Flood simulation and disaster prediction method and device

Abstract

The embodiment of the specification provides a water disaster simulation and disaster situation prediction method and device, the method comprises the following steps: acquiring initial scene data, determining a station construction model based on the initial scene data; acquiring rainfall parameter information, determining rainstorm situation data based on the rainfall parameter information and a rainstorm intensity formula; designing a water disaster evolution model based on the principle of cellular automata, and combining the rainstorm situation data and the station construction model to perform evolution simulation of underground station construction water disaster, and determining disaster situation data. Therefore, before the disaster occurs, a variety of rainstorm situations can be simulated to predict the damage of the underground station construction site caused by water disaster under different situations, so as to formulate a suitable disaster emergency plan and take corresponding preventive measures to reduce economic losses and casualties.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of data analysis technology, and in particular to methods for flood simulation and disaster prediction. Background Technology

[0002] In the face of extreme torrential rain, conventional knowledge and experience in protecting underground railway station construction sites may be inadequate. Conducting simulations and verifications using digital methods beforehand is of significant practical importance for disaster emergency prevention. Current research on urban flooding largely focuses on large-scale, city-level studies, making it difficult to simulate small-scale engineering-level flooding scenarios like those at underground railway station construction sites. Simulation methods suitable for small to medium scales are still under development, requiring large computational loads and high precision, and are difficult to integrate with the geographical environment, resulting in insufficient detail in simulating flooding in construction pits.

[0003] Visualization is the theory, method, and technology that uses computer graphics and image processing techniques to convert data into graphics or images for display on a screen, followed by interactive processing. Currently, conventional narrative visualization methods are insufficient for representing complex geographical events such as floods in underground stations induced by rainstorms. Most methods suffer from two-dimensional and static limitations, making it difficult to conduct visualization research on three-dimensional dynamic scenes and present geographical events within three-dimensional scenes. Summary of the Invention

[0004] In view of this, embodiments of this specification provide methods for flood simulation and disaster prediction. One or more embodiments of this specification also relate to a flood simulation and disaster prediction device, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0005] According to a first aspect of the embodiments of this specification, a method for flood simulation and disaster prediction is provided, including:

[0006] Acquire initial scene data and determine the station construction model based on the initial scene data;

[0007] Obtain rainfall parameter information, and determine rainstorm scenario data based on rainfall parameter information and rainstorm intensity formula;

[0008] A flood evolution model was designed based on the principle of cellular automata, and the evolution of floods during underground station construction was simulated by combining rainstorm scenario data with a station construction model to determine the disaster data.

[0009] Obtain rainfall parameter information, and determine rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula, including:

[0010] Obtain parameters such as the return period of the rainstorm, the duration of rainfall, and the rainfall intensity.

[0011] Based on the rainstorm return period parameter, rainfall duration parameter, and rainfall intensity parameter, rainstorm scenario data are determined using the rainstorm intensity formula.

[0012] The formula for rainstorm intensity includes:

[0013] 50-year return period rainstorm intensity:

[0014]

[0015] Intensity of a once-in-100-year rainstorm:

[0016]

[0017] Intensity of a 1000-year rainstorm:

[0018]

[0019] Where A, B, C, and n are local climate condition parameters, which are set differently for different regions.

[0020] In one possible implementation, initial scene data is acquired, and a station construction model is determined based on the initial scene data, including:

[0021] Acquire DEM data, remote sensing image data, and BIM data, and determine the station construction model based on the DEM data, remote sensing image data, and BIM data.

[0022] In one possible implementation, rainstorm scenario data is determined using a rainstorm intensity formula based on rainstorm return period parameters, rainfall duration parameters, and rainfall intensity parameters, including:

[0023] Based on the return period parameters, rainfall duration parameters, and rainfall intensity parameters of the rainstorm, the rainstorm intensity and rainstorm pattern of at least one period are determined by the rainstorm intensity formula.

[0024] Identify surface runoff obstruction factors, revise the station construction model based on these factors, and determine the catchment area;

[0025] Rainfall scenario data are determined based on rainfall intensity, rainfall pattern, and catchment area.

[0026] In one possible implementation, a flood evolution model is designed based on the principle of cellular automata, and the evolution of floods during underground station construction is simulated by combining rainstorm scenario data with a station construction model to determine disaster data, including:

[0027] A physical model was constructed based on 3D printing technology and a station construction model, and a fluid physics field model was established based on the physical model.

