Deep learning-based digital twinborn rehearsal submerging disaster assessment method, device and program product

Abstract

The invention provides a deep learning-based digital twinborn rehearsal submerging disaster assessment method and device and a program product. The digital twinborn rehearsal submerging disaster assessment method comprises the following steps of collecting basic geographic data, natural resource survey data, geological data, meteorological data, water conservancy basic data and rainwater condition monitoring data; training a convolutional neural network deep learning model by using basic geographic data, natural resource survey data, geological data, meteorological data, water conservancy basic data and rainwater condition monitoring data; creating a topographic three-dimensional model according to the image data and the topographic data, extracting key features from the image data and the topographic map data, and constructing a digital twin base three-dimensional model based on the extracted key features and the topographic three-dimensional model; performing flooding disaster simulation and rehearsal by using a hydrodynamic model, a digital twin base three-dimensional model and a trained convolutional neural network deep learning model; performing evaluation based on simulation and prediction results; and carrying out visual display on the simulation result and the evaluation data.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster assessment, and in particular to a method, device and program product for digital twin pre-production flooding disaster assessment based on deep learning. Background Art

[0002] Flood disasters can destroy buildings and crops on a large scale and pollute the environment on a large scale. They are one of the major natural disasters that have been experienced since ancient times. At present, the prevention and control of flood disasters mainly rely on meteorological information monitoring, predicting the arrival of flood disasters, and proposing targeted prevention and control measures. This method mainly has the following problems: lack of predictive assessment of the development trend of flood disasters, which makes the practicality of prevention and control measures poor.

[0003] CN115146469 B proposes a flood disaster simulation method and system based on a digital twin simulation platform, which solves the technical problem that the prior art lacks an evaluation scheme for the development trend of flood disasters, resulting in unsatisfactory flood disaster prevention and control effects.

[0004] CN114444791A proposes a remote sensing monitoring and assessment method for flood disasters based on machine learning. It uses the random forest algorithm in machine learning to predict the possible flooding range and assess the disaster situation, which can provide important data and theoretical support for flood control decision-making and disaster relief work.

[0005] It can be seen that the existing technology is basically based on a single technology to assess disasters, using the random forest algorithm in machine learning to predict the possible flooding range and disaster assessment, or using decision training trees to analyze and calculate disasters, etc., and it is impossible to simulate and rehearse various situations when disasters occur.

[0006] In order to solve the above problems, people have been seeking an ideal technical solution. Summary of the invention

[0007] Based on this, it is necessary to provide a digital twin pre-simulation flooding disaster assessment method, device and program product based on deep learning to address the above technical problems.

[0008] In order to achieve the above-mentioned object, the first aspect of the present invention provides a digital twin preview flooding disaster assessment method based on deep learning, comprising the following steps: Collect basic geographic data, natural resource survey data, geological data, meteorological data, basic water conservancy data, and rain and water monitoring data, wherein the basic geographic data at least includes administrative division data, image data, DEM data, and topographic map data; the natural resource survey data at least includes land use status data, geographic national conditions census data, and natural resource registration data; the geological data at least includes remote sensing data and hydrological data; the basic water conservancy data at least includes water system data and river section data; the rain and water monitoring data at least includes real-time and historical monitoring data of hydrological stations, real-time and historical monitoring data of rainfall stations, and real-time and historical monitoring data of flow stations; The basic geographic data, the natural resources survey data, the geological data, the meteorological data, the basic water conservancy data, and the rain and water monitoring data are used as input to train a convolutional neural network deep learning model, wherein the output of the convolutional neural network deep learning model is flood coverage data; Create a terrain 3D model based on the image data and terrain data, extract key features from the image data and terrain map data, and build a digital twin base 3D model based on the extracted key features and the terrain 3D model; Use hydrodynamic models, digital twin base 3D models, and trained convolutional neural network deep learning models to simulate and rehearse flooding disasters; Based on the simulation and rehearsal results, the flood impact disaster data is evaluated and counted; Visualize simulation results and evaluation data.

