrogen transport model for river reservoirs is established based on the correlation relationship and the nitrogen transport process of the target reservoir.

3. The method according to claim 2, characterized in that After the one-dimensional nitrogen transport model of the river reservoir is established based on the association relationship and the nitrogen transport process of the target reservoir, the method further includes: A one-dimensional nitrogen convection-diffusion equation is established based on the one-dimensional nitrogen transport model of the river reservoir; Determine the boundary conditions of the nitrogen element convection-diffusion equation.

4. The method according to claim 3, characterized in that The one-dimensional nitrogen element convection-diffusion equation is established based on the one-dimensional nitrogen element transport model of the river reservoir, including: Based on the one-dimensional nitrogen transport model of the river reservoir, the one-dimensional nitrogen convection-diffusion equation is established according to the following formula 1; Formula 1 is: Among them: t is the current moment; v is the amplitude of variable stress at each level; x is the spatial position; v is the flow parameter; D is the diffusion coefficient, which describes the diffusion capacity of nitrogen in the reservoir; U is the concentration of nitrate in the reservoir river; R is the nitrification and denitrification coefficient of the water body, which represents the nitrification and denitrification rate of the water body, reflects the activity of plankton and microorganisms in the water body, and is affected by the oxygen content of the water body.

5. The method according to claim 3, characterized in that: The boundary conditions include upper boundary conditions and lower boundary conditions; The boundary conditions for determining the nitrogen element convection-diffusion equation include: Determining the upper boundary condition as the inflow nitrogen concentration of the target reservoir; The lower boundary condition is determined as the outflow nitrogen concentration of the target reservoir.

6. The method according to claim 1, characterized in that The neural network for calibrating the nitrification and denitrification coefficients in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized, include: According to the one-dimensional nitrogen transport model of the river reservoir, the nitrification and denitrification coefficient calibration neural network of the nitrogen transport process of the target reservoir is determined according to the following formulas 2 and 3; Formula 2 is: Where: e1 is the residual of the one-dimensional nitrogen transport model of the river reservoir; U s is the approximate value of the actual nitrogen concentration; t is the current moment; v is the stress amplitude at each level; x is the spatial position, v is the flow parameter; D is the diffusion coefficient; R s It is the approximate value of the true nitrification and denitrification coefficient; Formula three is: e2=U s -U * ; Where: e2 is the approximation error of the neural network output to the observed cross-section nitrogen element; U s is the approximate value of the actual nitrogen concentration; U * is the observed nitrogen concentration in the cross section.

7. The method according to claim 6, characterized in that The neural network for calibrating the nitrification and denitrification coefficients in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized, include: The objective function to be optimized is determined according to the following formula 4: Formula 4 is: Where: L(θ u ,θ n ) is the objective function to be optimized; θ u is the approximate value of the true nitrification and denitrification coefficient R s The fitting model parameters of n is the approximate value of the actual nitrogen concentration U s The fitting model parameters; e1 is the residual of the one-dimensional nitrogen transport model of the river reservoir; e2 is the approximation error of the neural network output to the observed cross-section nitrogen element; is the square of the second norm of the corresponding parameter.

8. The method according to claim 7, characterized in that The step of inputting the historical data into the objective function to be optimized, determining the neural network optimization parameters, and thus determining the nitrification and denitrification optimization coefficients, comprises: Inputting the historical data into the objective function to be optimized; Solving the objective function to be optimized based on a gradient descent method to obtain neural network optimization parameters; The nitrification and denitrification optimization coefficient is determined based on the neural network optimization parameters.

9. The method according to claim 8, characterized in that The method of solving the objective function to be optimized based on the gradient descent method to obtain the neural network optimization parameters includes: Calculating the gradient of each parameter in the objective function to be optimized; Updating the parameter value of the neural network according to the gradient information of the gradient; It is determined whether the parameter value of the neural network meets the convergence condition. If the update amplitude of the parameter value of the neural network is less than a preset threshold or reaches the maximum number of iterations, the iteration is stopped to obtain the optimization parameters of the neural network.

10. The method according to claim 1, characterized in that The method of predicting the greenhouse gas emissions of the target reservoir based on the real-time data of nitrogen elements of the target reservoir and the nitrification and denitrification optimization coefficient, thereby evaluating the greenhouse effect of the target reservoir, includes: Drawing a two-dimensional dot matrix diagram based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient; The greenhouse gas emissions of the target reservoir are predicted based on the two-dimensional dot matrix, and the greenhouse effect of the target reservoir is evaluated.

11. The method according to claim 10, characterized in that The method further comprises: Inputting the nitrification and denitrification optimization coefficient into a one-dimensional nitrogen element convection diffusion equation; Solving the one-dimensional nitrogen convection-diffusion equation based on an implicit difference method to obtain the nitrogen content of the target reservoir after a preset time; Determining the loss of nitrogen in the target reservoir based on the nitrogen content in the target reservoir after the preset time and the nitrification and denitrification optimization coefficient; Based on the loss amount and the two-dimensional dot matrix diagram, the greenhouse gas emission of the target reservoir is predicted, and the greenhouse effect of the target reservoir is evaluated.

12. The method according to claim 1, characterized in that The historical data collected from the target reservoir monitoring site includes: Collecting the target reservoir area information, and obtaining the historical data of the monitoring stations set up on the main and tributary rivers in the target reservoir area; The historical data at least include: flow rate, average flow rate, water temperature, nitrogen content, dissolved oxygen, microbial content, and greenhouse gas absorption.

13. A reservoir greenhouse effect assessment device based on physical driven neural network, characterized in that: The device comprises: A data collection module, used to collect historical data from target reservoir monitoring sites; A first model building module is used to build a one-dimensional nitrogen transport model for river reservoirs based on the nitrogen transport process of the target reservoir; A neural network building module, used to determine the nitrification and denitrification coefficient calibration neural network in the nitrogen transport process of the target reservoir according to the one-dimensional nitrogen transport model of the river reservoir, and the corresponding objective function to be optimized; An optimization coefficient determination module is used to input the historical data into the target function to be optimized, determine the neural network optimization parameters, and thus determine the nitrification and denitrification optimization coefficients; An evaluation module is used to predict the greenhouse gas emissions of the target reservoir based on the real-time data of nitrogen elements in the target reservoir and the nitrification and denitrification optimization coefficient, so as to evaluate the greenhouse effect of the target reservoir.

14. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the reservoir greenhouse effect assessment method based on a physics-driven neural network as described in any one of claims 1 to 12 are implemented.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the reservoir greenhouse effect assessment method based on a physics-driven neural network as described in any one of claims 1 to 12 are implemented.

Images