A method and apparatus for calibrating the diffusion coefficient of phosphate transport processes.

Abstract

This application provides a method and apparatus for calibrating the diffusion coefficient of phosphate transport processes. The method includes: collecting historical reservoir information of a target reservoir; constructing a two-dimensional phosphate transport model of the reservoir based on its topographic features; constructing a two-dimensional phosphorus convection-diffusion equation based on parameters contained in the historical reservoir information; setting boundary conditions for the two-dimensional phosphorus convection-diffusion equation based on the parameters contained in the historical reservoir information and the topographic features; constructing an optimization objective function based on the two-dimensional phosphorus convection-diffusion equation; training the two-dimensional phosphate transport model of the reservoir based on the historical reservoir information to obtain the two-dimensional phosphate transport model; inputting the current reservoir information into the two-dimensional phosphate transport model to obtain the phosphorus diffusion coefficient; and calibrating the diffusion coefficient of the phosphate transport process based on the phosphate concentration, phosphorus diffusion coefficient, and the two-dimensional phosphorus convection-diffusion equation in the current reservoir information. This method can improve the accuracy of the obtained diffusion coefficient.

Description

Technical Field

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

[0002] Large reservoirs play a vital role in water resource storage, flood control, and power generation. However, due to human activities such as rice paddy fertilization and aquaculture, excessive application of nutrients is carried into reservoirs by rainwater, leading to the accumulation of phosphorus in the form of phosphates, a serious environmental problem. Excessive phosphorus accumulation causes eutrophication, triggering a series of ecological and environmental problems such as cyanobacteria and aquatic plants, while also threatening the water quality and ecosystem stability of the reservoirs.

[0003] Phosphorus exists in water in both dissolved and particulate forms. Particulate phosphorus tends to adhere to suspended solids, thus exhibiting strong enrichment properties in water bodies and easily accumulating and depositing in reservoirs. In the process of phosphate (phosphorus) transport, the diffusion coefficient is a core parameter describing the diffusion and migration capacity of phosphorus in reservoirs. The diffusion coefficient reflects the transfer rate and migration distance of phosphorus in water and is influenced by factors such as water temperature, pH, salinity, hydrodynamic conditions, and phosphorus speciation, making it a non-constant parameter. Therefore, accurately obtaining the diffusion coefficient of phosphate transport is crucial for water quality management and maintaining the stability of reservoir ecosystems. However, existing models such as least squares fitting and linear regression statistics struggle to address the problem of multi-objective parameter identification, resulting in non-unique parameters and poor model accuracy, leading to low precision in the obtained diffusion coefficient of phosphate transport. Summary of the Invention

[0004] This application discloses a method and apparatus for calibrating the diffusion coefficient of phosphate transport processes.

[0005] In a first aspect, this application discloses a method for calibrating the diffusion coefficient of a phosphate transport process, the method comprising:

[0006] Collect historical reservoir area information for the target reservoir;

[0007] Based on the topographic features of the target reservoir, a two-dimensional phosphate transport model of the reservoir is constructed. Based on the parameters contained in the historical reservoir information, a two-dimensional phosphorus convection-diffusion equation for the two-dimensional phosphate transport model of the reservoir is constructed.

[0008] Based on the parameters contained in the historical reservoir information and the topographic features of the target reservoir, boundary conditions are set for the two-dimensional phosphorus convection-diffusion equation.

[0009] Based on the two-dimensional phosphorus convection-diffusion equation, an optimization objective function based on the two-dimensional phosphate transport model of the reservoir is constructed.

[0010] Based on the historical reservoir area information of the target reservoir, the two-dimensional phosphate transport model of the reservoir is trained. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir meets the preset conditions, the two-dimensional phosphate transport model is obtained.

[0011] The current information of the target reservoir area is collected and input into the two-dimensional phosphate transport model to obtain the diffusion coefficient of phosphorus. Based on the phosphate concentration, phosphorus diffusion coefficient and the two-dimensional phosphorus convection-diffusion equation contained in the current information of the reservoir area, the diffusion coefficient of the phosphate transport process in the target reservoir is calibrated.

[0012] The optimization objective function constructed based on the two-dimensional phosphorus convection-diffusion equation and the two-dimensional phosphate transport model of the reservoir includes:

[0013] Based on the parameters in the two-dimensional phosphorus convection-diffusion equation, a neural network equation for the residual of the diffusion coefficient is established.

[0014] Based on the output of the neural network equation and the phosphate concentration parameters in the historical reservoir information, an approximation error equation for phosphate concentration is constructed.

[0015] Based on the neural network equation and the approximation error equation, an optimization objective function is constructed based on the two-dimensional phosphate transport model of the reservoir.

[0016] Optionally, the step of training the two-dimensional phosphate transport model of the reservoir based on the historical reservoir area information of the target reservoir, and obtaining the two-dimensional phosphate transport model when the optimization objective function of the two-dimensional phosphate transport model of the reservoir satisfies the preset conditions, includes:

[0017] The reservoir two-dimensional phosphate transport model is calculated based on the historical reservoir area information from the previous historical moment to obtain the predicted diffusion coefficient and phosphorus content.

[0018] Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0019] The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the current historical moment.

[0020] Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0021] If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the reservoir two-dimensional phosphate transport model is executed according to the historical reservoir area information of the previous historical moment.

[0022] Optionally, the step of training the two-dimensional phosphate transport model of the reservoir based on the historical reservoir area information of the target reservoir, and obtaining the two-dimensional phosphate transport model when the optimization objective function of the two-dimensional phosphate transport model of the reservoir satisfies the preset conditions, includes:

[0023] Phosphorus content is filtered out from historical reservoir information at the target historical moment to obtain training data;

[0024] The reservoir two-dimensional phosphate transport model performs calculations based on the input training data to obtain the predicted diffusion coefficient and phosphorus content;

[0025] Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0026] The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the target historical moment.

