A Method for Urban Disaster Simulation and Facility Layout Optimization Integrating Multi-Source Data

Abstract

This invention provides a method for urban disaster simulation and facility layout optimization that integrates multi-source data, relating to the field of urban disaster prevention and mitigation technology. The method includes: acquiring multi-source data of the study area; fusing the multi-source data to generate a basic dataset; constructing an urban disaster simulation model based on the basic dataset to obtain a spatiotemporal distribution map of disaster risk; calculating the urban spatial vulnerability index and emergency facility service effectiveness index for each spatial unit based on the spatiotemporal distribution map and the basic data; constructing a comprehensive resilience assessment function based on the two indices, and establishing a facility layout optimization model with the objective of maximizing the comprehensive resilience value; solving the model using a heuristic optimization algorithm to obtain and output the optimal facility layout scheme. This invention, by integrating multi-source data, dynamic disaster simulation, and resilience optimization, achieves accurate assessment of urban disaster risk and scientific layout of emergency facilities, effectively improving the city's comprehensive disaster prevention and mitigation capabilities.

Description

Technical Field

[0001] This invention relates to the field of urban disaster prevention and mitigation technology, and in particular to a method for urban disaster simulation and facility layout optimization that integrates multi-source data. Background Technology

[0002] In traditional urban planning and disaster prevention and mitigation, disaster risk assessment and emergency facility layout are typically two relatively independent workflows. On the one hand, disaster risk assessment relies on data from a single source, such as historical disaster statistics or topographic and hydrological models, which fails to comprehensively reflect the true risk level of a complex mega-system like a city under the influence of multiple factors. On the other hand, emergency facility layout planning often uses administrative divisions or population density to simply cover service radius areas, lacking consideration of the dynamic evolution of disasters and the actual service effectiveness of facilities during disasters. This fragmented approach leads to a disconnect between facility layout optimization and real disaster risk scenarios, failing to provide the most effective rescue and protection during disasters.

[0003] Existing urban disaster simulation methods are typically based on physical models. While these models can accurately simulate the physical processes of single disasters, their high computational complexity and numerous parameters make them unsuitable for rapid response to large-scale urban simulations and difficult to couple with subsequent optimization algorithms for iterative improvement. Furthermore, these simulation methods often neglect disaster-bearing information within the urban system, such as population distribution, building structure, and critical infrastructure networks. This results in simulations that merely capture the natural attributes of disasters, failing to translate them into socially significant disaster risks. Consequently, planning decision-makers struggle to intuitively understand the potential impact of disasters on urban operations and residents' lives.

[0004] In optimizing the layout of emergency facilities, existing technologies mostly employ traditional site selection models, such as central location models or coverage models. These models use distance or time as a single optimization objective, aiming to maximize the covered population or minimize response time. However, this optimization approach fails to fully integrate the dynamic risk information output from disaster simulations. As a result, while the facility layout may perform well under normal circumstances, its actual service effectiveness is significantly reduced in abnormal disaster scenarios due to factors such as road disruptions, surges in demand, and damage to the facilities themselves. Furthermore, the objective functions of existing optimization models are relatively simple, lacking a comprehensive evaluation index that can comprehensively measure urban vulnerability, facility service capacity, and the interaction between the two. Therefore, they are difficult to truly guide the planning and construction of resilient cities.

[0005] In summary, the core problem with existing technologies lies in the lack of an integrated technical framework that combines multi-source data fusion, dynamic disaster simulation, urban spatial vulnerability assessment, and emergency facility service effectiveness analysis. Specifically, this manifests in several ways: data sources are singular and inconsistent in format, making comprehensive analysis difficult; disaster simulation and facility optimization are disconnected, with optimization results lacking responsiveness to the dynamic processes of disasters; and assessment indicators are one-sided, failing to comprehensively measure a city's resilience in the face of disasters. These issues result in limited effectiveness of the final facility layout schemes in actual disaster response, failing to effectively improve a city's comprehensive disaster prevention and mitigation capabilities. Summary of the Invention

[0006] To address the technical problems in existing technologies, such as the disconnect between urban disaster simulation and emergency facility layout optimization, insufficient data utilization, and one-sided evaluation indicators that prevent optimization results from accurately reflecting urban resilience requirements under disaster scenarios, this invention provides a method for urban disaster simulation and facility layout optimization that integrates multi-source data.

