Urban flood disaster comprehensive defense capability evaluation method based on weight initialization

Abstract

The application discloses a kind of urban flood disaster comprehensive defense capability evaluation method based on weight initialization, including collecting the historical data of research area, the historical data is preprocessed;Based on the historical data, evaluation partition is obtained, and evaluation index is obtained by screening the historical data according to flood prevention influence degree;Based on the evaluation index, an evaluation index system is constructed, the evaluation index system is initialized by weight using He initialization, and the comprehensive flood prevention grade is obtained according to the evaluation index system and the evaluation partition;Based on the comprehensive flood prevention grade, a flood prevention evaluation model is established, the evaluation data is input into the flood prevention evaluation model, and the evaluation result is output.The method can not only improve the accuracy of urban space flood disaster comprehensive defense capability evaluation, but also has good interpretability, and can be directly applied to urban space flood disaster comprehensive defense capability evaluation system.

Description

Technical Field

[0001] This invention relates to the field of urban flood assessment, and in particular to a method for evaluating the comprehensive defense capabilities of urban flood disasters based on weight initialization. Background Technology

[0002] In recent years, influenced by climate change and rapid urbanization, urban water cycles have undergone significant changes, with the frequency and intensity of floods in some cities showing a marked increase. Urban flooding not only directly threatens human life but also causes substantial socio-economic losses. How to effectively prevent flood disasters and minimize the socio-economic losses they cause is a crucial research topic in the field of urban flooding. Currently, influenced by factors such as land use, terrain conditions, and water conservancy project construction, there are significant differences in flood disaster prevention capabilities among different spatial functional areas of a city. Assessing the flood disaster prevention capabilities of different urban areas has become particularly important. Traditional methods for evaluating flood prevention capabilities typically consider the defensive capabilities of engineering projects, while neglecting spatial infrastructure layout, emergency management capabilities, and resource allocation capabilities. Therefore, there is an urgent need to develop a rapid and accurate method for evaluating the comprehensive urban spatial flood prevention capabilities. Summary of the Invention

[0003] The purpose of this invention is to provide a method for evaluating the comprehensive defense capabilities of urban flood disasters based on weight initialization.

[0004] To achieve the above objectives, the present invention is implemented according to the following technical solution:

[0005] This invention includes the following steps:

[0006] Collect historical data of the study area and preprocess the historical data;

[0007] Evaluation zones are obtained based on the historical data, and evaluation indicators are obtained by filtering the historical data according to the impact of flood prevention.

[0008] An evaluation index system is constructed based on the evaluation indexes. The weights of the evaluation index system are initialized using He initialization. The comprehensive flood defense level is obtained according to the evaluation index system and the evaluation zone.

[0009] A flood defense evaluation model is established based on the comprehensive flood defense level. The data to be evaluated is input into the flood defense evaluation model, and the evaluation results are output.

[0010] Furthermore, methods for collecting historical data for the study area include:

[0011] Historical data includes basic geographic data, land use data, industry distribution data, socio-economic data, emergency management data, public awareness data, and historical flood event datasets. Basic geographic data includes topographic maps, remote sensing images, and spatial vector data. Land use data includes land use type distribution maps and land use rights information. Industry distribution data includes enterprise directories, industry categories, and industry scale.

[0012] Furthermore, the method for obtaining evaluation partitions based on the historical data includes:

[0013] Data points were established using point data from the spatial vector data of the study area and their corresponding land use types, land use rights, and industry distribution data. These data points were then clustered.

[0014] Neighborhood of data points:

[0015] N ∈ (p)={q∈D|dist(p,q)≤∈∧q≠p∧w(q)≥w min}

[0016] Where, N ∈ (p) is the neighborhood with data point p as the neighborhood core and ∈ as the neighborhood radius, D is the set of data points, and w(q) is the local density weight of data point q. min It is the weight threshold of the neighborhood, and dist(p,q) represents the Euclidean distance between data point p and data point q.

[0017] The core points of the neighborhood:

[0018]

[0019] Where, |N ∈ (p)| represents the neighborhood N ∈ (p) represents the number of data points within a given area, where MinPts is the minimum number of points threshold used to determine whether a data point can become a core point, and ν(p) represents the neighborhood N. ∈ (p) represents the noise term, where α is the adjustment parameter for the noise term.

