Method and system for predicting long-term evolution of beach shoreline under influence of typhoon

Abstract

The invention provides a method and a system for predicting long-term evolution of a beach shoreline under the influence of typhoon. The method comprises the following steps: acquiring a preset probability distribution model; acquiring historical typhoon data, and generating multiple groups of typhoon scene data; dividing the initial area into a plurality of grid areas; performing simulation in each grid region by utilizing typhoon scene data to obtain a simulation result; and extracting hydrodynamic field data of the beach shoreline region from the simulation result, extracting a feature vector and identifying a target region, further simulating the change process of the beach shoreline by using a preset time scale, and predicting to obtain a beach shoreline evolution path. The typhoon intensity and the moving path are described through the probability distribution model, multiple groups of typhoon scene data are generated in combination with historical typhoon data and are used for simulation in each grid region, the difference between the grid regions in the space level, namely the influence of the typhoon on different grids in the initial region, can be considered, and the typhoon simulation accuracy is improved. And the evolution prediction effect of the beach shoreline under the influence of typhoon is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of image analysis, and in particular to a method and system for predicting the long-term evolution of beach coastlines under the influence of typhoons. Background Art

[0002] In the time dimension of years, the beach coastline will be affected by external factors such as typhoons and waves, and will be eroded and evolve. When studying the long-term evolution prediction of beach coastlines under the influence of typhoons, there are many difficulties. For example, a typhoon is a complex meteorological process, and its intensity, movement path and duration will affect the evolution of the beach coastline; secondly, the ocean dynamics caused by typhoons are also very complex, such as wind-driven currents, storm surges and waves, and these ocean dynamics phenomena vary significantly in time and space; thirdly, the beach coastline is affected by the combined influence of factors such as ocean currents and sediment movement, and these factors interact with each other. When the feedback mechanism is not clear, it is difficult to quantitatively simulate the response of the coastline to the typhoon. There is a certain uncertainty. When the existing technology deduces and predicts the evolution of the beach coastline, it mainly simulates the typhoon intensity in a fixed area at the probability level, while ignoring the change factors at the spatial level, such as the impact of typhoons on different areas of the beach coastline, so the prediction effect is general. Summary of the invention

[0003] The present invention application provides a method and system for predicting the long-term evolution of beach shorelines under the influence of typhoons, so as to solve the technical problem of how to improve the effect of predicting the evolution of beach shorelines under the influence of typhoons.

[0004] In order to solve the above technical problems, the present invention provides a method for predicting the long-term evolution of beach coastline under the influence of typhoon, comprising: Obtaining a preset probability distribution model, where the probability distribution model is used to describe the intensity and movement path of a typhoon; Acquire historical typhoon data, and generate multiple sets of typhoon scenario data based on the historical typhoon data and a probability distribution model; The nested grid technique is used to divide the initial area into several grid areas; Using the multiple sets of typhoon scenario data to perform simulation in each of the grid areas, obtaining simulation results of each grid data, wherein the simulation results include wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; The hydrodynamic field data of the beach shoreline area is extracted from the simulation results, and the characteristic vector of the hydrodynamic field data is extracted by principal component analysis. The target area is identified from the hydrodynamic field data according to the characteristic vector, and then the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area are used to simulate the change process of the beach shoreline and predict the evolution path of the beach shoreline.

[0005] As a preferred solution, the method utilizes the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale in the target area to simulate the change process of the beach shoreline and predict the beach shoreline evolution path, including: Calculate the frequency distribution of the beach coastline according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area; Performing fitting processing on the frequency distribution to obtain a fitting model of the beach coastline, wherein the fitting model is used to characterize the random process of the beach coastline change; Generate a number of random samples using the fitted model through a Monte Carlo method; At least one beach shoreline evolution path is generated based on the random sample using the time scale.

[0006] As a preferred solution, the method of using the time scale to generate at least one beach shoreline evolution path based on the random sample includes: Calculate the position and range of the target area according to the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data of the target area to obtain a boundary condition data set; Inputting the boundary condition data set into a preset sediment movement model, calculating sediment transport parameters and deposition process parameters in the target area, obtaining sediment temporal and spatial variation characteristics, and using the sediment temporal and spatial variation characteristics as the first shoreline response characteristics; Based on the time scale and the random sample, a second shoreline response characteristic is obtained; wherein the time scale corresponding to the second shoreline response characteristic is greater than that of the first shoreline response characteristic; At least one beach shoreline evolution path is generated based on the first shoreline response characteristic and the second shoreline response characteristic.

