Urban flood disaster dynamic monitoring method and system based on big data

Abstract

The invention discloses an urban flood disaster dynamic monitoring method and system based on big data, and relates to the technical field of disaster management, and the method comprises the steps: constructing an urban three-dimensional model, carrying out the decoupling evaluation of the structure, function and load vulnerability, and forming a disaster supervision architecture; a disaster supervision assembly is supervised and trained based on the architecture and is embedded into a city information platform, and intelligent learning of disaster probability dependence and vulnerability entropy is realized; combined evaluation is carried out in combination with multi-source sensing data, a disaster monitoring state is determined in real time, and intelligent management and directional monitoring guidance of urban flood disasters are implemented according to a monitoring result. The technical problems of lagging disaster identification and insufficient monitoring precision caused by lack of comprehensive assessment and real-time dynamic monitoring of urban complex environments in the existing urban flood monitoring method are solved, a three-dimensional disaster supervision architecture based on big data driving is achieved, multi-dimensional dynamic assessment of urban flood disasters is realized, and the urban flood disaster monitoring efficiency is improved. And the disaster identification precision and the response efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of disaster management, in particular to a city flood disaster dynamic monitoring method and system based on big data. BACKGROUND

[0002] With the acceleration of urbanization and the frequent occurrence of extreme climate events, urban flood disasters have become an important risk factor affecting the safe operation of cities and the lives and property of residents. The existing city flood monitoring methods mostly rely on single hydrological or meteorological data, lacking comprehensive assessment and real-time dynamic monitoring capability for complex urban environments. These methods are difficult to timely discover the dynamic evolution characteristics of disasters, achieve precise prevention and control, and real-time management in the face of complex urban topography, dense infrastructure and variable weather conditions. SUMMARY

[0003] The present application provides a city flood disaster dynamic monitoring method and system based on big data, which is used to solve the technical problems of the existing city flood monitoring methods lacking comprehensive assessment and real-time dynamic monitoring of complex urban environments, leading to lagging disaster identification and insufficient monitoring accuracy.

[0004] In a first aspect, the present application provides a city flood disaster dynamic monitoring method based on big data, which comprises: constructing a city three-dimensional model, performing decoupling evaluation of structural vulnerability, functional vulnerability and load vulnerability based on the city three-dimensional model for flood disaster dimensions, and constructing a disaster supervision architecture; supervising training of a disaster supervision component according to the disaster supervision architecture and embedding it in a city information platform, wherein the training direction includes disaster probability dependency relationship, flood vulnerability entropy quantification and coupling evaluation; performing joint evaluation of the disaster supervision component under data initialization by performing city multi-source sensing and returning to the city information platform, and determining a disaster monitoring state; and performing city flood disaster management and directional monitoring guidance according to the disaster monitoring state.

[0005] In a second aspect, the present application provides a city flood disaster dynamic monitoring system based on big data, which comprises: a multi-dimensional decoupling evaluation module for constructing a city three-dimensional model, performing decoupling evaluation of structural vulnerability, functional vulnerability and load vulnerability based on the city three-dimensional model for flood disaster dimensions, and constructing a disaster supervision architecture; a supervision component training module for supervising training of a disaster supervision component according to the disaster supervision architecture and embedding it in a city information platform, wherein the training direction includes disaster probability dependency relationship, flood vulnerability entropy quantification and coupling evaluation; a joint evaluation module for performing joint evaluation of the disaster supervision component under data initialization by performing city multi-source sensing and returning to the city information platform, and determining a disaster monitoring state; and a disaster management module for performing city flood disaster management and directional monitoring guidance according to the disaster monitoring state.

[0006] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] The method and system for dynamically monitoring urban flood disasters based on big data provided by the present application relate to the technical field of disaster management. By constructing a dynamic monitoring system for flood disasters based on big data and a three-dimensional model of a city, the structural, functional and load vulnerability are decoupled and evaluated, a disaster supervision architecture is established, and an embedded disaster supervision component is trained to realize real-time monitoring, entropy quantization analysis and intelligent early warning under multi-source data fusion, thereby solving the technical problem that the existing urban flood monitoring method lacks comprehensive evaluation and real-time dynamic monitoring of complex urban environments, resulting in lagging disaster identification and insufficient monitoring accuracy, realizing a three-dimensional disaster supervision architecture driven by big data, achieving multi-dimensional dynamic evaluation of urban flood disasters, and improving the technical effects of disaster identification accuracy and response efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0009] Figure 1 The method and system for dynamically monitoring urban flood disasters based on big data provided by the present application are provided with a flowchart of the method.

[0010] Figure 2 The method and system for dynamically monitoring urban flood disasters based on big data provided by the present application are provided with a structural diagram of the system.

[0011] The reference signs are explained as follows: multi-dimensional decoupling evaluation module 11, supervision component training module 12, joint evaluation module 13, and disaster management module 14. DETAILED DESCRIPTION

[0012] The method and system for dynamically monitoring urban flood disasters based on big data provided by the present application are used to solve the technical problem that the existing urban flood monitoring method lacks comprehensive evaluation and real-time dynamic monitoring of complex urban environments, resulting in lagging disaster identification and insufficient monitoring accuracy.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0014] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, this application provides a method for dynamic monitoring of urban flood disasters based on big data, the method including:

[0016] P10: Construct a 3D model of the city, conduct a decoupled assessment of the structural vulnerability, functional vulnerability and load vulnerability based on the 3D model of the city for the dimension of flood disaster, and construct a disaster monitoring architecture.

