River shoreline form prediction method and device

Abstract

The invention discloses a river shoreline form prediction method and device. The river shoreline form prediction method comprises the following steps: acquiring a deposition prediction model and an erosion prediction model; training the model; obtaining current shoreline coordinate information, current water level data, current flow data, current rainfall data, current osmotic pressure data, current seepage data and current geological data; generating fusion features according to the current shoreline coordinate information, the current water level data, the current flow data, the current rainfall data, the current osmotic pressure data, the current seepage data and the current geological data; and inputting the fusion features into the siltation prediction model and / or the erosion prediction model so as to obtain siltation prediction information and / or erosion prediction information. According to the method, the neural network and the historical element data of shoreline erosion and siltation are combined for learning to generate the corresponding erosion and siltation prediction model, so that the prediction accuracy and reliability are improved.

Description

Technical Field

[0001] The present application relates to the technical field of river shoreline morphology, and in particular to a river shoreline morphology prediction method and a river shoreline morphology prediction device. Background Art

[0002] Existing water conservancy remote sensing data processing primarily focuses on remote sensing image analysis, including shoreline extraction, morphological evolution prediction, and data comparative analysis. However, current processing methods rely solely on single remote sensing data for sampling, analysis, and prediction, resulting in unsatisfactory results. With the rapid development of smart water conservancy, water conservancy monitoring systems are becoming increasingly sophisticated, enabling more comprehensive and real-time collection of information on water conditions, rainfall, and construction conditions. Therefore, comprehensive analysis combining multi-source data—water conservancy monitoring data, remote sensing data, geographic imagery data, and geological data—has become an important means of improving river bank erosion and sedimentation prediction.

[0003] Existing technical solutions can only solve the analysis of single remote sensing imaging data, and cannot achieve comprehensive data processing and analysis of structured data, semi-structured data, and unstructured data generated by multi-source data; based on big data systems and machine learning algorithms, comprehensive processing and analysis of structured data, semi-structured data, and unstructured data are carried out, aiming to extract valuable information by integrating multiple data types and utilizing advanced analysis technologies to support result prediction and decision-making. Summary of the Invention

[0004] The object of the present invention is to provide a river bank morphology prediction method to solve at least one of the above-mentioned technical problems.

[0005] One aspect of the present invention provides a river bank morphology prediction method, the river bank morphology prediction method comprising: Obtain historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data; Obtain sedimentation prediction models and erosion prediction models; The sedimentation prediction model and the erosion prediction model are trained respectively by using historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data and historical geological data, thereby obtaining a trained sedimentation prediction model and a trained erosion prediction model; Obtain current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; Generate fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; The fused features are input into the sedimentation prediction model and / or the erosion prediction model, thereby obtaining sedimentation prediction information and / or erosion prediction information.

[0006] Optionally, the sedimentation prediction model and the erosion prediction model are trained respectively by using historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data, thereby obtaining the trained sedimentation prediction model and erosion prediction model, including: Obtaining historical coordinate information of shoreline changes for training sedimentation prediction models and obtaining historical coordinate information of shoreline changes for training erosion prediction models; Obtain historical data on training water levels, flow rates, rainfall, seepage pressure, seepage flow, and geological history; Performing a first preprocessing on the historical coordinate information of the shoreline change used for training the sedimentation prediction model, thereby obtaining a first eigenvector; Preprocessing the training water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data to obtain a second eigenvector; Performing a third preprocessing on the historical coordinate information of the shoreline change used for training the erosion prediction model, thereby obtaining a third eigenvector; Training the sedimentation prediction model using the first eigenvector and the second eigenvector; The erosion prediction model is trained using the second eigenvector and the third eigenvector.

[0007] Optionally, the training of the sedimentation prediction model using the first eigenvector and the second eigenvector includes: fusing the first eigenvector and the second eigenvector through an implicit spatial encoding network to generate a fourth eigenvector; Get the regression mapping network; Training the regression mapping network according to the fourth eigenvector, thereby obtaining a trained regression mapping network; Obtaining sedimentation prediction marking result data; Extracting features from the sedimentation prediction marking result data to obtain a fifth feature vector; The sedimentation prediction model is trained using the fourth eigenvector and the fifth eigenvector.