[0007] The technical solution provided by this invention is as follows: This invention provides a method for urban disaster simulation and facility layout optimization that integrates multi-source data, comprising: S1: Obtain multi-source data for the study area, including geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data; S2: Perform fusion processing on the multi-source data to generate a basic dataset in a unified format; S3: Construct an urban disaster simulation model based on the aforementioned basic dataset to simulate the disaster evolution process under preset disaster scenarios and obtain a spatiotemporal distribution map of disaster risk; S4: Based on the aforementioned disaster risk spatiotemporal distribution map and urban basic data, calculate the urban spatial vulnerability index for each spatial unit within the study area, and calculate the service efficiency index of existing emergency facilities; S5: Based on the urban spatial vulnerability index and the emergency facility service efficiency index, construct a comprehensive resilience assessment function, and establish a facility layout optimization model with the goal of maximizing the comprehensive resilience value. The optimization model includes decision variables, constraints and objective function. S6: The facility layout optimization model is solved using a heuristic optimization algorithm to obtain the optimal facility layout scheme; S7: Output the optimal facility layout scheme.

[0008] The beneficial effects of the technical solution provided by this invention include at least the following: (1) In this invention, a unified format basic dataset is constructed by acquiring and integrating multi-source data such as geospatial, meteorological and hydrological, population distribution, infrastructure, and historical disasters. This technical approach solves the problem of single data sources and difficulty in integration and analysis in traditional methods, enabling subsequent disaster simulation and facility assessment to be based on a comprehensive and realistic data foundation that reflects the complex urban system. At the same time, by constructing an urban disaster simulation model, the evolution process of disasters is dynamically simulated, combining the natural attributes and socio-economic attributes of disasters. The output spatiotemporal distribution map of disaster risk can intuitively show the dynamic changes of risk in time and space, providing a scientific basis for accurately identifying high-risk areas and significantly improving the accuracy and refinement of urban disaster risk assessment.

[0009] (2) In this invention, based on disaster simulation results and urban basic data, the urban spatial vulnerability index and the service effectiveness index of existing emergency facilities for each spatial unit are innovatively calculated. These two self-created parameters quantify the core elements of urban resilience from two dimensions: the vulnerability of the disaster-bearing body and the guarantee capacity of disaster prevention facilities. In particular, by comprehensively considering multiple factors such as population, buildings, elevation, infrastructure, historical disasters, facility distance, response time, and traffic conditions through complex mathematical formulas, the vulnerability and effectiveness assessment is more comprehensive, objective, and accurate. This technical approach solves the problem of single assessment indicators and inability to reflect complex interactions in traditional methods, laying a solid foundation for the subsequent construction of a comprehensive resilience assessment function, and making resilience assessment truly evidence-based and quantifiable.

[0010] (3) In this invention, by constructing a comprehensive resilience assessment function and establishing a facility layout optimization model with the goal of maximizing the comprehensive resilience value, the disaster simulation results and facility layout optimization are successfully integrated. The optimization model not only considers vulnerability distribution and service effectiveness, but also incorporates practical constraints such as the number of facilities, coverage radius, capacity limit, and land suitability, and solves for the optimal solution through a heuristic algorithm. This technical approach breaks down the barriers between disaster risk assessment and facility layout optimization in traditional planning, enabling the optimized facility layout scheme to directly respond to dynamic disaster risks and effectively improve the overall resilience of the city in the face of disasters. The final output of the visualized map and statistical report provides urban planning managers with an intuitive and scientific decision support tool. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating a method for urban disaster simulation and facility layout optimization that integrates multi-source data, as provided in an embodiment of the present invention. Detailed Implementation

[0013] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0014] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0015] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0016] In embodiments of the present invention, sometimes the subscript is as follows: It may be mistakenly written as a non-subscript form such as W1. When the distinction is not emphasized, the meaning they express is the same.

[0017] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0018] Reference manual attached Figure 1 The diagram illustrates a flowchart of a method for urban disaster simulation and facility layout optimization that integrates multi-source data, provided by an embodiment of the present invention.

[0019] This invention provides a method for urban disaster simulation and facility layout optimization that integrates multi-source data. The processing flow may include the following steps: S1: Obtain multi-source data for the study area, including geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data.