[0009] In order to achieve the above-mentioned object, the second aspect of the present invention provides a digital twin preview flooding disaster assessment device based on deep learning, comprising: The data collection module is used to collect basic geographic data, natural resource survey data, geological data, meteorological data, basic water conservancy data, and rain and water monitoring data. The basic geographic data at least includes administrative division data, image data, DEM data, and topographic map data; the natural resource survey data at least includes land use status data, geographic national conditions census data, and natural resource registration data; the geological data at least includes remote sensing data and hydrological data; the basic water conservancy data at least includes water system data and river section data; the rain and water monitoring data at least includes real-time and historical monitoring data of hydrological stations, real-time and historical monitoring data of rainfall stations, and real-time and historical monitoring data of flow stations; A model training module, which uses the basic geographic data, the natural resources survey data, the geological data, the meteorological data, the basic water conservancy data, and the rain and water monitoring data as input to train a convolutional neural network deep learning model, wherein the output of the convolutional neural network deep learning model is flood coverage data; A digital twin base 3D model construction module is used to create a terrain 3D model based on image data and terrain data, extract key features from the image data and terrain map data, and construct a digital twin base 3D model based on the extracted key features and the terrain 3D model; The simulation rehearsal module is used to simulate and rehearse flooding disasters using the hydrodynamic model, the three-dimensional model of the digital twin base, the trained convolutional neural network deep learning model, and the real-time monitoring data of the hydrological station, the real-time monitoring data of the rainfall station, and the real-time monitoring data of the flow station; The disaster assessment module is used to evaluate and count flood disaster data based on simulation and prediction results; The display module is used to visualize the simulation results and evaluation data.

[0010] In order to achieve the above-mentioned purpose, the third aspect of the present invention provides a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store computer programs; the processor is used to implement the digital twin pre-production flooding disaster assessment method based on deep learning as mentioned above when executing the program stored in the memory.

[0011] In order to achieve the above-mentioned objectives, the fourth aspect of the present invention provides a readable storage medium having instructions stored thereon, which, when executed by one or more processors, enables the processors to execute the digital twin pre-rehearsal flooding disaster assessment method based on deep learning as described above.

[0012] In order to achieve the above-mentioned objectives, the fifth aspect of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned deep learning-based digital twin pre-rehearsal flooding disaster assessment method.

[0013] The beneficial effects of the present invention are: The present invention uses a convolutional neural network deep learning model to analyze data and predict the possibility and potential impact of disasters. It can quickly simulate the evolution of flood disasters and have a good evaluation of the simulation effect of the flood range and disaster data. By using the virtual reality technology of digital twins, the evolution of floods, the scope of flood inundation, the evaluation and statistics of flood disaster data, the visual display of disaster impacts, risk areas, transfer routes, etc. can be viewed on a three-dimensional model, providing managers with intuitive decision support; Combining deep learning algorithms and advanced digital twin technology, the Unet neural network model is used to extract the flooded area in the three-dimensional model of the digital twin base to assess the disaster, which has certain practicality and innovation in the preparedness, efficiency, accuracy and visualization of the assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flow chart of the digital twin preview flooding disaster assessment method of the present invention; Figure 2 is a schematic diagram of the disaster assessment index of the present invention; Figure 3 It is a structural schematic diagram of a digital twin preview flooding disaster assessment device of the present invention; Figure 4 It is a schematic diagram of the structure of the computer device of the present invention. DETAILED DESCRIPTION

[0015] Digital Elevation Model (DEM) is a physical ground model that represents ground elevation in the form of an ordered array of numerical values.

[0016] The technical solution of the present invention is further described in detail below through specific implementation methods.