[0028] Determine the initial water volume in the foundation pit based on heavy rainfall scenario data;

[0029] Based on the fluid physics field model and the principle of cellular automata, the initial water volume in the foundation pit was adjusted to determine the disaster data.

[0030] One possible implementation also includes:

[0031] Establish a disaster factor table, analyze the disaster factor table, and determine the disaster situation analysis diagram;

[0032] The rainfall situation is displayed using a disaster situation analysis map and a particle system.

[0033] One possible implementation also includes:

[0034] Determine spatial and temporal semantic information based on the disaster situation map;

[0035] Based on spatial semantic information and initial scene data, a fusion model is performed to determine the basic scene;

[0036] Scenario demonstrations are based on temporal semantic information and basic scenarios.

[0037] According to a second aspect of the embodiments of this specification, a flood simulation and disaster prediction device is provided, comprising:

[0038] The model determination module is configured to acquire initial scene data and determine the station construction model based on the initial scene data.

[0039] The data determination module is configured to acquire rainfall parameter information and determine rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula.

[0040] The scenario simulation module is configured to design a flood evolution model based on the principle of cellular automata and combine rainstorm scenario data with the station construction model to simulate the evolution of floods during underground station construction and determine disaster data.

[0041] Obtain rainfall parameter information, and determine rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula, including:

[0042] Obtain parameters such as the return period of the rainstorm, the duration of rainfall, and the rainfall intensity.

[0043] Based on the rainstorm return period parameter, rainfall duration parameter, and rainfall intensity parameter, rainstorm scenario data are determined using the rainstorm intensity formula.

[0044] The formula for rainstorm intensity includes:

[0045] 50-year return period rainstorm intensity:

[0046]

[0047] Intensity of a once-in-100-year rainstorm:

[0048]

[0049] Intensity of a 1000-year rainstorm:

[0050]

[0051] Where A, B, C, and n are local climate condition parameters, which are set differently for different regions.

[0052] According to a third aspect of the embodiments of this specification, a computing device is provided, comprising:

[0053] Memory and processor;

[0054] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the above-mentioned flood simulation and disaster prediction method.

[0055] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the above-described flood simulation and disaster prediction method.

[0056] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described flood simulation and disaster prediction method.

[0057] This specification provides a method and apparatus for flood simulation and disaster prediction. The method includes: acquiring initial scenario data; determining a station construction model based on the initial scenario data; acquiring rainfall parameter information; determining rainstorm scenario data based on the rainfall parameter information and a rainstorm intensity formula; designing a flood evolution model based on cellular automata principles and combining the rainstorm scenario data with the station construction model to simulate the evolution of floods during underground station construction, thereby determining disaster data. This allows for the prediction of damage to underground station construction sites caused by floods under different scenarios by simulating various rainstorm scenarios before a disaster occurs, enabling the development of appropriate disaster emergency plans and the implementation of corresponding preventative measures to reduce economic losses and casualties. Attached Figure Description

[0058] Figure 1 This is a logic diagram of a flood simulation and disaster prediction method provided in one embodiment of this specification;

[0059] Figure 2 This is a flowchart illustrating a flood simulation and disaster prediction method provided in one embodiment of this specification;

[0060] Figure 3 This is a schematic diagram illustrating the construction of a flood simulation and disaster prediction method provided in one embodiment of this specification;

[0061] Figure 4 This is a simulation diagram illustrating a flood simulation and disaster prediction method provided in one embodiment of this specification;

[0062] Figure 5 This is an event summary diagram of a flood simulation and disaster prediction method provided in one embodiment of this specification;

[0063] Figure 6 This is a schematic diagram of the spatiotemporal semantic construction of a flood simulation and disaster prediction method provided in one embodiment of this specification;

[0064] Figure 7 This is a schematic diagram of the structure of a flood simulation and disaster prediction device provided in one embodiment of this specification;

[0065] Figure 8 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0066] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0067] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0068] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0069] This specification provides a method for flood simulation and disaster prediction, and also relates to a flood simulation and disaster prediction device, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments.

[0070] See Figure 1 , Figure 1 A schematic diagram illustrating the logical principle of a flood simulation and disaster prediction method according to an embodiment of this specification is shown.

