Real-time web-based urban flood simulation device and method

Abstract

This invention provides a real-time web-based urban flood simulation device and simulation method. [Solution] The urban flood simulation device includes a hardware processor and a storage unit connected to the processor that stores a digital elevation model of the city, urban design information, precipitation information, and at least one computer program for performing an urban flood simulation method. The urban flood simulation method includes step S10 of generating simulation area information and water flow information using the digital elevation model of the city and urban design information; step S11 of generating information related to flooding using the simulation area information, water flow information, and precipitation information; and step S12 of visualizing and displaying the information related to flooding.

Description

Technical Field

[0001] The present invention relates to an urban flooding simulation apparatus and method, and more particularly, to a real-time web-based urban flooding simulation apparatus and method.

Background Art

[0002] The content described in this section merely provides background information for the embodiments described in this specification and does not necessarily constitute prior art.

[0003] Recently, urban areas have become more vulnerable to flooding due to rapid climate change and increased precipitation. Existing flooding simulation technologies are mainly optimized for predicting floods occurring in large-scale urban environments and have limitations in predicting floods occurring in small-scale cities and individual areas that require higher computing resources than large-scale urban environments. For example, the method of performing flooding simulation using Computational Fluid Dynamics (CFD) requires huge amounts of data and high-performance computer resources, takes a lot of time to derive results, and has limitations in generating real-time flood prediction information. In addition, since most flooding simulation systems belong to a local network, it is difficult to remotely access them, and there are limitations in reflecting the characteristics of individual drainage facilities and topography in the city.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] This specification aims to provide a real-time web-based urban flooding simulation apparatus and method.

[0006] This specification is not limited to the issues mentioned above, and any other issues not mentioned will be clearly understood by an ordinary person from the following description. [Means for solving the problem]

[0007] A city flood simulation device according to this specification for solving the above-mentioned problems may include: a storage unit for storing a digital elevation model of a city, urban design information, precipitation information, and at least one computer program configured to perform a city flood simulation method; a simulation setting unit for generating simulation area information and water flow information using the digital elevation model of the city and the urban design information; a flood information generation unit for generating information related to flooding using the simulation area information, the water flow information, and the precipitation information; and a simulation output unit for visualizing and displaying the information related to flooding.

[0008] According to one embodiment of this specification, the simulation setting unit can generate connection relationship information for elements constituting at least one drainage facility and location information for each drainage facility using the digital elevation model of the city and the urban design information.

[0009] According to one embodiment of this specification, the simulation setting unit can calculate the slope of the ground surface using the elevation values ​​of the city extracted from the numerical elevation model, and generate information regarding the direction of water flow using the slope of the ground surface.

[0010] According to one embodiment of this specification, the simulation setting unit extracts pipe angle values ​​installed in at least one drainage facility from the altitude value and the urban design information to determine the extent to which water flows to an adjacent point (F ij ) can be calculated using the following formula.

[0011] [Mathematical formula]

number

[0012] According to one embodiment of this specification, the simulation setting unit uses information on pipes installed in at least one drainage facility from the urban design information to determine the water discharge rate (D) in at least one drainage facility. out ) can be calculated using the following formula.

[0013] [Mathematical formula]

number

[0014] According to one embodiment of this specification, the flooding information generation unit can generate information related to a predicted flooding pattern based on at least one precipitation pattern using the simulation area information, the water flow information, and the precipitation information, and can further generate information related to the flooding using the information related to the predicted flooding pattern.

[0015] In this case, the simulation area information further includes content related to the watershed characteristics of the city, the content related to the watershed characteristics of the city includes at least one of the following: the rate of water infiltration into the soil, the amount of water runoff on the ground surface per unit time, and the time it takes for water to reach the runoff point, and the flood information generation unit can further utilize the content related to the watershed characteristics to generate information related to the predicted flood pattern.

[0016] According to an embodiment of the present specification, the storage unit further stores an artificial neural network model that generates the water outflow volume and the drainage volume information of at least one drainage facility using the simulation area information, the water flow information, and the precipitation information as input values, and the flooding information generation unit inputs the simulation area information, the water flow information, and the precipitation information into the artificial neural network model, and obtains the water outflow volume and the drainage volume of at least one drainage facility from the artificial neural network model, and can generate information related to the flooding.

[0017] According to an embodiment of the present specification, the artificial neural network model can include the Navier-Stokes equation expressed by the following mathematical formula as part of the loss function.

[0018] [Mathematical formula] [Number]

[0019] According to an embodiment of the present specification, when the water accumulation volume exceeds a preset critical value at at least one location included in the simulation area, the simulation output unit sets the local location as a flood risk area, and can display the flood risk level step by step according to the water accumulation volume.

[0020] In an urban flood simulation device, the device includes a hardware processor and a storage unit connected to the processor for storing a digital elevation model of a city, urban design information, precipitation information, and at least one computer program configured to perform an urban flood simulation method, the urban flood simulation method may include: (a) generating simulation area information and water flow information using the digital elevation model of the city and the urban design information; (b) generating information related to flooding using the simulation area information, the water flow information, and the precipitation information; and (c) visualizing and displaying the information related to flooding.

[0021] According to one embodiment of this specification, step (a) may include generating connection relationship information for elements constituting at least one drainage facility and location information for each drainage facility using the digital elevation model of the city and the urban design information.

[0022] According to one embodiment of this specification, step (a) may include calculating the slope of the ground surface using the elevation values ​​of the city extracted from the digital elevation model, and generating information about the direction of water flow using the slope of the ground surface.

[0023] According to one embodiment of this specification, step (a) extracts pipe angle values ​​installed in at least one drainage facility from the altitude value and the urban design information to determine the extent to which water flows to an adjacent point (F ij This may include calculating using the following formula.

[0024] [Mathematical formula]

number

[0025] According to one embodiment of this specification, step (a) uses information on pipes installed in at least one drainage facility from the urban design information to determine the water discharge rate (D) in at least one drainage facility. out This may include calculating ) using the following formula.

[0026] [Mathematical formula]

number

[0027] According to one embodiment of this specification, step (b) may be a step of generating information related to a predicted flood pattern based on at least one precipitation pattern using the simulation area information, the water flow information, and the precipitation information, and further using the information related to the predicted flood pattern to generate information related to the flood.

[0028] In this case, the simulation area information further includes content related to the watershed characteristics of the city, the content related to the watershed characteristics of the city includes at least one of the following: the rate of water infiltration into the soil, the amount of water runoff on the ground surface per unit time, and the time it takes for water to reach the runoff point, and step (b) may further utilize the content related to the watershed characteristics to generate information related to the predicted flood pattern.

[0029] According to one embodiment of this specification, the storage unit further stores an artificial neural network model that generates water outflow volume and drainage volume information for at least one drainage facility using the simulation area information, the water flow information, and the precipitation information as input values, and step (b) may be a step of inputting the simulation area information, the water flow information, and the precipitation information into the artificial neural network model, obtaining the water outflow volume and drainage volume for at least one drainage facility from the artificial neural network model, and generating information related to the flooding.

[0030] According to one embodiment of this specification, the artificial neural network model may include the Navier-Stokes equations, expressed by the following formula, as part of the loss function.

[0031] [Mathematical formula]

number

[0032] According to one embodiment of this specification, step (c) may include setting at least one location included in the simulation area as a flood-prone area when the amount of water accumulated at that location exceeds a predetermined critical value, and visualizing the degree of flood risk in stages according to the amount of water accumulated.