[0017] Example 1 This embodiment provides a digital twin pre-production flood disaster assessment method based on deep learning, such as Figure 1 As shown, the following steps are included: Step 1, collecting basic geographic data, natural resource survey data, geological data, meteorological data, basic water conservancy data, and rain and water monitoring data, wherein the basic geographic data at least includes administrative division data, image data, DEM data, and topographic map data; the natural resource survey data at least includes land use status data, geographic national conditions census data, and natural resource registration data; the geological data at least includes remote sensing data and hydrological data; the basic water conservancy data at least includes water system data and river section data; the rain and water monitoring data at least includes historical monitoring data of hydrological stations, historical monitoring data of rainfall stations, and historical monitoring data of flow stations; It should be noted that after obtaining these data, the data needs to be cleaned, denoised, normalized, standardized and integrated for subsequent training of the convolutional neural network deep learning model and as input parameters for the three-dimensional model of the digital twin base.

[0018] Step 2: Use the basic geographic data, the natural resource survey data, the geological data, the meteorological data, the basic water conservancy data, and the rainfall monitoring data as input to train a convolutional neural network deep learning model, wherein the output of the convolutional neural network deep learning model is flood coverage data.

[0019] In the specific implementation, before training the convolutional neural network deep learning model, SPSS statistical analysis is used to analyze the linearity between various types of data and remove data with strong correlation; the feature selection method is used to select data with a great influence on the flood coverage data as input variables, and the flood coverage data is used as the output variable to train the convolutional neural network deep learning model to simulate the probability of flood occurrence in each grid; classification is carried out according to the simulated flood probability results, and areas with a higher probability of flood occurrence are screened and clustered to determine the scope of flood occurrence.

[0020] Step 3: Create a terrain three-dimensional model based on the image data and terrain data, extract key features from the image data and terrain map data, and build a digital twin base three-dimensional model based on the extracted key features and the terrain three-dimensional model.

[0021] During the specific implementation, Maya tools were selected to construct a three-dimensional model of the digital twin base.

[0022] Step 4: Collect real-time monitoring data from hydrological stations, rainfall stations, and flow stations, and use the hydrodynamic model, the digital twin base 3D model, and the trained convolutional neural network deep learning model to simulate and rehearse flooding disasters.

[0023] Specifically, the hydrodynamic model is used to simulate physical information such as water velocity, flow, elevation direction, etc. In terms of flood disasters, common hydrodynamic models include one-dimensional river network models, two-dimensional shallow water models, and one- and two-dimensional coupled hydrodynamic models. In specific implementation, corresponding selection can be made according to needs.

[0024] Specifically, the hydrodynamic model, the digital twin base 3D model, and the trained convolutional neural network deep learning model are used to simulate and rehearse flooding disasters, including: Construct a hydrodynamic model including real-time monitoring data from hydrological stations, rainfall stations, and flow stations; Collect real-time monitoring data from hydrological stations, rainfall stations, and flow stations, and use the convolutional neural network deep learning model to simulate and obtain the spatiotemporal evolution of flood inundation; Demonstrate the spatiotemporal evolution of flood inundation on a 3D model of the digital twin base.

[0025] Furthermore, by inputting different parameters and conditions, such as different rainfall amounts, rainfall times, rainfall intervals, data sources, future times and other parameters and other conditions, the convolutional neural network deep learning model can be used to predict the time, intensity and impact range of disasters.

[0026] Furthermore, disaster drills are conducted based on the disaster simulation results to simulate the flood evolution process, inundated areas, inundation changes, water level rise, personnel evacuation routes, rescue material deployment and disaster impact range, etc., to ensure a rapid response when a real disaster occurs.

[0027] Furthermore, based on the simulation and prediction results, the trained convolutional neural network deep learning model can be evaluated using the validation set and the test set, and the performance indicators of the convolutional neural network deep learning model on new data, such as accuracy, recall rate, and F1 value, can be calculated.

[0028] Step 5: Based on the simulation and rehearsal results, evaluate and compile the flood impact disaster data.

[0029] Specifically, the Unet neural network model is used to extract the flood inundated area in the three-dimensional model of the digital twin base; Estimate the water depth of flooded areas based on DEM data; The flood disaster data are evaluated and counted based on the water depth of the flood-inundated area, disaster statistical indicators, and economic loss assessment indicators.

