Remote sensing inversion and hydrodynamic model fused water quality prediction method, device and equipment

Abstract

The invention provides a remote sensing inversion and hydrodynamic model fused water quality prediction method, device and equipment, and relates to the technical field of water quality prediction.The method comprises the steps that inversion is conducted on the basis of satellite remote sensing data at the initial moment, and pollutant concentration and water body depth inversion values are obtained and used for setting initial operation conditions of a hydrodynamic model; operating the hydrodynamic model at the current moment for water quality simulation to obtain predicted values of time sequence pollutant concentration and water body depth; performing inversion based on the satellite remote sensing data at the kth moment to obtain new pollutant concentration and water body depth inversion values; carrying out assimilation treatment to obtain pollutant concentration and water body depth assimilation values; if it is determined that hydrodynamic model optimization continues to be carried out, the assimilation value is used for updating the initial operation condition of the hydrodynamic model, the hydrodynamic model is operated again to carry out water quality simulation until it is determined that model optimization and water quality simulation are stopped, and a time sequence water quality prediction result is obtained. According to the method, the pollutant simulation precision of the hydrodynamic model can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality prediction, and particularly to a water quality prediction method, device and equipment that integrate remote sensing inversion and hydrodynamic model. Background Art

[0002] Hydrodynamic models have important applications in water quality pollution simulation. By simulating the processes of water body flow and pollutant transport, diffusion and transformation, they provide a scientific basis for water quality management and pollution control. The main applications include pollution diffusion and migration in river, lake, coastal and marine environments, urban water body pollution simulation, assessment of the impacts of agricultural and industrial pollution emissions, and water quality management of reservoirs and drinking water sources. Hydrodynamic models can predict changes in pollutant concentrations, evaluate the effectiveness of pollution control measures, support responses to sudden pollution incidents and predict long-term water quality changes.

[0003] However, water quality simulation requires high-resolution data such as flow rate, flow velocity, water depth and pollutant concentration. However, in practical applications, it is difficult to obtain data, and the spatial resolution of observed data is often insufficient, resulting in inaccurate initial conditions and boundary conditions of the hydrodynamic model and affecting the reliability of simulation results. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a water quality prediction method, device and equipment that integrate remote sensing inversion and hydrodynamic model, which can effectively improve the pollutant simulation accuracy of the hydrodynamic model.

[0005] In a first aspect, an embodiment of the present invention provides a water quality prediction method that integrates remote sensing inversion and hydrodynamic model, including:

[0006] Obtain satellite remote sensing data corresponding to the study area;

[0007] Based on the satellite remote sensing data at the initial moment, perform inversion to obtain the inversion value of pollutant concentration and the inversion value of water depth, so as to set the initial operating conditions of the hydrodynamic model by using the inversion value of pollutant concentration and the inversion value of water depth;

[0008] At the current moment, run the hydrodynamic model to perform water quality simulation to obtain the predicted value of time-series pollutant concentration and the predicted value of water depth, including the predicted value of pollutant concentration and the predicted value of water depth at the k-th moment; and, based on the satellite remote sensing data at the k-th moment corresponding to the current moment, perform inversion to obtain a new inversion value of pollutant concentration and a new inversion value of water depth;

[0009] Perform data assimilation processing on the predicted value of pollutant concentration at the k-th moment and the new inversion value of pollutant concentration, and the predicted value of water depth at the k-th moment and the new inversion value of water depth, respectively, to obtain the assimilation value of pollutant concentration and the assimilation value of water depth;

[0010] If it is determined to continue with the hydrodynamic model optimization, then the k-th moment is taken as the new current moment, and the initial operating conditions of the hydrodynamic model are updated using the assimilated pollutant concentration value and the assimilated water depth value, and the hydrodynamic model is continued to run at the new current moment for water quality simulation until it is determined to stop the model optimization and water quality simulation.

[0011] In one implementation, data assimilation processing is respectively performed on the predicted pollutant concentration value and the new inversed pollutant concentration value at the k-th moment, and the predicted water depth value and the new inversed water depth value at the k-th moment, to obtain the assimilated pollutant concentration value and the assimilated water depth value, including:

[0012] The new inversed pollutant concentration value is corrected using the measured pollutant concentration data corresponding to the study area, and data assimilation processing is performed on the corrected inversed pollutant concentration value and the predicted pollutant concentration value at the k-th moment to obtain the assimilated pollutant concentration value;

[0013] And, the new inversed water depth value is corrected using the measured water depth data corresponding to the study area, and data assimilation processing is performed on the corrected inversed water depth value and the predicted water depth value at the k-th moment to obtain the assimilated water depth value.

[0014] In one implementation, correcting the new inversed pollutant concentration value using the measured pollutant concentration data corresponding to the study area includes:

[0015] The support vector machine model is trained using the measured pollutant concentration data corresponding to the study area to obtain a pollutant concentration correction model;

[0016] The new inversed pollutant concentration value is input into the pollutant concentration correction model to correct the new inversed pollutant concentration value through the pollutant concentration correction model to obtain the corrected inversed pollutant concentration value.

[0017] In one implementation, data assimilation processing is performed on the corrected inversed pollutant concentration value and the predicted pollutant concentration value at the k-th moment to obtain the assimilated pollutant concentration value, including:

[0018] Determine the fusion weight based on the corrected inversed pollutant concentration value and the predicted pollutant concentration value at the k-th moment;

[0019] Using the fusion weight, perform weighted summation on the corrected inversed pollutant concentration value and the predicted pollutant concentration value at the k-th moment to achieve data assimilation processing and obtain the assimilated pollutant concentration value.