[0027] Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0028] If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the step of filtering out phosphorus content is performed from the historical reservoir information at another historical moment.

[0029] Optionally, the step of training the two-dimensional phosphate transport model of the reservoir based on the historical reservoir area information of the target reservoir, and obtaining the two-dimensional phosphate transport model when the optimization objective function of the two-dimensional phosphate transport model of the reservoir satisfies the preset conditions, includes:

[0030] The information from each historical reservoir area was sorted according to the chronological order of collection to obtain a sorted sequence.

[0031] Based on the pre-set number of sample datasets, historical database information is extracted from the sorting sequence at intervals of the number of datasets to obtain the number of sample datasets.

[0032] The phosphorus content was filtered out from each sample dataset to obtain the corresponding training dataset;

[0033] The training datasets are sorted according to the collection time of the first data point in each dataset;

[0034] The first training dataset with the earliest collection time is selected. Based on the first training dataset and the first sample dataset corresponding to the first training dataset, the reservoir two-dimensional phosphate transport model is trained until the optimized value of the reservoir two-dimensional phosphate transport model is less than the preset first optimization threshold, and the initial training transport model is obtained.

[0035] The second training dataset, which is collected at the second earliest time, is selected. Based on the second training dataset and the second sample dataset corresponding to the second training dataset, the initial training transport model is trained until the optimized value of the initial training transport model is less than a preset second optimization threshold, and the second optimization threshold is less than the first optimization threshold, until the training dataset collected at the latest time is trained.

[0036] Optionally, the two-dimensional phosphorus convection-diffusion equation is as follows:

[0037]

[0038] in:

[0039] x, y, and t represent the spatial location of phosphorus diffusion and the current time, respectively;

[0040] U represents the concentration of phosphate in the reservoir;

[0041] R represents the adsorption and desorption rates of water.

[0042] v x v y These are the water flow direction parameters and vertical flow parameters, respectively;

[0043] D x D y These are the water flow diffusion parameters and vertical diffusion parameters for phosphorus, respectively.

[0044] Optionally, the neural network equation for calibrating the diffusion coefficient is as follows:

[0045]

[0046] In the formula,

[0047] e1 represents the residual of the two-dimensional phosphate transport model of the reservoir;

[0048] U s The calculated phosphate concentration output by the two-dimensional phosphate transport model of the reservoir;

[0049] D xs D ysThese are the calculation parameters for the flow-direction diffusion and vertical diffusion of phosphorus, respectively.

[0050] Optionally, the method further includes:

[0051] The diffusion coefficient of the phosphate transport process in the target reservoir, which has been calibrated, is sent to a pre-set terminal device.

[0052] Optionally, the historical reservoir information includes: flow rate, water temperature, pH value, salinity, hydrodynamic conditions, phosphorus content and form.

[0053] Optionally, the historical reservoir information may also include: water adsorption and desorption rates.

[0054] Optionally, if the water depth of the target reservoir exceeds a preset water depth threshold, the historical reservoir information includes: historical hydrological data at multiple preset depths within the reservoir.

[0055] Optionally, the method further includes:

[0056] At each time point and at the corresponding location of the phosphate transport process in the calibrated target reservoir, the measured information of the reservoir area at the corresponding location of the target reservoir at that time point was collected.

[0057] Based on the diffusion coefficient of the target reservoir at that time and the phosphorus concentration information contained in the measured information of the reservoir area, the two-dimensional phosphate transport model is retrained.

[0058] Secondly, this application discloses an apparatus for calibrating the diffusion coefficient of a phosphate transport process, the apparatus comprising:

[0059] The data collection module is used to collect historical reservoir area information for the target reservoir;

[0060] The model building module is used to construct a two-dimensional phosphate transport model of the target reservoir based on the topographic features of the reservoir, and to construct a two-dimensional phosphorus convection-diffusion equation for the two-dimensional phosphate transport model of the reservoir based on the parameters contained in the historical reservoir information.

[0061] The boundary setting module is used to set boundary conditions for the two-dimensional phosphorus convection-diffusion equation based on the parameters contained in the historical reservoir information and the topographic features of the target reservoir.

[0062] An optimization module is used to construct an optimization objective function based on the two-dimensional phosphorus convection-diffusion equation and the reservoir two-dimensional phosphate transport model.

[0063] The model training module is used to train the two-dimensional phosphate transport model of the target reservoir based on the historical reservoir area information. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir meets the preset conditions, the two-dimensional phosphate transport model is obtained.

[0064] The diffusion coefficient acquisition module is used to collect the current information of the target reservoir area, input the two-dimensional phosphate transport model, obtain the diffusion coefficient of phosphorus, and calibrate the diffusion coefficient of the phosphate transport process in the target reservoir based on the phosphate concentration, the diffusion coefficient of phosphorus and the two-dimensional phosphorus convection-diffusion equation contained in the current information of the reservoir area.

[0065] The optimized construction module is specifically used for:

[0066] Based on the parameters in the two-dimensional phosphorus convection-diffusion equation, a neural network equation for the residual of the diffusion coefficient is established.

[0067] Based on the output of the neural network equation and the phosphate concentration parameters in the historical reservoir information, an approximation error equation for phosphate concentration is constructed.

[0068] Based on the neural network equation and the approximation error equation, an optimization objective function is constructed based on the two-dimensional phosphate transport model of the reservoir.