[0020] Formula for calculating cluster center:

[0021]

[0022] Among them, c j Let x be the center point of cluster j, and let w(x) be the local density weight of data point x. j For cluster j, I j This is the influence term of cluster j, which is the variance of the data points within cluster j.

[0023] Objective function:

[0024]

[0025] Where β and γ are weight parameters, K is the number of clusters, λ is the weight of the regularization term, and F Cj For the compactness of cluster j, N noise (C j Let be the number of noise points in cluster j, R be the global regularization term, and be the L1 norm.

[0026] The evaluation partitions of point data in the spatial vector data are obtained based on the clustering results.

[0027] Furthermore, the method for filtering the historical data based on the impact of flood prevention to obtain evaluation indicators includes:

[0028] The first feature is obtained by preliminary screening of historical data:

[0029]

[0030] Where u(h,y) is the information gain ratio of feature y, n is the number of features in the historical data, h is the amount of historical data, and h k Let |h| be the k-th feature in the historical data, and |h| be the number of historical data points. k | and |h m |representing h from historical data k and h m The quantity, h m It is a subset of features of the m-th eigenvalue in feature y, where m is the index of the eigenvalue in feature y, E(h m ) for h m The conditional entropy is used to select features using the information gain ratio of historical data to obtain the first feature.

[0031] The first feature is converted into a feature vector of the same dimension, with missing values ​​filled with 0. A hierarchical clustering algorithm is then used to cluster the first feature to obtain similar features. The formula for calculating the inter-cluster distance is:

[0032]

[0033] Among them, C S (g d ,g b ) is the first feature g d and g b The similarity, ||·|| represents the Euclidean distance, g d and g b Let d be the ξ-dimensional feature vector composed of the d-th and b-th first features. i Let D represent the component of vector d in the i-th dimension. U (I q ,Is ) for I q and I s Inter-cluster spacing, I q and I s For different clusters, |I q |and|I s |For I q and I s The number of primary features included;

[0034] Impact of flood prevention on similar characteristics:

[0035]

[0036] Where n1 is the number of similar features, U o Let y represent the flood defense impact of the o-th similar feature, and y represent the flood disaster impact data, which includes casualty data and economic loss data. o and I r For the o-th and r-th similar features, D UZ D is the sum of all spacings for similar features. U (I r ,I o ) for I r and I o Inter-cluster spacing, For I o and The joint probability distribution, p(I) o ) for I o Marginal probability distribution, for Marginal probability distribution, C S (I r ,I o ) for I r and I o The similarity is given by F, where F is the identity matrix and T denotes the transpose.

[0037] The similarity characteristic with a flood defense impact greater than 0.632 is used as the evaluation index.

[0038] Furthermore, the method for constructing an evaluation index system based on the aforementioned evaluation indicators includes:

[0039] The evaluation objective is to assess the city's spatial flood defense capabilities. Based on the evaluation indicators, an evaluation indicator system is constructed using the analytic hierarchy process (AHP), which includes a hierarchical evaluation structure with three levels: criterion level, subcriterion level, and indicator level.

[0040] The criteria layer includes five primary indicators: infrastructure, natural environment, socio-economic, emergency management, and public awareness. The secondary criteria layer consists of secondary indicators that connect the criteria layer and the indicator layer. The indicator layer consists of tertiary indicators, which are composed of evaluation indicators.

[0041] Furthermore, the method for initializing the weights of the evaluation index system using He initialization includes:

[0042] A He initialization model was established using historical flood event datasets and their corresponding evaluation indicators. This He initialization model employed a neural network algorithm to predict the impact of flood disasters based on the evaluation indicators.

[0043] Using the evaluation metrics as input nodes, calculate the standard deviation initialized by He, and extract the initial weight values ​​of the nodes from the Gaussian distribution:

[0044]

[0045] ω=N(0,Std 2 )

[0046] Where std represents the standard deviation, sqrt(·) represents the square root, and fan in Let N(0, Std) be the number of input nodes. 2 () indicates that the mean is 0 and the variance is std. 2 The node follows a normal distribution, where ω is the initial weight value of the node;

[0047] When the predicted loss is less than 1.43%, He initializes the weights of the output nodes of the model as the weights of the evaluation indicators. The weights of the secondary indicators are the sum of the weights of the tertiary indicators they contain, and the weights of the primary indicators are the sum of the weights of the secondary indicators they contain.