[0008] Optionally, the training of the sedimentation prediction model by using the fourth eigenvector and the fifth eigenvector includes: Performing multiple rounds of pre-training on the sedimentation prediction model and the erosion prediction model using the fourth eigenvector; After completing multiple rounds of pre-training, freeze the parameters of the fusion module according to the preset step size; The fourth eigenvector is compared with the fifth eigenvector to train a sedimentation prediction model, thereby obtaining a trained sedimentation prediction model.

[0009] Optionally, generating fusion features according to the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data, and current geological data includes: The current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data are subjected to feature fusion using a regression mapping network to obtain fusion features.

[0010] Optionally, before training the sedimentation prediction model and the erosion prediction model, the river bank morphology prediction and early warning method based on the BP algorithm further includes: The acquired historical data of water level, flow, rainfall, seepage pressure, seepage and geological history are denoised respectively.

[0011] Optionally, the obtained water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data are filtered and denoised using the following formula: ; n is the sample index, is the sampling signal, h[nk] is the value of the impulse response of the filter when n is nk, N is the length of x[n], and M is the length of the impulse response of the filter.

[0012] Optionally, the sedimentation prediction model and / or erosion prediction model is a BP neural network.

[0013] The present application also provides a river bank morphology prediction device, the river bank morphology prediction device comprising: A data acquisition module, wherein the data acquisition module is used to obtain historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data; A model acquisition module, wherein the model acquisition module is used to acquire a sedimentation prediction model and an erosion prediction model; A training module, wherein the training module is used to train the sedimentation prediction model and the erosion prediction model respectively through historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data, thereby obtaining a trained sedimentation prediction model and a trained erosion prediction model; A prediction data acquisition module, wherein the prediction data acquisition module is used to obtain current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data, and current geological data; A feature fusion module, the feature fusion module is used to generate fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; A prediction module is used to input the fusion features into the sedimentation prediction model and / or the erosion prediction model, thereby obtaining sedimentation prediction information and / or erosion prediction information.

[0014] Beneficial effects: The river bank morphology prediction method proposed in this application combines a neural network with historical data on shoreline erosion and siltation to generate corresponding erosion and siltation prediction models. This prediction model is used to predict river bank morphology under specific time, water, rainfall, and construction conditions. This process not only utilizes historical data and real-time monitoring information, but also optimizes model performance through deep learning algorithms, thereby improving the accuracy and reliability of predictions and providing a scientific basis for water management and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a river shoreline morphology prediction method according to an embodiment of the present application.

[0016] Figure 2 It is a schematic diagram of an electronic device for implementing the river shoreline morphology prediction method according to an embodiment of the present application.

[0017] Figure 3 It is a schematic diagram of sample element information processing.

[0018] Figure 4 It is a schematic diagram of the prediction results. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the implementation of this application clearer, the technical solutions in the embodiments of this application will be described in more detail below in conjunction with the drawings in the embodiments of this application. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of this application, not all of the embodiments. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain this application, and should not be understood as limitations on this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The embodiments of this application are described in detail below in conjunction with the drawings.

[0020] like Figure 1 The river bank morphology prediction methods shown include: Obtain historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data; Obtaining a sedimentation prediction model and an erosion prediction model; in this embodiment, there are two types of shoreline morphological changes: one is shoreline deformation after sedimentation accumulation (predicted by the sedimentation prediction model), and the other is shoreline deformation after being washed away (predicted by the erosion prediction model); The sedimentation prediction model and the erosion prediction model are trained respectively by using historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data and historical geological data, thereby obtaining trained sedimentation prediction models and erosion prediction models; Obtain current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; Generate fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; The fused features are input into the sedimentation prediction model and / or the erosion prediction model, thereby obtaining sedimentation prediction information and / or erosion prediction information.

[0021] The river bank morphology prediction and early warning method proposed in this application combines a neural network with historical data on bank erosion and siltation to generate corresponding erosion and siltation prediction models. This prediction model is used to predict river bank morphology under specific time, water, rainfall, and construction conditions. This process not only utilizes historical data and real-time monitoring information, but also optimizes model performance through deep learning algorithms, thereby improving the accuracy and reliability of predictions and providing a scientific basis for water management and decision-making.