[0030] Specifically, when extracting the scope of the flood inundation area, first select the samples of the flood water body, iteratively train the model based on the selected sample data set, and continuously optimize the parameters of the model through forward propagation and back propagation algorithms. The data is input into the model through forward propagation, and the prediction results of the model are obtained through calculation; the back propagation is to calculate the loss function based on the difference between the prediction result and the true label, and update the parameters of the model through the gradient descent algorithm. The value of the loss function is gradually reduced through the loss function and optimization algorithm.

[0031] Specifically, the Unet network is used to classify the flood images in the three-dimensional model of the digital twin base into water bodies and non-water bodies. The network consists of two parts: a downsampling part and an upsampling part. The input image is a flood image in the three-dimensional model of the digital twin base, the training image size is 256×256 pixels, and the output image is a water body and non-water body annotation map. The downsampling part is mainly composed of two 3×3 convolutional layers and two ReLU layers. The output result of each downsampling part is subjected to a maximum pooling operation with a step size of 2×2 and then transmitted to the next downsampling part. The upsampling part is composed of a structure symmetrical to the encoding part, except that the result in the encoding part must be connected to the decoding part of the same level to increase the image size. The operations of different decoding parts are processed through deconvolution operations to increase the image size, and finally obtain high-dimensional features of the same size as the original image. The high-dimensional features undergo a 1×1 convolution operation to obtain dimensional features corresponding to the number of categories, and finally undergo a Softmax operation to output images as water body and non-water body annotation maps.

[0032] like Figure 2 As shown, the disaster statistical indicators include flooded area indicators, disaster-affected population indicators, affected GDP indicators and flooded road length indicators; The economic loss assessment indicators include residential housing loss indicators, household property loss indicators, agricultural loss indicators, road loss indicators and industrial loss indicators.

[0033] This embodiment gives the meaning of the disaster-affected population index. Specifically, the residential area method is used to perform spatial analysis on population statistics. It is considered that the population is discretely distributed in the residential areas of the administrative region, and the population on each residential area is a uniformly distributed variable. The population density is used d i，j To express it, the calculation of the disaster-affected population index is as follows: , in, A i，j For the i Administrative division j The flooded area of ​​residential areas d i，j For the i Administrative division j The population density of a residential area.

[0034] The economic loss assessment indicators include residential housing loss indicators, household property loss indicators, agricultural loss indicators, road loss indicators and industrial loss indicators.

[0035] When assessing economic losses, the various economic loss indicators are assessed based on disaster statistics on the flooded area, length and number of flooded people, combined with the distribution of socio-economic data.

[0036] In specific implementation, the pre-disaster value of various disaster-bearing bodies at different water depth levels is determined based on the social and economic distribution information and disaster statistical information; combined with the corresponding water depth-loss rate relationship, the classified economic loss is estimated, and the formula is as follows: , Where: R i For the i Total value of various types of losses in each administrative division (yuan); R ij is the first administrative division in the i-th administrative division j Class loss value; n is the number of administrative divisions; m is the number of loss types.

[0037] It can be understood that the water depth-loss rate relationship can also be set accordingly according to the characteristics of different regions. The following table is an example of the water depth-loss rate relationship.

[0038]

[0039] The disaster statistics calculated based on the above example are shown in the following table:

[0040] Step 6: Visualize the simulation results and evaluation data.

[0041] During the specific implementation, the simulation results and evaluation data will be displayed through GIS technology, 3D visualization technology, digital twin technology and other means to show the evolution of the flood, the progress of water level changes, the inundated areas, risk areas, resettlement areas, transfer routes, flooded areas, peak water levels, peak times, the start and end times of the flood, duration and other statistical data on a water conservancy map, visually displaying the possible impact of the disaster and providing interactive query and analysis.

[0042] It is understandable that during the disaster assessment process, real-time hydrological monitoring data is also used to dynamically adjust the digital twin base three-dimensional model and deep learning model, calibrate the model, and improve the real-time and accuracy of disaster assessment.

[0043] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0044] Example 2 Based on the same inventive concept, the embodiment of the present application also provides a deep learning-based digital twin pre-play flooding disaster assessment device for implementing the deep learning-based digital twin pre-play flooding disaster assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more deep learning-based digital twin pre-play flooding disaster assessment device embodiments provided below can refer to the limitations of the deep learning-based digital twin pre-play flooding disaster assessment method above, and will not be repeated here.