[0007] As a preferred solution, the acquiring of historical typhoon data and generating multiple sets of typhoon scenario data according to the historical typhoon data and a probability distribution model include: Acquire the historical typhoon data, wherein the historical typhoon data includes typhoon location data, wind speed data, and air pressure data; The probability distribution model is used to obtain the correlation between the position data, wind speed data and air pressure data, thereby generating multiple sets of typhoon scenario data, wherein the typhoon scenario data includes parameter changes within the life cycle of a typhoon.

[0008] As a preferred solution, the typhoon scenario data includes the typhoon's wind stress, pressure gradient force and Coriolis force; The using the multiple groups of typhoon scenario data to simulate in each of the grid areas to obtain simulation results of each grid data includes: Using the multiple sets of typhoon scenario data to perform simulations in each of the grid areas, constructing a parameterized wind field model based on gradient wind balance and boundary layer theory, and obtaining wind field spatiotemporal distribution data; Input the wind stress, pressure gradient force and Coriolis force into a preset FVCOM model, simulate the ocean current model in each grid area, and then obtain the spatiotemporal distribution data of the flow field; Inputting the plurality of sets of typhoon scenario data into a preset SWAN model to obtain wave spatiotemporal distribution data; The wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data and the wave spatiotemporal distribution data are coupled, and the coupling results are updated at preset time intervals to obtain simulation results of the grid data.

[0009] As a preferred solution, the beach shoreline long-term evolution prediction method further includes: Constructing an evolution data set according to the plurality of beach shoreline evolution paths; dividing the target area into shoreline units, and calculating the vulnerability of each shoreline unit according to the geological type, terrain slope and vegetation coverage of each shoreline unit; Using the evolution data set to train the preset long short-term memory network corresponding to each shoreline unit; The fragility parameters are used to iteratively optimize the model structure and training parameters of each long short-term memory network. When the performance parameters of the long short-term memory network meet the preset convergence requirements, the long short-term memory networks that meet the convergence requirements are weightedly fused according to the preset weights of each shoreline unit to obtain a shoreline prediction model.

[0010] Correspondingly, the present invention also provides a long-term beach coastline evolution prediction system under the influence of typhoons, including an acquisition module, a generation module, a division module, a simulation module and a prediction module; wherein, The acquisition module is used to acquire a preset probability distribution model, where the probability distribution model is used to describe the intensity and movement path of the typhoon; The generating module is used to obtain historical typhoon data and generate multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model; The division module is used to divide the initial area into a number of grid areas by using a nested grid technology; The simulation module is used to use the multiple groups of typhoon scenario data to perform simulation in each of the grid areas to obtain simulation results of each grid data, wherein the simulation results include wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; The prediction module is used to extract the hydrodynamic field data of the beach coastline area from the simulation results, and extract the characteristic vector of the hydrodynamic field data through the principal component analysis method, identify the target area from the hydrodynamic field data according to the characteristic vector, and then use the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach coastline and predict the evolution path of the beach coastline.

[0011] As a preferred solution, the prediction module uses the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale in the target area to simulate the change process of the beach coastline and predict the beach coastline evolution path, including: The prediction module calculates the frequency distribution of the beach shoreline according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area; Performing fitting processing on the frequency distribution to obtain a fitting model of the beach coastline, wherein the fitting model is used to characterize the random process of the beach coastline change; Generate a number of random samples using the fitted model through a Monte Carlo method; At least one beach shoreline evolution path is generated based on the random sample using the time scale.

[0012] As a preferred solution, the prediction module generates at least one beach shoreline evolution path based on the random sample using the time scale, including: The prediction module calculates the position and range of the target area according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area to obtain a boundary condition data set; Inputting the boundary condition data set into a preset sediment movement model, calculating sediment transport parameters and deposition process parameters in the target area, obtaining sediment temporal and spatial variation characteristics, and using the sediment temporal and spatial variation characteristics as the first shoreline response characteristics; Based on the time scale and the random sample, a second shoreline response characteristic is obtained; wherein the time scale corresponding to the second shoreline response characteristic is greater than that of the first shoreline response characteristic; At least one beach shoreline evolution path is generated based on the first shoreline response characteristic and the second shoreline response characteristic.

[0013] As a preferred solution, the generation module obtains historical typhoon data, and generates multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model, including: The generating module acquires the historical typhoon data, wherein the historical typhoon data includes the location data, wind speed data and air pressure data of the typhoon; The probability distribution model is used to obtain the correlation between the position data, wind speed data and air pressure data, thereby generating multiple sets of typhoon scenario data, wherein the typhoon scenario data includes parameter changes within the life cycle of a typhoon.