[0048] Furthermore, the method for obtaining the comprehensive flood control level based on the evaluation index system and the evaluation zoning includes:

[0049] Evaluation of flood control capacity index values ​​for different zones:

[0050]

[0051]

[0052] Where W represents the flood control capability index value, and z represents the number of primary indicators. As a primary indicator The number of secondary indicators included. Secondary indicator The number of included tertiary indicators. For the i-th primary indicator The weight, For the first Secondary indicators The weight, For the first Three-level indicators The weight,

[0053] The flood defense capacity index values ​​are sorted from smallest to largest to obtain a flood defense capacity sequence. Flood defense levels are then classified according to this sequence: the first quantile (0, 10%) is low; the range from the first to the third quantile (10%, 30%) is relatively low; the range from the third quantile to the median (30%, 50%) is medium; the range from the median to the seventh quantile (50%, 70%) is high; and the range from the seventh to the tenth quantile (70%, 100%) is extremely high. The comprehensive flood defense level of the study area is the median level of the flood defense level of its evaluation sub-region.

[0054] Furthermore, the method for establishing a flood defense evaluation model based on the aforementioned comprehensive flood defense level includes:

[0055] A dataset was established using evaluation indicators and a comprehensive flood control level. The dataset was randomly sampled and divided into a training set and a validation set. The comprehensive flood control level served as the classification label for the evaluation indicators. The training set was used to learn the mapping relationship between the evaluation indicators and the comprehensive flood control level using the SVM algorithm, and a flood control evaluation model was established. The validation set was used to adjust the hyperparameters of the flood control evaluation model.

[0056] Secondly, embodiments of this application also provide an electronic device, including:

[0057] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the steps of the method described in the first aspect.

[0058] Thirdly, embodiments of this application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform the steps of the method described in the first aspect.

[0059] The beneficial effects of this invention are:

[0060] This invention is a method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization. Compared with existing technologies, this invention has the following technical advantages:

[0061] This invention improves the accuracy and interpretability of flood disaster prevention capacity assessment through weight initialization, comprehensively evaluates urban defense capabilities by integrating multiple factors, enables rapid response to emergencies, is applicable to different regions, and enhances the efficiency of urban flood disaster management. Attached Figure Description

[0062] Figure 1 This is a flowchart illustrating the steps of a weight-initialized method for evaluating the comprehensive urban flood disaster prevention capabilities according to the present invention.

[0063] Figure 2 This is a schematic diagram of the structure of an electronic device in an embodiment of this specification. Detailed Implementation

[0064] The present invention will be further described below through specific embodiments. The illustrative embodiments and descriptions herein are used to explain the present invention, but are not intended to limit the present invention.

[0065] The present invention provides a method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization, comprising the following steps:

[0066] like Figure 1 As shown, this embodiment includes the following steps:

[0067] Collect historical data of the study area and preprocess the historical data;

[0068] In the actual assessment, the urban flood defense capacity of study area A was assessed. The collected historical data was cleaned to remove invalid and erroneous data, the text data was converted into data encoding, and the historical data was standardized.

[0069] Evaluation zones are obtained based on the historical data, and evaluation indicators are obtained by filtering the historical data according to the impact of flood prevention.

[0070] In the actual assessment, the study area A was divided into the main urban area, the slope and gully area and the area adjacent to the reservoir, and 21 evaluation indicators were selected.

[0071] An evaluation index system is constructed based on the evaluation indexes. The weights of the evaluation index system are initialized using He initialization. The comprehensive flood defense level is obtained according to the evaluation index system and the evaluation zone.

[0072] In actual evaluation, the evaluation indicator system and the weights of the indicators are as follows:

[0073]

[0074] The industrial structure includes industry classification and the economic contribution ratio of each industry; the completeness of the emergency plan includes the coverage and level of detail of the plan; the publicity and education activities include the number of activities and the number of participants; the publicity and education materials include the quantity of materials distributed; and the self-rescue and mutual rescue skills training includes the number of training sessions and the number of participants.