[0020] First, multi-source data for the study area is acquired. This multi-source data includes geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data. Geospatial data is obtained through satellite remote sensing imagery, aerial photogrammetry, or geographic information system databases, and includes digital elevation models, land use types, and building outlines. Meteorological and hydrological data is collected from meteorological stations, hydrological stations, or reanalysis data, covering rainfall, wind speed, and water levels. Population distribution data comes from census statistics or mobile location big data such as mobile phone signaling, representing population density in raster or vector form. Infrastructure data includes transportation networks, power and water supply pipelines, and the location and capacity of emergency facilities, obtained from municipal departments or publicly available maps. Historical disaster data records the time, location, intensity, and damage of past disasters, sourced from disaster archives or scientific literature. All data is cropped and projected uniformly according to the study area scope to lay the foundation for subsequent processing.

[0021] S2: Perform fusion processing on the multi-source data to generate a basic dataset in a unified format.

[0022] The acquired multi-source data are fused to generate a unified basic dataset. First, the data types are converted to a common raster or vector format and standardized to the same spatial reference coordinate system. Then, data quality checks are performed to identify missing and outlier values, which are corrected using interpolation or statistical methods. For data from different sources, spatial overlay analysis is used to match attribute information to the same spatial units. For example, using a fixed-size grid as the basic unit, data on population, buildings, facilities, etc., are aggregated into each grid. Simultaneously, time-series data such as meteorological and hydrological data are time-aligned to generate dynamic inputs that match the time step of the disaster simulation. Finally, a basic dataset covering the entire study area and containing all necessary attribute fields is obtained for subsequent disaster simulation and assessment.

[0023] S3: Construct an urban disaster simulation model based on the aforementioned basic dataset to simulate the disaster evolution process under preset disaster scenarios and obtain a spatiotemporal distribution map of disaster risk.

[0024] Based on the aforementioned basic dataset, an urban disaster simulation model is constructed to simulate the evolution of disasters under preset disaster scenarios, obtaining a spatiotemporal distribution map of disaster risk. First, according to the types of disasters the study area may face, such as floods, earthquakes, or typhoons, an appropriate physical mechanism model or empirical statistical model is selected. Using topographic, hydrological, and meteorological data from the basic dataset as initial and boundary conditions, disaster triggering parameters are set, such as rainfall intensity, magnitude, and typhoon path. Numerical simulation methods, such as the finite difference method or cellular automata, are used to iteratively calculate the diffusion and evolution of the disaster in time and space, obtaining disaster intensity indicators at different times, such as inundation depth, flow velocity, seismic intensity, or wind pressure. The simulation results are output according to the time step, forming a series of spatiotemporal distribution maps of disaster risk, reflecting the dynamic changes of risk in space during the disaster occurrence process.

[0025] S4: Based on the aforementioned disaster risk spatiotemporal distribution map and urban basic data, calculate the urban spatial vulnerability index for each spatial unit within the study area, and calculate the service efficiency index of existing emergency facilities.

[0026] Based on the aforementioned spatiotemporal distribution map of disaster risk and urban basic data, the urban spatial vulnerability index for each spatial unit within the study area, as well as the service effectiveness index of existing emergency facilities, are calculated. The urban spatial vulnerability index reflects the degree of potential loss to each spatial unit in the face of a disaster. It is calculated based on a combination of exposure and sensitivity indicators for that unit. Exposure indicators include population density and building value, while sensitivity indicators include ground elevation, historical disaster frequency, and critical infrastructure density. These indicators are extracted from the basic dataset and obtained through weighted or function transformations to arrive at vulnerability values. The emergency facility service effectiveness index characterizes the rescue and support capabilities that existing emergency facilities can provide during a disaster. Its calculation considers the facility's location, capacity, service radius, and accessibility to the demand point. A spatial accessibility model is used to assess the population covered by the facilities and response efficiency, ultimately yielding a comprehensive service effectiveness value for the entire region.

[0027] S5: Based on the urban spatial vulnerability index and the emergency facility service efficiency index, construct a comprehensive resilience assessment function, and establish a facility layout optimization model with the goal of maximizing the comprehensive resilience value. The optimization model includes decision variables, constraints and objective function.