[0017] Specifically, the first step is to construct a three-dimensional model of the city. This model is based on digital twin city technology and integrates geographic information systems (GIS), remote sensing data, building information models, and real-time sensing data to achieve high-precision modeling of urban spatial morphology, infrastructure structure, and surface hydrological characteristics, providing refined spatial support for subsequent flood and waterlogging vulnerability analysis.

[0018] Building upon this foundation, a multi-dimensional vulnerability decoupling assessment of urban systems is conducted, focusing on flood disasters. Structural vulnerability refers to the resistance of urban physical structures to flood impacts, with assessment parameters including building material properties, drainage system bearing capacity, and terrain elevation distribution. Functional vulnerability refers to the resilience and recovery capabilities of key urban functional units, such as transportation, power, and communication, identified through topological analysis of the infrastructure network to pinpoint functional coupling and potential failure chains. Load vulnerability characterizes the sensitivity of urban population density, traffic flow, and economic activity intensity to flood events, calculated using socioeconomic big data and dynamic travel models. Decoupling analysis methods, such as principal component analysis or multi-objective hierarchical regression models, can be introduced to separate the correlations among the three types of vulnerability factors, eliminating statistical interference between different disaster impact dimensions and obtaining independent and quantifiable risk characteristic indicators. Finally, based on the aforementioned vulnerability indicator system, a disaster monitoring architecture for flood disaster monitoring and assessment is constructed. This architecture defines monitoring objects, monitoring indicators, and data flow relationships, providing a standardized structural foundation and technical interfaces for the subsequent training and embedded deployment of disaster monitoring components.

[0019] Further, for the dimension of flood disaster, the application embodiment step P10 further includes:

[0020] P11: According to the urban three-dimensional model, the first urban element is the drainage catchment area and the pipe network, the joint evaluation of the topographic convergence potential and the dependence of the drainage path is performed on each drainage catchment area, and the obstruction linear relationship is determined, wherein the drainage catchment area and the obstruction linear relationship are one-to-one corresponding; P12: Taking the first urban element as the base, the base position matching mark of the obstruction linear relationship is generated, and the first structure vulnerability map is generated.

[0021] Optionally, the process of structure vulnerability decoupling evaluation based on urban three-dimensional model for flood disaster dimension can be further refined to more accurately identify and quantify the structure vulnerability of the city in flood disaster.

[0022] Specifically, first, according to the constructed urban three-dimensional model, the drainage catchment area and the pipe network system are determined as the first urban element, which is the basic unit representing the urban drainage function and the flood response characteristics. Among them, the drainage catchment area refers to the natural or artificial catchment area of rainwater or surface runoff in urban terrain, and its spatial boundary can be automatically divided through the terrain elevation model (DEM) and flow direction analysis; the pipe network system includes rainwater pipes, inspection wells, pumping stations and drainage outlets and other basic drainage facilities.

[0023] On this basis, the joint evaluation of the topographic convergence potential and the dependence of the drainage path is performed on each drainage catchment area, wherein the topographic convergence potential is used to measure the trend strength of the terrain to the water flow aggregation and catchment, and the slope direction, catchment area and minimum potential path and other topographic factors are often used as input; the dependence of the drainage path is used to represent the dependence of the drainage system on a specific pipe or node, which can be calculated based on the pipe network topology and flow distribution model, and is used to identify the key path under the condition of system overload or blockage. By jointly evaluating the above two indicators, the obstruction linear relationship can be established, which refers to those key obstruction nodes that will cause large area paralysis once blocked or overloaded, and the quantitative degree of drainage and water potential under different water conditions. It is worth noting that each drainage catchment area and the obstruction linear relationship are one-to-one corresponding, which means that each drainage catchment area has its specific key obstruction node and corresponding water potential quantitative index.

[0024] Next, based on the first urban element, the determined obstruction linear relationship is marked with a base position matching. This process is to accurately match the specific position information of the obstruction linear relationship with the corresponding position in the three-dimensional model of the city, and mark it. In this way, the first structural vulnerability map can be generated. This map can intuitively show the key obstruction nodes and their positions of each drainage catchment in the city, providing quantitative and visual structural vulnerability basis for subsequent disaster monitoring and management.

[0025] Further, for the dimension of flood disaster, the application embodiment step P10 further includes:

[0026] P13: According to the three-dimensional model of the city, taking the road network as the second urban element, the road network passing capacity of the key traffic hub is evaluated, and the traffic flow resilience relationship is determined, wherein the key traffic hub and the traffic flow resilience relationship are one-to-one corresponding; P14: Taking the second urban element as the base, the traffic flow resilience relationship is marked with a base position matching, and a second functional vulnerability map is generated.

[0027] It should be understood that the process of functional vulnerability decoupling evaluation based on the three-dimensional model of the city for the dimension of flood disaster can be further refined to more accurately identify and quantify the functional vulnerability of the city in flood disasters.