[0071] exist Figure 1 First, multi-source scene data, including DEM data, remote sensing image data, and BIM data, was acquired through various means such as online collection and on-site photography. A multi-source data fusion modeling method was used to establish a virtual terrain model and an underground station construction model. Then, information such as the recurrence period of rainstorms, rainfall duration, and rainfall parameters were obtained through literature review. The rainfall process was designed with reference to the rainstorm intensity formula, and various rainstorm scenarios were constructed. Fine parameters were obtained by iteratively adjusting the physical field model and numerical model. A flood evolution model was designed based on the principle of cellular automata, and the evolution of floods during underground station construction was simulated by combining rainstorm scenarios and construction scenarios. Finally, disaster information such as inundation area and water depth was obtained, the disaster process was sorted out, and corresponding narrative enhancement visualization was performed.

[0072] The embodiments in this specification can simulate various rainstorm scenarios before a disaster occurs, predict the damage caused by floods to underground station construction sites under different scenarios, so as to formulate appropriate disaster emergency plans, take corresponding preventive measures, and minimize economic losses and casualties.

[0073] See Figure 2 , Figure 2 A flowchart of a flood simulation and disaster prediction method according to an embodiment of this specification is shown, which specifically includes the following steps.

[0074] Step 201: Obtain initial scene data and determine the station construction model based on the initial scene data.

[0075] In one possible implementation, initial scene data is acquired, and a station construction model is determined based on the initial scene data, including: acquiring DEM data, remote sensing image data, and BIM data, and determining the station construction model based on the DEM data, remote sensing image data, and BIM data.

[0076] In practical applications, multi-source scene data, including DEM data, remote sensing image data, and BIM data, are first obtained through various means such as online collection and on-site photography. A multi-source data fusion modeling method is then used to establish a virtual terrain model and an underground station construction model.

[0077] Specifically, underground stations are small-scale scenarios with complex internal elements, including small movable objects such as sandbags and engineering facilities. Accurate simulation of rainstorm-induced flooding requires the construction of a high-precision scene model. To address the issue of insufficient model accuracy, this embodiment proposes a method for refining the construction scene of underground stations through multi-source data fusion.

[0078] Because underground stations contain small, movable features such as sandbags and engineering facilities, the placement and storage locations of equipment may differ at different construction stages. Furthermore, these movable features significantly impede water flow, substantially impacting the spatiotemporal evolution of floods. Therefore, a more detailed physical model of the movable features (sandbags, walls, engineering equipment, etc.), the foundation pit construction model, and DEM data can be combined to form a more refined and realistic underground station construction grid model, providing a data foundation for subsequent flood simulations. (See diagram below.) Figure 3 As shown.

[0079] Step 202: Obtain rainfall parameter information, and determine the rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula.

[0080] In the embodiments of this application, there are multiple possible ways to determine the rainstorm scenario data. This application only illustrates the following two possible ways.

[0081] In one possible implementation, rainfall parameter information is obtained, and rainstorm scenario data is determined based on the rainfall parameter information and the rainstorm intensity formula. This includes: obtaining rainstorm return period parameters, rainfall duration parameters, and rainfall intensity parameters; and determining rainstorm scenario data based on the rainstorm return period parameters, rainfall duration parameters, and rainfall intensity parameters using the rainstorm intensity formula.

[0082] In practical applications, information such as the recurrence period of rainstorms, rainfall duration, and rainfall parameters are obtained through literature review. Rainfall processes are designed with reference to rainstorm intensity formulas to construct various rainstorm scenarios.

[0083] In another possible implementation, rainstorm scenario data is determined using a rainstorm intensity formula based on rainstorm return period parameters, rainfall duration parameters, and rainfall intensity parameters. This includes: determining the rainstorm intensity and rainstorm pattern for at least one period using a rainstorm intensity formula based on rainstorm return period parameters, rainfall duration parameters, and rainfall intensity parameters; identifying surface runoff obstruction factors; modifying the station construction model based on surface runoff obstruction factors; and determining the catchment area. Finally, rainstorm scenario data is determined based on rainstorm intensity, rainstorm pattern, and catchment area.

[0084] In practical applications, existing rainstorm scenarios lack comprehensive theoretical support and rarely take into account regional climate characteristics, thus failing to provide accurate rainfall simulation data. To address these deficiencies, this embodiment proposes a multi-rainstorm scenario design method that takes into account regional climate conditions, specifically designing rainstorm scenarios from three aspects: rainstorm intensity, rainstorm pattern, and catchment area.