[0075] Flood prevention level:

[0076] The main urban area is rated as medium, the sloping and gully area as low, and the area near the reservoir as low. Overall, the city’s comprehensive flood control capacity is rated as low.

[0077] A flood defense evaluation model is established based on the comprehensive flood defense level. The data to be evaluated is input into the flood defense evaluation model, and the evaluation results are output.

[0078] In this embodiment, the method for collecting historical data of the study area includes:

[0079] Historical data includes basic geographic data, land use data, industry distribution data, socio-economic data, emergency management data, public awareness data, and historical flood event datasets. Basic geographic data includes topographic maps, remote sensing images, and spatial vector data. Land use data includes land use type distribution maps and land use rights information. Industry distribution data includes enterprise directories, industry categories, and industry scale.

[0080] In this embodiment, the method for obtaining evaluation partitions based on the historical data includes:

[0081] Data points were established using point data from the spatial vector data of the study area and their corresponding land use types, land use rights, and industry distribution data. These data points were then clustered.

[0082] Neighborhood of data points:

[0083] N ∈ (p)={q∈D|dist(p,q)≤∈∧q≠p∧w(q)≥w min}

[0084] Where, N ∈ (p) is the neighborhood with data point p as the neighborhood core and ∈ as the neighborhood radius, D is the set of data points, and w(q) is the local density weight of data point q. min It is the weight threshold of the neighborhood, and dist(p,q) represents the Euclidean distance between data point p and data point q.

[0085] The core points of the neighborhood:

[0086]

[0087] Where, |N ∈ (p)| represents the neighborhood N ∈ (p) represents the number of data points within a given area, where MinPts is the minimum number of points threshold used to determine whether a data point can become a core point, and ν(p) represents the neighborhood N. ∈ (p) represents the noise term, where α is the adjustment parameter for the noise term.

[0088] Formula for calculating cluster center:

[0089]

[0090] Among them, c j Let x be the center point of cluster j, and let w(x) be the local density weight of data point x. j For cluster j, I j This is the influence term of cluster j, which is the variance of the data points within cluster j.

[0091] Objective function:

[0092]

[0093] Where β and γ are weight parameters, K is the number of clusters, and λ is the weight of the regularization term. For the compactness of cluster j, N noise (C j Let be the number of noise points in cluster j, R be the global regularization term, and be the L1 norm.

[0094] The evaluation partitions of point data in the spatial vector data are obtained based on the clustering results.

[0095] In this embodiment, the method for obtaining evaluation indicators by filtering the historical data based on the impact of flood prevention includes:

[0096] The first feature is obtained by preliminary screening of historical data:

[0097]

[0098] Where u(h,y) is the information gain ratio of feature y, n is the number of features in the historical data, h is the amount of historical data, and h k Let |h| be the k-th feature in the historical data, and |h| be the number of historical data points. k | and |h m |representing h from historical data k and h m The quantity, h m It is a subset of features of the m-th eigenvalue in feature y, where m is the index of the eigenvalue in feature y, E(h m ) for h m The conditional entropy is used to select features using the information gain ratio of historical data to obtain the first feature.

[0099] The first feature is converted into a feature vector of the same dimension, with missing values ​​filled with 0. A hierarchical clustering algorithm is then used to cluster the first feature to obtain similar features. The formula for calculating the inter-cluster distance is:

[0100]

[0101] Among them, C S (g d ,g b ) is the first feature g d and g b The similarity, ||·|| represents the Euclidean distance, g d and g b Let d be the ξ-dimensional feature vector composed of the d-th and b-th first features. i Let D represent the component of vector d in the i-th dimension. U (I q ,I s ) for I q and I s Inter-cluster spacing, I q and I s For different clusters, |I q |and|I s |For I q and I s The number of primary features included;

[0102] Impact of flood prevention on similar characteristics:

[0103]

[0104] Where n1 is the number of similar features, U o Let y represent the flood defense impact of the o-th similar feature, and y represent the flood disaster impact data, which includes casualty data and economic loss data. o and I r For the o-th and r-th similar features, D UZ D is the sum of all spacings for similar features. U (I r ,I o ) for I r and I o Inter-cluster spacing, For I o and The joint probability distribution, p(I) o ) for I o Marginal probability distribution, for Marginal probability distribution, C S (I r ,I o ) for I r and I o The similarity is given by F, where F is the identity matrix and T denotes the transpose.