[0028] Specifically, first, according to the constructed three-dimensional model of the city, the road network is defined as the second urban element, which is used to represent the traffic passing capacity and functional maintenance capacity of the city under flood disaster conditions. On this basis, the road network passing capacity of the key traffic hub is evaluated, and the traffic flow resilience relationship is determined. The traffic flow resilience relationship refers to the recovery ability and anti-interference ability of traffic flow of the key traffic hub under different flood water conditions. This evaluation process needs to consider multiple factors such as the flooding depth of the road, the traffic flow, the connectivity of the road network, and the availability of alternative paths. For example, combined with the water depth simulation data under flood conditions and the traffic flow dynamic simulation model, the passing capacity of each hub node is analyzed in time sequence, and the variation law of traffic flow under different water depth is obtained. By comparing the traffic flow recovery speed, detouring capacity and flow decay coefficient under normal traffic state and flood disturbance state, the traffic flow resilience relationship is established, which describes the anti-interference and recovery index system of the traffic system under disaster impact. This relationship is used to quantify the ability of each key traffic hub to maintain function under flood disaster conditions, and realizes one-to-one mapping of key nodes and traffic flow resilience relationship, providing a quantitative basis for functional vulnerability distribution.

[0029] Subsequently, the traffic flow resilience relationship determined above is marked with a base position matching based on the second urban element. Specifically, the traffic flow resilience evaluation result is spatially mapped in the three-dimensional model, and in combination with geographical features such as road elevation, terrain slope, and drainage conditions, the road sections and node positions with high flood-affected degree are marked. Through multi-dimensional spatial data fusion and geographical registration, a second functional vulnerability map is generated, which presents the functional weaknesses of the urban traffic system under the action of flood disasters in the form of resilience level, traffic risk index, or traffic interruption probability. The map can not only help identify the functional weak links of the city in flood disasters, but also provide a scientific basis for formulating targeted traffic relief measures and emergency plans, thereby improving the ability of the city to cope with flood disasters.

[0030] Further, the load vulnerability based on the three-dimensional model of the city is decoupled and evaluated for the flood disaster dimension, and a disaster supervision architecture is constructed. The step P10 of the embodiment of the present application further includes:

[0031] P15: Based on the first urban element and the second urban element, the rainfall spatiotemporal aggregation and the surface rainfall are evaluated for drainage impact, the drainage impact relationship is determined and marked with a base position matching, and a third load vulnerability map is generated; P16: Taking the three-dimensional model of the city as a layer, taking the third load vulnerability map as a second layer, and taking the first structural vulnerability map and the second functional vulnerability map in parallel as a third layer, a disaster supervision architecture is constructed.

[0032] Optionally, the process of load vulnerability decoupling evaluation based on the three-dimensional model of the city for the flood disaster dimension and the construction of the disaster supervision architecture can be further refined to more comprehensively identify and quantify the load vulnerability of the city in flood disasters, and to integrate the vulnerability evaluation results to construct the disaster supervision architecture.

[0033] Specifically, first, the first urban element (drainage catchment area and pipe network) and the second urban element (road network) are taken as the base to evaluate the drainage impact of rainfall spatio-temporal aggregation and area rainfall. Specifically, high-resolution spatio-temporal distribution information of rainfall is obtained by combining radar inversion rainfall data with ground meteorological monitoring station measured data, and the aggregation of rainfall in the time dimension, i.e. the concentration of rainfall in a unit of time, and the aggregation in the spatial dimension, i.e. the concentration or dispersion characteristics of rainfall distribution, are calculated. On this basis, the area rainfall index of different regions is obtained by using an area rainfall calculation model, such as the Thiessen polygon method or the grid weighted average method, to reflect the spatial distribution of the overall load of the drainage system by rainfall. Then, according to the comprehensive results of rainfall aggregation and area rainfall, a drainage impact relationship is established, which is a probability relationship model describing the overload or failure of the drainage system under specific rainfall conditions. This relationship is supported by a hydrodynamic model, which quantifies the overload risk of different catchment areas and road nodes by simulating the rainfall runoff process and the response of the drainage system. Subsequently, the drainage impact relationship is matched and marked with the base position, and the high-risk drainage nodes and traffic disturbed areas are marked in the spatial projection manner in the urban three-dimensional model, and finally the third load vulnerability map is generated. This map can comprehensively reflect the dynamic impact of rainfall spatio-temporal characteristics on urban drainage and transportation systems, and provide quantitative basis for disaster response at the load level.

[0034] Then, taking the urban three-dimensional model as the first layer of the overall spatial framework, the third load vulnerability map as the second layer, and the first structural vulnerability map and the second functional vulnerability map as the third layer, a multi-dimensional integrated disaster supervision architecture is constructed by parallel superposition. This architecture takes the urban three-dimensional model as the basic layer, the third load vulnerability map as the intermediate layer, and the first structural vulnerability map and the second functional vulnerability map as the top layer, forming a multi-layer and comprehensive disaster supervision system. This architecture design enables the various vulnerability assessment results to complement and verify each other, thereby more comprehensively and accurately reflecting the overall vulnerability of the city in the flood disaster. Through this architecture, the monitoring, prediction and response of urban flood disasters can be coordinated in a multi-dimensional data environment, providing systematic model support and spatial semantic basis for the supervision training and real-time monitoring of subsequent disaster supervision components.

[0035] P20: According to the disaster supervision architecture, supervise and train the disaster supervision components and embed them in the city information platform, wherein the training direction includes disaster probability dependence relationship, flood vulnerability entropy quantification and coupling evaluation.