[0014] As a preferred solution, the typhoon scenario data includes the typhoon's wind stress, pressure gradient force and Coriolis force; The simulation module uses the multiple sets of typhoon scenario data to perform simulation in each of the grid areas to obtain simulation results of each grid data, including: The simulation module uses the multiple sets of typhoon scenario data to perform simulations in each of the grid areas, constructs a parameterized wind field model based on gradient wind balance and boundary layer theory, and obtains wind field spatiotemporal distribution data; Input the wind stress, pressure gradient force and Coriolis force into a preset FVCOM model, simulate the ocean current model in each grid area, and then obtain the spatiotemporal distribution data of the flow field; Inputting the plurality of sets of typhoon scenario data into a preset SWAN model to obtain wave spatiotemporal distribution data; The wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data and the wave spatiotemporal distribution data are coupled, and the coupling results are updated at preset time intervals to obtain simulation results of the grid data.

[0015] As a preferred solution, the beach shoreline long-term evolution prediction system further includes a model building module, and the model building module is used to: Constructing an evolution data set according to the plurality of beach shoreline evolution paths; dividing the target area into shoreline units, and calculating the vulnerability of each shoreline unit according to the geological type, terrain slope and vegetation coverage of each shoreline unit; Using the evolution data set to train the preset long short-term memory network corresponding to each shoreline unit; The fragility parameters are used to iteratively optimize the model structure and training parameters of each long short-term memory network. When the performance parameters of the long short-term memory network meet the preset convergence requirements, the long short-term memory networks that meet the convergence requirements are weightedly fused according to the preset weights of each shoreline unit to obtain a shoreline prediction model.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention application provides a method and system for predicting the long-term evolution of a beach shoreline under the influence of a typhoon, the method comprising: obtaining a preset probability distribution model, the probability distribution model being used to describe the intensity and movement path of a typhoon; obtaining historical typhoon data, and generating multiple sets of typhoon scenario data based on the historical typhoon data and the probability distribution model; using a nested grid technology to divide an initial area into a plurality of grid areas; using the multiple sets of typhoon scenario data to perform simulations in each of the grid areas to obtain simulation results of each grid data, the simulation results including wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; extracting hydrodynamic field data of a beach shoreline area from the simulation results, and extracting characteristic vectors of the hydrodynamic field data through a principal component analysis method, identifying a target area from the hydrodynamic field data based on the characteristic vector, and then using the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data, and a preset time scale of the target area to simulate the change process of the beach shoreline and predict the evolution path of the beach shoreline. The present invention describes the intensity and movement path of a typhoon through a probability distribution model, and then generates multiple sets of typhoon scenario data in combination with historical typhoon data, and uses them for simulation in each grid area. The differences in spatial aspects between different grid areas, that is, the impact of the typhoon on different grids in the initial area, can be taken into account, effectively improving the prediction effect of the evolution of the beach coastline under the influence of the typhoon; in addition, the simulation results of the grid data of the present application include the spatiotemporal distribution data of the wind field, the spatiotemporal distribution data of the flow field, and the spatiotemporal distribution data of the wave. By extracting the hydrodynamic field data of the beach coastline area, the beach coastline area may contain the simulation results of one or more grids, which further improves the significance of the prediction method of the present application at the spatial level; furthermore, the characteristic vector of the hydrodynamic field data is extracted by the principal component analysis method to identify the target area, and the beach coastline area and its spatiotemporal distribution are locked by using the hydrodynamic field data and the characteristic vector, so as to simulate the evolution of the beach coastline, and effectively realize long-term and short-term multi-scale predictions through a preset time period, thereby ensuring the accuracy of the prediction method at different time scales. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 : A flow chart of an embodiment of a method for predicting the long-term evolution of beach shoreline under the influence of typhoons provided in the present invention.

[0018] Figure 2 : A structural schematic diagram of an embodiment of a system for predicting the long-term evolution of beach shorelines under the influence of typhoons provided in the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1 Please refer to Figure 1 , Figure 1 The present invention provides a method for predicting the long-term evolution of a beach coastline under the influence of a typhoon, comprising steps S101 to S105; wherein each step is described in detail as follows: Step S101, obtaining a preset probability distribution model.

[0021] In this step, the probability distribution model is used to describe the intensity and movement path of the typhoon. It can describe the correlation between parameters such as the typhoon center position, movement speed, central air pressure and maximum wind speed through, for example, joint probability distribution, and be used in subsequent steps to generate typhoon scenario data.

[0022] Step S102, obtaining historical typhoon data, and generating multiple sets of typhoon scenario data according to the historical typhoon data and a probability distribution model.