[0033] The urban flood simulation method described herein can be implemented in the form of a computer program, which is written to perform each step on a computer and recorded on a computer-readable recording medium.

[0034] Other specific details of the present invention are included in the detailed description and drawings. [Effects of the Invention]

[0035] According to one aspect of this specification, the urban flood simulation device can drive urban flood simulations in a web-based environment. Urban administrators can remotely connect to a web server via a terminal without belonging to a local network and monitor water flow information, water accumulation information, and flood risk information due to precipitation in real time. Administrators can monitor flood risk via a terminal anytime, anywhere, when needed. Through this, urban administrators can respond immediately to floods and inundation situations caused by precipitation, quickly identify high-risk areas, and take immediate countermeasures. In addition, the urban flood simulation device can provide administrators with simulation results in 3D through metaverse integration, thereby improving the administrators' visual understanding and speed of analysis compared to conventional methods.

[0036] According to other aspects of this specification, in order to solve the problem of conventional urban flood simulation methods' insufficient reflection of detailed characteristics of small areas, the urban flood simulation device can reflect the characteristics of urban drainage facilities and topographic information more precisely than conventional methods. Through this, the urban flood simulation device can generate flood information that may occur in small cities or specific areas more quickly than conventional methods. While conventional simulation methods have focused on generating flood information for large cities as a whole, the urban flood simulation device according to this specification can generate flood risk information for specific areas or zones more precisely than conventional methods by utilizing detailed design data such as information included in the city's digital elevation model (altitude of each point, topographic slope, etc.), urban design information (width of drainage channels, angle of drainage channels, depth of manholes, width of pipes, rotation angle of pipes, etc.), and precipitation information (precipitation amount, duration of precipitation, etc.). The urban flood simulation device can use such customized data to reflect the specific drainage patterns and watershed flows of individual areas and generate more accurate flood information. As a result, the urban flood simulation device can provide urban administrators with flood risk information that is more customized to specific areas than before, enabling urban administrators to develop flood response strategies customized to those areas.

[0037] According to other aspects of this specification, the urban flood simulation device can generate water flow information, accumulation information, and flood risk information more efficiently and accurately than conventional methods by utilizing a Physics Informed Neural Network (PINN) model that integrates physical water flow information. Unlike the fixed computational structure in conventional urban flood simulation methods, the urban flood simulation device can reduce data consumption compared to conventional methods by utilizing the artificial neural network model.

[0038] According to other aspects of this specification, the urban flood simulation device can reduce the urban administrator's dependence on high-performance computing resources. Furthermore, the urban flood simulation device can provide urban administrators with customized simulations tailored to various precipitation conditions and topographic characteristics, as well as accurate urban flood prediction information.

[0039] The effects of the present invention are not limited to those mentioned above, and any other effects not mentioned will be clearly understood by an ordinary person from the following description. [Brief explanation of the drawing]

[0040] [Figure 1] This diagram illustrates the relationship between an urban flood simulation device and a user terminal according to one embodiment of this specification. [Figure 2] This is a diagram illustrating the design of the metaverse provided by a web-based urban flood simulation device according to one embodiment of this specification. [Figure 3] This is a diagram illustrating an example of setting precipitation amounts. [Figure 4] This diagram illustrates an example of a visual representation of the results of an urban flooding simulation based on rainfall. [Figure 5] This is a block diagram of an urban flood simulation device according to one embodiment of this specification. [Figure 6] This is a flowchart of a method for simulating urban flooding according to one embodiment of this specification. [Figure 7] This is a diagram illustrating a method for simulating urban flooding. [Figure 8] This is a flowchart of the process for generating simulation area information and water flow information in step S10. [Figure 9] This is a flowchart of the process for generating information related to flooding in step S11. [Figure 10] This is a block diagram of an urban flood simulation device according to another embodiment of this specification. [Figure 11] This diagram illustrates the process by which a fluid analysis model according to one embodiment of this specification learns based on spatial information and physical conditions. [Figure 12] This diagram illustrates the process of generating information related to flooding using a fluid analysis model according to one embodiment of this specification. [Modes for carrying out the invention]

[0041] The advantages and features of the inventions disclosed herein, as well as methods for achieving them, will become clearer with reference to the embodiments described below in detail with the accompanying drawings. However, this specification is not limited to the embodiments disclosed below, and can be realized in a variety of different forms. These embodiments are merely provided to complete the disclosure of this specification and to fully inform the ordinary articulators (hereinafter, "those skilled in the art") of the scope of this specification, and the scope of this specification is defined solely by the scope of the claims.

[0042] The terms used herein are for illustrative purposes only and are not intended to limit the scope of the rights herein. In this specification, the singular form includes the plural form unless otherwise specified in the text. The terms “comprises” and / or “comprising” as used in this specification do not preclude the presence or addition of one or more other components beyond those mentioned.

[0043] Throughout the specification, the same reference numerals refer to the same component, and "and / or" includes each of the components mentioned and all combinations of one or more of them. Even though terms such as "first," "second," etc., are used to describe various components, these components are not limited by these terms. These terms are simply used to distinguish one component from another. Therefore, the first component mentioned below may also be the second component within the technical concept of the present invention.

[0044] Unless otherwise defined, all terms used herein (including technical and scientific terms) are used in the sense that would be commonly understood by an ordinary technician in the art to which this specification pertains. Furthermore, terms defined in commonly used dictionaries are not ideally or excessively analyzed unless explicitly defined otherwise.

[0045] An artificial neural network (ANN) is a system that uses artificial neurons, which are mathematically modeled after the neurons that make up the human brain, to create artificial intelligence by connecting them to each other.

[0046] In this specification, an "artificial neural network model" can consist of a set of interconnected computational units that may generally be called nodes. Such nodes may also be called neurons. A neural network consists of at least one node. The nodes (or neurons) that make up a neural network may be interconnected by one or more links.

[0047] Within a neural network, one or more nodes connected via links can form a relative input-output node relationship. The concepts of input and output nodes are relative; any node that is an output node to another node can be an input node to another node, and vice versa. As mentioned above, input-output node relationships can be generated around links. One input node can be connected to one or more output nodes via links, and vice versa.

[0048] The initial input node can refer to one or more nodes in a neural network that receive data directly without being linked to other nodes. Alternatively, it can refer to a node in a neural network that does not have other input nodes connected by links, based on the relationships between nodes. Similarly, the final output node can refer to one or more nodes in a neural network that do not have an output node in relation to other nodes. Furthermore, a hidden node can refer to a node that makes up the neural network, but is neither the initial input node nor the final output node.

[0049] In this specification, "inputting" data into an artificial neural network model means that a value at the initial input node is input. In this specification, "value acquisition," "data output," "information acquisition," etc., from the artificial neural network means that some data is output from the final output node.

[0050] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to the input and output layers. Deep neural networks can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, Generative Adversarial Networks (GANs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Siam networks, and Generative Adversarial Networks (GANs). The above descriptions of deep neural networks are illustrative only, and this disclosure is not limited thereto.

[0051] A neural network can be trained using at least one of the following methods: supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Training a neural network may be the process of applying knowledge to the neural network to enable it to perform specific actions.