[0028] Based on the urban spatial vulnerability index and the emergency facility service effectiveness index, a comprehensive resilience assessment function is constructed, and a facility layout optimization model is established with the objective of maximizing the comprehensive resilience value. The comprehensive resilience assessment function combines vulnerability and service effectiveness, typically converting the vulnerability index into resilience, and then fusing it with the service effectiveness index through multiplicative or additive methods to obtain the resilience value of each spatial unit, which is then aggregated into the comprehensive resilience value for the entire region. The facility layout optimization model uses the location and capacity of facilities as decision variables, with the objective function being the maximization of the comprehensive resilience value. It also sets a series of constraints, including an upper limit on the number of facilities, coverage distance restrictions, capacity constraints, and land suitability requirements. This model is a multi-constraint nonlinear optimization problem, requiring the search for the layout scheme that maximizes resilience within the feasible region.

[0029] S6: Use a heuristic optimization algorithm to solve the facility layout optimization model to obtain the optimal facility layout scheme.

[0030] A heuristic optimization algorithm is used to solve the facility layout optimization model to obtain the optimal facility layout scheme. Since facility layout problems are typically NP-hard, heuristic algorithms can obtain near-optimal solutions within a reasonable time. The algorithm initializes by generating a set of random layout schemes as an initial population, each scheme containing the spatial coordinates and service capacity of the facilities. Then, the fitness value of each scheme is calculated according to the objective function, and a new generation of population is generated through selection, crossover, and mutation operations. This process is iteratively repeated until the convergence condition is met, and finally, the layout scheme with the highest overall resilience value is output as the optimal solution. During the solution process, genetic algorithms, particle swarm optimization algorithms, or simulated annealing algorithms can be selected depending on the problem size.

[0031] S7: Output the optimal facility layout scheme.

[0032] Output the optimal facility layout scheme. The solved facility layout scheme will be presented in the form of a visual map and structured data. The locations of newly added or adjusted emergency facilities will be marked on the map, along with attribute information such as facility type and capacity. Comparison charts will also be generated to show the improvement in the overall resilience index before and after optimization, as well as the changes in service coverage in each area. The output scheme file can be imported into a geographic information system or urban management platform for reference by planning decision-makers.

[0033] In one possible implementation, calculating the urban spatial vulnerability index for each spatial unit in step S4 specifically includes: S401: Divide the study area into several grid units; S402: For each grid cell, extract population density, building type and number, ground elevation, historical disaster frequency, and critical infrastructure density indicators; S403: Calculate the urban spatial vulnerability index for each grid cell using the following formula. : ; in, Let i be the population of grid cell i. The average population of all grid cells; Let i be the number of buildings of type n within grid cell i. The maximum number of buildings of type n in all grid cells; N is the total number of building types; Let i be the ground elevation of grid cell i. and These represent the minimum and maximum elevations of the study area, respectively. Let m be the density of the m-th type of critical infrastructure within grid cell i. M represents the maximum density of the m-th type of critical infrastructure in all grid cells; M is the total number of critical infrastructure types. The normalized value of the historical disaster frequency for grid cell i. This represents the maximum frequency of historical disasters across all grid cells.

[0034] The study area was divided into several regular grid units, each serving as the basic spatial unit for vulnerability assessment. For each grid unit, population density, building type and number, ground elevation, historical disaster frequency, and critical infrastructure density indicators were extracted from the base dataset. Population density was calculated based on the population within the grid; building type and number were categorized and statistically analyzed based on building census data; ground elevation was obtained from a digital elevation model; historical disaster frequency was calculated based on the number of disasters occurring within the grid; and critical infrastructure density was obtained by dividing the length or number of facilities such as water supply, power supply, and transportation by the grid area. Subsequently, the urban spatial vulnerability index for each grid unit was calculated using the following formula. This formula comprehensively considers population exposure, building vulnerability, the buffering effect of topography on disasters, the redundancy of critical infrastructure, and the enhancing effect of historical disaster frequency on vulnerability. The vulnerability index for each grid unit is obtained by combining these indicators using this formula.

[0035] In one possible implementation, calculating the emergency facility service effectiveness index in step S4 specifically includes: S411: Determine the set J of all emergency facilities and the set I of all demand points within the study area, where the demand points are grid cells; S412: Obtain the capacity of each emergency facility j Service radius and the population at each demand point i ; S413: Calculate the emergency facility service effectiveness index E for the entire region using the following formula: ; in, The Euclidean distance or network distance from demand point i to emergency facility j; The estimated travel time from demand point i to emergency facility j; The standard response time threshold for facility j; This represents the real-time traffic congestion index along the route. I represents the maximum congestion index within the study area; J represents the total number of demand points and the total number of emergency facilities.