[0036] Further, the disaster supervision components are supervised and trained, and the step P30 of the embodiments of the present application further includes:

[0037] P21: Perform first-order training on the disaster monitoring architecture based on disaster probability dependency to determine the first monitor; P22: Perform second-order training on the disaster monitoring architecture based on flood vulnerability entropy quantification to determine the second monitor; P23: Deploy the first monitor and the second monitor in parallel, and perform third-order training with coupled evaluations of parallel output to build the disaster monitoring component.

[0038] It should be understood that the disaster monitoring component is trained according to the disaster monitoring architecture and embedded in the city information platform to ensure that the disaster monitoring component can comprehensively and accurately assess and monitor urban flood disasters.

[0039] Specifically, the disaster monitoring architecture is first trained using a first-order model based on the probabilistic dependencies of disasters. This training, based on probabilistic graphical models such as Bayesian networks or Markov random fields, quantifies the mutual information relationships among relevant elements of urban flooding disasters, establishing a causal dependency chain for disasters. Specifically, rainfall concentration, topographic convergence potential, and traffic flow resilience are used as the main analytical variables. Historical disaster data and real-time sensing data are used to calculate the conditional and joint probability relationships between different variables. For example, when rainfall concentration increases, the probability of water accumulation in areas with high topographic convergence potential increases, leading to a synchronous change in the probability of decreased traffic flow resilience. By calculating the mutual information among these variables, the dependence strength between various elements in the disaster propagation path can be quantified, and key nodes in disaster evolution can be identified. Based on the training results, a first monitor is constructed to monitor the dynamic changes in disaster causal relationships in real time, achieving early warning and trend identification at the probabilistic dependency level.

[0040] Next, the disaster monitoring architecture undergoes second-order training based on flood vulnerability entropy quantification. Entropy is used here as an indicator of the stability and predictability of the urban system. High entropy indicates a highly unstable and unpredictable state; a small anomaly, such as a clogged manhole cover, can trigger a chain reaction through the network, leading to a rapid escalation of the disaster. Conversely, low entropy indicates a stable system with strong resilience. By quantifying flood vulnerability entropy, a heat map of urban flood vulnerability entropy can be generated, visually demonstrating the vulnerability levels of different urban areas. Based on this analysis, a second monitor is constructed to continuously track the trend of system entropy changes, enabling the monitoring and quantification of the dynamic evolution of urban vulnerability.

[0041] Finally, the first and second monitors are deployed in parallel, and the output results of both are taken as inputs for third-order training of the coupling assessment. The coupling assessment refers to comprehensive consideration of disaster probability dependency and flood vulnerability entropy quantization of two dimensions for risk assessment. Specifically, through parallel computing and feature weighting fusion, a comprehensive response function of the system under multi-dimensional disturbance is obtained, realizing comprehensive assessment of disaster propagation path, risk diffusion speed and system recovery capability. Finally, a complete disaster supervision component is built through third-order training, which can monitor, assess and warn urban flood disasters in real time, and provide accurate data support for the city information platform.

[0042] P30: Perform joint evaluation of the disaster supervision component under data initialization by performing city multi-source sensing and returning to the city information platform to determine the disaster monitoring state.

[0043] Further, the disaster supervision component is data initialized, and the embodiment of the present application step P30 further comprises:

[0044] P31: According to city multi-source sensing, a multi-source data set is collected, wherein the multi-source data set at least contains radar rainfall data, terrain data, GPS data and communication information flow field; P32: According to the multi-source data set, data initialization is performed on the city three-dimensional model in the disaster supervision component; P33: Based on the disaster supervision component after data initialization, the disaster monitoring state is analyzed.

[0045] Specifically, first, according to city multi-source sensing, a multi-source data set is collected. These data sets at least contain radar rainfall data, terrain data, GPS data and communication information flow field. Radar rainfall data is used to monitor the spatio-temporal distribution of rainfall in real time, terrain data provides detailed information of the city terrain, GPS data is used to locate and track the position of key facilities and vehicles, and communication information flow field reflects the real-time state of the city communication network. These multi-source data sets provide rich basic data for the disaster supervision component, which can ensure the comprehensiveness and accuracy of subsequent analysis.

[0046] Then, according to the collected multi-source data set, data initialization is performed on the city three-dimensional model in the disaster supervision component. Data initialization refers to integrating and loading the collected multi-source data set into the city three-dimensional model to ensure that the model can reflect the real state of the city. Specifically, the radar rainfall data is superimposed on the weather layer of the city three-dimensional model to realize the spatial mapping of rainfall dynamics; the terrain data and the drainage system topology data are spatially registered to update the surface water catchment path and pipe network smoothness parameters; the GPS and communication flow data are injected into the functional layer and load layer of the model in real time to dynamically correct the traffic flow and population migration characteristics. Through data initialization, the transformation from a static structure model to a dynamic operation model is completed, and the disaster supervision component has real-time response capability to reflect the current environmental state.

[0047] Finally, based on the initialized disaster monitoring component, the disaster monitoring state is analyzed. By calling the outputs of the first and second monitors, the probability dependence relationship and the flood vulnerability entropy distribution are jointly determined, and the dynamic characteristics of real-time multi-source data are combined to calculate the disaster risk level, the affected area range and the risk evolution trend, and output the multi-dimensional indicators of the disaster monitoring state, including the water level warning index, the traffic interruption probability, the communication failure risk and the drainage system overload rate, etc., to provide accurate decision basis for real-time monitoring of urban flood disasters.