[0020] In one implementation, determining the fusion weight based on the corrected inversed pollutant concentration value and the predicted pollutant concentration value at the k-th moment includes:

[0021] Determine a first error value between the corrected retrieved pollutant concentration value and the measured pollutant concentration data, and determine a second error value between the predicted pollutant concentration value at the k-th moment and the measured pollutant concentration data;

[0022] Determine the fusion weight based on the comparison result between the first error value and the second error value.

[0023] In one implementation, use the retrieved pollutant concentration value and the retrieved water depth value to set the initial operating conditions of the hydrodynamic model, including:

[0024] Set the water level parameter and the flow velocity parameter of the hydrodynamic model at the initial moment, and use the retrieved pollutant concentration value as the water quality parameter of the hydrodynamic model at the initial moment to obtain the initial conditions;

[0025] And, determine the water body range at the initial moment based on the retrieved water depth value, so as to set the boundary conditions of the hydrodynamic model at the initial moment based on the water body range;

[0026] Wherein, the initial operating conditions include the initial conditions and the boundary conditions.

[0027] In a second aspect, an embodiment of the present invention further provides a water quality prediction device for the integration of remote sensing inversion and a hydrodynamic model, including:

[0028] A data acquisition module, configured to acquire satellite remote sensing data corresponding to the study area;

[0029] A model configuration module, configured to perform inversion based on the satellite remote sensing data at the initial moment to obtain the retrieved pollutant concentration value and the retrieved water depth value, so as to use the retrieved pollutant concentration value and the retrieved water depth value to set the initial operating conditions of the hydrodynamic model;

[0030] A prediction and inversion module, configured to run the hydrodynamic model at the current moment to perform water quality simulation to obtain the predicted time-series pollutant concentration value and the predicted water depth value, including the predicted pollutant concentration value and the predicted water depth value at the k-th moment; and, perform inversion based on the satellite remote sensing data at the k-th moment corresponding to the current moment to obtain a new retrieved pollutant concentration value and a new retrieved water depth value;

[0031] An assimilation module, configured to perform data assimilation processing on the predicted pollutant concentration value at the k-th moment and the new retrieved pollutant concentration value, and the predicted water depth value at the k-th moment and the new retrieved water depth value, respectively, to obtain the assimilated pollutant concentration value and the assimilated water depth value;

[0032] A water quality prediction module, which is used to, if it is determined to continue optimizing the hydrodynamic model, take the k-th moment as the new current moment, update the initial operating conditions of the hydrodynamic model by using the assimilated pollutant concentration value and the assimilated water depth value, and continue to run the hydrodynamic model at the new current moment for water quality simulation until it is determined to stop model optimization and water quality simulation.

[0033] In one implementation, the assimilation module is specifically used for:

[0034] Calibrating the new pollutant concentration inversion value by using the measured pollutant concentration data corresponding to the study area, and performing data assimilation processing on the calibrated pollutant concentration inversion value and the pollutant concentration prediction value at the k-th moment to obtain the assimilated pollutant concentration value;

[0035] And, calibrating the new water depth inversion value by using the measured water depth data corresponding to the study area, and performing data assimilation processing on the calibrated water depth inversion value and the water depth prediction value at the k-th moment to obtain the assimilated water depth value.

[0036] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of the first aspect.

[0037] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions cause the processor to implement the method according to any one of the first aspect.

[0038] The water quality prediction method, device and equipment integrating remote sensing inversion and hydrodynamic model provided by the embodiments of the present invention, after obtaining the satellite remote sensing data corresponding to the research area, first perform inversion based on the satellite remote sensing data at the initial moment to obtain the pollutant concentration inversion value and the water depth inversion value, so as to set the initial operating conditions of the hydrodynamic model by using the pollutant concentration inversion value and the water depth inversion value; then run the hydrodynamic model at the current moment for water quality simulation to obtain the pollutant concentration prediction value and the water depth prediction value, including the pollutant concentration prediction value and the water depth prediction value at the k-th moment; and, perform inversion based on the satellite remote sensing data at the k-th moment corresponding to the current moment to obtain a new pollutant concentration inversion value and a new water depth inversion value; then perform assimilation processing on the pollutant concentration prediction value at the k-th moment and the new pollutant concentration inversion value, and the water depth prediction value at the k-th moment and the new water depth inversion value respectively to obtain the pollutant concentration assimilation value and the water depth assimilation value; if it is determined to continue model optimization, then take the k-th moment as the new current moment, update the initial operating conditions of the hydrodynamic model by using the pollutant concentration assimilation value and the water depth assimilation value, and continue to run the hydrodynamic model at the new current moment for water quality simulation until it is determined to stop water quality prediction, and finally take the pollutant concentration assimilation value at the moment when water quality prediction stops as the water quality prediction result. The above method obtains data such as pollutant concentration inversion values and water depth inversion values through satellite remote sensing data to set the initial operating conditions of the hydrodynamic model, making up for the deficiencies and uneven distribution of ground observation points; at the same time, satellite remote sensing data can comprehensively reflect the situation of large-scale water bodies and basins, and cover a wide area on the same time scale, thus ensuring data consistency; in addition, by dynamically updating the initial operating conditions of the hydrodynamic model, the initial operating conditions gradually approach the real physical conditions, so that the simulation accuracy of the pollutant concentration of the hydrodynamic model is gradually improved.