[0023] In this step, the historical typhoon data is obtained, and multiple groups of typhoon scenario data are generated according to the historical typhoon data and the probability distribution model, including: obtaining the historical typhoon data, the historical typhoon data including the typhoon's position data, wind speed data and air pressure data (such as the typhoon center position, moving speed, central air pressure and maximum wind speed, etc.); obtaining the correlation between the position data, wind speed data and air pressure data through the probability distribution model, and then generating multiple groups of typhoon scenario data, the typhoon scenario data including parameter changes during the typhoon life cycle.

[0024] Exemplarily, the above historical typhoon data may be, for example, a typhoon best path data set for every 6 hours in the northwest Pacific Ocean from 1979 to 2022, including parameters such as the center position (latitude and longitude), maximum wind speed, and minimum air pressure, and further generate multiple sets of typhoon scenario data (e.g., 1,000 sets) through its fitting of the probability distribution model. Each set of typhoon scenario data contains complete parameter changes throughout the life cycle of the typhoon to ensure the integrity of the typhoon scenario data, which facilitates the complete and accurate simulation of the typhoon scenario in step S104.

[0025] Step S103, using nested grid technology to divide the initial area into a number of grid areas.

[0026] In this step, the nested grid technology can use three layers of nested grids. For example, the outer grid covers the entire study area (initial area), and the grid resolution corresponds to about 9 kilometers; the middle grid covers the main impact area, and the grid resolution corresponds to about 3 kilometers; the inner grid covers the nearshore key area, and the grid resolution corresponds to about 1 kilometer.

[0027] In addition, data exchange and boundary condition transfer between different grids can be achieved through bilinear interpolation method.

[0028] This embodiment can achieve division of different scales by dividing different grids, including dividing the initial area into an outer grid, a middle grid and an inner grid, and further dividing the outer grid, the middle grid and the inner grid into multiple grids, that is, achieving adaptive scale changes for different sub-areas of the initial area, which is beneficial to the subsequent step S104 to achieve accurate simulation of typhoon scenario data in each grid area.

[0029] Step S104, using the multiple sets of typhoon scenario data to perform simulation in each of the grid areas to obtain simulation results for each grid data.

[0030] In this step, the simulation results include wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data.

[0031] Furthermore, the typhoon scenario data includes typhoon mechanical data, specifically including but not limited to typhoon wind stress, pressure gradient force and Coriolis force.

[0032] The using the multiple groups of typhoon scenario data to simulate in each of the grid areas to obtain simulation results of each grid data includes: The above 1000 sets of typhoon scenario data are used to perform simulations in each of the grid areas, and a parameterized wind field model is constructed based on gradient wind balance and boundary layer theory to obtain the spatiotemporal distribution data of the wind field (such as wind speed and wind direction at each grid point).

[0033] The wind stress, pressure gradient force and Coriolis force are input into the preset FVCOM model (FVCOM model (Finite Volume Coastal Ocean Model) is an ocean numerical model based on the finite volume method), and the ocean current model is simulated in each grid area to obtain the spatiotemporal distribution data of the flow field.

[0034] The 1000 sets of typhoon scenario data were input into the preset SWAN model (SWAN model (Simulating Waves Nearshore) is a numerical model used to simulate nearshore wave propagation, refraction, shoaling, breaking and nonlinear interaction) to obtain wave spatiotemporal distribution data (such as wave height, wave period and wave direction of each grid point).

[0035] The spatiotemporal distribution data of the wind field, the spatiotemporal distribution data of the flow field, and the spatiotemporal distribution data of the waves are coupled (this can be achieved through a preset coupling module), and the coupling results are updated at preset time intervals (for example, data is exchanged every hour to update the coupling results. Specifically, since the wind field drives the ocean currents and waves, the ocean currents affect the wind stress by affecting the bottom flow velocity, and the waves affect the ocean currents and storm surge water levels through radiation stress), and the latest coupling results are determined as the simulation results of the above-mentioned grid data.

[0036] The simulation results can be used for statistical analysis to obtain the distribution maps of extreme water levels and extreme wave heights in different grid areas.

[0037] Step S105, extracting the hydrodynamic field data of the beach coastline area from the simulation results, and extracting the characteristic vector of the hydrodynamic field data by principal component analysis, identifying the target area from the hydrodynamic field data according to the characteristic vector, and then using the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach coastline and predict the evolution path of the beach coastline.

[0038] In this step, the hydrodynamic field data of the beach shoreline area is extracted from the simulation results, and the hydrodynamic field data is preprocessed to remove noise and outliers to obtain standardized data.

[0039] Then, the standardized data can be processed by principal component analysis to reduce the dimension, extract the main features of the hydrodynamic field, form the above-mentioned feature vector, and identify the target area from the feature vector.