[0069] Optionally, the model training module is specifically used for:

[0070] The reservoir two-dimensional phosphate transport model is calculated based on the historical reservoir area information from the previous historical moment to obtain the predicted diffusion coefficient and phosphorus content.

[0071] Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0072] The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the current historical moment.

[0073] Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0074] If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the reservoir two-dimensional phosphate transport model is executed according to the historical reservoir area information of the previous historical moment.

[0075] Optionally, the model training module is specifically used for:

[0076] Phosphorus content is filtered out from historical reservoir information at the target historical moment to obtain training data;

[0077] The reservoir two-dimensional phosphate transport model performs calculations based on the input training data to obtain the predicted diffusion coefficient and phosphorus content;

[0078] Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0079] The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the target historical moment.

[0080] Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0081] If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the step of filtering out phosphorus content is performed from the historical reservoir information at another historical moment.

[0082] 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.

[0083] Fourthly, this application discloses a non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the methods described in any of the preceding aspects.

[0084] 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.

[0085] The technical solution provided in this application may include the following beneficial effects:

[0086] By analyzing the parameters contained in historical reservoir information, a two-dimensional phosphorus convection-diffusion equation is constructed. Based on the parameters and topographic features of the historical reservoir information, boundary conditions are set for the two-dimensional phosphorus convection-diffusion equation. Then, based on the two-dimensional phosphorus convection-diffusion equation, an optimization objective function is constructed. Combining the actual aquatic environment of the target reservoir, multiple transport mechanisms of phosphorus transport in the target reservoir are considered. The phosphorus transport process is accurately simulated through model training, and the diffusion coefficient of the phosphate transport process is calibrated. This can effectively improve the accuracy of the assessment of the phosphorus transport process and enhance the accuracy of the calibrated phosphorus diffusion coefficient, providing more accurate data support for water quality management and maintenance of reservoir ecosystem stability. Attached Figure Description

[0087] Figure 1 This is a flowchart illustrating the steps of a method for calibrating the diffusion coefficient of a phosphate transport process according to this application.

[0088] Figure 2 This is a schematic diagram of the phosphorus transport process in the reservoir of this application.

[0089] Figure 3 This is a structural block diagram of an apparatus for calibrating the diffusion coefficient of a phosphate transport process according to this application.

[0090] Figure 4 This is a block diagram of an electronic device according to this application.

[0091] Figure 5 This is a block diagram of an electronic device according to this application. Detailed Implementation

[0092] 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.

[0093] The diffusion coefficient is a core parameter describing the diffusion and migration capacity of phosphorus in reservoirs. It is influenced by factors such as water temperature, pH, salinity, hydrodynamic conditions, and phosphorus speciation, making it a non-constant parameter. Existing methods for calculating the diffusion coefficient using models constructed with least squares fitting and linear regression statistics suffer from low accuracy due to the non-uniqueness of the target parameters, thus impacting water treatment based on phosphorus diffusion coefficients.

[0094] This embodiment proposes a method for calibrating the diffusion coefficient of phosphorus (phosphate) transport in large reservoirs. By utilizing a two-dimensional phosphorus transport equation and combining it with the actual aquatic environment of the reservoir, the method increases the constraints of the diffusion coefficient calibration process, thereby considering multiple transport mechanisms of phosphorus in the reservoir and calibrating the diffusion coefficient. This accurately simulates the phosphorus transport process, improves the accuracy of phosphorus transport process assessment, and enhances the precision of the calibrated phosphorus diffusion coefficient. This provides more accurate data support for water quality management and maintaining the stability of the reservoir ecosystem.

[0095] Reference Figure 1 The diagram illustrates a flowchart of a method for calibrating the diffusion coefficient of a phosphate transport process according to this application. This method can be applied to electronic devices, and specifically includes the following steps:

[0096] S101, Collect historical reservoir area information of the target reservoir;

[0097] In step S101, the historical reservoir information refers to historical parameter information affecting the diffusion coefficient of phosphorus. As an optional embodiment, the content of the historical reservoir information can be determined by a professional technician based on parameters related to the diffusion coefficient of phosphorus, including but not limited to: historical data from monitoring stations established on the main streams and tributaries within the target reservoir area, and reservoir capacity information. The historical data includes, but is not limited to: flow rate, water temperature, pH value, salinity, hydrodynamic conditions, phosphorus content, and phosphorus speciation. Hydrodynamic conditions include, but are not limited to: flow direction parameters and vertical flow parameters. As another optional embodiment, the historical reservoir information also includes water adsorption and desorption rates.

[0098] In this embodiment, as an optional implementation, since the diffusion coefficient of phosphorus in the reservoir area is related to the water temperature, and the water temperature varies at different depths within the reservoir area, if it is determined that the water depth of the target reservoir area exceeds a preset water depth threshold, the historical reservoir information also includes: historical hydrological data at multiple preset depths within the reservoir area. The content of the historical hydrological data is the same as that of the historical data at the monitoring stations, including but not limited to: flow rate, water temperature, pH value, salinity, hydrodynamic conditions, phosphorus content, and phosphorus form at that preset depth.

[0099] S102, Based on the topographic features of the target reservoir, a two-dimensional phosphate transport model of the reservoir is constructed, and based on the parameters contained in the historical reservoir information, a two-dimensional phosphorus convection-diffusion equation for the two-dimensional phosphate transport model of the reservoir is constructed.