[0052] Neural networks can be trained to minimize the error in their output. This training process involves repeatedly inputting training data into the neural network, calculating the neural network's output and target error for the training data, and then backpropagating the error from the output layer to the input layer to update the weights of each node in the neural network in a way that reduces the error. In supervised learning, training data with the correct answer labeled is used (i.e., labeled training data), while in unsupervised learning, the training data may not have the correct answer labeled. For example, in supervised learning for data classification, the training data may have categories labeled on each data point. Labeled training data is input into the neural network, and the error can be calculated by comparing the neural network's output (category) with the labels on the training data. As another example, in unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network's output. The calculated error is backpropagated in the neural network (i.e., from the output layer to the input layer), and this backpropagation can update the connection weights of each node in each layer of the neural network. The amount of change in the connection weight of each node that is updated can be determined by the learning rate. The calculation of the neural network on the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of learning to increase efficiency by enabling the neural network to quickly achieve a certain level of performance, while a low learning rate can be used in the later stages of learning to improve accuracy.

[0053] In this specification, "training" of an artificial neural network model means that the neural network updates the connection weights of each node so that the error in the output is minimized, and "training" according to this specification is not limited by any specific training method.

[0054] In this specification, a “processor” can consist of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general-purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. A processor can read computer programs stored in memory and perform data processing for machine learning according to one embodiment of this specification. According to one embodiment of this specification, a processor can perform calculations for training a neural network. A processor can perform calculations for training a neural network in deep learning (DL), such as processing input data for training, extracting features from the input data, calculating errors, and updating the weight values ​​of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of a processor can process the training of network functions. For example, a CPU and a GPGPU can work together to train a network function and process data classification using the network function. Also, in one embodiment of this specification, processors from multiple computing devices can be used together to train a network function and process data classification using the network function. Furthermore, the computer program executed in the computing device according to one embodiment of this specification may be a CPU, GPGPU, or TPU executable program.

[0055] Embodiments of the present invention will be described in detail below with reference to the attached drawings.

[0056] Figure 1 illustrates the relationship between an urban flood simulation device and a user terminal according to one embodiment of this specification.

[0057] Referring to Figure 1, the urban flood simulation device 10 may be a server device that provides web-based urban flood simulations. Terminal 20 can access the urban flood simulation device 10 via an external network. Users can check the urban flood simulation results provided by the urban flood simulation device 10 using a web application installed on terminal 20. Terminal 20 can be a computer, laptop, smartphone, tablet computer, etc., and is not limited to any specific device.

[0058] Figure 2 illustrates a design diagram of the metaverse provided by a web-based urban flood simulation device according to one embodiment of this specification.

[0059] Referring to Figure 2, the urban flood simulation device 10 can provide the user (city administrator) with a Metaverse Platform server 100. The user can connect to the platform server 100 using a web application installed on terminal 20. Through terminal 20, the user can input variable values ​​for the flood simulation and operational values ​​for interaction with the metaverse environment.

[0060] The urban flood simulation device 10 can transmit urban flood simulation results to terminal 20. Users can view the simulation results, represented in 3D, within the metaverse via a web application installed on terminal 20.

[0061] The administrator (server administrator) can input flood environment information due to environmental changes in a specific city into the urban flood simulation device 10 via the asset management module. The urban flood simulation device 10 can update the flood environment data based on the data input by the administrator. The urban flood simulation device 10 can provide the administrator with the updated flood environment information.

[0062] User data and flood environment information may be stored in the storage unit 11. Alternatively, the user data and flood environment information may be stored in a separate database server device.

[0063] The urban flood simulation device 10 can perform an urban flood simulation based on the input data and visualize and display the simulation results. The urban flood simulation device 10 may include a simulation module 101 and a metaverse module 102.

[0064] The simulation module 101 may include a communication module 103 for communicating with the terminal 20 via a network. The communication module 103 can communicate with the terminal 20 using an IoT (Internet of Things) communication protocol, and this is just one example; it is not limited by the aforementioned communication protocol. The simulation module 101 can control an urban flood simulation and collect data for the simulation from the terminal 20 and / or an external data server.

[0065] The metaverse module 102 may include a data synchronization module 104 and a WebRTC support module 105. The data synchronization module 104 can synchronize data between multiple users and / or multiple devices. The data synchronization module 104 can synchronize the location and status of multiple users, track the activities of multiple users, and manage sessions. The WebRTC support module 105 can use WebRTC (Web Real-Time Communication) to support web-based image screen sharing and voice calls between multiple users.

[0066] Figure 3 is a diagram illustrating an example of setting precipitation amounts, and Figure 4 is a diagram illustrating an example of visualizing the results of an urban flooding simulation based on precipitation amounts.

[0067] Referring to Figure 3, the user can use terminal 20 to set precipitation duration, precipitation amount per hour, etc., for urban flooding simulation. Alternatively, the urban flooding simulation device 10 can set precipitation duration, precipitation amount per hour, etc., for simulation based on precipitation information provided by the Korea Meteorological Administration.

[0068] Referring to Figure 4, the urban flood simulation device 10 can proceed with the urban flood simulation based on the set rainfall amount. The urban flood simulation device 10 can visually realize the simulation results, as shown in Figure 4(a). The simulation results screen 200 can be visualized as shown in Figure 4(b). The simulation results screens 200 and 201 can display the flood-prone areas together with a map image of a specific area of ​​the city. In addition, the simulation results, including location information (Junction ID) of the flood-prone areas, water accumulation information (depth current), maximum depth information (depth max), and flood information (overflow width), can be displayed on the dashboard 202.

[0069] The urban flood simulation device described herein will be explained in more detail below.

[0070] Figure 5 is a block diagram of an urban flood simulation device according to one embodiment of this specification.

[0071] Referring to Figure 5, the urban flood simulation device 10 according to one embodiment of this specification may include a storage unit 11, a simulation setting unit 12, a flood information generation unit 13, and a simulation output unit 14. The simulation setting unit 12 may include a simulation module 101. The simulation output unit 14 may include a metaverse module 102.

[0072] The simulation setting unit 12, the flooding information generation unit 13, the simulation output unit 14, and the learning unit 15 (described later) can be implemented as a hardware processor. The simulation setting unit 12, the flooding information generation unit 13, the simulation output unit 14, and the learning unit 15 may include processors, ASICs (application-specific integrated circuits), other chipsets, logic circuits, registers, communication modems, data processing devices, etc., known in the art to which the present invention belongs, in order to perform calculations and various control logics. Furthermore, if the above-mentioned control logic is implemented as software, the simulation setting unit 12, the flooding information generation unit 13, the simulation output unit 14, and the learning unit 15 can be implemented as a collection of program modules. In this case, the program modules can be stored in the memory device and executed by the processor.

[0073] The storage unit 11 can store at least one computer program configured to perform an urban flood simulation method. The processor can perform the urban flood simulation by running at least one computer program configured to perform the urban flood simulation method, and can visually realize the simulation results. The processor can provide the urban flood simulation to users via the web.

[0074] Figure 6 is a flowchart of an urban flood simulation method according to one embodiment of this specification, and Figure 7 is a diagram illustrating the urban flood simulation method.

[0075] Referring to Figures 6 and 7, in step S10, the simulation setting unit 12 can generate simulation area information using the city's digital elevation model (DEM) 300 and urban design information 301. The simulation setting unit 12 can then use the generated simulation area information to realize the simulation area in 3D.

[0076] Figure 8 is a flowchart showing the process of generating simulation area information and water flow information in step S10.

[0077] Referring to Figure 8, the simulation setting unit 12 can generate simulation area information based on the city's digital elevation model and urban design information to construct a simulation environment.