[0039] Other features and advantages of the present invention will be described in the following specification, and in part will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0040] To make the above objectives, features and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and detailed descriptions are made in conjunction with the accompanying drawings as follows. Brief Description of the Drawings

[0041] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 Schematic flow chart of a water quality prediction method integrating remote sensing inversion and hydrodynamic model provided by an embodiment of the present invention;

[0043] Figure 2 Overall flow chart of a water quality prediction method integrating remote sensing inversion and hydrodynamic model provided by an embodiment of the present invention;

[0044] Figure 3 Schematic structural diagram of a water quality prediction device integrating remote sensing inversion and hydrodynamic model provided by an embodiment of the present invention;

[0045] Figure 4 Schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0047] Currently, the method of using a hydrodynamic model for water quality prediction is affected by difficulties in data acquisition and insufficient spatial resolution of observational data, etc., and there are problems with low reliability of simulation results. Moreover, the calibration and verification of the hydrodynamic model require a large amount of observational data. However, in many regions, observational data is scarce or incomplete, which limits the application and accuracy of the hydrodynamic model. Remote sensing data has many unique characteristics, making it have important advantages in making up for the data deficiencies of the hydrodynamic model. With its advantages of large-scale coverage, high-altitude resolution, multi-spectral observation, long time series, etc., remote sensing data effectively makes up for the deficiencies of the hydrodynamic model in monitoring data acquisition and data accuracy. Based on this, the embodiments of the present invention provide a water quality prediction method, device, and equipment integrating remote sensing inversion and hydrodynamic model, which can effectively improve the simulation accuracy of pollutants in the hydrodynamic model.

[0048] To facilitate the understanding of this embodiment, first, a detailed introduction will be given to a water quality prediction method integrating remote sensing inversion and hydrodynamic model disclosed in the embodiments of the present invention. SeeFigure 1 Schematic flow chart of a water quality prediction method integrating remote sensing inversion and hydrodynamic model. The method mainly includes the following steps S102 to S110:

[0049] Step S102: Obtain satellite remote sensing data corresponding to the study area.

[0050] Step S104: Based on the satellite remote sensing data at the initial moment, perform inversion to obtain the inversion values of pollutant concentration and water depth, so as to set the initial operating conditions of the hydrodynamic model by using the inversion values of pollutant concentration and water depth.

[0051] Among them, the current moment or a neighboring moment of the current moment can be used as the initial moment. The initial operating conditions include initial conditions and boundary conditions. The initial conditions are used to set parameters such as water level, flow velocity, and water quality of the hydrodynamic model at the initial moment, and the boundary conditions are used to define the boundaries of the hydrodynamic model area, including inflow boundaries, outflow boundaries, water level boundaries, etc.

[0052] In one example, by performing pollutant concentration inversion based on the satellite remote sensing data at the initial moment, the inversion value of pollutant concentration can be obtained; by performing water body range inversion based on the satellite remote sensing data at the initial moment, the inversion value of water body range can be obtained, and by superimposing the inversion value of water body range with the high-precision DEM (Digital Elevation Model) data corresponding to the study area, the inversion value of water depth (i.e., the inversion value of water depth or water level) can be obtained.

[0053] In one example, by using the inversion value of pollutant concentration to configure the water quality parameters in the initial conditions, and setting the water level, flow velocity, etc. of the hydrodynamic model at the initial moment; and by using the inversion value of water depth to set the boundary conditions, the initial operating conditions required for running the hydrodynamic model can be obtained.

[0054] Step S106: Run the hydrodynamic model at the current moment for water quality simulation to obtain the predicted values of time-series pollutant concentration and water depth, including the predicted values of pollutant concentration and water depth at the k-th moment; and, based on the satellite remote sensing data at the k-th moment corresponding to the current moment, perform inversion to obtain the new inversion values of pollutant concentration and water depth.

[0055] Among them, the current moment can be denoted as t 0 moment. In one example, according to business requirements and computing power conditions, set the time step δt, set the running period of the hydrodynamic model, and start running the hydrodynamic model from t 0 moment to obtain the predicted values of time-series river channel pollutant concentration, water body range, and water depth with a time resolution of δt.

[0056] Among them, the k-th moment can be denoted as t k moment. In one example, based on the satellite remote sensing data at time t k , the inversion of the pollutant concentration can be carried out to obtain a new inversion value of the pollutant concentration; based on the satellite remote sensing data at time t k , the inversion of the water body range can be carried out to obtain a new inversion value of the water body range. By superimposing the new inversion value of the water body range with the high-precision DEM data corresponding to the study area, a new inversion value of the water body depth can be obtained.

[0057] Step S108: Perform data assimilation processing on the predicted value of the pollutant concentration and the new inversion value of the pollutant concentration at the k-th moment, and the predicted value of the water body depth and the new inversion value of the water body depth at the k-th moment, respectively, to obtain the assimilated value of the pollutant concentration and the assimilated value of the water body depth.

[0058] In one example, for the pollutant concentration, the fusion method of the predicted value of the pollutant concentration output by the hydrodynamic model, the inversion value of the pollutant concentration obtained by remote sensing inversion, and the ground water quality detection result (i.e., the measured data of the pollutant concentration) can be realized by data assimilation technology to obtain the assimilated value of the pollutant concentration; similarly, the assimilated value of the water body range and the assimilated value of the water body depth can be obtained. In the embodiment of the present invention, the ground water quality monitoring result is combined with the predicted value of the pollutant concentration output by the hydrodynamic model by using the assimilation technology to optimize the state of the hydrodynamic model and improve the accuracy of the hydrodynamic model. The data assimilation content mainly includes pollutant concentration, water body range and water body depth.

[0059] Step S110: If it is determined to continue optimizing the hydrodynamic model, then take the k-th moment as the new current moment t 0 , update the initial operating conditions of the hydrodynamic model by using the assimilated value of the pollutant concentration and the assimilated value of the water body depth, and continue to run the hydrodynamic model at the new current moment for water quality simulation until it is determined to stop model optimization and water quality simulation.

[0060] In one example, it can be determined whether to continue data assimilation and water quality prediction according to the accuracy of the water quality prediction result of the hydrodynamic model. In the case of determining to continue model optimization, the initial operating conditions of the hydrodynamic model will be reset by using the assimilated value of the pollutant concentration and the assimilated value of the water body depth corresponding to the current moment, so that the initial operating conditions gradually approach the real physical conditions, and steps S106 to S108 are repeatedly executed until it is determined to stop model optimization and water quality simulation.