[0022] In this embodiment, the sedimentation prediction model and the erosion prediction model are trained respectively by using the historical coordinate information of shoreline changes, water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data, thereby obtaining the trained sedimentation prediction model and erosion prediction model, which include: Obtaining historical coordinate information of shoreline changes for training sedimentation prediction models and obtaining historical coordinate information of shoreline changes for training erosion prediction models; Obtain historical data on training water levels, flow rates, rainfall, seepage pressure, seepage flow, and geological history; Performing a first preprocessing on the historical coordinate information of the shoreline change used for training the sedimentation prediction model, thereby obtaining a first eigenvector; Preprocessing the training water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data to obtain a second eigenvector; Performing a third preprocessing on the historical coordinate information of the shoreline change used for training the erosion prediction model, thereby obtaining a third eigenvector; Training the sedimentation prediction model using the first eigenvector and the second eigenvector; The erosion prediction model is trained using the second eigenvector and the third eigenvector. In this embodiment, the difference between the methods used to train the sedimentation prediction model and the erosion prediction model is that, on the one hand, the methods for obtaining the historical coordinate information of the shoreline changes are different. When the erosion model obtains the historical coordinate information of the shoreline changes, it obtains it through remote sensing data, oblique photography data, geographic data (shoreline), water level historical data, flow historical data, rainfall historical data, seepage pressure historical data (optional), seepage historical data (optional), and geological historical data. Compared with the erosion model, the sedimentation model has an additional underwater photography data.

[0023] On the other hand, the specific training data used in the historical coordinate information of shoreline changes is different. For example, if the historical coordinate information of shoreline changes is 1 year's data, it includes Figure 3 As shown, the shoreline develops from a1-a7 to b1-b7, which is the data used in the erosion model (hereinafter referred to as shoreline reduction data), and also includes, for example, the shoreline develops from b1-b7 to a1-a7, which is the data used in the sedimentation model (hereinafter referred to as shoreline increase data).

[0024] For example, there are 100 historical coordinate information of shoreline changes used for training, including 50 shoreline reduction data and 50 shoreline increase data. Then, the 50 shoreline reduction data are used to train the erosion model, and the 50 shoreline increase data are used to train the sedimentation model.

[0025] The remaining data, such as water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data, correspond to the data on the day when the shoreline reduction data is used or the data on the day when the shoreline increase data is used.

[0026] For example, the data on March 1, 2024 is shoreline addition data, which is used to train the sedimentation model. Then, the historical water level data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data on March 1, 2024 are also used to train the sedimentation model.

[0027] In this embodiment, the sedimentation prediction model and the erosion prediction model are trained respectively by using the historical coordinate information of shoreline changes, water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data, thereby obtaining the trained sedimentation prediction model and erosion prediction model, which include: Obtaining historical coordinate information of shoreline changes for training sedimentation prediction models and obtaining historical coordinate information of shoreline changes for training erosion prediction models; Obtain historical data on training water levels, flow rates, rainfall, seepage pressure, seepage flow, and geological history; Performing a first preprocessing on the historical coordinate information of the shoreline change used for training the sedimentation prediction model, thereby obtaining a first eigenvector; Preprocessing the training water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data to obtain a second eigenvector; Performing a third preprocessing on the historical coordinate information of the shoreline change used for training the erosion prediction model, thereby obtaining a third eigenvector; Training the sedimentation prediction model using the first eigenvector and the second eigenvector; The erosion prediction model is trained using the second eigenvector and the third eigenvector.

[0028] In this embodiment, the training of the sedimentation prediction model using the first eigenvector and the second eigenvector includes: fusing the first eigenvector and the second eigenvector through an implicit spatial encoding network to generate a fourth eigenvector; Get the regression mapping network; Training the regression mapping network according to the fourth eigenvector, thereby obtaining a trained regression mapping network; Obtaining sedimentation prediction marking result data; Extracting features from the sedimentation prediction marking result data to obtain a fifth feature vector; The sedimentation prediction model is trained using the fourth eigenvector and the fifth eigenvector.

[0029] In this embodiment, training the sedimentation prediction model using the fourth eigenvector and the fifth eigenvector includes: Performing multiple rounds of pre-training on the sedimentation prediction model and the erosion prediction model using the fourth eigenvector; After completing multiple rounds of pre-training, freeze the parameters of the fusion module according to the preset step size; The fourth eigenvector is compared with the fifth eigenvector to train a sedimentation prediction model, thereby obtaining a trained sedimentation prediction model.