[0100] Figure 2 This is a schematic diagram of the phosphorus transport process in the reservoir according to this application. Figure 2As shown, the target reservoir is divided into an upstream river surface (reservoir surface) and a downstream river surface, with the dam serving as the dividing interface. The reservoir surface corresponds to the reservoir riverbed, and the downstream river surface corresponds to the downstream riverbed. In this embodiment, as an optional implementation, a two-dimensional phosphate transport model of the reservoir is established based on the topological structure including the reservoir surface, reservoir riverbed, dam, downstream river surface, and downstream riverbed. In the two-dimensional phosphate transport model of the reservoir, the water depth (vertical) direction is the y-direction, and the water flow (horizontal) direction is the x-direction.

[0101] In this embodiment, as an optional implementation, considering that the diffusion coefficient of phosphorus in the reservoir varies spatially, the diffusion coefficient is set as a spatial step function. Based on the parameters contained in the historical reservoir information, a two-dimensional convection-diffusion equation for phosphorus is established, as follows:

[0102]

[0103] in:

[0104] x, y, and t represent the spatial location of phosphorus diffusion and the current time, respectively;

[0105] U represents the concentration of phosphate (phosphorus element concentration) in the reservoir;

[0106] R represents the adsorption and desorption rate of water, which is affected by factors such as water temperature, pH value, and phosphorus form. It can be measured by collecting water samples from the target reservoir in the laboratory.

[0107] v x v y These are the water flow direction parameters and vertical flow parameters, respectively;

[0108] D x D y These are the water flow direction diffusion parameters and vertical diffusion parameters for phosphorus, respectively, used to describe the diffusion capacity of phosphate in the reservoir. In other words, the diffusion coefficient of phosphorus includes the water flow direction diffusion parameters and the vertical diffusion parameters.

[0109] S103, Based on the parameters contained in the historical reservoir information and the topographic features of the target reservoir, set boundary conditions for the two-dimensional phosphorus convection-diffusion equation;

[0110] In this embodiment, the boundary conditions of the two-dimensional phosphorus convection-diffusion equation are determined based on the correlation between various parameters contained in the reservoir information and the topographic features of the target reservoir. As an optional embodiment, the boundary conditions include an upper boundary condition and a lower boundary condition. The upper boundary condition is a fixed boundary condition (inflow phosphorus concentration), and the lower boundary condition is a free boundary condition (phosphorus change rate), which is a constant value, and in an optional embodiment, is set to 0. For example, the upper boundary condition is a first-type boundary condition, and the lower boundary condition is a second-type boundary condition.

[0111] S104, Based on the two-dimensional phosphorus convection-diffusion equation, construct an optimization objective function based on the two-dimensional phosphate transport model of the reservoir;

[0112] In this embodiment, based on the two-dimensional phosphorus convection-diffusion equation and boundary conditions, a neural network equation for calibrating the diffusion coefficient under the constraints of the reservoir phosphate transport process is established, so as to calculate the residual of the reservoir two-dimensional phosphate transport model based on the neural network equation.

[0113] In this embodiment, as an optional implementation, based on the two-dimensional phosphorus convection-diffusion equation, an optimization objective function based on the reservoir two-dimensional phosphate transport model is constructed, including:

[0114] A11. Based on the parameters in the two-dimensional phosphorus convection-diffusion equation, a neural network equation is established for calibrating the residual of the diffusion coefficient.

[0115] In this embodiment, the neural network equation for calibrating the diffusion coefficient is established as follows:

[0116]

[0117] In the formula,

[0118] e1 is the residual of the two-dimensional phosphate transport model of the reservoir, and Dx and Dy are the physical driving neural network models corresponding to the diffusion coefficients. That is, the physical driving force of the physical driving neural network model is the two-dimensional phosphate transport model of the reservoir.

[0119] U s The calculated concentration of phosphate (predicted phosphorus concentration) output by the two-dimensional phosphate transport model of the reservoir;

[0120] D xs D ys These are the calculation parameters for the flow-direction diffusion and vertical diffusion of phosphorus, respectively.

[0121] In this embodiment, the two-dimensional phosphate transport model of the reservoir outputs the flow direction diffusion calculation parameters and vertical diffusion calculation parameters of phosphorus element, which are approximate values ​​of the true diffusion coefficient.

[0122] In this embodiment, Dxs =D xs (x,y,q u ), D ys =D ys (x,y,q u ), U s =U s (x,y,t;q n ), where q u q n These are the model parameters for a two-dimensional phosphate transport model of a reservoir.

[0123] In this embodiment, the model parameters need to be obtained by fitting using a neural network algorithm. The output of the neural network model (two-dimensional phosphate transport model of a reservoir) includes: an approximate value (predicted value) of phosphorus concentration and an approximate value of phosphorus diffusion coefficient.

[0124] A12. Based on the output of the neural network equation and the phosphate concentration parameters in the historical reservoir information, an approximation error equation for phosphate concentration is constructed.

[0125] In this embodiment, as an optional implementation, the approximation error of the phosphate concentration is obtained based on the output of the two-dimensional phosphate transport model of the reservoir and the measured concentration of phosphate in the reservoir area information.

[0126] In this embodiment, as an optional implementation, the approximation error of the phosphate concentration is calculated using the following formula (approximation error equation):

[0127] e2 = U s -U *

[0128] In the formula, e2 is the approximation error of the neural network model's output to the observed concentration of phosphate at the cross section;

[0129] U * The concentration of phosphate at the observed cross-section is the phosphorus content (measured concentration of phosphate) in the historical reservoir information.

[0130] A13. Based on the neural network equation and the approximation error equation, construct an optimization objective function based on the two-dimensional phosphate transport model of the reservoir.

[0131] In this embodiment, an optimization objective function based on the residuals of the two-dimensional phosphate transport model of the reservoir and the approximation error of the phosphate concentration is constructed.