[0085] Specifically, rainstorm intensity refers to the concentration of rainfall; the greater the intensity, the greater the rainfall. Currently, some cities have issued relevant rainfall regulations, designing extreme rainfall events such as once-in-a-decade or once-in-a-century events as construction design standards. However, with increasingly severe climate extremism, once-in-a-century rainfall alone is insufficient to meet the needs of precise disaster prevention. This embodiment uses a rainstorm intensity formula for rainstorm intensity design. Addressing the gaps in urban rainfall prevention and control plans, it designs 24-hour rainstorm intensities Q (unit: [L / (hm²)]) with return periods of 50 years, 100 years, and 1000 years. 2 ·s)]) as follows:

[0086] 50-year return period rainstorm intensity:

[0087]

[0088] Intensity of a once-in-100-year rainstorm:

[0089]

[0090] Intensity of a 1000-year rainstorm:

[0091]

[0092] In the above formula, A, B, C, and n are local climate condition parameters, which are set differently for different regions.

[0093] Furthermore, each rainstorm with the same total rainfall amount has different temporal and area distributions, resulting in floods of varying magnitudes and flood process curves of different shapes. To better reflect actual rainfall conditions, this embodiment introduces a rainfall peak coefficient r to correct for rainstorm intensity based on the rainstorm intensity formula, forming the Chicago rainfall pattern curve:

[0094] First, the average rainfall intensity is obtained as follows:

[0095]

[0096] Where T is the rainfall duration, and the instantaneous rainfall intensity at time t is obtained from the total rainfall:

[0097]

[0098] The above is a rainfall process curve. To better reflect actual rainfall conditions, a peak rainfall coefficient r is introduced. aFor the post-peak duration, T b If the duration is before the peak, then the corrected process line is the Chicago rain pattern:

[0099]

[0100] Furthermore, the construction of underground stations is a result of urbanization, with the surrounding environment dominated by artificial features such as buildings and paved roads, along with drainage points. The commonly used D8 flow direction algorithm based on DEM data is not accurate enough for dividing the catchment area and needs further improvement based on actual conditions. Considering the obstruction effect of buildings on surface runoff, building surface features are extracted and overlaid with the DEM, and building height is increased to achieve fusion between the DEM and buildings. Then, buildings are abstracted into line objects to form building lines, which are merged and categorized based on socio-cultural factors as correction conditions. Finally, Thiessen polygons are drawn with the municipal drainage outlet and the simulated water intrusion point of the foundation pit as the center points. Corrections are made using topographic and hydrological lines and building lines to complete the division of the catchment area and obtain the sub-catchment area of ​​the foundation pit location. The amount of water intruding into the foundation pit can be obtained by combining the catchment area with rainfall under various rainstorm scenarios.

[0101] This specification's embodiments improve the model's practicality by fully considering regional climate differences, making the simulation results more closely reflect local characteristics. These embodiments consulted rainfall data and designed rainstorm formulas, constructing and simulating various rainstorm scenarios, and comprehensively considering disaster prevention measures under different conditions.

[0102] Step 203: Design a flood evolution model based on the principle of cellular automata and combine rainstorm scenario data with the station construction model to simulate the evolution of floods during underground station construction and determine the disaster data.

[0103] In practical applications, fine parameters are obtained by iteratively adjusting the physical field model and numerical model. A flood evolution model is designed based on the principle of cellular automata, and the evolution of floods during underground station construction is simulated by combining rainstorm scenarios and construction scenarios. Finally, disaster information such as flood area and water depth is obtained.

[0104] In one possible implementation, a physical model is constructed based on 3D printing technology and a station construction model, and a fluid physics field model is established based on the physical model; the initial water volume in the foundation pit is determined based on rainstorm scenario data; and the initial water volume in the foundation pit is adjusted based on the fluid physics field model and the principle of cellular automata to determine the disaster data.

[0105] In practical applications, existing urban flood simulations are mostly focused on large-scale regional flood events, lacking sufficient refinement for small-scale engineering-level flood simulations. This embodiment utilizes various rainstorm scenarios and high-precision underground station scenarios, combined with 3D printed models to construct a physical field model, determine refined experimental parameters, and design a cellular automata-based model of the spatiotemporal evolution of floods in underground station construction scenarios to obtain key disaster information.

[0106] The embodiments in this specification improve the accuracy of the simulation, making the simulation results more applicable to local underground station construction scenarios. Since existing technologies are mostly applicable to large-scale, regional, urban-level flood simulation studies, this embodiment focuses on small-scale, engineering-level flood studies, and uses 3D printing to construct a physical field model to calibrate the numerical model.

[0107] For details, see Figure 4 Since it is impossible to obtain parameters through actual scenarios, this embodiment is based on a refined construction scenario. It uses 3D printing technology to construct a physical model of the underground station as a base, establishes a fluid physics field model to replace the real scenario, and sets up sensors in the scenario to obtain observed values ​​of water depth and other information and iteratively corrects them with the numerical model simulation values.