[0030] In this embodiment, the training method of the erosion prediction model is the same as the training method of the above-mentioned sedimentation prediction model. The only difference is the data, which will not be repeated here.

[0031] In this embodiment, generating fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data, and current geological data includes: The current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data are subjected to feature fusion using a regression mapping network to obtain fusion features.

[0032] In this embodiment, obtaining the historical coordinate information of shoreline changes includes: Obtain comprehensive remote sensing data and oblique photography data, and extract shoreline data through remote sensing image recognition algorithms; Using deformation displacement sensor data and map data, the shoreline morphology data is normalized by GIS and converted into GIS coordinate system data that corresponds to each other in time and geographic space; Extract sedimentation change elements, integrate remote sensing data, oblique photography and underwater terrain data, extract sedimentation pattern data through image recognition algorithms, and use data fusion methods to convert them into three-dimensional GIS data in time and geographic space; According to the shoreline change process from a1, a2...an to b1, b2...bn, the GIS coordinate data is converted into relative displacement data.

[0033] It can be understood that the above-mentioned historical coordinate information of shoreline changes is existing technology and will not be described in detail here.

[0034] In this embodiment, before training the sedimentation prediction model and the erosion prediction model, the river bank morphology prediction and early warning method based on the BP algorithm further includes: The acquired historical data of water level, flow, rainfall, seepage pressure, seepage and geological history are denoised respectively.

[0035] In this embodiment, the obtained water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data are filtered and denoised using the following formula: ; n is the sample index, is the sampling signal, h[nk] is the value of the impulse response of the filter when n is nk, N is the length of x[n], and M is the length of the impulse response of the filter.

[0036] In this embodiment, the sedimentation prediction information and / or erosion prediction information is a BP neural network.

[0037] The present application is further described in detail below by way of examples. It should be understood that the examples do not constitute any limitation to the present application.

[0038] By comprehensively collecting and preserving data related to river shoreline morphology, including data from the smart water conservancy monitoring system, remote sensing data, geological data, and geographic data; processing, cleaning, and integrating these structured, semi-structured, and unstructured data through the model of the feature extraction model platform and machine learning and data analysis algorithms, spatiotemporal feature data related to shoreline erosion and siltation are obtained and stored in the data warehouse; the prediction model platform uses the spatiotemporal data in the data warehouse and combines it with the BP artificial neural network algorithm to perform in-depth calculations on shoreline erosion and siltation data, thereby obtaining prediction results under specific time, water conditions, rainfall conditions, and working conditions. Specifically, the sensor data from the water conservancy platform's database is structured, image data is unstructured, and weather forecasts obtained online are unstructured; the feature extraction model: obtains the coordinate information of the reference objects in the existing images or remote sensing extraction algorithms; machine learning and data analysis algorithms are mainly used for ETL to clean up erroneous data.

[0039] The Water Conservancy Digital Base is based on a data warehouse and uses classified storage to efficiently integrate and manage real-time data from the smart water conservancy monitoring system. This data includes: water level data, flow data, rainfall data, seepage pressure data, seepage data, deformation data, as well as remote sensing data, oblique photography, underwater topography, geographic information data, map data, and geological data. The Water Conservancy Digital Base can achieve efficient storage and management of various types of data. The data processing and analysis platform, based on big data technology, has built a model platform and an algorithm platform capable of batch computing relevant structured, semi-structured, and unstructured data. This platform is primarily used to obtain shoreline morphology and sedimentation factor data, and store this data in a data warehouse according to time and space dimensions. The feature extraction model platform extracts shoreline morphological features by integrating remote sensing data and oblique photography data, and extracting shoreline data through remote sensing image recognition algorithms. Using deformation displacement sensor data and map data, shoreline morphological data is normalized by GIS and converted into GIS coordinate system data that corresponds to time and geographic space. For sedimentation change feature extraction, remote sensing data, oblique photography, and underwater terrain data are integrated, and sedimentation pattern data is extracted through image recognition algorithms. Data fusion methods are used to convert this data into three-dimensional GIS data in time and geographic space. For the shoreline change process from a1, a2…an to b1, b2…bn, GIS coordinate data is converted into relative displacement data: the movement distance on the X axis and the movement distance on the Y axis. For example, a shoreline is a line, but lines cannot be calculated. For example, line A can be viewed as connected by points consisting of a1, a2…an. This a1 is the reference point, and the value of a1 is the corresponding GIS coordinate, which corresponds to the x and y axis values ​​of the reference coordinate system in the algorithm. At time T, the shoreline line is A, and at time T+1, the shoreline line is B. The corresponding reference point a1, Move to b1.