[0036] The study area is defined by identifying the set of all emergency facilities and the set of all demand points, which are represented by the aforementioned grid cells. The capacity and service radius of each emergency facility, as well as the population of each demand point, are obtained. Capacity refers to the maximum number of people or the amount of supplies a facility can serve, and service radius refers to the maximum distance a facility can effectively cover. Population data for each demand point is extracted from the base dataset. The emergency facility service efficiency index for the entire area is then calculated using the following formula. This formula integrates the effects of distance decay, response time constraints, and real-time traffic congestion on service efficiency, quantifying the overall service efficiency of the facilities.

[0037] In one possible implementation, step S2 involves fusing the multi-source data, including: S201: Perform format conversion and coordinate unification on geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data respectively; S202: The random forest algorithm is used to impute missing values ​​and correct outliers in the transformed data; S203: Based on the corrected data, spatial overlay analysis is performed using geographic information system technology to generate a basic dataset in a unified format, wherein the basic dataset contains attribute information for each spatial unit.

[0038] First, the acquired geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data were converted to common formats such as GeoTIFF or Shapefile, and the coordinate system was set to the projected coordinate system used in the study area. Then, a random forest algorithm was used to impute missing values ​​and correct outliers in the converted data. A regression model was trained to predict missing values ​​using relevant features and identify and correct outliers that deviated from the normal range. Finally, based on the corrected data, spatial overlay analysis was performed using Geographic Information System (GIS) technology. Data from different layers were correlated by grid cell to generate a unified base dataset. This base dataset contains all attribute information for each spatial cell, including population, buildings, elevation, facilities, and historical disasters.

[0039] In one possible implementation, step S3, which involves constructing an urban disaster simulation model, specifically includes: S301: Select the appropriate physical or empirical model based on the type of disaster, including floods, earthquakes, and typhoons; S302: Using topographic, hydrological, and meteorological data from the basic dataset as model input, the cellular automata method is used to simulate the spatiotemporal diffusion process of disasters; S303: Accelerate the simulation process through parallel computing technology and output a spatiotemporal distribution map of disaster risk at a preset time step. The distribution map includes parameters such as inundation range, water depth, flow velocity, or seismic intensity.

[0040] The appropriate physical or empirical model is selected based on the types of potential disasters in the study area. For floods, a hydrodynamic model is used; for earthquakes, a ground motion attenuation model or intensity distribution model is used; and for typhoons, a wind field model and storm surge model are used. Using topographic, hydrological, and meteorological data from the basic dataset as model input, a cellular automata method is employed to simulate the spatiotemporal diffusion process of disasters. The study area is discretized into a cellular grid, and the state of each cell is iteratively updated according to local transformation rules. Parallel computing technology is used to accelerate the simulation process, distributing the simulation task to multiple computing cores for simultaneous execution. The output is a spatiotemporal distribution map of disaster risk at a preset time step, including parameters such as inundation range, water depth, flow velocity, or seismic intensity, reflecting the dynamic risk of the disaster evolving over time.

[0041] In one possible implementation, the construction of the comprehensive resilience assessment function in step S5 specifically includes: S501: The vulnerability index is obtained by reciprocal transformation and normalization of the urban spatial vulnerability index; S502: Normalize the emergency facility service effectiveness index; S503: Multiply the vulnerability resilience index by the emergency facility service effectiveness index to obtain the comprehensive resilience value of each spatial unit, and summarize them to obtain the comprehensive resilience assessment function of the entire region.

[0042] First, the urban spatial vulnerability index is transformed by its reciprocal and normalized to obtain the vulnerability resilience index. This is achieved by taking the reciprocal of the vulnerability index for each grid cell and then performing minimum-maximum normalization, ensuring the resilience index falls between zero and one. Next, the emergency facility service effectiveness index is normalized using the same minimum-maximum normalization method. Finally, the vulnerability resilience index of each grid cell is multiplied by the emergency facility service effectiveness index to obtain the overall resilience value for that cell. The overall resilience values ​​of all cells are then aggregated to obtain the overall resilience assessment function for the entire region. This function measures the overall resilience of the region in the face of disasters.