[0078] According to one embodiment of this specification, the storage unit 11 can pre-store a digital elevation model 300 of a city and urban design information 301. As the digital elevation model 300, a digital elevation model provided by the Geospatial Information Authority of Japan of the Ministry of Land, Infrastructure, Transport and Tourism may be used. The urban design information 301 may include design drawings of the city in question and / or design drawings of at least one drainage facility installed in the city in question. The urban drainage facility may include components such as manholes, sewers, and pipes installed for water to flow into and out to outlets such as rivers and streams.

[0079] Furthermore, urban design information 301 may also include content related to land use plan maps, current land use maps, land information, current status of sewage treatment facilities, current status of urban planning facilities, watershed classification information, watershed characteristic-related information, flood management area information, geological structure information, etc., which are provided through the public data portal.

[0080] The simulation setting unit 12 can receive the digital elevation model 300 and urban design information 301 from the administrator's terminal and save them in the storage unit 11. Alternatively, the processor can acquire the digital elevation model 300 and urban design information 301 using the open API (Open Application Programming Interface) provided by the public data portal.

[0081] The simulation setting unit 12 can generate 3D modeling information of the city in question using the numerical elevation model 300 and urban design information 301. This is a technique widely known among those skilled in the art, so a detailed explanation will be omitted. In this case, the simulation setting unit 12 can generate connection relationship information for components (manholes, sewers, pipes, etc.) constituting at least one drainage facility using the numerical elevation model 300 and urban design information 301, and generate location information for each drainage facility. The simulation setting unit 12 can generate simulation area information including the connection relationship information, the location information for each drainage facility, and drainage area information for each drainage facility.

[0082] In step S10-1, the simulation setting unit 12 can extract the latitude, longitude, and altitude values ​​of the city from the digital elevation model 300. The simulation setting unit 12 can also calculate the slope of the city's ground surface from the digital elevation model 300. The slope of the ground surface can be used to set the direction in which water flows in the simulation environment.

[0083] The simulation setting unit 12 can calculate the slope of the ground surface by calculating the rate of change in altitude around each cell using the numerical elevation model 300. The simulation setting unit 12 can use [Equation 1] and [Equation 2] to calculate the rate of change in altitude in the east-west direction (x-axis direction) and the rate of change in altitude in the south-north direction (y-axis direction), respectively.

[0084] [Formula 1]

number

[0085] [Formula 2]

number

[0086] Subsequently, the simulation setting unit 12 can calculate the slope of the ground surface using the rate of change in altitude in the x-axis direction and the rate of change in altitude in the y-axis direction. The simulation setting unit 12 can calculate the slope of the ground surface using [Equation 3].

[0087] [Formula 3]

number

[0088] Furthermore, the simulation setting unit 12 can generate information related to at least one drainage facility using the urban design information 301. The simulation setting unit 12 can extract connection information between manholes and sewers using the urban design information. The simulation setting unit 12 can also extract information on the thickness, length, diameter, and angle of inclination from the horizontal plane of multiple pipes included in the sewer system from the urban design information 301. The simulation setting unit 12 can also extract information such as the connection relationships between multiple pipes and whether or not there is a change in the direction of water flow due to pipe elbows, etc. The simulation setting unit 12 can generate network information of the drainage system, which is connection relationship information of the components of the urban drainage system (manholes, sewers, pipe piping, etc.), using the information extracted from the urban design information. The simulation setting unit 12 can extract the information from the urban design information using an image analysis algorithm and / or an optical character recognition algorithm, etc. The simulation setting unit 12 can also acquire the information by inputting the urban design information into a pre-trained artificial neural network model.

[0089] The simulation setting unit 12 can integrate the information obtained using the numerical elevation model 300 and urban design information 301 to generate location information for each drainage facility in three-dimensional space, and generate 3D modeling information for the city's drainage facilities.

[0090] In step S10-2, the simulation setting unit 12 can generate water flow information, including the direction of water flow, water flow velocity, and water discharge volume at each drainage facility, using information obtained from the digital elevation model 300 and urban design information 301. Based on the water flow information, the simulation setting unit 12 can generate information regarding the direction of water flow in the overall network of the city's drainage system, the location of outlets where water exits drainage facilities into rivers or streams, and so on.

[0091] The process by which the simulation setting unit 12 obtains the elevation value and gradient of the city from the numerical elevation model may be essential for understanding the drainage capabilities of each drainage facility. For example, water may flow easily at locations with relatively high elevations, while water may accumulate at locations with relatively low elevations. The simulation setting unit 12 can set the water flow path based on the elevation value and gradient of the city.

[0092] In the initial step of the urban flood simulation, precipitation R is distributed to each point in the simulation area, and the increase in precipitation over time can be accumulated at each point. The simulation setting unit 12 can calculate the extent to which water flows from a specific point (or specific drainage facility) in the simulation area to an adjacent point (or adjacent drainage facility), taking into account the slope of the ground surface and the characteristics of the drainage facility. The simulation setting unit 12 can calculate the extent to which water flows to an adjacent point using the following [Equation 4].

[0093] [Equation 4]

number

[0094] The aforementioned θ is the angle of the pipe, which can reflect the resistance to water flow. In this case, the pipe angle can mean the angle at which the pipe is inclined with respect to the horizontal plane. The pipe angle can be a value extracted from the design drawings of the drainage facility.

[0095] The aforementioned drainage characteristic coefficient can be calculated based on the pipe material, diameter, length, fluid viscosity, and other factors.

[0096] The simulation setting unit 12 can set the direction of water movement so that water flows from a point with a relatively high altitude to a point with a lower altitude. By setting the direction of water movement, the simulation setting unit 12 can generate information about the water inflow path at a specific point.

[0097] The simulation setting unit 12 can calculate the amount of water discharged at each point in the simulation area in real time and identify locations where water flow is likely to occur.

[0098] The simulation setting unit 12 reflects the characteristics of each drainage facility (pipe diameter, length, angle, whether or not there is a change in direction, etc.) and sets the water discharge volume D out This can be calculated dynamically. The amount of water discharged changes depending on the design of the drainage facility and real-time precipitation conditions, and can be adjusted by the resistance elements and capacity of the pipes. The simulation setting unit 12 can calculate the discharge amount using the following [Equation 5].

[0099] [Formula 5]

number

[0100] The number of rotations of the aforementioned pipe can refer to the number of times the direction of water flow changes due to pipe elbows, U-shaped pipes, tee pipes, etc.

[0101] The simulation setting unit 12 dynamically adjusts the amount of water that the pipe can discharge using the [equation 5], and the discharge amount may be relatively smaller if the number of rotations is high or the width of the pipe is narrow. Through this, the simulation setting unit 12 can calculate the amount of water discharged according to the characteristics of the actual drainage facility.

[0102] The flood information generation unit 13 can generate information on the risk of overload of drainage facilities by utilizing the amount of water inflow due to precipitation and the amount of water discharged from drainage facilities. In particular, the flood information generation unit 13 can determine the limits that each drainage facility can handle when the amount of precipitation increases rapidly.

[0103] In step S10-3, the simulation setting unit 12 can use the water flow information to set the water flow direction, velocity, and discharge volume in multiple drainage facilities. Based on this, the simulation setting unit 12 can set the contents related to water flow in the network of the entire city drainage system. In addition, the simulation setting unit 12 can use the water flow information to set the contents related to water flow in small units, such as a sewer connected to one manhole and another adjacent manhole; contents related to water flow in medium-scale units, such as a sewer connecting multiple manholes in one block of a city; and contents related to water flow in large units, such as the network of the entire city drainage system. Through this, the simulation setting unit 12 can efficiently generate the results of urban flood simulations in small, medium, and large units. Furthermore, the simulation setting unit 12 can precisely analyze the impact of the characteristics of the drainage facilities installed in each unit on water flow in small, medium, and large units, thereby improving the accuracy of the urban flood simulation.