[0040] Real-time data from sensors such as water level, flow, rainfall, seepage pressure, and seepage flow are processed and standardized to produce data of water level, flow, rainfall, seepage pressure, and seepage flow after data quality processing. These data are aggregated based on the sampling frequency of the shoreline and converted into time-based element data. Data normalization methods are used for geological data, converting them into standardized data items with a time dimension. The prediction model platform uses the data of river bank morphology and sedimentation elements, and applies the prediction model generated by the BP artificial neural network algorithm to calculate and generate prediction results for a period of time in the future based on specific input information. These prediction results include shoreline erosion prediction and sedimentation prediction. Sample data processing is as follows Figure 3As shown in the figure, it is known that the shoreline graph of month A is composed of line segments a1, a2…a8; the shoreline graph of month B is composed of line segments b1, b2…b8; the shoreline graph of month C is composed of line segments c1, c2…c8; the date of month C is greater than that of month B, and month B is greater than that of month A; Divide the shoreline of month A into a1…an according to the monitoring points, and divide month B into b1…bn according to month A; assume that the shoreline change of segment a1-a2 corresponds to the shoreline change of segment b1-b2; similarly, the shoreline change of segment b1-b2 corresponds to the shoreline change of segment c1-c2; the shoreline coordinates of segment a1-a2 include (a11, a12, a13…a1n), the shoreline coordinates of segment b1-b2 include (b11, b12, b13…b1n), the X-axis relative displacement of b11 relative to a11 is (ab11x, ab12x…ab1nx), and the X-axis relative displacement of b11 relative to a11 is (ab11y, ab12y…ab1ny); water level data m1, flow data m2, Rainfall data m3, seepage pressure data m4, seepage data m5, geological data m6, by using the BP algorithm: input values ​​are a11, a12…a1n, m1, m2, m3, m4, m5, m6; verification results are ab11x, ab12x…ab1nx; input values ​​are a11, a12…a1n, m1, m2, m3, m4, m5, m6; verification results are ab11y, ab12y…ab1ny; Similarly: the shoreline coordinate array of the b1-b2 segment includes (b11, b12, b13…b1n), the shoreline coordinate data of the c1-c2 segment includes (c11, c12, c13…c1m, water level data m1, flow data m2, rainfall data m3, seepage pressure data m4, seepage data m5, geological data m6, by using the BP algorithm: input values ​​are b11, b12, b13…b1n, m1, m2, m3, m4, m5, m6; the verification results are bc11x, bc12x…bc1nx; input values ​​are b11, b12, b13…b1n, m1, m2, m3, m4, m5, m6; the verification results are bc11y, bc12y…bc1ny; the shoreline a1-a2 The segment changes from b1 to b2 and the segment changes from b1 to b2 to c1 to c2 are regarded as the same group of samples, and learning is used to generate sedimentation prediction models and erosion prediction models.

[0041] Sedimentation and erosion prediction models are generated using a sample set where the shoreline segment a1-a2 changes to the b1-b2 segment, and the b1-b2 segment changes to the c1-c2 segment. For the c1-c2 segment, user-defined water level data m1, flow data m2, rainfall data m3, seepage pressure data m4, seepage data m5, and geological data m6 are used to predict the shoreline data for the d1-d2 segment. The user enters m1…m6 and the known values ​​[c11, c12, c13], [c12, c13, c14]… [c1n-2, c1n-1, c1n] to predict the corresponding relative shoreline points [d11x, d11y], [d12x, d12y]… [d1nx, d1ny]. Finally, the relative position data is converted into GIS coordinate points [d1, d11, d12…d2…d3…dn], such as Figure 4 shown.