[0132] In this embodiment, as an optional implementation, the constructed optimization objective function is as follows:

[0133]

[0134] S105, Based on the historical reservoir area information of the target reservoir, the two-dimensional phosphate transport model of the reservoir is trained. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir meets the preset conditions, the two-dimensional phosphate transport model is obtained.

[0135] In this embodiment, as an optional embodiment, the two-dimensional phosphate transport model of the target reservoir is trained based on the historical reservoir area information. When the optimization objective function of the two-dimensional phosphate transport model satisfies the preset conditions, the two-dimensional phosphate transport model is obtained, including:

[0136] B11, the reservoir two-dimensional phosphate transport model is calculated based on the historical reservoir area information of the previous historical moment to obtain the predicted diffusion coefficient and phosphorus content;

[0137] In this embodiment, historical reservoir information is sorted chronologically, and the reservoir two-dimensional phosphate transport model is trained using the reservoir information collected at each collection time as a unit.

[0138] In this embodiment, as an optional embodiment, the historical database information can also be preprocessed, including but not limited to: abnormal data detection, missing data completion, and abnormal data correction.

[0139] In this embodiment, the model parameters of the reservoir two-dimensional phosphate transport model are initialized. The historical reservoir area information of the previous moment is input into the initialized reservoir two-dimensional phosphate transport model. The reservoir two-dimensional phosphate transport model performs calculations according to a pre-set neural network algorithm and inputs the predicted diffusion coefficient and phosphorus content.

[0140] B12. Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0141] B13, based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the current historical moment, obtain the approximation error;

[0142] B14. Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0143] B15. If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the reservoir two-dimensional phosphate transport model is executed according to the historical reservoir area information of the previous historical moment.

[0144] In this embodiment, if the optimized value is greater than the minimum optimization threshold, it indicates that the training of the reservoir two-dimensional phosphate transport model is not complete. Based on the backpropagation algorithm, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted. Based on the adjusted parameters, the reservoir two-dimensional phosphate transport model continues to be trained according to the historical reservoir area information of the previous historical moment until the obtained optimized value is not greater than the minimum optimization threshold. The current training ends, and the historical reservoir area information of another historical moment is selected to continue training until the dataset used for training is completed or the accuracy of the trained reservoir two-dimensional phosphate transport model reaches the preset accuracy threshold.

[0145] In this embodiment, as another optional embodiment, the two-dimensional phosphate transport model of the target reservoir is trained based on the historical reservoir area information. When the optimization objective function of the two-dimensional phosphate transport model satisfies the preset conditions, the two-dimensional phosphate transport model is obtained, including:

[0146] C11: Filter out phosphorus content from historical reservoir information at the target historical moment to obtain the training data;

[0147] C12, the reservoir two-dimensional phosphate transport model performs calculations based on the input training data to obtain the predicted diffusion coefficient and phosphorus content;

[0148] C13. Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0149] C14. Based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the target historical moment, the approximation error is obtained.

[0150] C15, Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0151] C16. If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the step of filtering out phosphorus content is performed from the historical reservoir information at another historical moment.

[0152] In this embodiment, as another optional embodiment, the two-dimensional phosphate transport model of the reservoir is trained based on the historical reservoir area information of the target reservoir. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir satisfies the preset conditions, the two-dimensional phosphate transport model is obtained, including:

[0153] D11. The information from each historical reservoir area is sorted according to the order of collection time to obtain the sorted sequence.

[0154] D12, based on the pre-set number of sample datasets, extract historical database information from the sorting sequence at intervals of the number of datasets to obtain the number of sample datasets;

[0155] In this embodiment, multiple sample datasets are constructed for subsequent tiered training. As an optional embodiment, if the number of sample datasets is 3, the information of the 1st, 4th, ..., 3n-2nd historical reservoirs is extracted from the sorted sequence as the first sample dataset. Then, the information of the 2nd, 5th, ..., 3n-1st historical reservoirs is extracted as the second sample dataset. Finally, the information of the 3rd, 6th, ..., 3nth historical reservoirs is extracted as the third sample dataset. In this way, by extracting historical reservoir information at intervals, better discriminative power is achieved.

[0156] D13, from each sample dataset, filter out the phosphorus content to obtain the corresponding training dataset;

[0157] D14, sort the training datasets according to the collection time of the first data in each training dataset;

[0158] D15, select the first training dataset with the earliest collection time, and train the reservoir two-dimensional phosphate transport model based on the first training dataset and the first sample dataset corresponding to the first training dataset until the optimized value of the reservoir two-dimensional phosphate transport model is less than the preset first optimization threshold, and obtain the initial training transport model.

[0159] D16, select the second training dataset with the next earlier acquisition time, and train the initial training transport model based on the second training dataset and the second sample dataset corresponding to the second training dataset until the optimized value of the initial training transport model is less than the preset second optimization threshold, and the second optimization threshold is less than the first optimization threshold, until the training dataset with the last acquisition time is trained.

[0160] In this embodiment, as an optional implementation, for each monitoring data (historical reservoir information) of the target reservoir, a two-dimensional phosphate transport model of the reservoir is input. The two-dimensional phosphate transport model of the reservoir performs calculations based on the two-dimensional phosphorus convection-diffusion equation to obtain the predicted diffusion coefficient and phosphorus content corresponding to the next monitoring data. Based on the predicted diffusion coefficient and phosphorus content, the actual diffusion coefficient and phosphorus content contained in the next monitoring data, and the optimization objective function, the model parameters of the two-dimensional phosphate transport model of the reservoir are adjusted until the preset conditions are met.