[0061] The water quality prediction method that integrates remote sensing inversion and hydrodynamic model provided by the embodiments of the present invention obtains data such as pollutant concentration inversion values and water depth inversion values through satellite remote sensing data, and uses them to set the initial operating conditions of the hydrodynamic model, making up for the deficiencies and uneven distribution of ground observation points; at the same time, satellite remote sensing data can comprehensively reflect the situation of large-scale water bodies and river basins, and cover a wide area on the same time scale, thus ensuring the consistency of data; in addition, by dynamically updating the initial operating conditions of the hydrodynamic model, the initial operating conditions gradually approach the real physical conditions, so that the simulation accuracy of pollutant concentration of the hydrodynamic model is gradually improved.

[0062] For the convenience of understanding, the embodiments of the present invention provide a specific implementation manner of a water quality prediction method that integrates remote sensing inversion and hydrodynamic model. It includes:

[0063] (1) Data preparation and processing: The initial conditions of the hydrodynamic model are the basis for the operation of the model, directly affecting the simulation accuracy and reliability. In the study area, remote sensing technology is used to provide various initial conditions for the hydrodynamic model. Especially in large-scale areas with scarce hydrological data, remote sensing technology can provide important data support. By integrating remote sensing data and ground observation data, the accuracy and reliability of the hydrodynamic model are improved.

[0064] It mainly includes three parts: remote sensing inversion of pollutant concentration, inversion of water body range and water depth, and collection of other data:

[0065] (1.1) Remote sensing inversion of pollutant concentration:

[0066] 1) Obtain high-resolution multispectral satellite remote sensing data and measured concentrations of water body pollutants, such as total suspended solids (TSS), chlorophyll-a (Chl-a), chemical oxygen demand (COD), etc.;

[0067] 2) Extract features related to pollutant concentration from satellite remote sensing data, including reflectance of each band, band combination, texture features, etc.;

[0068] 3) Select the feature variables extracted from satellite remote sensing data as model inputs, and select the measured concentrations of water body pollutants as target variables;

[0069] 4) Use the training set data to train the random forest model. The specific steps include:

[0070] a. Set the parameters of the random forest, including the number of trees (n_estimators), maximum depth (max_depth), minimum number of samples for splitting (min_samples_split), etc.;

[0071] b. Fit the model using the training data to generate multiple decision trees, and obtain the final prediction result through majority voting (average value in the case of regression problems);

[0072] 5) Use the trained random forest model to predict the pollutant concentration of the satellite remote sensing data at the initial moment, and generate the inversion value of the pollutant concentration in the study area.

[0073] (1.2) Inversion of water body range and water depth:

[0074] 1) Water body extraction based on threshold:

[0075] Identify water bodies based on the unsupervised classification K-means method. The main steps include: Feature selection: Select features for classification, such as reflectance of each band, water body index, etc.; Clustering: Apply the clustering algorithm to classify the image and cluster pixels into several classes; Post-processing: Manually or automatically identify the water body class in the clustering result to generate the final water body range extraction result.

[0076] 2) Water depth calculation:

[0077] Overlay the water body range extraction result with the high-precision DEM, and calculate the inversion value of the water depth at each point in the study area.

[0078] (1.3) Collection of other data:

[0079] 1) Hydrological and hydrodynamic parameters, including: Flow rate and velocity: The flow rate and velocity of rivers or water bodies.

[0080] 2) Meteorological parameters, including: Rainfall: Rainfall intensity and distribution, used as the input of water volume in the model; Evaporation: Surface evaporation rate, used to calculate the water balance; Wind speed and direction: Affect the water surface fluctuation and water body mixing.

[0081] 3) Topographic and geomorphic parameters, including: Digital elevation model (DEM): Topographic elevation data, defining the topographic morphology of the basin or water body; Channel morphology: Geometric parameters such as channel width, depth, slope, etc.

[0082] 4) Flow rate at the upstream and downstream cross-sections, pollutant concentration data at the upstream and downstream cross-sections.

[0083] (2) Two-dimensional hydrodynamic model modeling, including: Convert the collected and processed topographic data into a format compatible with the hydrodynamic model, correct the data, and interpolate the irregular data to generate regular grid data. Specifically:

[0084] (2.1) Import topographic data: Import high-precision digital elevation model (DEM) data.

[0085] (2.2) Generate triangular mesh: Use a mesh generation tool to create a triangular mesh suitable for model calculation.

[0086] (2.3) Set mesh parameters: Set the refinement degree of the mesh according to the research area and simulation accuracy requirements to obtain a triangular mesh file compatible with the hydrodynamic model.

[0087] (III) Hydrodynamic model parameter settings, including:

[0088] (3.1) Initial conditions and boundary conditions:

[0089] Initial conditions: Set parameters such as water level, flow velocity, and water quality at the initial moment of the model. In specific implementation, set the water level parameter and flow velocity parameter of the hydrodynamic model at the initial moment, and use the inversion value of the pollutant concentration as the water quality parameter of the hydrodynamic model at the initial moment to obtain the initial conditions.

[0090] Boundary conditions: Define the boundary conditions of the model area, including inflow boundary, outflow boundary, water level boundary, etc. In specific implementation, determine the water body range at the initial moment based on the inversion value of the water body depth, and set the boundary conditions of the hydrodynamic model at the initial moment based on the water body range.

[0091] (3.2) Model parameters:

[0092] Physical parameters: Set the channel friction coefficient (such as Manning roughness coefficient), turbulence parameters, diffusion coefficient, etc.

[0093] Water quality parameters: Set the biochemical reaction rate, sedimentation rate, resuspension rate, etc.