[0040] For example, the hydrodynamic field is identified through a pre-trained support vector machine model to obtain the target area.

[0041] Furthermore, the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area are used to simulate the change process of the beach coastline and predict the beach coastline evolution path, including: Calculate the frequency distribution of the beach coastline according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area; Performing fitting processing on the frequency distribution to obtain a fitting model of the beach coastline, wherein the fitting model is used to characterize the random process of the beach coastline change; Generate a number of random samples using the fitted model through a Monte Carlo method; At least one beach shoreline evolution path is generated based on the random sample using the time scale.

[0042] For example, considering that shoreline changes may be affected by multiple factors and are usually not completely symmetrically distributed, it is possible to consider using lognormal distribution to fit the frequency distribution to better describe skewed data and avoid the unreasonable situation where shoreline changes are negative infinity.

[0043] Based on the fitting situation, the maximum likelihood estimation method can be used, and the statistical tools of MATLAB or Python can be used to estimate the lognormal distribution, and then the Monte Carlo method can be used to generate random samples, so as to generate at least one beach shoreline evolution path based on the random samples using a preset time scale (generally a long-term time scale, such as fifty years). These paths reflect various possible scenarios of shoreline evolution in the next 50 years under current climate conditions, and can be used in specific application scenarios such as risk assessment and planning and design of coastal protection projects. For example, if a path shows that the shoreline erosion exceeds 30 meters in 50 years, it can be considered that the area has a high risk of erosion and corresponding protective measures need to be taken.

[0044] In order to further improve the accuracy of the prediction, the short-term time scale evolution can be further considered on the basis of the long-term time scale. Generally speaking, the evolution of the short-term time scale is related to sediment transport and deposition.

[0045] For example, the use of the time scale to generate at least one beach shoreline evolution path based on the random sample includes: calculating the position and range of the target area according to the spatiotemporal distribution data of the wind field, the spatiotemporal distribution data of the flow field, and the spatiotemporal distribution data of the wave in the target area to obtain a boundary condition data set; inputting the boundary condition data set into a preset sediment movement model to calculate the sediment transport parameters and deposition process parameters of the target area to obtain the spatiotemporal variation characteristics of the sediment, and using the spatiotemporal variation characteristics of the sediment as the first shoreline response characteristics; obtaining the second shoreline response characteristics based on the time scale and the random sample; wherein the time scale corresponding to the second shoreline response characteristics is larger than the first shoreline response characteristics; based on the first shoreline response characteristics of the short-term time scale and the second shoreline response characteristics of the long-term time scale, at least one beach shoreline evolution path can be accurately generated to take into account the complex nonlinear relationship between dynamic processes of various scales and shoreline morphology, and to construct a unified prediction model framework from the short-term event scale to the long-term scale.

[0046] In a preferred embodiment, in order to facilitate the use of the results of the long-term evolution prediction method of the beach coastline under the influence of typhoons in this application to ensure that the accuracy of the prediction method of this application can be migrated to other application scenarios, the prediction results of the prediction method of this application can be used to train a large artificial intelligence model.

[0047] Exemplarily, a long short-term memory network LSTM is used as a basic model, and the beach shoreline long-term evolution prediction method further includes: Constructing an evolution data set according to the plurality of beach shoreline evolution paths; dividing the target area into shoreline units, and calculating the vulnerability of each shoreline unit according to the geological type, terrain slope and vegetation coverage of each shoreline unit; The preset long short-term memory network corresponding to each shoreline unit is trained respectively using the evolution data set; the training is evaluated using the vulnerability parameter, and the model structure and training parameters of each long short-term memory network are iteratively optimized respectively. When the performance parameters of the long short-term memory network meet the preset convergence requirements, the long short-term memory networks that meet the convergence requirements are weightedly fused according to the preset weights of each shoreline unit to obtain a shoreline prediction model.

[0048] This preferred implementation constructs an evolution data set and uses a shoreline prediction model to learn the beach shoreline evolution laws contained in the evolution data set, thereby extracting the prediction features of the prediction method of the present application. The shoreline prediction model can be used by other application scenarios to migrate the accuracy of the prediction method of the present application to other sea areas or other prediction scenarios, so as to achieve further utilization of the prediction results of the present application.