[0043] In one possible implementation, step S5 establishes a facility layout optimization model, the constraints of which include: S511: The number of facilities does not exceed the preset upper limit; S512: Each demand point is covered by at least one emergency facility, and the coverage distance does not exceed the service radius of the facility; S513: The capacity of each emergency facility shall not exceed its maximum carrying capacity; S514: Facility site selection should comply with land use planning and construction conditions.

[0044] The constraints include: the number of facilities not exceeding a preset upper limit, determined based on resource allocation and planning requirements; each demand point being covered by at least one emergency facility, with the coverage distance not exceeding the facility's service radius to ensure basic services are available to all areas; and each emergency facility's capacity not exceeding its maximum carrying capacity to avoid overloading. Facility locations must comply with land use planning and construction conditions, for example, they cannot be located in water areas, nature reserves, or geologically unstable areas. These constraints collectively constitute the feasible region of the optimization model, ensuring the optimization results are practically feasible.

[0045] In one possible implementation, step S6 employs a heuristic optimization algorithm to solve the facility layout optimization model, specifically including: S601: Initialize the population, with each individual representing a facility layout scheme, including the location and capacity of the facilities; S602: Calculate the fitness value of each individual based on the comprehensive resilience assessment function; S603: A new generation population is generated using selection, crossover, and mutation operations of a non-dominated sorting genetic algorithm. S604: Iterate through S602 to S603 until the termination condition is met, and output the Pareto optimal solution set as the optimal facility layout scheme.

[0046] Initialize the population, with each individual representing a facility layout scheme, including the facility's location coordinates and capacity configuration. The population size is set appropriately based on the problem complexity. Calculate the fitness value of each individual using the comprehensive resilience assessment function; this fitness value is the objective function value. A new generation of the population is generated using a non-dominated sorting genetic algorithm with selection, crossover, and mutation operations. The selection operation employs tournament selection or roulette wheel selection, the crossover operation simulates biological chromosome exchange, and the mutation operation randomly perturbs certain decision variables in the scheme. Iteratively execute fitness calculations and genetic operations until the maximum number of iterations or the convergence condition is met. Output the Pareto optimal solution set as the optimal facility layout scheme; each solution in this set is not dominated by any other solution across multiple objectives.

[0047] In one possible implementation, after outputting the Pareto optimal solution set in step S604, the method further includes: S605: Perform a multi-criteria evaluation on each solution in the Pareto optimal solution set, the multi-criteria evaluation including cost-benefit analysis, environmental impact assessment and social equity test; S606: Based on preset weights or decision-maker preferences, select the optimal facility layout scheme from the Pareto optimal solution set as the final output.

[0048] For each solution in the Pareto optimal solution set, a multi-criteria evaluation is performed. The evaluation includes cost-benefit analysis (calculating the construction cost and expected benefits of the proposed solution); environmental impact assessment (evaluating the potential impact of the solution on the natural environment); and social equity test (checking whether the solution leads to uneven distribution of service resources among different regions). Based on pre-defined weights or decision-maker preferences, a multi-attribute decision-making method is used to select the comprehensively optimal facility layout scheme from the Pareto optimal solution set as the final output. This scheme balances resilience maximization with multi-criteria equilibrium.

[0049] In one possible implementation, step S7, which outputs the optimal facility layout scheme, specifically includes: S701: Generate a visual map to show the comparison of facility layout before and after optimization, as well as the improvement in the overall resilience index; S702: Generates a statistical report containing comparative data on various indicators before and after optimization.

[0050] Generate a visual map, marking the locations of newly added or adjusted emergency facilities with symbols, and using different colors to represent changes in service coverage before and after optimization. The map also displays the spatial distribution of the improvement in the overall resilience index. Generate a statistical report containing comparative data on various indicators before and after optimization, such as the number of facilities, average response time, coverage percentage, and overall resilience value, clearly presenting the optimization effects in tables and charts. Finally, integrate the map and report for output as a reference for planning departments' decision-making.