[0094] (IV) Run the hydrodynamic model: After creating the triangular mesh file and setting the model parameters, set the time step according to business requirements and computing power conditions. Set the running period of the model, usually determined according to research needs and data availability. Start running the hydrodynamic model from time t 0 to simulate the set of time series model states, where the set of model states includes predicted values of pollutant concentration predicted values of water body range and predicted values of water body depth where n is the total number of time moments.

[0095] (V) Analysis of simulation results and data fusion: Run the hydrodynamic model to output the water quality simulation results, that is, the aforementioned predicted values of pollutant concentration, predicted values of water body range, and predicted values of water body depth; obtain satellite remote sensing data of the research area, and obtain data on water body depth, flow velocity, and pollutant concentration through inversion; obtain high-time-resolution and high-precision ground monitoring data (including measured data of pollutant concentration and measured data of water body depth) through automatic hydrological stations and water quality stations.

[0096] The fusion method of the water quality simulation results of the hydrodynamic model, the retrieved pollutant concentration values from remote sensing inversion, and the ground monitoring data is achieved through data assimilation technology. Data assimilation technology combines the observed data with the model prediction results, optimizes the model state, and improves the simulation accuracy. The data assimilation content mainly includes water depth, water body extent, and pollutant concentration. It is mainly divided into the following two cases:

[0097] Case 1, for pollutant concentration: Use the measured pollutant concentration data corresponding to the study area to correct the new retrieved pollutant concentration values, and perform data assimilation on the corrected retrieved pollutant concentration values and the predicted pollutant concentration values to obtain the assimilated pollutant concentration values;

[0098] Case 2, for water depth, use the measured water depth data corresponding to the study area to correct the new retrieved water depth values, and perform data assimilation on the corrected retrieved water depth values and the predicted water depth values to obtain the assimilated water depth values.

[0099] Taking the pollutant concentration as an example, the embodiments of the present invention provide a specific step of assimilation:

[0100] (5.1) Use the measured pollutant concentration data corresponding to the study area to correct the new retrieved pollutant concentration values, including: training the support vector machine model with the measured pollutant concentration data corresponding to the study area to obtain a pollutant concentration correction model; inputting the new retrieved pollutant concentration values into the pollutant concentration correction model to correct the new retrieved pollutant concentration values through the pollutant concentration correction model to obtain the corrected retrieved pollutant concentration values.

[0101] In one example, at time t k (the k-th moment) the satellite remote sensing data, after being processed by algorithm (1), obtains the remote sensing inversion results, including the new retrieved pollutant concentration values the new retrieved water depth values Use the ground monitoring data to correct the remote sensing inversion results to obtain the corrected retrieved pollutant concentration value C' k and the corrected retrieved water depth value H' k , and the specific method is as follows:

[0102] a. Collect the measured pollutant data of the river section at time t k , perform data cleaning, process missing values and outliers, establish a data sample set, and divide the data set into a training set and a test set;

[0103] b. Use the training set data to train the SVM (Support Vector Machine) model. The goal of the SVM model is to find an optimal hyperplane to separate data points of different classes:

[0104] 1) Select the polynomial kernel function, or other kernel functions can also be selected;

[0105] 2) Initialize the SVM model using the selected kernel function and parameters;

[0106] 3) Use the training set data to train the SVM model. The SVM finds a separating surface that can maximize the distance from the support vectors to the hyperplane through an optimization algorithm.

[0107] 4) Use the test set to evaluate the model performance, calculate classification accuracy, F1-score, AUC-ROC and other metrics to evaluate the classification effect of the model.

[0108] 5) According to the evaluation results, further adjust the hyperparameters of the model (including the C value, kernel function type and parameters), and repeat the training and evaluation process until the model meets the requirements.

[0109] c. Use the trained SVM model to process the retrieved pollutant concentration values Obtain the corrected retrieved pollutant concentration value C k ′ ;

[0110] Similarly, train the water depth SVM model in a similar way and use the model to process the new retrieved water depth values Obtain the corrected retrieved water depth value H ′ k .

[0111] (5.2) Perform data assimilation on the corrected retrieved pollutant concentration values and the predicted pollutant concentration values at the k-th moment to obtain the assimilated pollutant concentration values, including:

[0112] a. Determine the fusion weights based on the corrected retrieved pollutant concentration values and the predicted pollutant concentration values. Specifically, determine the first error value between the corrected retrieved pollutant concentration value and the measured pollutant concentration data, and determine the second error value between the predicted pollutant concentration value at the k-th moment and the measured pollutant concentration data; determine the fusion weights based on the comparison result between the first error value and the second error value.

[0113] b. Use the fusion weights to perform weighted summation on the corrected retrieved pollutant concentration values and the predicted pollutant concentration values at the k-th moment to achieve assimilation processing and obtain the assimilated pollutant concentration values.

[0114] In practical applications, for the corrected retrieved pollutant concentration value C at time t k and the predicted pollutant concentration value output by the hydrodynamic model k ′ and Perform weighted summation to obtain the optimal estimated value at this moment, which is also the assimilated value of the pollutant concentration The formula for assimilating the pollutant concentration is as follows:

[0115]

[0116] Similarly, the assimilated value of the water depth can be obtained The formula for assimilating the water depth is as follows:

[0117]

[0118] Among them, α and β are weight coefficients, where 0 ≤ α ≤ 1 and 0 ≤ β ≤ 1. α and β are determined based on the error analysis of the remote sensing inversion correction value and the model prediction value. The one with a smaller error accounts for a larger proportion, and the values of α and β are adjusted accordingly.

[0119] Then, according to the assimilated value of the water depth Adjust the water body range to update the boundary conditions of the hydrodynamic model.

[0120] (6) Model state update: If continued water quality prediction is required, use the pollutant concentration distribution, water body range, and water depth obtained through data assimilation in (4) as the initial conditions to output the hydrodynamic model and restart the water quality simulation of the hydrodynamic model.