[0048] Further, joint evaluation under data initialization is performed, and the step P30 of the embodiment of the present application further includes:

[0049] P34: According to the first monitor, the anisotropic projection mapping of the two-layer graph and the three-layer graph of the data-initialized urban three-dimensional model is performed; P35: The analysis based on the third load vulnerability graph of the two layers is performed to determine the one-step analysis result; P36: The one-step analysis result is transferred to the three layers, and the independent analysis based on the first structure vulnerability graph and the second function vulnerability graph is performed to determine the two-step analysis result; P37: According to the one-step analysis result and the two-step analysis result, real-time disaster probability dependence analysis is performed to output one-dimensional monitoring results.

[0050] Optionally, the process of joint evaluation can be further refined. First, according to the output of the first monitor, the anisotropic projection mapping of the two-layer graph and the three-layer graph of the data-initialized urban three-dimensional model is performed. Among them, the two-layer graph corresponds to the third load vulnerability graph, and the three-layer graph includes the first structure vulnerability graph and the second function vulnerability graph. Anisotropic projection mapping refers to projecting graph data in different directions to capture the vulnerability characteristics in different directions of the urban three-dimensional model. For example, in the scenario of heavy rainfall, the hydrodynamic effect shows significant directional influence in low-lying areas, while the distribution characteristics of structure damage and function decay have local aggregation in space. Through anisotropic mapping algorithms such as weighted Gaussian kernel projection or spatial direction matrix transformation, spatial coupling projection between rainfall field, drainage impact field and traffic disturbance field can be realized, providing refined input data set for subsequent analysis steps.

[0051] Next, a third load vulnerability map based on two layers is analyzed to determine the one-step analysis result. This step mainly focuses on the immediate impact of rainfall conditions on the urban drainage system. By analyzing the spatiotemporal aggregation of rainfall and the impact of surface rainfall on the drainage system, the current load vulnerability state is determined. For example, by hydrodynamic modeling and time series analysis, the evolution trend of local waterlogging caused by short-term heavy rainfall and the system critical state are identified, thereby forming a spatial distribution result reflecting the impact of rainfall, i.e., the one-step analysis result. This result describes the immediate response capability of the urban drainage system under the current rainfall scenario, which is a key prior input condition for subsequent structural and functional vulnerability analysis.

[0052] Then, the one-step analysis result is transferred to the third layer, i.e., input into the analysis module of the first structural vulnerability map and the second functional vulnerability map, to perform independent analysis to determine the two-step analysis result. This step uses the one-step analysis result as a prior condition to independently analyze structural vulnerability and functional vulnerability. By analyzing the structural vulnerability map and the functional vulnerability map, the actual state of each is determined. Specifically, the rainfall impact is used as a prior constraint to simulate the response of the structure layer and the function layer: in the structure layer, by analyzing the pressure state and failure probability of drainage facilities, underground space and surface buildings, the local structure disaster distribution is determined; in the function layer, by evaluating the traffic flow interruption rate, communication network connectivity and service accessibility, the function degradation area is identified. Further, a probability mutual information analysis is performed, i.e., the degree of information sharing between different vulnerability maps is analyzed to assess their mutual dependence, forming the two-step analysis result.

[0053] Finally, according to the one-step analysis result and the two-step analysis result, real-time disaster probability dependence analysis is performed to output one-dimensional monitoring results. This step considers the immediate impact of rainfall on the drainage system (one-step analysis result) and the actual state of structural and functional vulnerability (two-step analysis result), and through a disaster probability dependence model, the occurrence probability of urban flood disaster is evaluated in real time. The one-dimensional monitoring result will directly show the flood disaster risk of the city under the current conditions, providing real-time disaster monitoring data for the city information platform.

[0054] Further, the step P30 of the embodiment of the present application further comprises:

[0055] P38: According to the lateral interaction channel, the one-step analysis result and the two-step analysis result are shared to the second monitor; P39: The second monitor performs real-time quantification of flood vulnerability entropy to output two-dimensional monitoring results; P310: Coupling evaluation of spatiotemporal mapping of the one-dimensional monitoring result and the two-dimensional monitoring result is performed to output a disaster monitoring state.

[0056] In a possible embodiment of the present application, the joint evaluation process under data initialization can be further extended to ensure comprehensive and accurate evaluation and monitoring of the real-time state of urban flood disasters, and output the final disaster monitoring state.

[0057] Specifically, first, the one-step analysis result is shared to the second monitor according to the lateral interaction channel. The lateral interaction channel refers to a data sharing mechanism established between different monitors, which can ensure that each monitor can obtain and utilize the analysis results of other monitors in real time. This step can ensure that the analysis results of the first monitor, including the immediate impact of rainfall on the drainage system and the actual condition of structural and functional vulnerability, can be obtained by the second monitor, providing data support for subsequent flood vulnerability entropy quantification.