[0104] Referring further to Figures 6 and 7, in step S11, the flooding information generation unit 13 can generate information related to flooding due to precipitation in the simulation area using the simulation area information, water flow information, and precipitation information. The storage unit 11 may be pre-installed with SWMM (Storm Water Management Model) software provided by the U.S. Environmental Protection Agency. The flooding information generation unit 13 can generate information related to flooding by performing an urban flooding simulation using SWMM 400. The information related to flooding may refer to the simulation results calculated via SWMM 400. The information related to flooding may include content related to water flow, water accumulation, and flood risk in the drainage system network.

[0105] Since conducting urban flood simulations using SWMM400 is a widely known technique among those skilled in the art, a detailed explanation will be omitted.

[0106] Figure 9 is a flowchart of the process for generating flood-related information in step S11.

[0107] Referring to Figure 9, in step S11-1, the flood information generation unit 13 can set a precipitation pattern from the precipitation information of the city in question. The storage unit 11 may have the city's precipitation information 302 stored in advance. As the precipitation information, city-specific precipitation information provided by the Korea Meteorological Administration can be used. The precipitation information 302 may include, but is not limited to, content related to the current hourly precipitation, expected precipitation time, predicted precipitation, predicted cumulative precipitation, and past precipitation. The flood information generation unit 13 can retrieve actual city precipitation information in real time using the Korea Meteorological Administration's open API. Alternatively, the precipitation information can be input in real time from the terminal 20.

[0108] The flood information generation unit 13 can analyze the precipitation information 302 and generate at least one precipitation pattern 303. The flood information generation unit 13 can use the precipitation information to set the amount of precipitation per hour and generate the precipitation pattern 303. In addition, the flood information generation unit 13 can set the total cumulative precipitation and set the time interval in which precipitation is concentrated to generate the precipitation pattern 303. The flood information generation unit 13 can use the precipitation information to generate precipitation patterns in various ways.

[0109] Alternatively, the user can directly input the precipitation pattern 303 via terminal 20.

[0110] In step S11-2, the flood information generation unit 13 can generate information 304 related to at least one predicted flood pattern that may occur in the city, using the simulation area information, the water flow information, the precipitation information, and the precipitation pattern.

[0111] As an example, the flood information generation unit 13 can generate a precipitation pattern 303 by setting the amount of precipitation per hour using the precipitation information 302. Subsequently, the flood information generation unit 13 can generate information 304 related to the predicted flood pattern based on the simulation area information, the water flow information, and the generated precipitation pattern. The information 304 related to the predicted flood pattern may include information related to the area that is flooded first during precipitation, the area that is flooded last, and the manhole that is saturated first. The information 304 related to the predicted flood pattern may also include information related to the area from which water first flows out when the precipitation weakens. The flood information generation unit 13 can calculate the water accumulation rate at each point by comparing the amount of water discharged from drainage facilities based on the water flow information with the amount of water inflow due to precipitation, and generate the information 304 related to the predicted flood pattern.

[0112] According to one embodiment of this specification, the simulation area information may include content related to the watershed characteristics of the city. The flood information generation unit 13 can extract content related to the watershed characteristics from the city design information.

[0113] The contents related to the aforementioned watershed characteristics may include contents related to the watershed's morphology, area, elevation, slope, slope direction, river flow rate, soil and geological types, etc. The flood information generation unit 13 can generate hydrological characteristic information for the urban watershed by utilizing the contents related to the aforementioned watershed characteristics.

[0114] The flood information generation unit 13 can further utilize the content related to the watershed characteristics to generate information 304 related to the predicted flood pattern.

[0115] The flood information generation unit 13 can calculate the water inflow and outflow at each point using the simulation area information, the water flow information, the precipitation information, and the content related to the watershed characteristics. The water inflow and outflow calculated using the content related to the watershed characteristics can represent the water inflow and outflow at the ground surface.

[0116] The flood information generation unit 13 can calculate the amount of water inflow using the precipitation information and the information related to the watershed characteristics. The flood information generation unit 13 can calculate the water infiltration rate over time based on the information related to the soil and geology, which is related to the watershed characteristics. The water infiltration rate can be calculated using the Horton infiltration model defined in [Equation 6] below.

[0117] [Formula 6]

number

[0118] Since calculating the amount of water that infiltrates into the soil using the Horton infiltration model is a widely known technique among those skilled in the art, a detailed explanation will be omitted.

[0119] The flood information generation unit 13 can calculate the amount of water that infiltrates the soil and the amount of evaporation loss. Based on this, the flood information generation unit 13 can calculate the final inflow amount using the hourly precipitation, the amount of water flowing into the relevant location from an adjacent location, the amount of water that infiltrates the soil, and the amount of water that is lost through evaporation.

[0120] The flood information generation unit 13 can calculate the final inflow amount by subtracting the amount of water that infiltrates the soil and the amount of water lost through evaporation from the hourly rainfall and the amount of water flowing into the relevant location from adjacent locations.

[0121] Furthermore, the flood information generation unit 13 can calculate the amount of water runoff at each location using the information related to the watershed characteristics. The flood information generation unit 13 can calculate the amount of runoff per unit time using the following [Equation 7].

[0122] [Equation 7]

number

[0123] Furthermore, the flood information generation unit 13 can calculate the time it takes for water to flow out using the following [Equation 8]. The time it takes for water to flow from each point to an adjacent point.

[0124] [Formula 8]

number

[0125] The flood information generation unit 13 can calculate the final runoff amount at the ground surface using the water inflow, outflow, and runoff time at each location. The flood information generation unit 13 can further use the water inflow and outflow amounts at the ground surface calculated using the watershed characteristics to generate information 304 related to the predicted flood pattern.

[0126] Furthermore, the storage unit 11 can further store an artificial neural network model (hereinafter referred to as the "pattern analysis model") that has been trained to generate information related to the predicted flood pattern, using the simulation area information, the water flow information, and the precipitation information as input values. The flood information generation unit 13 can input the simulation area information, the water flow information, and the precipitation information into the pattern analysis model to obtain information related to the predicted flood pattern.

[0127] In step S11-3, the flood information generation unit 13 can generate information related to the flood using the simulation area information, the water flow information, the information related to at least one predicted flood pattern, and the precipitation information used for the urban flood simulation.

[0128] Subsequently, the flood information generation unit 13 can generate information related to the flood using the simulation area information, the water flow information, the information related to at least one predicted flood pattern, and the precipitation information used for urban flood simulation.

[0129] The urban flood simulation device 10 can enhance the reliability of urban flood simulations by reflecting realistic weather conditions. The flood information generation unit 13 can set appropriate precipitation patterns for areas where heavy rainfall is expected. Through this, the urban flood simulation device 10 can identify areas at high risk of flooding under specific precipitation conditions in advance. Unlike existing systems that simply input precipitation amounts, the flood information generation unit 13 can generate water flow information between points, taking into account the size and shape of the watershed, as well as the inflow routes. Through this, users can check the amount of water accumulated and drained in specific areas and take early action against flooding.