[0049] Accordingly, if Figure 2 As shown, the present invention also provides a long-term beach coastline evolution prediction system 200 under the influence of typhoons, including an acquisition module 201, a generation module 202, a division module 203, a simulation module 204 and a prediction module 205; wherein, The acquisition module 201 is used to acquire a preset probability distribution model, where the probability distribution model is used to describe the intensity and movement path of the typhoon; The generating module 202 is used to obtain historical typhoon data and generate multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model; The division module 203 is used to divide the initial area into a number of grid areas by using a nested grid technology; The simulation module 204 is used to perform simulation in each of the grid areas using the multiple sets of typhoon scenario data to obtain simulation results of each grid data, wherein the simulation results include wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; The prediction module 205 is used to extract the hydrodynamic field data of the beach coastline area from the simulation results, and extract the characteristic vector of the hydrodynamic field data through the principal component analysis method, identify the target area from the hydrodynamic field data according to the characteristic vector, and then use the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach coastline and predict the evolution path of the beach coastline.

[0050] As a preferred solution, the prediction module 205 uses the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach coastline and predict the beach coastline evolution path, including: The prediction module 205 calculates the frequency distribution of the beach shoreline according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area; Performing fitting processing on the frequency distribution to obtain a fitting model of the beach coastline, wherein the fitting model is used to characterize the random process of the beach coastline change; Generate a number of random samples using the fitted model through a Monte Carlo method; At least one beach shoreline evolution path is generated based on the random sample using the time scale.

[0051] As a preferred solution, the prediction module 205 generates at least one beach shoreline evolution path based on the random sample using the time scale, including: The prediction module 205 calculates the position and range of the target area according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area to obtain a boundary condition data set; Inputting the boundary condition data set into a preset sediment movement model, calculating sediment transport parameters and deposition process parameters in the target area, obtaining sediment temporal and spatial variation characteristics, and using the sediment temporal and spatial variation characteristics as the first shoreline response characteristics; Based on the time scale and the random sample, a second shoreline response characteristic is obtained; wherein the time scale corresponding to the second shoreline response characteristic is greater than that of the first shoreline response characteristic; At least one beach shoreline evolution path is generated based on the first shoreline response characteristic and the second shoreline response characteristic.

[0052] As a preferred solution, the generating module 202 obtains historical typhoon data, and generates multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model, including: The generating module 202 acquires the historical typhoon data, wherein the historical typhoon data includes the location data, wind speed data and air pressure data of the typhoon; The probability distribution model is used to obtain the correlation between the position data, wind speed data and air pressure data, thereby generating multiple sets of typhoon scenario data, wherein the typhoon scenario data includes parameter changes within the life cycle of a typhoon.

[0053] As a preferred solution, the typhoon scenario data includes the typhoon's wind stress, pressure gradient force and Coriolis force; The simulation module 204 uses the multiple sets of typhoon scenario data to perform simulation in each of the grid areas to obtain simulation results of each grid data, including: The simulation module 204 uses the multiple sets of typhoon scenario data to perform simulation in each of the grid areas, constructs a parameterized wind field model based on gradient wind balance and boundary layer theory, and obtains wind field spatiotemporal distribution data; Input the wind stress, pressure gradient force and Coriolis force into a preset FVCOM model, simulate the ocean current model in each grid area, and then obtain the spatiotemporal distribution data of the flow field; Inputting the plurality of sets of typhoon scenario data into a preset SWAN model to obtain wave spatiotemporal distribution data; The wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data and the wave spatiotemporal distribution data are coupled, and the coupling results are updated at preset time intervals to obtain simulation results of the grid data.

[0054] As a preferred solution, the beach shoreline long-term evolution prediction system 200 further includes a model building module, and the model building module is used to: Constructing an evolution data set according to the plurality of beach shoreline evolution paths; dividing the target area into shoreline units, and calculating the vulnerability of each shoreline unit according to the geological type, terrain slope and vegetation coverage of each shoreline unit; Using the evolution data set to train the preset long short-term memory network corresponding to each shoreline unit; The fragility parameters are used to iteratively optimize the model structure and training parameters of each long short-term memory network. When the performance parameters of the long short-term memory network meet the preset convergence requirements, the long short-term memory networks that meet the convergence requirements are weightedly fused according to the preset weights of each shoreline unit to obtain a shoreline prediction model.