[0161] In this embodiment, if the historical reservoir information consists of hydrological historical data at multiple preset depths within the reservoir area, then training is performed based on the hydrological historical data at each depth to obtain a two-dimensional phosphate transport sub-model for the reservoir corresponding to that depth. The two-dimensional phosphate transport sub-models of the reservoir together form the two-dimensional phosphate transport model of the reservoir.

[0162] In this embodiment, by setting up multiple training datasets, subsequent training datasets are trained on the model trained on the previous training datasets, which can effectively reduce the amount of computation required to train the model and improve the model training efficiency. At the same time, the training datasets used for training have similar characteristics but also have a certain degree of differentiation from each other, which can effectively reduce the influence of neighboring interference factors.

[0163] S106, Collect the current information of the target reservoir area, input the two-dimensional phosphate transport model, obtain the diffusion coefficient of phosphorus, and calibrate the diffusion coefficient of the phosphate transport process in the target reservoir based on the phosphate concentration, the diffusion coefficient of phosphorus and the two-dimensional phosphorus convection-diffusion equation contained in the current information of the reservoir area.

[0164] In this embodiment, the diffusion coefficient of the phosphate transport process in the calibrated target reservoir is used to characterize the real-time dynamic change process of phosphate content in the reservoir.

[0165] In this embodiment, historical phosphate content flow data is collected, and a classic gradient descent method is used for training until the optimal neural network model parameters are found. This ensures that the output of the neural network model satisfies the control equations as closely as possible and approximates the observed data. After optimization, the current monitoring data is input into the reservoir's two-dimensional phosphate transport model to obtain the predicted diffusion coefficient. Then, the real-time phosphate content data observed at the monitoring stations and the calibrated diffusion coefficient function are input into the two-dimensional phosphorus convection-diffusion equation, and the finite difference method is used to solve it, allowing for real-time calculation of the reservoir's phosphate content changes.

[0166] In this embodiment, as an optional embodiment, the method further includes:

[0167] The diffusion coefficient of the phosphate transport process in the target reservoir, which has been calibrated, is sent to a pre-set terminal device.

[0168] In this embodiment, as an optional implementation, the terminal device is the terminal device of relevant personnel in the reservoir management department, such as a mobile phone, personal email, cloud server, etc. The calculation results are fed back to the reservoir management department to support its decision-making.

[0169] In this embodiment, as another optional embodiment, the method further includes:

[0170] At each time point and at the corresponding location of the phosphate transport process in the calibrated target reservoir, the measured information of the reservoir area at the corresponding location of the target reservoir at that time point was collected.

[0171] Based on the diffusion coefficient of the target reservoir at that time and the phosphorus concentration information contained in the measured information of the reservoir area, the two-dimensional phosphate transport model is retrained.

[0172] In this embodiment, the model can be retrained based on the feedback until a result that matches the actual situation is obtained.

[0173] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily required by this application.

[0174] Reference Figure 3 The diagram shows a structural block diagram of an apparatus for calibrating the diffusion coefficient of a phosphate transport process according to this application. The apparatus includes:

[0175] Data collection module 301 is used to collect historical reservoir area information of the target reservoir;

[0176] In this embodiment, as an optional embodiment, historical reservoir information includes, but is not limited to: flow rate, water temperature, pH value, salinity, hydrodynamic conditions, phosphorus content and form.

[0177] In this embodiment, as an optional embodiment, the historical reservoir information also includes: water adsorption and desorption rates.

[0178] In this embodiment, as an optional embodiment, if the water depth of the target reservoir exceeds a preset water depth threshold, the historical reservoir information includes: hydrological historical data of multiple preset depths within the reservoir.

[0179] The model building module 302 is used to build a two-dimensional phosphate transport model of the target reservoir based on the topographic features of the reservoir, and to build a two-dimensional phosphorus convection and diffusion equation for the two-dimensional phosphate transport model of the reservoir based on the parameters contained in the historical reservoir information.

[0180] In this embodiment, as an optional implementation, the two-dimensional phosphorus convection-diffusion equation is as follows:

[0181]

[0182] in:

[0183] x, y, and t represent the spatial location of phosphorus diffusion and the current time, respectively;

[0184] U represents the concentration of phosphate in the reservoir;

[0185] R represents the adsorption and desorption rates of water.

[0186] v x v y These are the water flow direction parameters and vertical flow parameters, respectively;

[0187] D x D y These are the water flow diffusion parameters and vertical diffusion parameters for phosphorus, respectively.

[0188] Boundary setting module 303 is used to set boundary conditions for the two-dimensional phosphorus convection-diffusion equation based on the parameters contained in the historical reservoir information and the topographic features of the target reservoir.

[0189] The optimization module 304 is used to construct an optimization objective function based on the two-dimensional phosphorus convection-diffusion equation and the reservoir two-dimensional phosphate transport model.

[0190] The model training module 305 is used to train the two-dimensional phosphate transport model of the target reservoir based on the historical reservoir area information. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir meets the preset conditions, the two-dimensional phosphate transport model is obtained.

[0191] The diffusion coefficient acquisition module 306 is used to collect the current information of the target reservoir area, input the two-dimensional phosphate transport model, obtain the diffusion coefficient of phosphorus, and calibrate the diffusion coefficient of the phosphate transport process in the target reservoir based on the phosphate concentration, the diffusion coefficient of phosphorus and the two-dimensional phosphorus convection-diffusion equation contained in the current information of the reservoir area.

[0192] The optimized construction module 304 is specifically used for:

[0193] Based on the parameters in the two-dimensional phosphorus convection-diffusion equation, a neural network equation for the residual of the diffusion coefficient is established.