[0108] The physical field water volume is determined based on the 24-hour cumulative rainfall and catchment area obtained from the design rainstorm scenario. In view of the two main causes of water intrusion accidents in the foundation pit: the destruction of waterproof facilities and the backflow of municipal pipe network, this embodiment designs two methods to determine the final water volume: In the case of the destruction of waterproof facilities, the total water volume intruding into the foundation pit is determined by setting the height of the sandbags destroyed, as shown in Equation (7).

[0109]

[0110] Backflow caused by overload of municipal pipe network drainage capacity is determined by the drainage capacity of the municipal pipe network, as shown in equation (8-9):

[0111] V real =V sum -V 排 (8)

[0112]

[0113] In equation (6), V real V represents the actual amount of water that intruded into the foundation pit. sum To calculate the total volume of water in the flooded area of ​​the foundation pit, H water To calculate the precipitation (mm), H destroy V represents the height of the retaining wall after it is destroyed. In equation (7-8), V 排 Q represents the drainage volume of the municipal pipe network. 瞬t represents the instantaneous flow rate of the pipeline network, and t represents the duration of rainfall.

[0114] After constructing the physical field model, considering that rainwater may fall directly into the foundation pit during the rainstorm, which will also have a certain impact on the water volume, the observed changes in water depth, flow rate, and water volume are mapped to the numerical model by setting up the "rainstorm" scenario in the physical field model and the rainstorm scenario. The simulated values ​​of water volume are then adjusted to obtain accurate water volume parameters that take into account the "rainstorm" scenario.

[0115] The refined roughness is obtained by adjusting the numerical calculation and observation results. The initial simulation value is set and the water depth data is collected by setting sensors inside and around the foundation pit model in the physical field model. The observed water depth value is obtained. The roughness is adjusted by a one-dimensional roughness adjustment mechanism according to the relationship between the observed value and the simulation value, as shown in Equation (10):

[0116]

[0117] In equation (10), the flood simulation depth at point M in the k iterations is defined as... Observation of water level positioning Let M be the initial roughness. The roughness is calculated after k iterations, where α is the coefficient to avoid over-adjustment, and i is the number of iterations to simulate advance observation.

[0118] Because the initial flood velocities at the moment of backflow from the municipal pipeline network and collapse of the waterproof wall are both relatively high when simulating flooding in a foundation pit, if the physical velocity of the flood exceeds the numerical simulation velocity, the numerical method cannot capture the physical characteristics of the next time step. Furthermore, the calculation is unstable when the numerical model cannot cover the entire physical characteristic region. Therefore, the Courant number is used to set the time step.

[0119]

[0120] In equation (11), Δx is the cell size, and H max The maximum water depth is used. A smaller time step is initially adopted at the beginning of the simulation; this is adjusted to a larger time step after the water flow inside the pit stabilizes. After determining the refined parameters, they are input into the model to obtain more realistic disaster information data.

[0121] One possible implementation also includes: establishing a disaster factor table, sorting out the disaster factor table, and determining a disaster situation map; displaying rainfall information based on the disaster situation map and a particle system.

[0122] In practical applications, the disaster process can be analyzed and corresponding narrative enhancement visualizations can be implemented. This includes constructing a spatiotemporal narrative of the flooding in an underground station triggered by heavy rain based on the cause, process, and consequences of the disaster, forming a storyline to guide subsequent visualizations. After establishing a basic model of the flooding scenario during underground station construction, it is necessary to express the process, key visualization elements, and disaster information. This embodiment selects a combination of multiple narrative techniques to visualize key disaster information in the flooding accident during underground station construction triggered by heavy rain.

[0123] Specifically, flooding accidents in underground stations often originate from regional water accumulation caused by extreme weather, which washes away the waterproofing facilities of the foundation pit, leading to flooding and damage to the pit itself and the equipment. The factors involved in the entire process are first summarized in Table 1:

[0124] Table 1. Factors contributing to flooding incidents during underground station construction.

[0125]

[0126] Based on Table 1, the factors that triggered the flooding of the underground station caused by the rainstorm were analyzed to form a storyline, as shown in Figure 5.