[0130] The flood information generation unit 13 can construct an urban flood simulation environment by inputting the simulation area information, water flow information, precipitation information, precipitation pattern information, and predicted flood pattern information into the SWMM400. The flood information generation unit 13 processes the input precipitation information in real time using the SWMM400 and can automatically calculate the simulation each time the data is updated. The amount of precipitation at each location can change according to the time step. The flood information generation unit 13 can generate information related to flooding according to the amount of precipitation which changes depending on the capacity and slope of the drainage facilities, and can save it in real time in the storage unit 11.

[0131] The urban flood simulation device 10 uses SWMM400 to simulate water outflow and drainage flow, and can visualize the simulation results. Users can access the urban flood simulation device 10 using a web application installed on terminal 20 and view the visualized simulation results. Through this, users can be provided with visualized simulation results from the urban flood simulation device 10 without the need for a high-performance GUI (Graphical User Interface).

[0132] The flood information generation unit 13 can generate real-time information on ground surface runoff and the status of drainage facilities based on precipitation conditions using SWMM400. The flood information generation unit 13 can simultaneously simulate flood conditions by receiving various climate scenarios (such as precipitation patterns) from the user's terminal 20. Users can monitor the flood conditions by accessing a web page using the terminal 20.

[0133] Unlike conventional systems limited to local networks, the urban flood simulation device 10 according to this specification can be designed so that multiple users can monitor and manage the flood situation in real time, even on an external network.

[0134] The urban flood simulation device 10 can automatically calculate whether each facility can handle the excess capacity if rainfall increases during the simulation based on SWMM400, and can warn of flooding and / or backflow risks at each location.

[0135] According to one embodiment of this specification, the storage unit 11 can store an artificial neural network model (hereinafter referred to as the "flow analysis model") that generates information on the amount of water runoff at the ground surface and the amount of water discharged at each drainage facility, using the simulation area information, the water flow information, and the precipitation information as input values.

[0136] In step S11-3, the flooding information generation unit 13 inputs the simulation area information, the water flow information, and the precipitation information into the flow analysis model 401, and can obtain information on the amount of water runoff at the ground surface and the amount of water discharged at each drainage facility (hereinafter referred to as "flow prediction information") from the flow analysis model.

[0137] The flooding information generation unit 13 can generate information related to the flooding using the flow prediction information 307 obtained from the flow analysis model 401.

[0138] Figure 10 is a block diagram of an urban flood simulation device according to another embodiment of this specification, Figure 11 illustrates the process by which a fluid analysis model according to one embodiment of this specification learns based on spatial information and physical conditions, and Figure 12 illustrates the process of generating flood-related information using a fluid analysis model according to one embodiment of this specification.

[0139] Referring to Figures 10 to 12, the urban flood simulation device 10' according to other embodiments of this specification may include a storage unit 11, a simulation setting unit 12, a flood information generation unit 13, a simulation output unit 14, and a learning unit 15. Repeated descriptions of the storage unit 11, the simulation setting unit 12, the flood information generation unit 13, and the simulation output unit 14 are omitted.

[0140] The learning unit 15 can train the flow analysis model 401 using the illustrated 3D mesh data 305, generated based on the city's digital elevation model 300 and urban design information 301, as training data. The city's 3D mesh data 305 can correspond to the simulation area information. The flow analysis model 401 can learn spatial information for the simulation area using the city's 3D mesh data 305.

[0141] The learning unit 15 can train the flow analysis model 401 using the simulation area information, water flow information, and precipitation information from a specific city as training data.

[0142] According to one embodiment of this specification, the fluid analysis model 401 may be a Physics Informed Neural Network (PINN) model that integrates physical laws into its learning process. In this case, the fluid analysis model 401 may correspond to a regression model.

[0143] The flow analysis model 401 can have boundary conditions and physical conditions set during the learning process 306. The loss function of the flow analysis model 401 may include equations corresponding to the boundary conditions and physical conditions.

[0144] Boundary conditions can be set as Dirichlet boundary conditions and Neumann boundary conditions. The Dirichlet boundary conditions may be for analyzing water level and flow velocity at each point. The Neumann boundary conditions may be for analyzing flow rate changes and flow velocity at each point.

[0145] The physical conditions may include the Green-Ampt model and at least one momentum equation based on external forces (gravity, friction, resistance, etc.). The said at least one momentum equation may include physical laws of fluid dynamics, such as the Navier-Stokes equations and the law of conservation of momentum.

[0146] The process of setting boundary conditions and physical conditions in a physical information artificial neural network model is a technique widely known among those skilled in the art, and therefore a detailed explanation will be omitted.

[0147] The flow analysis model 401 can be trained to generate the amount of water runoff at the ground surface and the amount of water discharged from each drainage facility based on the simulation area information, the water flow information, the precipitation information, the boundary conditions, and the physical conditions. The flow analysis model 401 can be trained to minimize the value of a loss function that includes the boundary conditions and physical conditions. The flow analysis model 401 can be trained to take the simulation area information, the water flow information, and the precipitation information as training data and generate flow prediction information 307 that minimizes the value of the loss function.

[0148] The flood information generation unit 13 can acquire the flow prediction information 307 in real time using the flow analysis model 401. The flow analysis model 401 can generate the flow prediction information 307 through the physical laws and mathematical equations. Furthermore, the flow analysis model 401 can increase the data processing speed through parallel computing.

[0149] The flood information generation unit 13 can use the flow analysis model 401 to obtain the flow prediction information 307 at each location in real time using information such as rainfall, pipe size, and drainage route.

[0150] The fluid analysis model 401 can include essential equations of fluid dynamics, such as the Navier-Stokes equations, the law of conservation of momentum, and the infiltration equation, as part of its loss function. Through this, the fluid analysis model 401 can generate the fluid flow prediction information 307 within a city with only a small amount of data and parallel processing. The urban flood simulation device 10' according to this specification can efficiently generate complex water flow information within a city by utilizing such a physical law-based artificial neural network model.

[0151] The aforementioned fluid analysis model 401 has the advantage of being able to generate complex physical fluid pattern information with less data than the traditional CFD (Computational Fluid Dynamics) method.

[0152] Traditional numerical analysis methods divide a 3D space into multiple small grids (mesh) to generate information related to water flow, and calculate physical variables (water velocity, pressure, etc.) in each grid. In this case, the more complex the grid structure, the greater the data consumption. However, the flow analysis model 401 can generate physical flow pattern information in a mesh-free manner by including the boundary conditions and physical conditions in the loss function. In other words, unlike traditional numerical analysis methods, the physical law-based artificial neural network model does not divide the 3D space into a grid, thus reducing the amount of data consumed and computation required to generate physical flow pattern information compared to conventional methods.

[0153] Furthermore, traditional numerical analysis methods calculate physical variables through fixed calculation processes predetermined for each grid. In this case, boundary conditions and physical conditions can be set independently for each grid. If the boundary conditions and physical conditions change, the administrator must separately modify the boundary conditions and physical conditions for each grid. However, the fluid analysis model 401 may include the boundary conditions and physical conditions as a loss function. If the boundary conditions and physical conditions change, the administrator can deal with the situation more flexibly than before by modifying only the loss function of the fluid analysis model 401.

[0154] The flood information generation unit 13 can acquire information such as flow velocity, pressure, and flow rate at various points within the city in real time using the flow analysis model 401. Through this, the urban flood simulation device 10 according to this specification can generate the flow prediction information 307 in real time, which was difficult with conventional methods, and can send early warnings to the terminal 20 for areas at high risk of flooding.