[0058] Then, the second monitor performs real-time quantification of flood vulnerability entropy and outputs two-dimensional monitoring results. This step is based on the function of the second monitor and uses flood vulnerability entropy quantification technology to evaluate the overall vulnerability state of the city in real time. Specifically, by real-time sampling of drainage system flow fluctuations, traffic flow time-varying characteristics, and communication network connectivity, the conditional entropy and joint entropy values of each spatial node are calculated to quantify system complexity and stability. High entropy values indicate that the city system is in a highly unstable and unpredictable state, while low entropy values indicate that the system state is stable and has strong impact resistance. By differentiating the entropy values at multiple times, the time gradient field of flood vulnerability entropy is obtained, and the two-dimensional monitoring results in the form of spatial thermal distribution are output, which can reflect the dynamic disaster sensitivity and risk evolution trend of different regions of the city under the current environment.

[0059] Finally, the one-dimensional monitoring results and two-dimensional monitoring results are coupled and evaluated by spatiotemporal mapping, and the disaster monitoring state is output. This process builds a spatiotemporal fusion model to perform multidimensional correlation analysis of one-dimensional monitoring results (reflecting risk evolution trajectories under probability dependence) and two-dimensional monitoring results (reflecting risk diffusion patterns under entropy space distribution), achieving global cognition and local response recognition of disaster risk. Specifically, spatiotemporal covariance matrix and mutual information mapping algorithms are used to calculate the risk coupling strength between different time slices and spatial units, and then form a disaster monitoring state matrix. Further, according to the matrix, comprehensive disaster state indicators are output, including risk level, affected range, vulnerability distribution, and trend vector, etc., achieving a dynamic closed loop from the probability layer to the entropy layer, from local analysis to global evaluation, which can provide comprehensive and accurate decision support for urban flood disaster management.

[0060] P40: According to the disaster monitoring state, urban flood disaster management and targeted monitoring guidance are performed.

[0061] Further, the step P40 of the embodiment of the present application further includes:

[0062] P41: Identify the disaster monitoring state, locate the risk control point and determine the risk control plan, generate disaster management instructions; P42: According to the risk control point, generate directional monitoring instructions with risk control trend; P43: Decouple and multi-thread the minimum execution unit of the disaster management instructions and directional monitoring instructions, and execute the dynamic supervision of urban flood disasters.

[0063] Specifically, first, the disaster monitoring state is identified and analyzed, and based on the comprehensive judgment of risk level, vulnerability distribution and trend vector in the monitoring state matrix, the risk control point in the city is automatically located and the corresponding disaster management instructions are generated. Among them, the risk control point refers to the node with high risk propagation potential or key control effect in the disaster propagation chain, including high water risk area, critical node of drainage system, traffic bottleneck point and communication high density area, etc. Further, based on these risk control points, the spatial position and risk level of the risk control points can be determined through time and space clustering algorithm and multi-dimensional risk weight evaluation, and corresponding risk control plans are generated according to different levels, including emergency response measures, resource allocation plan and personnel evacuation scheme, etc. Then, according to the risk control plan, disaster management instructions are generated, which will guide the subsequent disaster management actions.

[0064] Then, according to the identified risk control points and their risk evolution trend, directional monitoring instructions are generated, that is, based on the identification of risk control points and the formulation of risk control plans, further directional monitoring instructions are generated. Directional monitoring instructions refer to monitoring tasks for specific risk control points, which aim to track the state changes of risk control points in real time, evaluate risk trends, and adjust disaster management measures in time. For example, when the rising rate of flood water level of the risk control point exceeds the threshold, the system automatically schedules the water level sensor, video monitoring and drainage flow meter in the corresponding area for high frequency sampling; if the risk control point is located in a traffic hub or underground passage, the instruction contains the priority tasks of traffic flow monitoring and water depth detection. Through directional monitoring, the development dynamics of disaster can be more accurately mastered, providing real-time data support for disaster management.

[0065] Finally, the minimum execution unit decoupling and multi-threading of the disaster management instructions and directional monitoring instructions are performed, and the dynamic supervision of urban flood disasters is executed. This step involves decomposing disaster management instructions and directional monitoring instructions into minimum execution units, which are the basic units of task execution and can run independently and complete specific tasks, such as single node drainage scheduling, local traffic control or single area video review. Through minimum execution unit decoupling, the flexibility and efficiency of task execution can be improved. At the same time, by using multi-threading, tasks are allocated to multiple execution units for parallel processing, ensuring that tasks can be quickly responded and executed. In this way, the city can realize multi-department and multi-system linkage response during disaster occurrence, ensuring the real-time and efficiency of disaster monitoring, management and control process.

[0066] To sum up, the embodiments of the present application have at least the following technical effects:

[0067] The present application realizes the spatial fine identification of urban flood risk by constructing a three-dimensional model of the city and decoupling the evaluation of structure, function and load vulnerability; an intelligent analysis mechanism based on disaster probability dependence relationship and flood vulnerability entropy quantification is established through the supervised training of the disaster supervision component, realizing the dynamic prediction of disaster evolution; the real-time data initialization and joint evaluation of the model are completed by combining urban multi-source sensor data, improving the accuracy and response speed of monitoring; and the risk control and directional monitoring instructions are generated through disaster state identification, which are executed through multi-thread scheduling, realizing the automation of the closed loop from disaster monitoring, evaluation to management, and significantly enhancing the intelligent and emergency response capabilities of urban flood control.

[0068] The technical effects of the three-dimensional disaster supervision architecture based on big data are achieved, realizing multi-dimensional dynamic evaluation of urban flood disasters and improving the accuracy and response efficiency of disaster identification.