[0051] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: (1) In this invention, a unified format basic dataset is constructed by acquiring and integrating multi-source data such as geospatial, meteorological and hydrological, population distribution, infrastructure, and historical disasters. This technical approach solves the problem of single data sources and difficulty in integration and analysis in traditional methods, enabling subsequent disaster simulation and facility assessment to be based on a comprehensive and realistic data foundation that reflects the complex urban system. At the same time, by constructing an urban disaster simulation model, the evolution process of disasters is dynamically simulated, combining the natural attributes and socio-economic attributes of disasters. The output spatiotemporal distribution map of disaster risk can intuitively show the dynamic changes of risk in time and space, providing a scientific basis for accurately identifying high-risk areas and significantly improving the accuracy and refinement of urban disaster risk assessment.

[0052] (2) In this invention, based on disaster simulation results and urban basic data, the urban spatial vulnerability index and the service effectiveness index of existing emergency facilities for each spatial unit are innovatively calculated. These two self-created parameters quantify the core elements of urban resilience from two dimensions: the vulnerability of the disaster-bearing body and the guarantee capacity of disaster prevention facilities. In particular, by comprehensively considering multiple factors such as population, buildings, elevation, infrastructure, historical disasters, facility distance, response time, and traffic conditions through complex mathematical formulas, the vulnerability and effectiveness assessment is more comprehensive, objective, and accurate. This technical approach solves the problem of single assessment indicators and inability to reflect complex interactions in traditional methods, laying a solid foundation for the subsequent construction of a comprehensive resilience assessment function, and making resilience assessment truly evidence-based and quantifiable.

[0053] (3) In this invention, by constructing a comprehensive resilience assessment function and establishing a facility layout optimization model with the goal of maximizing the comprehensive resilience value, the disaster simulation results and facility layout optimization are successfully integrated. The optimization model not only considers vulnerability distribution and service effectiveness, but also incorporates practical constraints such as the number of facilities, coverage radius, capacity limit, and land suitability, and solves for the optimal solution through a heuristic algorithm. This technical approach breaks down the barriers between disaster risk assessment and facility layout optimization in traditional planning, enabling the optimized facility layout scheme to directly respond to dynamic disaster risks and effectively improve the overall resilience of the city in the face of disasters. The final output of the visualized map and statistical report provides urban planning managers with an intuitive and scientific decision support tool.

[0054] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0055] The following points need to be explained: (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0056] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the invention, i.e., these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element or there may be intermediate elements.

[0057] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0058] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for urban disaster simulation and facility layout optimization that integrates multi-source data, characterized in that, include: S1: Obtain multi-source data for the study area, including geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data; S2: Perform fusion processing on the multi-source data to generate a basic dataset in a unified format; S3: Construct an urban disaster simulation model based on the aforementioned basic dataset to simulate the disaster evolution process under preset disaster scenarios and obtain a spatiotemporal distribution map of disaster risk; S4: Based on the aforementioned disaster risk spatiotemporal distribution map and urban basic data, calculate the urban spatial vulnerability index for each spatial unit within the study area, and calculate the service efficiency index of existing emergency facilities; S5: Based on the urban spatial vulnerability index and the emergency facility service efficiency index, construct a comprehensive resilience assessment function, and establish a facility layout optimization model with the goal of maximizing the comprehensive resilience value. The optimization model includes decision variables, constraints and objective function. S6: The facility layout optimization model is solved using a heuristic optimization algorithm to obtain the optimal facility layout scheme; S7: Output the optimal facility layout scheme.

2. The method for urban disaster simulation and facility layout optimization by fusing multi-source data as described in claim 1, characterized in that, The calculation of the urban spatial vulnerability index for each spatial unit in step S4 specifically includes: S401: Divide the study area into several grid units; S402: For each grid cell, extract population density, building type and number, ground elevation, historical disaster frequency, and critical infrastructure density indicators; S403: Calculate the urban spatial vulnerability index for each grid cell using the following formula. : ； in, Let i be the population of grid cell i. The average population of all grid cells; Let i be the number of buildings of type n within grid cell i. The maximum number of buildings of type n in all grid cells; N is the total number of building types; Let i be the ground elevation of grid cell i. and These represent the minimum and maximum elevations of the study area, respectively. Let m be the density of the m-th type of critical infrastructure within grid cell i. M represents the maximum density of the m-th type of critical infrastructure in all grid cells; M is the total number of critical infrastructure types. The normalized value of the historical disaster frequency for grid cell i. This represents the maximum frequency of historical disasters across all grid cells.