[0155] The aforementioned fluid analysis model 401 may include physical laws of fluid dynamics, such as the Navier-Stokes equations and the law of conservation of momentum, as part of its loss function.

[0156] [Formula 9]

number

[0157] Based on this, the flow analysis model 401 can receive the simulation area information, the water flow information, and the precipitation information as input and generate the flow prediction information 307 in real time. In this process, the flow analysis model 401 can calculate the water flow through physical laws and mathematical equations and increase the data processing speed through parallel computing. The flow analysis model 401 can calculate the water flow in real time using information such as precipitation, pipe size, and drainage route.

[0158] By utilizing a physical information artificial neural network model, water flow can be calculated based on physical laws, enabling rapid and accurate prediction of flood risk. Unlike conventional CFD methods, the physical information artificial neural network model integrates physical laws into neural network learning to generate real-time information such as water flow, flow velocity, and pressure distribution. This prediction result can be used for immediate and efficient response based on precipitation.

[0159] The flood information generation unit 13 can extract multiple feature information from the simulation area information, the water flow information, and the precipitation information. The feature information may include location feature information 308, time feature information 309, and sensor feature information 310.

[0160] The location feature information 308 may include information related to the location of each drainage facility. The time feature information 309 may include information related to rainfall duration, the time it takes for water to be discharged from each drainage facility, the time it takes for water to flow out of the watershed, etc. The sensor feature information 310 may include information related to manhole depth, sewer (or water pipe) length, water resistance force according to flow changes due to pipe elbows, etc., rainfall amount, land use information, watershed characteristics information, soil infiltration amount, etc. In addition, all information related to the simulation area information, water flow information, rainfall information, rainfall pattern information, and predicted inundation pattern information described above can be input into the flow analysis model 401.

[0161] According to one embodiment of this specification, the flooding information generation unit 13 can independently generate information related to the flooding using SWMM400 and the flow analysis model 401. For example, the flooding information generation unit 13 can use SWMM400 to generate water level information for each manhole, sewer, etc., in the drainage system network. In conjunction with this, the flooding information generation unit 13 can use the flow analysis model 401 to generate the flow prediction information in the drainage system network. The flooding information generation unit 13 can generate information related to the flooding using the information generated by SWMM400 and the flow prediction information generated by the flow analysis model 401. The flooding information generation unit 13 can use the information generated by SWMM400 and the flow prediction information generated by the flow analysis model 401 to generate information such as whether or not flooding has occurred at each point in the drainage system network and the predicted time of flooding.

[0162] The flooding information generation unit 13 can use the information generated by SWMM400 to supplement and weight the flow prediction information.

[0163] For example, the flood information generation unit 13 can use the information generated by SWMM400 to identify and remove abnormal values ​​in the flow prediction information.

[0164] As another example, during the training process of the fluid analysis model 401, the learning unit 15 can further utilize the information generated by the SWMM 400 to train the fluid analysis model 401. The flooding information generation unit 13 can further input the information generated by the SWMM 400 into the fluid analysis model 401 to generate the fluid prediction information. Subsequently, the flooding information generation unit 13 can use the information generated by the SWMM 400 and the fluid prediction information to generate information related to flooding.

[0165] Through this, the flood information generation unit 13 can generate more accurate flood-related information than before.

[0166] According to other embodiments of this specification, the flooding information generation unit 13 can input the flow prediction information 307 generated by the flow analysis model to the SWMM400. Based on the flow prediction information 307, the SWMM400 can generate more accurate urban flooding simulation results than conventional methods.

[0167] Furthermore, referring to Figures 6 and 7, in step S12, the simulation output unit 14 can visualize and display information related to the flooding in the simulation area.

[0168] As shown in Figure 4, the simulation output unit 14 can visualize the simulation results in a 3D model and represent the water accumulation and flow conditions in real time. The simulation output unit 14 can visually divide and display flood-prone areas and provide warnings in color or graph format when dangerous water levels are reached.

[0169] As an example, as shown in Figure 4(b), the simulation output unit 14 can display flood-prone areas in stages. In this case, the simulation output unit 14 can display flood-prone areas in stages from step 0, which has the lowest flood risk, to step 3, which has the highest flood risk. If water has accumulated to 0-25% of the manhole depth in the area, the flood risk may correspond to step 0. If water has accumulated to 25-50% of the manhole depth in the area, the flood risk may correspond to step 1. If water has accumulated to 50-75% of the manhole depth in the area, the flood risk may correspond to step 2. If water has accumulated to 75-100% of the manhole depth in the area, the flood risk may correspond to step 3. If the flood risk is step 0, the simulation output unit 14 may not display a warning at the location. If the flood risk is step 1, the simulation output unit 14 can display a green warning indicator 203 at the location. If the flood risk level is 2 steps, the simulation output unit 14 can display a yellow warning indicator 204 at the corresponding location. If the flood risk level is 3 steps, the simulation output unit 14 can display a red warning indicator 205 at the corresponding location. The criteria for the flood risk level and the method for displaying the flood risk level are examples only and are not limited thereto.

[0170] The simulation output unit 14 can retrieve the simulation results for each location from the storage unit 11 and configure a 3D environment that is automatically updated.

[0171] The simulation output unit 14 can visualize the simulation results in a 3D environment so that users can intuitively understand the simulation results through the terminal 20 and respond quickly to flooding. By visualizing the status of each drainage facility and the amount of runoff on the ground surface, the simulation output unit 14 can provide warning notifications when the risk of flooding increases in a specific area. Unlike conventional 2D-based visualizations, the urban flood simulation devices 10 and 10' according to this specification can represent the water flow and accumulation state in three dimensions at various points in the city, supporting intuitive monitoring for the user. Users can check warnings in real time using the web application on the terminal 20 and take immediate countermeasures for high-risk areas.

[0172] The simulation output unit 14 determines that the amount of water accumulated at each point reaches a specific critical value W. threshold If it exceeds W, it can be classified as a flood-prone area and a warning can be sent to terminal 20. The simulation output unit 14 monitors data from all locations in real time and can display the relevant information on a web-based dashboard when a warning is issued. The simulation output unit 14 is W i (t)>W threshold If this is the case, location i can be classified as a flood-prone area, and a warning notification can be issued.

[0173] Flood risk prediction is an essential function that enables users to recognize and respond to high-risk flooding in advance. The urban flood simulation devices 10 and 10' according to this specification can automatically identify high-risk areas and provide real-time visual warnings. Through this, users can receive real-time notifications about high-risk areas via a web-based dashboard and intuitively understand the level of risk at each location.

[0174] The urban flood simulation method according to the embodiments of this specification can be implemented in the form of a computer program written to perform each step on a computer and recorded on a computer-readable recording medium. The aforementioned computer program may include code coded in a computer language such as C / C++, C#, Java®, Python, or machine language, which is read by the computer's processor (CPU) through the computer's device interface in order for the computer to read the program and execute the method implemented in the program. Such code may include functional code associated with functions that define the functions necessary to perform the method, and may include execution procedure-related control code necessary for the computer's processor to execute the functions in a predetermined procedure. Furthermore, such code may further include memory reference-related code indicating where (address) in the computer's internal or external memory the additional information and media necessary for the computer's processor to execute the functions should be referenced. Furthermore, if the computer's processor needs to communicate with any other computer or server located remotely in order to perform the aforementioned function, the code may further include communication-related code specifying how to communicate with any remote computer or server using the computer's communication module, and what information or media must be sent and received during communication.