[0045] The digital twin pre-production flood disaster assessment device based on deep learning is as follows: Figure 3 As shown, including: The data collection module is used to collect basic geographic data, natural resource survey data, geological data, meteorological data, basic water conservancy data, and rain and water monitoring data. The basic geographic data at least includes administrative division data, image data, DEM data, and topographic map data; the natural resource survey data at least includes land use status data, geographic national conditions census data, and natural resource registration data; the geological data at least includes remote sensing data and hydrological data; the basic water conservancy data at least includes water system data and river section data; the rain and water monitoring data at least includes real-time and historical monitoring data of hydrological stations, real-time and historical monitoring data of rainfall stations, and real-time and historical monitoring data of flow stations; A model training module, which uses the basic geographic data, the natural resources survey data, the geological data, the meteorological data, the basic water conservancy data, and the rain and water monitoring data as input to train a convolutional neural network deep learning model, wherein the output of the convolutional neural network deep learning model is flood coverage data; A digital twin base 3D model construction module is used to create a terrain 3D model based on image data and terrain data, extract key features from the image data and terrain map data, and construct a digital twin base 3D model based on the extracted key features and the terrain 3D model; The simulation rehearsal module is used to simulate and rehearse flooding disasters using the hydrodynamic model, the three-dimensional model of the digital twin base, the trained convolutional neural network deep learning model, and the real-time monitoring data of the hydrological station, the real-time monitoring data of the rainfall station, and the real-time monitoring data of the flow station; The disaster assessment module is used to evaluate and count flood disaster data based on simulation and prediction results; The display module is used to visualize the simulation results and evaluation data.

[0046] Example 3 This embodiment provides a computer device, which can be a terminal, and its internal structure diagram can be as follows: Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a digital twin pre-play flooding disaster assessment method based on deep learning is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0047] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0048] Example 4 Based on the above embodiments, this embodiment provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, a digital twin pre-rehearsal flooding disaster assessment method based on deep learning described in Example 1 is implemented.

[0049] Example 5 Based on the above embodiments, this embodiment provides a computer program product, including a computer program. When the computer program is executed by a processor, the digital twin pre-production flooding disaster assessment method based on deep learning described in Example 1 is visually demonstrated.

[0050] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0051] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0052] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or some technical features can be replaced by equivalents without departing from the spirit of the technical solution of the present invention, which should be included in the scope of the technical solution for protection of the present invention.

Claims

1. A digital twin pre-production flood disaster assessment method based on deep learning, characterized in that: The following steps are involved: Collect basic geographic data, natural resource survey data, geological data, meteorological data, basic water conservancy data, and rain and water monitoring data, wherein the basic geographic data at least includes administrative division data, image data, DEM data, and topographic map data; the natural resource survey data at least includes land use status data, geographic national conditions census data, and natural resource registration data; the geological data at least includes remote sensing data and hydrological data; the basic water conservancy data at least includes water system data and river section data; the rain and water monitoring data at least includes historical monitoring data of hydrological stations, historical monitoring data of rainfall stations, and historical monitoring data of flow stations; The basic geographic data, the natural resources survey data, the geological data, the meteorological data, the basic water conservancy data, and the rain and water monitoring data are used as input to train a convolutional neural network deep learning model, wherein the output of the convolutional neural network deep learning model is flood coverage data; Create a terrain 3D model based on the image data and terrain data, extract key features from the image data and terrain map data, and build a digital twin base 3D model based on the extracted key features and the terrain 3D model; Collect real-time monitoring data from hydrological stations, rainfall stations, and flow stations, and use hydrodynamic models, digital twin base 3D models, and trained convolutional neural network deep learning models to simulate and rehearse flooding disasters; Based on the simulation and rehearsal results, the flood impact disaster data is evaluated and counted; Visualize simulation results and evaluation data.