[0121] (7) Iterative operation: Repeat steps (4) to (6), repeat the prediction and update steps, and the initial conditions of the model gradually approach the real physical conditions, and the simulation accuracy of the pollutant concentration of the hydrodynamic model is gradually improved.

[0122] (8) Model verification and adjustment:

[0123] (8.1) Use actual observed data such as water level, flow velocity, flow rate, and pollutant concentration to verify the model output. By comparing the model output and the observed data, identify the accuracy and error distribution of the model. Use statistical methods such as mean square error and bias analysis methods to analyze the spatial and temporal distribution of the model error and determine which regions and time periods have poor model performance.

[0124] (8.2) Through parameter sensitivity analysis, determine the model parameters that have the greatest impact on the output results (such as Manning coefficient, roughness coefficient, boundary conditions, initial conditions, etc.). By changing the value of a certain parameter, observe its impact on the simulation results and evaluate its sensitivity.

[0125] (8.3) Parameter adjustment and optimization: Based on the error analysis and sensitivity analysis, prioritize adjusting the parameters that are the most sensitive to the simulation results and also contribute more to the error. Include model parameters such as roughness coefficient, boundary conditions, and initial conditions, and make the parameters reflect the real physical environment as much as possible.

[0126] (8.4) Model Structure Calibration:

[0127] Mesh Optimization: Optimize the spatial mesh of the model. By increasing the mesh resolution in areas with larger errors, the simulation accuracy can be improved. The higher the mesh resolution, the more accurately small-scale hydrodynamic characteristics can be simulated, but the computational cost will also increase.

[0128] Improvement of Water Body Boundary Conditions: Calibrate the boundary conditions and water body characteristics of the model by introducing more hydrodynamic boundary condition data or more accurate terrain data.

[0129] (8.5) Model Evaluation and Optimization Loop: Compare the results of the adjusted model with the previous simulation results to evaluate the improvement in accuracy. If the effect is not satisfactory, the parameters can be further adjusted. Through continuous adjustment and verification, an optimization loop is carried out until the model reaches the required accuracy level.

[0130] In summary, the embodiments of the present invention provide an overall flowchart of a water quality prediction method for the fusion of remote sensing inversion and hydrodynamic model as shown in Figure 2 which includes: obtaining satellite remote sensing data, water quality parameters, hydrographic and hydrodynamic parameters, meteorological parameters, terrain and geomorphic data; performing pollutant concentration inversion and water body range and water depth inversion based on satellite remote sensing data, and configuring hydrodynamic model parameters in combination with water quality parameters, hydrographic and hydrodynamic adoption numbers, and meteorological parameters; using terrain and geomorphic data to build a two-dimensional hydrodynamic model; after configuring the hydrodynamic model parameters and building the two-dimensional hydrodynamic model, running the hydrodynamic model to perform water quality simulation to obtain model simulation results (including predicted values of pollutant concentration and predicted values of water body depth); in addition, for the satellite remote sensing data at time t k obtaining water body spatial distribution data (i.e., new water body range inversion value), pollutant concentration spatial distribution data (i.e., new pollutant concentration inversion value), and water depth spatial distribution data (i.e., new water body depth inversion value) through the remote sensing inversion model, then correcting the water body data based on ground observation data, correcting the pollutant concentration water body data based on ground observation data, correcting the water depth data based on ground observation data, and performing data assimilation in combination with the aforementioned model simulation results to update the hydrodynamic model parameters; determining whether to continue data assimilation, when the determination result is yes, making t 0 = t k and re-obtaining the model simulation results, and when the determination result is no, model verification can be carried out.

[0131] Embodiments of the present invention make full use of the wide coverage of remote sensing data to construct a remote sensing inversion model. Data such as the water body range, water depth, and pollutant concentration in the study area are obtained through multi-spectral and hyper-spectral satellites and used as input data for the two-dimensional hydrodynamic model, making up for the deficiencies and uneven distribution of ground observation points. At the same time, remote sensing data can comprehensively reflect the situation of large-scale water bodies and river basins, and cover a wide area on the same time scale, ensuring data consistency. The water quality simulation results of the hydrodynamic model in this case, the pollutant concentrations retrieved by remote sensing, and the ground real-time observation data are used for data correction and data assimilation, and the hydrodynamic model is output as the initial condition, which can improve the accuracy of the model initial condition and further improve the pollutant simulation accuracy of the hydrodynamic model.

[0132] Based on the foregoing embodiments, embodiments of the present invention provide a water quality prediction device integrating remote sensing inversion and a hydrodynamic model. Refer to Figure 3 the structural schematic diagram of a water quality prediction device integrating remote sensing inversion and a hydrodynamic model as shown, and the device mainly includes the following parts:

[0133] A data acquisition module 302, configured to acquire satellite remote sensing data corresponding to the study area;

[0134] A model configuration module 304, configured to perform inversion based on the satellite remote sensing data at the initial moment to obtain the retrieved pollutant concentration value and the retrieved water depth value, so as to set the initial operating conditions of the hydrodynamic model by using the retrieved pollutant concentration value and the retrieved water depth value;

[0135] A prediction and inversion module 306, configured to run the hydrodynamic model at the current moment for water quality simulation to obtain the predicted time-series pollutant concentration value and the predicted water depth value, including the predicted pollutant concentration value and the predicted water depth value at the k-th moment; and, perform inversion based on the satellite remote sensing data at the k-th moment corresponding to the current moment to obtain a new retrieved pollutant concentration value and a new retrieved water depth value;

[0136] An assimilation module 308, configured to perform data assimilation processing on the predicted pollutant concentration value and the new retrieved pollutant concentration value at the k-th moment, and the predicted water depth value and the new retrieved water depth value at the k-th moment, respectively, to obtain the assimilated pollutant concentration value and the assimilated water depth value;

[0137] A water quality prediction module 310, configured to, if it is determined to continue optimizing the hydrodynamic model, use the k-th moment as the new current moment, update the initial operating conditions of the hydrodynamic model by using the assimilated pollutant concentration value and the assimilated water depth value, and continue to run the hydrodynamic model at the new current moment for water quality simulation until it is determined to stop optimizing the model and performing water quality simulation.