[0069] Embodiment two, based on the same inventive concept as the aforementioned embodiment of the big data-based dynamic monitoring method of urban flood disasters, as shown in Figure 2 The present application provides a big data-based dynamic monitoring system of urban flood disasters, and the system and method embodiments in the present application are based on the same inventive concept. The system comprises:

[0070] The multi-dimensional decoupling evaluation module 11 is used to construct a three-dimensional model of the city, and decouple the evaluation of structure vulnerability, function vulnerability and load vulnerability based on the three-dimensional model of the city for the dimensions of flood disasters, and construct a disaster supervision architecture.

[0071] The supervision component training module 12 is used to supervise the training of the disaster supervision component according to the disaster supervision architecture and embed it in the city information platform, wherein the training direction includes disaster probability dependence relationship, flood vulnerability entropy quantification and coupling evaluation.

[0072] The joint evaluation module 13 is used to perform joint evaluation of the disaster supervision component under data initialization by performing urban multi-source sensing and returning to the city information platform, and determine the disaster monitoring state.

[0073] The disaster management module 14 is used to perform urban flood disaster management and directional monitoring guidance according to the disaster monitoring state.

[0074] Further, the multi-dimensional decoupling evaluation module 11 is further used to perform the following steps:

[0075] According to the urban three-dimensional model, a drainage catchment area and a pipe network are taken as a first urban element, a terrain convergence potential and a drainage path dependence degree of each drainage catchment area are jointly evaluated, and a linear obstruction relationship is determined, wherein the drainage catchment area and the linear obstruction relationship are one-to-one corresponding; the first urban element is taken as a base, the linear obstruction relationship is marked for base position matching, and a first structural vulnerability map is generated.

[0076] Further, the multi-dimensional decoupling evaluation module 11 is further used to execute the following steps:

[0077] According to the urban three-dimensional model, a road network is taken as a second urban element, a road network passing evaluation of a key traffic hub is performed, a traffic flow resilience relationship is determined, wherein the key traffic hub and the traffic flow resilience relationship are one-to-one corresponding; the second urban element is taken as a base, the traffic flow resilience relationship is marked for base position matching, and a second functional vulnerability map is generated.

[0078] Further, the multi-dimensional decoupling evaluation module 11 is further used to execute the following steps:

[0079] The first urban element and the second urban element are taken as a base, a rainfall spatio-temporal aggregation degree and a surface rainfall are evaluated for drainage impact, a drainage impact relationship is determined and marked for base position matching, and a third load vulnerability map is generated; the urban three-dimensional model is taken as a layer, the third load vulnerability map is taken as a second layer, and the first structural vulnerability map and the second functional vulnerability map are taken as third layers in parallel, to constitute a disaster supervision architecture.

[0080] Further, the supervision component training module 12 is further used to execute the following steps:

[0081] The disaster supervision architecture is trained based on a first-order disaster probability dependence relationship to determine a first monitor; the disaster supervision architecture is trained based on a second-order flood vulnerability entropy quantization to determine a second monitor; the first monitor and the second monitor are deployed in parallel, a third-order training is performed based on a coupled evaluation output in parallel, and the disaster supervision component is built.

[0082] Further, the joint evaluation module 13 is further used to execute the following steps:

[0083] According to urban multi-source sensing, a multi-source data set is collected, wherein the multi-source data set at least contains radar rainfall data, terrain data, GPS data and communication information flow field; according to the multi-source data set, a data initialization is performed on the urban three-dimensional model in the disaster supervision component; based on the disaster supervision component after data initialization, a disaster monitoring state is analyzed.

[0084] Further, the joint evaluation module 13 is further used to execute the following steps:

[0085] According to the first monitor, the city three-dimensional model after data initialization is subjected to anisotropic projection mapping of two-layer atlas and three-layer atlas; analysis based on the third load vulnerability atlas of the two layers is performed to determine one-step analysis results; the one-step analysis results are transferred to the three layers, independent analysis based on the first structure vulnerability atlas and the second function vulnerability atlas is performed to determine two-step analysis results; real-time disaster probability dependence analysis is performed according to the one-step analysis results and the two-step analysis results, and one-dimensional monitoring results are output.

[0086] Further, the joint evaluation module 13 is further used to perform the following steps:

[0087] According to the lateral interaction channel, the one-step analysis results and the two-step analysis results are shared to the second monitor; the second monitor performs real-time quantification of flood vulnerability entropy, and outputs two-dimensional monitoring results; the one-dimensional monitoring results and the two-dimensional monitoring results are subjected to coupling evaluation of space-time mapping, and disaster monitoring states are output.

[0088] Further, the disaster management module 14 is further used to perform the following steps:

[0089] The disaster monitoring states are identified, a risk control point is located, a risk control plan is determined, disaster management instructions are generated; according to the risk control point, directional monitoring instructions are generated in a risk control trend; the disaster management instructions and the directional monitoring instructions are subjected to minimum execution unit decoupling and multi-threaded decentralization, and dynamic supervision of urban flood disasters is performed.

[0090] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes a specific embodiment of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0091] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0092] The specification and drawings are merely exemplary of the present application, and any and all modifications, variations, combinations or equivalents that fall within the scope of the present application are considered to be covered by the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and changes.