[0127] The timeline of the flooding at the underground station triggered by torrential rain is constructed according to the logic of the cause, process, and consequences of the disaster. First, due to extreme rainstorms, an extreme precipitation event with a recurrence period of X years and a duration of t occurs at a certain time and place, causing regional water accumulation in the area where the underground station construction pit is located; when the water accumulation reaches the limit of the enclosure, the enclosure fails, or the municipal drainage network is overloaded, causing a backflow accident, and water flows into the pit of the underground station construction site; ultimately, the equipment inside the pit and the pit itself are damaged.

[0128] After establishing the basic model of the flood scenario during the construction of the underground station, it is necessary to... Figure 5 The process, key visual elements and disaster information are presented in the example. This embodiment uses a combination of various narrative methods to visually display key disaster information in the flood accident caused by rainstorms during the construction of an underground station.

[0129] Extreme precipitation events are displayed in a 3D scene using a particle system, with particle density representing rainfall at different return periods. The particle system attributes include coordinates, initial velocity, direction of motion, particle size, color, and lifespan, undergoing a "generation → activity → death" process over time to achieve a dynamic effect of extreme rainfall. Disaster information such as location, return period, and rainfall duration is displayed in text form; rainstorm patterns are shown as line graphs based on the Chicago Rain Pattern Curve.

[0130] Regional waterlogging can be mitigated by creating a water surface that intersects with the terrain and gradually rises, creating the illusion that the water level gradually increases with rainfall.

[0131] The flood evolution process is realized through animation. The flood simulation results at each moment include information such as water depth, flow velocity, and arrival time. Using a 2×2 cell consisting of four adjacent cells as the basic unit, a triangular model is constructed by sequentially checking whether the water depth value in the cell is empty. The area covered by the triangular network is the inundation area; water depth is represented by color intensity and mapped onto a color band; while information such as arrival time and flow velocity is indicated by "signboards" with text.

[0132] The extent of damage to the equipment is indicated by different colored blocks: red blocks represent severe damage, and green blocks represent safety. The submerged parts inside the pit are covered by red areas, the surrounding buffer zones are covered by yellow areas, and the unsubmerged safe areas are covered by green areas.

[0133] Because the process of flooding in underground stations caused by rainstorms is complex, traditional visualization methods are mostly static and two-dimensional, which are insufficient for expressing three-dimensional dynamic geographic time. This embodiment introduces the theory of geographic spatiotemporal narrative and designs a spatiotemporal three-dimensional dynamic visualization method, which can significantly improve the audience's understanding of this type of complex geographic time.

[0134] One possible implementation also includes: determining spatial and temporal semantic information based on the disaster situation map; performing fusion modeling based on spatial semantic information and initial scene data to determine the basic scene; and demonstrating the scene based on temporal semantic information and the basic scene.

[0135] In practical applications, temporal and spatial semantic constraints are established, and multi-source data are fused and modeled under the guidance of spatial semantics. Optimization operations such as positioning, rotation, translation, scaling, fitting, and deletion are performed on scene objects to make the constructed 3D scene more standardized and closer to the real scene. Under the constraints of temporal semantics, narrative elements, thematic data, simulation effects, and basic scenes are integrated and expressed to enhance narrative visualization.

[0136] Specifically, the principle of disaster scenario fusion construction is as follows: Figure 6As shown. Spatial semantic constraints mainly include spatial orientation, attribute category, and spatial topology, representing the orientation, attribute, and topological relationships between objects in space. Temporal semantic constraints represent the order of events occurring within the same space, including sequence, parallel overlap, inclusion, and connection. Multi-source data is fused and modeled under the guidance of spatial semantics. To make the constructed 3D scene more standardized and closer to the real scene, scene objects need to be optimized, mainly including positioning, rotation, translation, scaling, fitting, and deletion. After optimization, the triangular mesh of the contact area between the bottom of the ground features and the terrain model is reconstructed to achieve fusion, forming the basic scene of underground station construction. Finally, under the guidance of temporal semantics, narrative elements, thematic data, and simulation effects are integrated with the basic scene to achieve enhanced visualization of the underground station construction flood scene narrative.

[0137] This specification provides a method and apparatus for flood simulation and disaster prediction. The method includes: acquiring initial scenario data; determining a station construction model based on the initial scenario data; acquiring rainfall parameter information; determining rainstorm scenario data based on the rainfall parameter information and a rainstorm intensity formula; designing a flood evolution model based on cellular automata principles and combining the rainstorm scenario data with the station construction model to simulate the evolution of floods during underground station construction, thereby determining disaster data. This allows for the prediction of damage to underground station construction sites caused by floods under different scenarios by simulating various rainstorm scenarios before a disaster occurs, enabling the development of appropriate disaster emergency plans and the implementation of corresponding preventative measures to reduce economic losses and casualties.