[0138] The water quality prediction device integrating remote sensing inversion and hydrodynamic model provided by the embodiment of the present invention obtains data such as the inversion value of pollutant concentration and the inversion value of water depth through satellite remote sensing data, and is used to set the initial operating conditions of the hydrodynamic model, making up for the deficiencies and uneven distribution of ground observation points; at the same time, satellite remote sensing data can comprehensively reflect the situation of large-scale water bodies and river basins, and cover a wide area on the same time scale, thus ensuring the consistency of data; in addition, by dynamically updating the initial operating conditions of the hydrodynamic model, the initial operating conditions gradually approach the real physical conditions, so that the simulation accuracy of pollutant concentration of the hydrodynamic model is gradually improved.

[0139] In one implementation, the water quality prediction module 310 is specifically configured to:

[0140] Use the measured pollutant concentration data corresponding to the study area to correct the new inversion value of pollutant concentration, and perform data assimilation processing on the corrected inversion value of pollutant concentration and the predicted value of pollutant concentration at the k-th moment to obtain the assimilated value of pollutant concentration;

[0141] And use the measured water depth data corresponding to the study area to correct the new inversion value of water depth, and perform data assimilation processing on the corrected inversion value of water depth and the predicted value of water depth at the k-th moment to obtain the assimilated value of water depth.

[0142] In one implementation, the water quality prediction module 310 is specifically configured to:

[0143] Use the measured pollutant concentration data corresponding to the study area to train the support vector machine model to obtain the pollutant concentration correction model;

[0144] Input the new inversion value of pollutant concentration into the pollutant concentration correction model to correct the new inversion value of pollutant concentration through the pollutant concentration correction model to obtain the corrected inversion value of pollutant concentration.

[0145] In one implementation, the water quality prediction module 310 is specifically configured to:

[0146] Determine the fusion weight based on the corrected inversion value of pollutant concentration and the predicted value of pollutant concentration;

[0147] Use the fusion weight to perform weighted summation on the corrected inversion value of pollutant concentration and the predicted value of pollutant concentration to achieve assimilation processing and obtain the assimilated value of pollutant concentration.

[0148] In one implementation, the water quality prediction module 310 is specifically configured to:

[0149] Determine a first error value between the calibrated pollutant concentration inversion value and the measured pollutant concentration data, and determine a second error value between the predicted pollutant concentration value and the measured pollutant concentration data;

[0150] Determine the fusion weight based on the comparison result between the first error value and the second error value.

[0151] In one implementation, the model configuration module 304 is specifically configured to:

[0152] Set the water level parameter and the flow velocity parameter of the hydrodynamic model at the initial moment, and use the pollutant concentration inversion value as the water quality parameter of the hydrodynamic model at the initial moment to obtain the initial conditions;

[0153] And, determine the water body range at the initial moment based on the water body depth inversion value, and set the boundary conditions of the hydrodynamic model at the initial moment based on the water body range;

[0154] Wherein, the initial operating conditions include the initial conditions and the boundary conditions.

[0155] The device provided by the embodiments of the present invention has the same implementation principle and the same technical effects as those of the foregoing method embodiments. For a brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding contents in the foregoing method embodiments.

[0156] The embodiments of the present invention provide an electronic device. Specifically, the electronic device includes a processor and a storage device; a computer program is stored on the storage device, and the computer program executes the method described in any one of the above embodiments when being run by the processor.

[0157] Figure 4 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device 100 includes: a processor 40, a memory 41, a bus 42, and a communication interface 43. The processor 40, the communication interface 43, and the memory 41 are connected through the bus 42; the processor 40 is configured to execute an executable module stored in the memory 41, such as a computer program.

[0158] Wherein, the memory 41 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 43 (which may be wired or wireless), a communication connection between the system network element and at least one other network element is realized, and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0159] The bus 42 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 4 only a bidirectional arrow is used in Figure 4 , but it does not mean that there is only one bus or one type of bus.

[0160] Among them, the memory 41 is used to store a program. After receiving an execution instruction, the processor 40 executes the program. The method executed by the device defined by the flow process disclosed in any embodiment of the foregoing embodiments of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0161] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 40 or by the instructions in the form of software. The above-mentioned processor 40 can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and combines its hardware to complete the steps of the above method.

[0162] The computer program product of the readable storage medium provided by the embodiments of the present invention includes a computer-readable storage medium storing program codes. The instructions included in the program codes can be used to execute the method described in the foregoing method embodiments. For the specific implementation, reference can be made to the foregoing method embodiments and will not be elaborated herein.

[0163] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0164] Finally, it should be noted that the above-mentioned embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A water quality prediction method integrating remote sensing inversion and hydrodynamic model, characterized in that: include: Obtain satellite remote sensing data corresponding to the study area; Inverting the satellite remote sensing data at the initial moment to obtain pollutant concentration inversion values ​​and water body depth inversion values, so as to set the initial operating conditions of the hydrodynamic model using the pollutant concentration inversion values ​​and the water body depth inversion values; Running the hydrodynamic model at the current moment to perform water quality simulation, obtaining a time series pollutant concentration prediction value and a water body depth prediction value, including a pollutant concentration prediction value and a water body depth prediction value at the kth moment; and performing inversion based on the satellite remote sensing data at the kth moment corresponding to the current moment, obtaining a new pollutant concentration inversion value and a new water body depth inversion value; Performing data assimilation processing on the predicted value of pollutant concentration at the kth moment and the new inverted value of the pollutant concentration, as well as the predicted value of water body depth at the kth moment and the new inverted value of water body depth, respectively, to obtain the assimilated value of pollutant concentration and the assimilated value of water body depth; If it is determined to continue the hydrodynamic model optimization, the kth moment is taken as the new current moment, the pollutant concentration assimilation value and the water body depth assimilation value are used to update the initial operating conditions of the hydrodynamic model, and the hydrodynamic model is continued to be run at the new current moment to perform water quality simulation until it is determined to stop the model optimization and water quality simulation.