3. The method for urban disaster simulation and facility layout optimization by fusing multi-source data as described in claim 1, characterized in that, The calculation of the emergency facility service effectiveness index in step S4 specifically includes: S411: Determine the set J of all emergency facilities and the set I of all demand points within the study area, where the demand points are grid cells; S412: Obtain the capacity of each emergency facility j Service radius and the population at each demand point i ; S413: Calculate the emergency facility service effectiveness index E for the entire region using the following formula: ； in, The Euclidean distance or network distance from demand point i to emergency facility j; The estimated travel time from demand point i to emergency facility j; The standard response time threshold for facility j; This represents the real-time traffic congestion index along the route. I represents the maximum congestion index within the study area; J represents the total number of demand points and the total number of emergency facilities.

4. The method for urban disaster simulation and facility layout optimization by fusing multi-source data as described in claim 1, characterized in that, The step S2, which involves fusing multi-source data, includes: S201: Perform format conversion and coordinate unification on geospatial data, meteorological and hydrological data, population distribution data, infrastructure data, and historical disaster data respectively; S202: The random forest algorithm is used to impute missing values ​​and correct outliers in the transformed data; S203: Based on the corrected data, spatial overlay analysis is performed using geographic information system technology to generate a basic dataset in a unified format, wherein the basic dataset contains attribute information for each spatial unit.

5. The method for urban disaster simulation and facility layout optimization by fusing multi-source data according to claim 1, characterized in that, The construction of the urban disaster simulation model in step S3 specifically includes: S301: Select the appropriate physical or empirical model based on the type of disaster, including floods, earthquakes, and typhoons; S302: Using topographic, hydrological, and meteorological data from the basic dataset as model input, the cellular automata method is used to simulate the spatiotemporal diffusion process of disasters; S303: Accelerate the simulation process through parallel computing technology and output a spatiotemporal distribution map of disaster risk at a preset time step. The distribution map includes parameters such as inundation range, water depth, flow velocity, or seismic intensity.

6. The method for urban disaster simulation and facility layout optimization by fusing multi-source data according to claim 1, characterized in that, The construction of the comprehensive resilience assessment function in step S5 specifically includes: S501: The vulnerability index is obtained by reciprocal transformation and normalization of the urban spatial vulnerability index; S502: Normalize the emergency facility service effectiveness index; S503: Multiply the vulnerability resilience index by the emergency facility service effectiveness index to obtain the comprehensive resilience value of each spatial unit, and summarize them to obtain the comprehensive resilience assessment function of the entire region.

7. The method for urban disaster simulation and facility layout optimization by fusing multi-source data according to claim 1, characterized in that, In step S5, a facility layout optimization model is established, and the constraints include: S511: The number of facilities does not exceed the preset upper limit; S512: Each demand point is covered by at least one emergency facility, and the coverage distance does not exceed the service radius of the facility; S513: The capacity of each emergency facility shall not exceed its maximum carrying capacity; S514: Facility site selection should comply with land use planning and construction conditions.

8. The method for urban disaster simulation and facility layout optimization by fusing multi-source data according to claim 1, characterized in that, Step S6 employs a heuristic optimization algorithm to solve the facility layout optimization model, specifically including: S601: Initialize the population, with each individual representing a facility layout scheme, including the location and capacity of the facilities; S602: Calculate the fitness value of each individual based on the comprehensive resilience assessment function; S603: A new generation population is generated using selection, crossover, and mutation operations of a non-dominated sorting genetic algorithm. S604: Iterate through S602 to S603 until the termination condition is met, and output the Pareto optimal solution set as the optimal facility layout scheme.

9. The method for urban disaster simulation and facility layout optimization by fusing multi-source data as described in claim 8, characterized in that, After outputting the Pareto optimal solution set in step S604, the following steps are also included: S605: Perform a multi-criteria evaluation on each solution in the Pareto optimal solution set, the multi-criteria evaluation including cost-benefit analysis, environmental impact assessment and social equity test; S606: Based on preset weights or decision-maker preferences, select the optimal facility layout scheme from the Pareto optimal solution set as the final output.

10. The method for urban disaster simulation and facility layout optimization by fusing multi-source data according to claim 1, characterized in that, The optimal facility layout scheme output in step S7 specifically includes: S701: Generate a visual map to show the comparison of facility layout before and after optimization, as well as the improvement in the overall resilience index; S702: Generates a statistical report containing comparative data on various indicators before and after optimization.

Images