Claims

1. A dynamic monitoring method for urban flood disasters based on big data, characterized in that, The method includes: Construct a 3D model of the city, and conduct a decoupled assessment of the structural vulnerability, functional vulnerability and load vulnerability based on the 3D model of the city for the dimension of flood disaster, and construct a disaster monitoring architecture; According to the disaster monitoring architecture, the disaster monitoring components are trained and embedded in the urban information platform. The training directions include disaster probability dependency, flood vulnerability entropy quantification and coupling assessment. By performing multi-source sensing in the city and transmitting the data back to the city information platform, a joint assessment of the disaster monitoring components is conducted under data initialization to determine the disaster monitoring status. Based on the disaster monitoring status, provide guidance for urban flood disaster management and targeted monitoring.

2. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 1, characterized in that, A decoupled structural vulnerability assessment based on a 3D urban model was conducted to address flood disasters, including: Based on the aforementioned three-dimensional urban model, taking drainage catchment areas and pipe networks as the first urban elements, a joint assessment of topographic convergence potential and drainage path dependence is conducted on each drainage catchment area to determine the obstruction linear relationship, wherein there is a one-to-one correspondence between drainage catchment areas and obstruction linear relationships. Using the first urban element as a base, the base position matching and marking are performed on the obstruction linear relationship to generate a first structural vulnerability map.

3. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 2, characterized in that, Functional vulnerability decoupling assessment based on a 3D urban model was conducted to address flood disasters, including: Based on the aforementioned three-dimensional urban model, with the road network as the second urban element, a road network traffic assessment is conducted on key transportation hubs to determine traffic flow resilience relationships. Here, key transportation hubs correspond one-to-one with traffic flow resilience relationships. Using the second urban element as a base, the traffic flow resilience relationship is matched and marked with the base location to generate a second functional vulnerability map.

4. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 3, characterized in that, A decoupled assessment of load vulnerability based on a 3D urban model is conducted to address flood disasters, and a disaster monitoring architecture is constructed, including: Based on the first and second city elements, the drainage impact is assessed by the spatiotemporal concentration of rainfall and areal rainfall, the drainage impact relationship is determined and the base location is matched and marked to generate a third load vulnerability map. The disaster monitoring architecture consists of a three-dimensional urban model as one layer, a third load vulnerability map as the second layer, and the first structural vulnerability map and the second functional vulnerability map in parallel as the third layer.

5. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 1, characterized in that, The training component for disaster monitoring includes: The disaster monitoring architecture is trained in a first-order manner based on the disaster probability dependency relationship to determine the first monitor; The disaster monitoring architecture is subjected to second-order training based on flood vulnerability entropy quantization to determine the second monitor; The first and second monitors are deployed in parallel, and the coupled evaluations with parallel outputs are used for third-order training to build the disaster monitoring component.

6. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 5, characterized in that, Data initialization of the disaster monitoring component includes: Based on urban multi-source sensing, a multi-source dataset is collected, wherein the multi-source dataset includes at least radar rainfall data, terrain data, GPS data, and communication information flow field. Based on the multi-source dataset, the city 3D model within the disaster monitoring component is initialized. Based on the disaster monitoring component after data initialization, analyze the disaster monitoring status.

7. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 6, characterized in that, Perform joint evaluation under data initialization, including: Based on the first monitor, anisotropic projection mapping of the second-layer and third-layer maps is performed on the city's three-dimensional model after data initialization; Perform analysis based on the second-layer third load vulnerability map to determine the results of the first-step analysis; The results of the first step analysis are transferred to the third layer to perform independent analysis based on the first structural vulnerability map and the second functional vulnerability map to determine the results of the second step analysis. Based on the results of the first and second steps of analysis, a real-time disaster probability dependency analysis is performed, and a one-dimensional monitoring result is output.

8. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 7, characterized in that, According to the lateral interaction channel, the results of the first step analysis and the results of the second step analysis are shared with the second monitor; The second monitor performs real-time quantification of flood vulnerability entropy and outputs two-dimensional monitoring results; The one-dimensional monitoring results and the two-dimensional monitoring results are coupled and evaluated through spatiotemporal mapping, and the disaster monitoring status is output.

9. The method for dynamic monitoring of urban flood disasters based on big data as described in claim 1, characterized in that, Provide guidance on urban flood disaster management and targeted monitoring, including: Identify the disaster monitoring status, locate risk control points and determine risk control plans, and generate disaster management instructions; Based on the risk control points, targeted monitoring instructions are generated according to the risk control trends; The disaster management instructions and the targeted monitoring instructions are decoupled into minimum execution units and decentralized to multiple threads to perform dynamic monitoring of urban flood disasters.

10. A dynamic monitoring system for urban flood disasters based on big data, characterized in that: The system includes: The multidimensional decoupled assessment module is used to construct a three-dimensional urban model and conduct a decoupled assessment of the structural vulnerability, functional vulnerability, and load vulnerability based on the three-dimensional urban model for flood disasters, thereby constructing a disaster monitoring architecture. The disaster supervision component training module is used to supervise and train the disaster supervision component according to the disaster supervision architecture and embed it in the urban information platform. The training directions include disaster probability dependency, flood vulnerability entropy quantification and coupling assessment. The joint assessment module is used to conduct a joint assessment of the disaster monitoring components under data initialization by performing multi-source sensing in the city and transmitting the data back to the city information platform, so as to determine the disaster monitoring status. The disaster management module is used to manage urban flood disasters and provide targeted monitoring guidance based on the disaster monitoring status.

Images