2. The water quality prediction method of remote sensing inversion and hydrodynamic model fusion according to claim 1 is characterized in that: The predicted value of the pollutant concentration at the kth moment and the new inverted value of the pollutant concentration, as well as the predicted value of the water body depth at the kth moment and the new inverted value of the water body depth, are respectively subjected to data assimilation processing to obtain the assimilated value of the pollutant concentration and the assimilated value of the water body depth, including: Correcting the new pollutant concentration inversion value using the measured pollutant concentration data corresponding to the study area, performing data assimilation processing on the corrected pollutant concentration inversion value and the pollutant concentration prediction value at the kth moment to obtain a pollutant concentration assimilation value; Furthermore, the new water depth inversion value is corrected using the measured water depth data corresponding to the study area, and the corrected water depth inversion value and the water depth prediction value at the kth moment are subjected to data assimilation processing to obtain the water depth assimilation value.

3. The water quality prediction method of remote sensing inversion and hydrodynamic model fusion according to claim 2 is characterized in that: Correcting the new pollutant concentration inversion value using the measured pollutant concentration data corresponding to the study area includes: The support vector machine model is trained using the measured pollutant concentration data corresponding to the study area to obtain a pollutant concentration correction model; The new pollutant concentration inversion value is input into the pollutant concentration correction model so as to correct the new pollutant concentration inversion value through the pollutant concentration correction model to obtain the corrected pollutant concentration inversion value.

4. The water quality prediction method of remote sensing inversion and hydrodynamic model fusion according to claim 2 is characterized in that: The corrected pollutant concentration inversion value and the pollutant concentration prediction value at the kth moment are subjected to data assimilation processing to obtain a pollutant concentration assimilation value, including: Determine a fusion weight based on the corrected pollutant concentration inversion value and the pollutant concentration prediction value at the kth moment; The fusion weight is used to perform weighted summation on the corrected pollutant concentration inversion value and the pollutant concentration prediction value to achieve data assimilation processing and obtain the pollutant concentration assimilation value.

5. The water quality prediction method of remote sensing inversion and hydrodynamic model fusion according to claim 4 is characterized in that: Determining a fusion weight based on the corrected pollutant concentration inversion value and the pollutant concentration prediction value at the kth moment includes: Determine a first error value between the corrected pollutant concentration inversion value and the pollutant concentration measured data, and determine a second error value between the pollutant concentration prediction value at the kth moment and the pollutant concentration measured data; A fusion weight is determined based on a comparison result between the first error value and the second error value.

6. The water quality prediction method of remote sensing inversion and hydrodynamic model fusion according to claim 1 is characterized in that: The initial operating conditions of the hydrodynamic model are set using the pollutant concentration inversion value and the water body depth inversion value, including: Setting the water level parameter and flow velocity parameter of the hydrodynamic model at the initial time, and using the pollutant concentration inversion value as the water quality parameter of the hydrodynamic model at the initial time, so as to obtain the initial condition; and, determining the water body range at the initial moment based on the water body depth inversion value, so as to set the boundary condition of the hydrodynamic model at the initial moment based on the water body range; The operating conditions include the initial conditions and the boundary conditions.

7. A water quality prediction device integrating remote sensing inversion and hydrodynamic model, characterized in that: include: Data acquisition module, used to obtain satellite remote sensing data corresponding to the study area; A model configuration module, used to perform inversion based on the satellite remote sensing data at the initial moment to obtain pollutant concentration inversion values ​​and water body depth inversion values, so as to set the initial operating conditions of the hydrodynamic model using the pollutant concentration inversion values ​​and the water body depth inversion values; A prediction and inversion module, for running the hydrodynamic model at the current moment to perform water quality simulation, and obtaining a time series pollutant concentration prediction value and a water body depth prediction value, including a pollutant concentration prediction value and a water body depth prediction value at the kth moment; and performing an inversion based on the satellite remote sensing data at the kth moment corresponding to the current moment, and obtaining a new pollutant concentration inversion value and a new water body depth inversion value; an assimilation module, for assimilating the predicted value of the pollutant concentration at the kth moment and the new inverted value of the pollutant concentration, and the predicted value of the water body depth at the kth moment and the new inverted value of the water body depth, respectively, to obtain an assimilated value of the pollutant concentration and an assimilated value of the water body depth; The water quality prediction module is used to, if it is determined to continue the hydrodynamic model optimization, take the kth moment as the new current moment, use the pollutant concentration assimilation value and the water body depth assimilation value to update the initial operating conditions of the hydrodynamic model, and continue to run the hydrodynamic model at the new current moment to perform water quality simulation until it is determined to stop the model optimization and water quality simulation.

8. The water quality prediction device integrating remote sensing inversion and hydrodynamic model according to claim 7 is characterized in that: The assimilation module is specifically used for: Correcting the new pollutant concentration inversion value using the measured pollutant concentration data corresponding to the study area, and assimilating the corrected pollutant concentration inversion value and the pollutant concentration prediction value to obtain a pollutant concentration assimilation value; Furthermore, the new water body depth inversion value is corrected using the measured water body depth data corresponding to the study area, and the corrected water body depth inversion value and the water body depth prediction value are assimilated to obtain the water body depth assimilation value.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 6.

Images