[0138] Corresponding to the above method embodiments, this specification also provides embodiments of a flood simulation and disaster prediction device. Figure 7 This specification illustrates a schematic diagram of a flood simulation and disaster prediction device according to one embodiment. Figure 7 As shown, the device includes:

[0139] The model determination module 701 is configured to acquire initial scene data and determine the station construction model based on the initial scene data.

[0140] The data determination module 702 is configured to acquire rainfall parameter information and determine rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula;

[0141] The scenario simulation module 703 is configured to design a flood evolution model based on the principle of cellular automata and combine the rainstorm scenario data with the station construction model to simulate the evolution of floods during underground station construction and determine the disaster data.

[0142] In one possible implementation, the data determination module 702 is further configured to acquire rainfall parameter information and determine rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula, including:

[0143] Obtain parameters such as the return period of the rainstorm, the duration of rainfall, and the rainfall intensity.

[0144] Based on the rainstorm return period parameter, rainfall duration parameter, and rainfall intensity parameter, rainstorm scenario data are determined using the rainstorm intensity formula.

[0145] The formula for rainstorm intensity includes:

[0146] 50-year return period rainstorm intensity:

[0147]

[0148] Intensity of a once-in-100-year rainstorm:

[0149]

[0150] Intensity of a 1000-year rainstorm:

[0151]

[0152] Where A, B, C, and n are local climate condition parameters, which are set differently for different regions.

[0153] In one possible implementation, the model determination module 701 is further configured as follows:

[0154] Acquire DEM data, remote sensing image data, and BIM data, and determine the station construction model based on the DEM data, remote sensing image data, and BIM data.

[0155] In one possible implementation, the data determination module 702 is further configured as follows:

[0156] Based on the return period parameters, rainfall duration parameters, and rainfall intensity parameters of the rainstorm, the rainstorm intensity and rainstorm pattern of at least one period are determined by the rainstorm intensity formula.

[0157] Identify surface runoff obstruction factors, revise the station construction model based on these factors, and determine the catchment area;

[0158] Rainfall scenario data are determined based on rainfall intensity, rainfall pattern, and catchment area.

[0159] In one possible implementation, the data determination module 702 is further configured as follows:

[0160] A physical model was constructed based on 3D printing technology and a station construction model, and a fluid physics field model was established based on the physical model.

[0161] Determine the initial water volume in the foundation pit based on heavy rainfall scenario data;

[0162] Based on the fluid physics field model and the principle of cellular automata, the initial water volume in the foundation pit was adjusted to determine the disaster data.

[0163] In one possible implementation, the scene simulation module 703 is further configured as follows:

[0164] A physical model is constructed based on the station construction model. Disaster evolution simulation is performed based on rainstorm scenario data and the station construction model to determine disaster data.

[0165] In one possible implementation, the scene simulation module 703 is further configured as follows:

[0166] Establish a disaster factor table, analyze the disaster factor table, and determine the disaster situation analysis diagram;

[0167] The rainfall situation is displayed using a disaster situation analysis map and a particle system.

[0168] In one possible implementation, the scene simulation module 703 is further configured as follows:

[0169] Determine spatial and temporal semantic information based on the disaster situation map;

[0170] Based on spatial semantic information and initial scene data, a fusion model is performed to determine the basic scene;

[0171] Scenario demonstrations are based on temporal semantic information and basic scenarios.

[0172] This specification provides a method and apparatus for flood simulation and disaster prediction. The apparatus includes: acquiring initial scenario data; determining a station construction model based on the initial scenario data; acquiring rainfall parameter information; determining rainstorm scenario data based on the rainfall parameter information and a rainstorm intensity formula; designing a flood evolution model based on cellular automata principles; and simulating the evolution of flooding during underground station construction by combining the rainstorm scenario data with the station construction model to determine disaster data. This allows for the prediction of damage to underground station construction sites caused by flooding under different scenarios by simulating various rainstorm scenarios before a disaster occurs, enabling the development of appropriate disaster emergency plans and the implementation of corresponding preventative measures to reduce economic losses and casualties.

[0173] The above is a schematic scheme of a flood simulation and disaster prediction device according to this embodiment. It should be noted that the technical solution of this flood simulation and disaster prediction device and the technical solution of the flood simulation and disaster prediction method described above belong to the same concept. For details not described in detail in the technical solution of the flood simulation and disaster prediction device, please refer to the description of the technical solution of the flood simulation and disaster prediction method described above.