[0042] This application has the following advantages: The system integrates multi-source data, including water conservancy monitoring data, remote sensing data, geographic image data, and geological data. It cleans and integrates these structured, semi-structured, and unstructured data, applying advanced machine learning and data analysis algorithms to extract spatiotemporal data related to shoreline morphology. Through this extracted data on water conditions, rainfall, construction conditions, remote sensing data, map images, and geology, it achieves prediction results under different conditions such as heavy rain and flooding, providing comprehensive data support for the development trends of shoreline erosion and siltation. For smart water conservancy's water level data, flow data, rainfall data, seepage pressure data, seepage data, deformation data, as well as remote sensing data, oblique photography, geographic information data, map data and geological data and other types of related data, the BP artificial neural network algorithm is used to generate corresponding erosion and sedimentation prediction models to realize the prediction and analysis of the shoreline erosion and sedimentation trends of rivers and lakes, so as to understand possible changes in advance and guide the planning of water conservancy projects, flood control facilities construction and ecological protection measures.

[0043] The present application also provides a river bank morphology prediction device, which includes a data acquisition module, a model acquisition module, a training module, a prediction data acquisition module, a feature fusion module, and a prediction module, wherein: The data acquisition module is used to obtain historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data and historical geological data; The model acquisition module is used to obtain sedimentation prediction model and erosion prediction model; The training module is used to train the sedimentation prediction model and the erosion prediction model respectively through the historical coordinate information of shoreline changes, water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data, thereby obtaining a trained sedimentation prediction model and a trained erosion prediction model; The prediction data acquisition module is used to obtain the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; The feature fusion module is used to generate fusion features according to the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; The prediction module is used to input the fusion features into the sedimentation prediction model and / or the erosion prediction model, thereby obtaining sedimentation prediction information and / or erosion prediction information.

[0044] It should be noted that the aforementioned explanation of the method embodiment is also applicable to the system of this embodiment and will not be repeated here.

[0045] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the above-mentioned river shoreline morphology prediction method is implemented.

[0046] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the above-mentioned river shoreline morphology prediction method.

[0047] Figure 2 This is an exemplary structural diagram of an electronic device capable of implementing the river bank morphology prediction method provided according to an embodiment of the present application.

[0048] like Figure 2As shown, the electronic device includes an input device 501, an input interface 502, a central processing unit 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processing unit 503, the memory 504, and the output interface 505 are interconnected via a bus 507. The input device 501 and the output device 506 are connected to the bus 507 via the input interface 502 and the output interface 505, respectively, and are then connected to other components of the electronic device. Specifically, the input device 501 receives input information from the outside and transmits the input information to the central processing unit 503 via the input interface 502; the central processing unit 503 processes the input information based on the computer-executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 via the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for use by the user.

[0049] That is to say, Figure 2 The electronic device shown may also be implemented as comprising: a memory storing computer executable instructions; and one or more processors, which can implement the combination of the computer executable instructions when executing the computer executable instructions. Figure 1 Described is a method for predicting river bank morphology.

[0050] In one embodiment, Figure 2 The electronic device shown can be implemented to include: a memory 504 configured to store executable program code; and one or more processors configured to run the executable program code stored in the memory 504 to execute the river bank morphology prediction method in the above embodiment.

[0051] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0052] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0053] Computer-readable media include permanent and non-permanent, removable and non-removable media, and media can be implemented using any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), data versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0054] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and a part of the module, program segment or code includes one or more executable instructions for realizing the prescribed logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes identified in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or overall flow chart can be implemented using a dedicated hardware-based system that performs the prescribed function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0055] The processor referred to in this embodiment may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0056] The memory can be used to store computer programs and / or modules. The processor implements various functions of the system / terminal device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of the mobile phone (such as audio data and a phone book). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0057] In this embodiment, if the modules / units integrated into the system / terminal device 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 present invention can implement all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include: any entity or system capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice within a jurisdiction. Although the present application is disclosed as above with reference to preferred embodiments, it is not intended to limit the present application. Any person skilled in the art may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

[0058] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] In addition, it is obvious that the word "comprising" does not exclude other units or steps. The multiple units, modules or systems stated in the system claims can also be implemented by one unit or the overall system through software or hardware.

[0060] Although the present invention has been described in detail above using general descriptions and specific embodiments, it will be apparent to those skilled in the art that modifications and improvements may be made based on the present invention. Therefore, such modifications and improvements, which do not depart from the spirit of the present invention, are intended to be within the scope of protection claimed herein.

Claims

1. A river bank morphology prediction method, characterized in that: The river bank morphology prediction method comprises: Obtain historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data; Obtain sedimentation prediction models and erosion prediction models; The sedimentation prediction model and the erosion prediction model are trained respectively by using historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data and historical geological data, thereby obtaining a trained sedimentation prediction model and a trained erosion prediction model; Obtain current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; Generate fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; The fused features are input into the sedimentation prediction model and / or the erosion prediction model, thereby obtaining sedimentation prediction information and / or erosion prediction information.