[0055] Compared with the prior art, the present invention has the following beneficial effects: The present invention application provides a method and system for predicting the long-term evolution of a beach shoreline under the influence of a typhoon, the method comprising: obtaining a preset probability distribution model, the probability distribution model being used to describe the intensity and movement path of a typhoon; obtaining historical typhoon data, and generating multiple sets of typhoon scenario data based on the historical typhoon data and the probability distribution model; using a nested grid technology to divide an initial area into a plurality of grid areas; using the multiple sets of typhoon scenario data to perform simulations in each of the grid areas to obtain simulation results of each grid data, the simulation results including wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; extracting hydrodynamic field data of a beach shoreline area from the simulation results, and extracting characteristic vectors of the hydrodynamic field data through a principal component analysis method, identifying a target area from the hydrodynamic field data based on the characteristic vector, and then using the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data, and a preset time scale of the target area to simulate the change process of the beach shoreline and predict the evolution path of the beach shoreline. The present invention describes the intensity and movement path of a typhoon through a probability distribution model, and then generates multiple sets of typhoon scenario data in combination with historical typhoon data, and uses them for simulation in each grid area. The differences in spatial aspects between different grid areas, that is, the impact of the typhoon on different grids in the initial area, can be taken into account, effectively improving the prediction effect of the evolution of the beach coastline under the influence of the typhoon; in addition, the simulation results of the grid data of the present application include the spatiotemporal distribution data of the wind field, the spatiotemporal distribution data of the flow field, and the spatiotemporal distribution data of the wave. By extracting the hydrodynamic field data of the beach coastline area, the beach coastline area may contain the simulation results of one or more grids, which further improves the significance of the prediction method of the present application at the spatial level; furthermore, the characteristic vector of the hydrodynamic field data is extracted by the principal component analysis method to identify the target area, and the beach coastline area and its spatiotemporal distribution are locked by using the hydrodynamic field data and the characteristic vector, so as to simulate the evolution of the beach coastline, and effectively realize long-term and short-term multi-scale predictions through a preset time period, thereby ensuring the accuracy of the prediction method at different time scales.

[0056] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting the long-term evolution of beach shoreline under the influence of typhoon, characterized in that: include: Obtaining a preset probability distribution model, where the probability distribution model is used to describe the intensity and movement path of a typhoon; Acquire historical typhoon data, and generate multiple sets of typhoon scenario data based on the historical typhoon data and a probability distribution model; The nested grid technique is used to divide the initial area into several grid areas; Using the multiple sets of typhoon scenario data to perform simulation in each of the grid areas, obtaining simulation results of each grid data, wherein the simulation results include wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; The hydrodynamic field data of the beach shoreline area is extracted from the simulation results, and the characteristic vector of the hydrodynamic field data is extracted by principal component analysis. The target area is identified from the hydrodynamic field data according to the characteristic vector, and then the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area are used to simulate the change process of the beach shoreline and predict the evolution path of the beach shoreline.

2. The method for predicting the long-term evolution of beach shoreline under the influence of typhoon as claimed in claim 1, characterized in that: The method utilizes the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach shoreline and predict the beach shoreline evolution path, including: Calculate the frequency distribution of the beach coastline according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area; Performing fitting processing on the frequency distribution to obtain a fitting model of the beach coastline, wherein the fitting model is used to characterize the random process of the beach coastline change; Generate a number of random samples using the fitted model through a Monte Carlo method; At least one beach shoreline evolution path is generated based on the random sample using the time scale.

3. The method for predicting the long-term evolution of beach shoreline under the influence of typhoon as claimed in claim 2, characterized in that: The step of utilizing the time scale to generate at least one beach shoreline evolution path based on the random sample comprises: Calculate the position and range of the target area according to the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data of the target area to obtain a boundary condition data set; Inputting the boundary condition data set into a preset sediment movement model, calculating the sediment transport parameters and deposition process parameters of the target area, obtaining the sediment temporal and spatial variation characteristics, and using the sediment temporal and spatial variation characteristics as the first shoreline response characteristics; Based on the time scale and the random sample, a second shoreline response characteristic is obtained; wherein the time scale corresponding to the second shoreline response characteristic is greater than that of the first shoreline response characteristic; At least one beach shoreline evolution path is generated based on the first shoreline response characteristic and the second shoreline response characteristic.

4. The method for predicting the long-term evolution of beach shoreline under the influence of typhoon as claimed in claim 1, characterized in that: The acquiring of historical typhoon data and generating multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model include: Acquire the historical typhoon data, wherein the historical typhoon data includes typhoon location data, wind speed data, and air pressure data; The probability distribution model is used to obtain the correlation between the position data, wind speed data and air pressure data, thereby generating multiple sets of typhoon scenario data, wherein the typhoon scenario data includes parameter changes within the life cycle of a typhoon.