2. According to the deep learning-based digital twin pre-production flooding disaster assessment method of claim 1, it is characterized in that: The basic geographic data, the natural resources survey data, the geological data, the meteorological data, the basic water conservancy data, and the rain and water monitoring data are used as input to train a convolutional neural network deep learning model, including: SPSS statistical analysis was used to analyze the linearity between various types of data and remove data with strong correlation; The feature selection method is used to select data with great influence on flood coverage data as input variables, and the flood coverage data is used as the output variable to train the convolutional neural network deep learning model to simulate the probability of flood occurrence in each grid; According to the simulated flood probability results, classification is carried out, areas with higher flood probability are screened and clustered, and the scope of flood occurrence is determined.

3. A method for evaluating flood disasters using a digital twin based on deep learning according to claim 1 or 2, characterized in that: Use the hydrodynamic model, the digital twin base 3D model, and the trained convolutional neural network deep learning model to simulate and rehearse flooding disasters, including: Construct a hydrodynamic model including real-time monitoring data from hydrological stations, rainfall stations, and flow stations; Collect real-time monitoring data from hydrological stations, rainfall stations, and flow stations, and use the convolutional neural network deep learning model to simulate and obtain the spatiotemporal evolution of flood inundation; Demonstrate the spatiotemporal evolution of flood inundation on a 3D model of the digital twin base.

4. According to the deep learning-based digital twin pre-production flooding disaster assessment method of claim 3, it is characterized in that: Based on the simulation and rehearsal results, the flood disaster data are evaluated and statistically analyzed, including: The Unet neural network model is used to extract the flooded area in the 3D model of the digital twin base. Estimate the water depth of flooded areas based on DEM data; The flood disaster data are evaluated and counted based on the water depth of the flood-inundated area, disaster statistical indicators, and economic loss assessment indicators.

5. According to the deep learning-based digital twin pre-production flooding disaster assessment method of claim 4, it is characterized in that: The disaster statistical indicators include the flooded area indicator, the affected population indicator, the affected GDP indicator and the flooded road length indicator; The economic loss assessment indicators include residential housing loss indicators, household property loss indicators, agricultural loss indicators, road loss indicators and industrial loss indicators.

6. A digital twin pre-rehearsal flood disaster assessment device based on deep learning, characterized in that: The data collection module is used to collect basic geographic data, natural resource survey data, geological data, meteorological data, basic water conservancy data, and rain and water monitoring data. The basic geographic data at least includes administrative division data, image data, DEM data, and topographic map data; the natural resource survey data at least includes land use status data, geographic national conditions census data, and natural resource registration data; the geological data at least includes remote sensing data and hydrological data; the basic water conservancy data at least includes water system data and river section data; the rain and water monitoring data at least includes real-time and historical monitoring data of hydrological stations, real-time and historical monitoring data of rainfall stations, and real-time and historical monitoring data of flow stations; A model training module, which uses the basic geographic data, the natural resources survey data, the geological data, the meteorological data, the basic water conservancy data, and the rain and water monitoring data as input to train a convolutional neural network deep learning model, wherein the output of the convolutional neural network deep learning model is flood coverage data; A digital twin base 3D model construction module is used to create a terrain 3D model based on image data and terrain data, extract key features from the image data and terrain map data, and construct a digital twin base 3D model based on the extracted key features and the terrain 3D model; The simulation rehearsal module is used to simulate and rehearse flooding disasters using the hydrodynamic model, the three-dimensional model of the digital twin base, the trained convolutional neural network deep learning model, and the real-time monitoring data of the hydrological station, the real-time monitoring data of the rainfall station, and the real-time monitoring data of the flow station; Conduct flood disaster simulations and rehearsals; The disaster assessment module is used to evaluate and count flood disaster data based on simulation and prediction results; The display module is used to visualize the simulation results and evaluation data.

7. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the deep learning-based digital twin preview flooding disaster assessment method as described in any one of claims 1 to 5 when executing the program stored in the memory.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the deep learning-based digital twin pre-production flooding disaster assessment method according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the deep learning-based digital twin pre-production flooding disaster assessment method described in any one of claims 1 to 5.

Images