2. The river bank morphology prediction method according to claim 1, wherein: The sedimentation prediction model and the erosion prediction model are trained respectively by using the historical coordinate information of shoreline changes, water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data, thereby obtaining the trained sedimentation prediction model and erosion prediction model, including: Obtaining historical coordinate information of shoreline changes for training sedimentation prediction models and obtaining historical coordinate information of shoreline changes for training erosion prediction models; Obtain historical data on training water levels, flow rates, rainfall, seepage pressure, seepage flow, and geological history; Performing a first preprocessing on the historical coordinate information of the shoreline change used for training the sedimentation prediction model, thereby obtaining a first eigenvector; Preprocessing the training water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data to obtain a second eigenvector; Performing a third preprocessing on the historical coordinate information of the shoreline change used for training the erosion prediction model, thereby obtaining a third eigenvector; Training the sedimentation prediction model using the first eigenvector and the second eigenvector; The erosion prediction model is trained using the second eigenvector and the third eigenvector.

3. The river bank morphology prediction method according to claim 2, characterized in that: The training of the sedimentation prediction model by using the first eigenvector and the second eigenvector includes: fusing the first eigenvector and the second eigenvector through an implicit spatial encoding network to generate a fourth eigenvector; Get the regression mapping network; Training the regression mapping network according to the fourth eigenvector, thereby obtaining a trained regression mapping network; Obtaining sedimentation prediction marking result data; Extracting features from the sedimentation prediction marking result data to obtain a fifth feature vector; The sedimentation prediction model is trained using the fourth eigenvector and the fifth eigenvector.

4. The river bank morphology prediction method according to claim 3, characterized in that: The training of the sedimentation prediction model by using the fourth eigenvector and the fifth eigenvector includes: Performing multiple rounds of pre-training on the sedimentation prediction model and the erosion prediction model using the fourth eigenvector; After completing multiple rounds of pre-training, freeze the parameters of the fusion module according to the preset step size; The fourth eigenvector is compared with the fifth eigenvector to train a sedimentation prediction model, thereby obtaining a trained sedimentation prediction model.

5. The river bank morphology prediction method according to claim 4, characterized in that: Generating fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data, and current geological data includes: The current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data are subjected to feature fusion using a regression mapping network to obtain fusion features.

6. The river bank morphology prediction method according to claim 5, characterized in that: Before training the sedimentation prediction model and the erosion prediction model, the river bank morphology prediction and early warning method based on the BP algorithm further includes: The acquired historical data of water level, flow, rainfall, seepage pressure, seepage and geological history are denoised respectively.

7. The river bank morphology prediction method according to claim 6, characterized in that: The following formula is used to filter and denoise the acquired water level historical data, flow historical data, rainfall historical data, seepage pressure historical data, seepage historical data and geological historical data: ； n is the sample index, is the sampling signal, h[nk] is the value of the impulse response of the filter when n is nk, N is the length of x[n], and M is the length of the impulse response of the filter.

8. The river bank morphology prediction method according to claim 7, characterized in that: The sedimentation prediction model and / or erosion prediction model is a BP neural network.

9. A river bank morphology prediction device, characterized in that: The river bank morphology prediction device comprises: A data acquisition module, wherein the data acquisition module is used to obtain historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data; A model acquisition module, wherein the model acquisition module is used to acquire a sedimentation prediction model and an erosion prediction model; A training module, wherein the training module is used to train the sedimentation prediction model and the erosion prediction model respectively through historical coordinate information of shoreline changes, historical water level data, historical flow data, historical rainfall data, historical seepage pressure data, historical seepage data, and historical geological data, thereby obtaining a trained sedimentation prediction model and a trained erosion prediction model; A prediction data acquisition module, wherein the prediction data acquisition module is used to obtain current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data, and current geological data; A feature fusion module, the feature fusion module is used to generate fusion features based on the current shoreline coordinate information, current water level data, current flow data, current rainfall data, current seepage pressure data, current seepage data and current geological data; A prediction module is used to input the fusion features into the sedimentation prediction model and / or the erosion prediction model, thereby obtaining sedimentation prediction information and / or erosion prediction information.

Images