5. The method for predicting the long-term evolution of beach shoreline under the influence of typhoon as claimed in claim 1, characterized in that: The typhoon scenario data include the wind stress, pressure gradient force and Coriolis force of the typhoon; The using the multiple groups of typhoon scenario data to simulate in each of the grid areas to obtain simulation results of each grid data includes: Using the multiple sets of typhoon scenario data to perform simulations in each of the grid areas, constructing a parameterized wind field model based on gradient wind balance and boundary layer theory, and obtaining wind field spatiotemporal distribution data; Input the wind stress, pressure gradient force and Coriolis force into a preset FVCOM model, simulate the ocean current model in each grid area, and then obtain the spatiotemporal distribution data of the flow field; Inputting the plurality of sets of typhoon scenario data into a preset SWAN model to obtain wave spatiotemporal distribution data; The wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data and the wave spatiotemporal distribution data are coupled, and the coupling results are updated at preset time intervals to obtain simulation results of the grid data.

6. A long-term beach shoreline evolution prediction system under the influence of typhoons, characterized in that: It includes acquisition module, generation module, division module, simulation module and prediction module; among them, The acquisition module is used to acquire a preset probability distribution model, where the probability distribution model is used to describe the intensity and movement path of the typhoon; The generating module is used to obtain historical typhoon data and generate multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model; The division module is used to divide the initial area into a number of grid areas by using a nested grid technology; The simulation module is used to use the multiple groups of typhoon scenario data to perform simulation in each of the grid areas to obtain simulation results of each grid data, wherein the simulation results include wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, and wave spatiotemporal distribution data; The prediction module is used to extract the hydrodynamic field data of the beach coastline area from the simulation results, and extract the characteristic vector of the hydrodynamic field data through the principal component analysis method, identify the target area from the hydrodynamic field data according to the characteristic vector, and then use the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach coastline and predict the evolution path of the beach coastline.

7. The long-term evolution prediction system of beach shoreline under typhoon influence as claimed in claim 6, characterized in that: The prediction module uses the wind field spatiotemporal distribution data, flow field spatiotemporal distribution data, wave spatiotemporal distribution data and a preset time scale of the target area to simulate the change process of the beach coastline and predict the beach coastline evolution path, including: The prediction module calculates the frequency distribution of the beach shoreline according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area; Performing fitting processing on the frequency distribution to obtain a fitting model of the beach coastline, wherein the fitting model is used to characterize the random process of the beach coastline change; Generate a number of random samples using the fitted model through a Monte Carlo method; At least one beach shoreline evolution path is generated based on the random sample using the time scale.

8. The long-term evolution prediction system of beach shoreline under typhoon influence as claimed in claim 7, characterized in that: The prediction module generates at least one beach shoreline evolution path based on the random sample using the time scale, including: The prediction module calculates the position and range of the target area according to the wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data, and the wave spatiotemporal distribution data of the target area to obtain a boundary condition data set; Inputting the boundary condition data set into a preset sediment movement model, calculating the sediment transport parameters and deposition process parameters of the target area, obtaining the sediment temporal and spatial variation characteristics, and using the sediment temporal and spatial variation characteristics as the first shoreline response characteristics; Based on the time scale and the random sample, a second shoreline response characteristic is obtained; wherein the time scale corresponding to the second shoreline response characteristic is greater than that of the first shoreline response characteristic; At least one beach shoreline evolution path is generated based on the first shoreline response characteristic and the second shoreline response characteristic.

9. The long-term evolution prediction system of beach shoreline under typhoon influence as claimed in claim 6, characterized in that: The generation module acquires historical typhoon data, and generates multiple sets of typhoon scenario data according to the historical typhoon data and the probability distribution model, including: The generating module acquires the historical typhoon data, wherein the historical typhoon data includes the location data, wind speed data and air pressure data of the typhoon; The probability distribution model is used to obtain the correlation between the position data, wind speed data and air pressure data, thereby generating multiple sets of typhoon scenario data, wherein the typhoon scenario data includes parameter changes within the life cycle of a typhoon.

10. The long-term evolution prediction system of beach shoreline under typhoon influence as claimed in claim 6, characterized in that: The typhoon scenario data include the wind stress, pressure gradient force and Coriolis force of the typhoon; The simulation module uses the multiple sets of typhoon scenario data to perform simulation in each of the grid areas to obtain simulation results of each grid data, including: The simulation module uses the multiple sets of typhoon scenario data to perform simulations in each of the grid areas, constructs a parameterized wind field model based on gradient wind balance and boundary layer theory, and obtains wind field spatiotemporal distribution data; Input the wind stress, pressure gradient force and Coriolis force into a preset FVCOM model, simulate the ocean current model in each grid area, and then obtain the spatiotemporal distribution data of the flow field; Inputting the plurality of sets of typhoon scenario data into a preset SWAN model to obtain wave spatiotemporal distribution data; The wind field spatiotemporal distribution data, the flow field spatiotemporal distribution data and the wave spatiotemporal distribution data are coupled, and the coupling results are updated at preset time intervals to obtain simulation results of the grid data.

Images