[0194] Based on the output of the neural network equation and the phosphate concentration parameters in the historical reservoir information, an approximation error equation for phosphate concentration is constructed.

[0195] Based on the neural network equation and the approximation error equation, an optimization objective function is constructed based on the two-dimensional phosphate transport model of the reservoir.

[0196] In this embodiment, as an optional embodiment, the model training module 305 is specifically used for:

[0197] The reservoir two-dimensional phosphate transport model is calculated based on the historical reservoir area information from the previous historical moment to obtain the predicted diffusion coefficient and phosphorus content.

[0198] Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0199] The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the current historical moment.

[0200] Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0201] If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the reservoir two-dimensional phosphate transport model is executed according to the historical reservoir area information of the previous historical moment.

[0202] In this embodiment, as another optional embodiment, the model training module 305 is specifically used for:

[0203] Phosphorus content is filtered out from historical reservoir information at the target historical moment to obtain training data;

[0204] The reservoir two-dimensional phosphate transport model performs calculations based on the input training data to obtain the predicted diffusion coefficient and phosphorus content;

[0205] Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained.

[0206] The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the target historical moment.

[0207] Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function;

[0208] If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the step of filtering out phosphorus content is performed from the historical reservoir information at another historical moment.

[0209] In this embodiment, as an optional embodiment, the device further includes:

[0210] The model retraining module (not shown in the figure) is used to collect measured information of the reservoir area at the corresponding position of the target reservoir at each time corresponding to the diffusion coefficient of the phosphate transport process in the calibrated target reservoir.

[0211] Based on the diffusion coefficient of the target reservoir at that time and the phosphorus concentration information contained in the measured information of the reservoir area, the two-dimensional phosphate transport model is retrained.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] Figure 4 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.

[0216] Reference Figure 4 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.

[0217] 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.

[0218] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of such 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] Figure 5 This is a block diagram of an electronic device 1900 shown in this application. For example, the electronic device 1900 can be provided as a server.

[0228] Reference Figure 5 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] Those skilled in the art will 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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 for calibrating the diffusion coefficient of phosphate transport processes, characterized in that, The method includes: Collect historical reservoir area information for the target reservoir; Based on the topographic features of the target reservoir, a two-dimensional phosphate transport model of the reservoir is constructed. Based on the parameters contained in the historical reservoir information, a two-dimensional phosphorus convection-diffusion equation for the two-dimensional phosphate transport model of the reservoir is constructed. Based on the parameters contained in the historical reservoir information and the topographic features of the target reservoir, boundary conditions are set for the two-dimensional phosphorus convection-diffusion equation. Based on the two-dimensional phosphorus convection-diffusion equation, an optimization objective function based on the two-dimensional phosphate transport model of the reservoir is constructed. Based on the historical reservoir area information of the target reservoir, the two-dimensional phosphate transport model of the reservoir is trained. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir meets the preset conditions, the two-dimensional phosphate transport model is obtained. The current information of the target reservoir area is collected and input into the two-dimensional phosphate transport model to obtain the diffusion coefficient of phosphorus. Based on the phosphate concentration, phosphorus diffusion coefficient and the two-dimensional phosphorus convection-diffusion equation contained in the current information of the reservoir area, the diffusion coefficient of the phosphate transport process in the target reservoir is calibrated. The optimization objective function constructed based on the two-dimensional phosphorus convection-diffusion equation and the two-dimensional phosphate transport model of the reservoir includes: Based on the parameters in the two-dimensional phosphorus convection-diffusion equation, a neural network equation for the residual of the diffusion coefficient is established. Based on the output of the neural network equation and the phosphate concentration parameters in the historical reservoir information, an approximation error equation for phosphate concentration is constructed. Based on the neural network equation and the approximation error equation, an optimization objective function is constructed based on the two-dimensional phosphate transport model of the reservoir.

2. The method according to claim 1, characterized in that, The process involves training a two-dimensional phosphate transport model of the target reservoir based on historical reservoir area information. When the objective function of the two-dimensional phosphate transport model satisfies pre-set conditions, a two-dimensional phosphate transport model is obtained, including: The reservoir two-dimensional phosphate transport model is calculated based on the historical reservoir area information from the previous historical moment to obtain the predicted diffusion coefficient and phosphorus content. Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained. The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the current historical moment. Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function; If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the reservoir two-dimensional phosphate transport model is executed according to the historical reservoir area information of the previous historical moment.

3. The method according to claim 1, characterized in that, The process involves training a two-dimensional phosphate transport model of the target reservoir based on historical reservoir area information. When the objective function of the two-dimensional phosphate transport model satisfies pre-set conditions, a two-dimensional phosphate transport model is obtained, including: Phosphorus content is filtered out from historical reservoir information at the target historical moment to obtain training data; The reservoir two-dimensional phosphate transport model performs calculations based on the input training data to obtain the predicted diffusion coefficient and phosphorus content; Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained. The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the target historical moment. Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function; If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the step of filtering out phosphorus content is performed from the historical reservoir information at another historical moment.

4. The method according to claim 1, characterized in that, The process involves training a two-dimensional phosphate transport model of the target reservoir based on historical reservoir area information. When the objective function of the two-dimensional phosphate transport model satisfies pre-set conditions, a two-dimensional phosphate transport model is obtained, including: The information from each historical reservoir area was sorted according to the chronological order of collection to obtain a sorted sequence. Based on the pre-set number of sample datasets, historical database information is extracted from the sorting sequence at intervals of the number of datasets to obtain the number of sample datasets. The phosphorus content was filtered out from each sample dataset to obtain the corresponding training dataset; The training datasets are sorted according to the collection time of the first data point in each dataset; The first training dataset with the earliest collection time is selected. Based on the first training dataset and the first sample dataset corresponding to the first training dataset, the reservoir two-dimensional phosphate transport model is trained until the optimized value of the reservoir two-dimensional phosphate transport model is less than the preset first optimization threshold, and the initial training transport model is obtained. The second training dataset, which is collected at the second earliest time, is selected. Based on the second training dataset and the second sample dataset corresponding to the second training dataset, the initial training transport model is trained until the optimized value of the initial training transport model is less than a preset second optimization threshold, and the second optimization threshold is less than the first optimization threshold, until the training dataset collected at the latest time is trained.