[0175] The storage medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short moment, such as a register, cache, or memory. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In other words, the program may be stored on various recording media on various servers that the computer can connect to, or on various recording media on the user's computer. Furthermore, the medium may be distributed across a network of connected computer systems, and the code stored on it may be readable by computers in a distributed manner.

[0176] While embodiments of this specification have been described above with reference to the attached drawings, a person of ordinary skill in the art to which this specification belongs will understand that the present invention can be carried out in other specific forms without altering its technical idea or essential features. Therefore, the embodiments described above should be understood to be illustrative and not restrictive in all respects. [Explanation of symbols]

[0177] 10. Urban flood simulation device 20... Terminals 11...Storage section 12. Simulation Settings Section 13... Flood information generation section 14. Simulation output section 15. Learning Department

Claims

1. A storage unit for storing at least one computer program configured to perform a digital elevation model of a city, urban design information, precipitation information, and urban flood simulation methods, A simulation setting unit that generates simulation area information and water flow information using the aforementioned digital elevation model of the city and the aforementioned urban design information, A flood information generation unit that generates information related to flooding using the simulation area information, the water flow information, and the precipitation information, and A city flood simulation device comprising: a simulation output unit that visualizes and displays information related to the aforementioned flooding.

2. The aforementioned simulation setting unit is: The urban flood simulation device according to claim 1, which generates connection relationship information of elements constituting at least one drainage facility and location information of each drainage facility using the aforementioned digital elevation model of the city and the aforementioned urban design information.

3. The aforementioned simulation setting unit is: The urban flood simulation device according to claim 2, which calculates the slope of the ground surface using the elevation values ​​of the city extracted from the aforementioned digital elevation model, and generates information regarding the direction of water flow using the slope of the ground surface.

4. The aforementioned simulation setting unit is: From the aforementioned altitude value and the urban design information, the pipe angle value installed in at least one drainage facility is extracted, and the degree to which water flows to an adjacent point F is determined. ij The urban flood simulation device according to claim 3, which calculates using the following formula. [Mathematical formula] [Math 1]

5. The aforementioned simulation setting unit is: Using the information on pipes installed in at least one drainage facility from the aforementioned urban design information, the amount of water discharged from at least one drainage facility (D out The urban flood simulation device according to claim 2, which calculates ) using the following formula. [Mathematical formula] [Math 2]

6. The aforementioned flood information generation unit, The urban flood simulation device according to claim 1, comprising generating information related to a predicted flood pattern based on at least one precipitation pattern using the simulation area information, the water flow information, and the precipitation information, and further generating information related to the flood using the information related to the predicted flood pattern.

7. The aforementioned simulation area information further includes content related to the urban watershed characteristics, The characteristics of the watershed of the aforementioned city include at least one of the following: the rate of water infiltration into the soil, the amount of water runoff on the ground surface per unit time, and the time it takes for water to reach the point of runoff. The aforementioned flood information generation unit, The urban flood simulation device according to claim 6, further utilizing the content related to the aforementioned watershed characteristics to generate information related to the predicted flood pattern.

8. The aforementioned storage unit is Further storing an artificial neural network model that generates water outflow volume and drainage volume information for at least one drainage facility using the aforementioned simulation area information, water flow information, and precipitation information as input values, The aforementioned flood information generation unit, The urban flood simulation device according to claim 1, wherein the simulation area information, the water flow information, and the precipitation information are input into the artificial neural network model, and the amount of water outflow and the amount of drainage from at least one drainage facility are obtained from the artificial neural network model to generate information related to the flooding.

9. The aforementioned artificial neural network model is The urban flood simulation device according to claim 8, characterized in that it includes the Navier-Stokes equations, expressed by the following formula, as part of the loss function. [Mathematical formula] [Math 3]

10. The aforementioned simulation output unit is The urban flood simulation device according to claim 1, wherein when the amount of water accumulated at at least one location within the simulation area exceeds a predetermined critical value, the location is designated as a flood-prone area, and the degree of flood risk is displayed in stages according to the amount of water accumulated.

11. Hardware processor and, A city flood simulation device comprising: a storage unit connected to the processor and storing at least one computer program configured to perform a city's digital elevation model, city design information, precipitation information, and a city flood simulation method; (a) A step of generating simulation area information and water flow information using the digital elevation model of the city and the urban design information, (b) A step of generating information related to flooding using the simulation area information, the water flow information, and the precipitation information, and (c) A method for simulating urban flooding, comprising the step of visualizing and displaying information related to the flooding.

12. Step (a) above is, A method for simulating urban flooding according to claim 11, comprising generating connection relationship information for elements constituting at least one drainage facility and location information for each drainage facility using the aforementioned digital elevation model of the city and the aforementioned urban design information.

13. Step (a) above is, A method for simulating urban flooding according to claim 12, comprising calculating the slope of the ground surface using the elevation values ​​of the city extracted from the aforementioned digital elevation model, and generating information regarding the direction of water flow using the slope of the ground surface.

14. Step (a) above is, From the aforementioned altitude values ​​and urban design information, the pipe angle values ​​installed in at least one drainage facility are extracted to determine the degree to which water flows to an adjacent point (F ij The urban flood simulation method according to claim 13, which includes calculating ) using the following formula. [Mathematical formula] [Math 4]

15. Step (a) above is, The urban flood simulation method according to claim 12, further comprising using information on pipes installed in at least one drainage facility from the aforementioned urban design information to calculate the amount of water discharged (Dout) in at least one drainage facility using the following formula. [Mathematical formula] [Math 5]

16. Step (b) above is: A method for simulating urban flooding according to claim 11, comprising the steps of generating information related to a predicted flood pattern based on at least one precipitation pattern using the simulation area information, the water flow information, and the precipitation information, and further generating information related to the flood using the information related to the predicted flood pattern.

17. The aforementioned simulation area information further includes content related to the urban watershed characteristics, The characteristics of the watershed of the aforementioned city include at least one of the following: the rate of water infiltration into the soil, the amount of water runoff on the ground surface per unit time, and the time it takes for water to reach the point of runoff. Step (b) above is: The urban flood simulation method according to claim 16, further comprising the step of generating information related to the predicted flood pattern by utilizing the content related to the watershed characteristics.

18. The aforementioned storage unit is Further storing an artificial neural network model that generates water outflow volume and drainage volume information for at least one drainage facility using the aforementioned simulation area information, water flow information, and precipitation information as input values, Step (b) above is: A method for simulating urban flooding according to claim 11, comprising the steps of inputting the simulation area information, the water flow information, and the precipitation information into the artificial neural network model, obtaining the amount of water outflow and the amount of drainage from at least one drainage facility from the artificial neural network model, and generating information related to the flooding.

19. The aforementioned artificial neural network model is The urban flood simulation method according to claim 18, characterized in that it includes the Navier-Stokes equations, expressed by the following formula, as part of the loss function. [Mathematical formula] [Math 6]

20. Step (c) above is, The urban flood simulation method according to claim 11, further comprising setting a location as a flood-prone area when the amount of water accumulated at at least one location within the simulation area exceeds a predetermined critical value, and visualizing the degree of flood risk in stages according to the amount of water accumulated.

21. A computer program prepared to perform each step of a city flood simulation method according to any one of claims 11 to 20 on a computer, and recorded on a computer-readable recording medium.

Images