[0174] Figure 8A structural block diagram of a computing device 800 according to one embodiment of this specification is shown. The components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0175] The computing device 800 also includes an access device 840, which enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 840 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0176] In one embodiment of this specification, the above-described components of the computing device 800 and Figure 8 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 8 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0177] The computing device 800 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 800 can also be a mobile or stationary server.

[0178] The processor 820 executes the following computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned flood simulation and disaster prediction method. The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned flood simulation and disaster prediction method belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the aforementioned flood simulation and disaster prediction method.

[0179] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described flood simulation and disaster prediction method.

[0180] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the above-described flood simulation and disaster prediction method. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the above-described flood simulation and disaster prediction method.

[0181] An embodiment of this specification also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described flood simulation and disaster prediction method.

[0182] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program belongs to the same concept as the technical solution of the above-described flood simulation and disaster prediction method. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the above-described flood simulation and disaster prediction method.

[0183] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0184] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0185] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0186] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0187] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for flood simulation and disaster prediction, characterized in that, include: Acquiring initial scene data and determining the station construction model based on the initial scene data includes: Acquiring DEM data, remote sensing image data, and BIM data, and determining the station construction model based on the DEM data, remote sensing image data, and BIM data, including: By combining the water-blocking sandbags, water-blocking walls, engineering equipment, and foundation pit construction model with the DEM data, a construction grid model for the underground station is formed. Obtaining rainfall parameter information, and determining rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula, including: Obtain parameters such as the return period of the rainstorm, the duration of rainfall, and the rainfall intensity. A flood evolution model was designed based on the principle of cellular automata. This model, combined with the aforementioned rainstorm scenario data and the station construction model, was used to simulate the evolution of flooding during underground station construction, determining the disaster data, including: A physical model was constructed based on 3D printing technology and the station construction model, and a fluid physics field model was established based on the physical model. The initial water volume in the foundation pit was determined based on the aforementioned rainstorm scenario data; Based on the fluid physics field model and the cellular automata principle, the initial water volume in the foundation pit is adjusted to determine the disaster data; Based on the rainstorm return period parameter, the rainfall duration parameter, and the rainfall intensity parameter, the rainstorm intensity and rainstorm pattern of at least one period are determined by the rainstorm intensity formula; Identify surface runoff obstruction factors, modify the station construction model based on these factors, and determine the catchment area; Rainfall scenario data is determined based on the rainfall intensity, rainfall pattern, and catchment area. The formula for rainstorm intensity includes: Intensity of a 50-year rainstorm: Intensity of a once-in-100-year rainstorm: Intensity of a 1000-year rainstorm: in, These are local climate condition parameters, and the settings vary depending on the region.

2. The method according to claim 1, characterized in that, Also includes: Establish a disaster factor table, analyze the disaster factor table, and determine the disaster analysis diagram; The disaster situation is illustrated using the disaster map and particle system to show the rainfall data.

3. The method according to claim 2, characterized in that, Also includes: Based on the disaster situation analysis map, determine spatial and temporal semantic information; Based on the spatial semantic information and the initial scene data, a fusion model is performed to determine the basic scene; A scenario demonstration is performed based on the aforementioned temporal semantic information and the aforementioned basic scenario.

4. A flood simulation and disaster prediction device, characterized in that, The method for implementing flood simulation and disaster prediction as described in any one of claims 1 to 3 includes: The model determination module is configured to acquire initial scene data and determine the station construction model based on the initial scene data. The data determination module is configured to acquire rainfall parameter information and determine rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula; The scenario simulation module is configured to design a flood evolution model based on the principle of cellular automata and combine the rainstorm scenario data with the station construction model to simulate the evolution of floods during underground station construction and determine the disaster data. The process of acquiring rainfall parameter information and determining rainstorm scenario data based on the rainfall parameter information and the rainstorm intensity formula includes: Obtain parameters such as the return period of the rainstorm, the duration of rainfall, and the rainfall intensity. Based on the rainstorm return period parameter, the rainfall duration parameter, and the rainfall intensity parameter, rainstorm scenario data are determined using the rainstorm intensity formula. The formula for rainstorm intensity includes: Intensity of a 50-year rainstorm: Intensity of a once-in-100-year rainstorm: Intensity of a 1000-year rainstorm: in, These are local climate condition parameters, and the settings vary depending on the region.

5. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the flood simulation and disaster prediction method according to any one of claims 1 to 3.

6. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the flood simulation and disaster prediction method according to any one of claims 1 to 3.

Images