5. The method according to claim 1, characterized in that, The two-dimensional phosphorus convection-diffusion equation is as follows: in: x, y, and t represent the spatial location of phosphorus diffusion and the current time, respectively; U represents the concentration of phosphate in the reservoir; R represents the adsorption and desorption rates of water. v x v y These are the water flow direction parameters and vertical flow parameters, respectively; D x D y These are the water flow diffusion parameters and vertical diffusion parameters for phosphorus, respectively.

6. The method according to claim 5, characterized in that, The neural network equation for calibrating the diffusion coefficient is as follows: In the formula, e1 represents the residual of the two-dimensional phosphate transport model of the reservoir; U s The calculated phosphate concentration output by the two-dimensional phosphate transport model of the reservoir; D xs D ys These are the calculation parameters for the flow-direction diffusion and vertical diffusion of phosphorus, respectively.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The diffusion coefficient of the phosphate transport process in the target reservoir, which has been calibrated, is sent to a pre-set terminal device.

8. The method according to any one of claims 1 to 6, characterized in that, The historical reservoir information includes: flow rate, water temperature, pH value, salinity, hydrodynamic conditions, phosphorus content and form.

9. The method according to claim 8, characterized in that, The historical reservoir information also includes: water adsorption and desorption rates.

10. The method according to any one of claims 1 to 6, characterized in that, If the water depth of the target reservoir exceeds a preset water depth threshold, the historical reservoir information includes: historical hydrological data at multiple preset depths within the reservoir.

11. The method according to any one of claims 1 to 6, characterized in that, The method further includes: At each time point and at the corresponding location of the phosphate transport process in the calibrated target reservoir, the measured information of the reservoir area at the corresponding location of the target reservoir at that time point was collected. Based on the diffusion coefficient of the target reservoir at that time and the phosphorus concentration information contained in the measured information of the reservoir area, the two-dimensional phosphate transport model is retrained.

12. An apparatus for calibrating the diffusion coefficient of phosphate transport processes, characterized in that, The device includes: The data collection module is used to collect historical reservoir area information for the target reservoir; The model building module is used to construct a two-dimensional phosphate transport model of the target reservoir based on the topographic features of the reservoir, and to construct a two-dimensional phosphorus convection-diffusion equation for the two-dimensional phosphate transport model of the reservoir based on the parameters contained in the historical reservoir information. The boundary setting module is used to set boundary conditions for the two-dimensional phosphorus convection-diffusion equation based on the parameters contained in the historical reservoir information and the topographic features of the target reservoir. An optimization module is used to construct an optimization objective function based on the two-dimensional phosphorus convection-diffusion equation and the reservoir two-dimensional phosphate transport model. The model training module is used to train the two-dimensional phosphate transport model of the target reservoir based on the historical reservoir area information. When the optimization objective function of the two-dimensional phosphate transport model of the reservoir meets the preset conditions, the two-dimensional phosphate transport model is obtained. The diffusion coefficient acquisition module is used to collect the current information of the target reservoir area, input the two-dimensional phosphate transport model, obtain the diffusion coefficient of phosphorus, and calibrate the diffusion coefficient of the phosphate transport process in the target reservoir based on the phosphate concentration, the diffusion coefficient of phosphorus and the two-dimensional phosphorus convection-diffusion equation contained in the current information of the reservoir area. The optimized construction module is specifically used for: Based on the parameters in the two-dimensional phosphorus convection-diffusion equation, a neural network equation for the residual of the diffusion coefficient is established. Based on the output of the neural network equation and the phosphate concentration parameters in the historical reservoir information, an approximation error equation for phosphate concentration is constructed. Based on the neural network equation and the approximation error equation, an optimization objective function is constructed based on the two-dimensional phosphate transport model of the reservoir.

13. The apparatus according to claim 12, characterized in that, The model training module is specifically used for: The reservoir two-dimensional phosphate transport model is calculated based on the historical reservoir area information from the previous historical moment to obtain the predicted diffusion coefficient and phosphorus content. Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained. The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the current historical moment. Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function; If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the reservoir two-dimensional phosphate transport model is executed according to the historical reservoir area information of the previous historical moment.

14. The apparatus according to claim 12, characterized in that, The model training module is specifically used for: Phosphorus content is filtered out from historical reservoir information at the target historical moment to obtain training data; The reservoir two-dimensional phosphate transport model performs calculations based on the input training data to obtain the predicted diffusion coefficient and phosphorus content; Based on the predicted diffusion coefficient and phosphorus content, the residual of the two-dimensional phosphate transport model of the reservoir is obtained. The approximation error is obtained based on the predicted phosphorus content and the phosphorus content contained in the historical reservoir information at the target historical moment. Based on the residual and the approximation error, the optimized value is obtained using the optimization objective function; If the optimized value is greater than the preset minimum optimization threshold, the model parameters of the reservoir two-dimensional phosphate transport model are adjusted using the preset backpropagation algorithm, and the step of filtering out phosphorus content is performed from the historical reservoir information at another historical moment.

15. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1 to 11.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 11.

Images