[0105] The similarity characteristic with a flood defense impact greater than 0.632 is used as the evaluation index.

[0106] In this embodiment, the method for constructing an evaluation index system based on the evaluation index includes:

[0107] The evaluation objective is to assess the city's spatial flood defense capabilities. Based on the evaluation indicators, an evaluation indicator system is constructed using the analytic hierarchy process (AHP), which includes a hierarchical evaluation structure with three levels: criterion level, subcriterion level, and indicator level.

[0108] The criteria layer includes five primary indicators: infrastructure, natural environment, socio-economic, emergency management, and public awareness. The secondary criteria layer consists of secondary indicators that connect the criteria layer and the indicator layer. The indicator layer consists of tertiary indicators, which are composed of evaluation indicators.

[0109] In this embodiment, the method for weight initialization of the evaluation index system using He initialization includes:

[0110] A He initialization model was established using historical flood event datasets and their corresponding evaluation indicators. This He initialization model employed a neural network algorithm to predict the impact of flood disasters based on the evaluation indicators.

[0111] Using the evaluation metrics as input nodes, calculate the standard deviation initialized by He, and extract the initial weight values ​​of the nodes from the Gaussian distribution:

[0112]

[0113] ω=N(0,Std 2 )

[0114] Where std represents the standard deviation, sqrt(·) represents the square root, and fan in Let N(0, Std) be the number of input nodes. 2 () indicates that the mean is 0 and the variance is std. 2 The node follows a normal distribution, where ω is the initial weight value of the node;

[0115] When the predicted loss is less than 1.43%, He initializes the weights of the output nodes of the model as the weights of the evaluation indicators. The weights of the secondary indicators are the sum of the weights of the tertiary indicators they contain, and the weights of the primary indicators are the sum of the weights of the secondary indicators they contain.

[0116] In this embodiment, the method for obtaining the comprehensive flood control level based on the evaluation index system and the evaluation zoning includes:

[0117] Evaluation of flood control capacity index values ​​for different zones:

[0118]

[0119] Where W represents the flood control capability index value, The number of primary indicators. As a primary indicator The number of secondary indicators included. Secondary indicator The number of included tertiary indicators. For the first Each primary indicator The weight, For the first Secondary indicators The weight, For the first Three-level indicators The weight,

[0120] The flood defense capacity index values ​​are sorted from smallest to largest to obtain a flood defense capacity sequence. Flood defense levels are then classified according to this sequence: the first quantile (0, 10%) is low; the range from the first to the third quantile (10%, 30%) is relatively low; the range from the third quantile to the median (30%, 50%) is medium; the range from the median to the seventh quantile (50%, 70%) is high; and the range from the seventh to the tenth quantile (70%, 100%) is extremely high. The comprehensive flood defense level of the study area is the median level of the flood defense level of its evaluation sub-region.

[0121] In this embodiment, the method for establishing a flood defense evaluation model based on the comprehensive flood defense level includes:

[0122] A dataset was established using evaluation indicators and a comprehensive flood control level. The dataset was randomly sampled and divided into a training set and a validation set. The comprehensive flood control level served as the classification label for the evaluation indicators. The training set was used to learn the mapping relationship between the evaluation indicators and the comprehensive flood control level using the SVM algorithm, and a flood control evaluation model was established. The validation set was used to adjust the hyperparameters of the flood control evaluation model.

[0123] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0124] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or...

[0125] EISA (Extended Industry Standard Architecture) bus, etc. These buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 2 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0126] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0127] The processor reads the corresponding computer program from non-volatile memory into memory and then runs it, forming a weight-initialized urban spatial flood disaster comprehensive defense capability evaluation device at the logical level. The processor executes the program stored in memory and is specifically used to execute any of the aforementioned weight-initialized urban flood disaster comprehensive defense capability evaluation methods.

[0128] The above is as stated in this application. Figure 1The illustrated embodiment discloses a weight-initialized comprehensive urban flood disaster defense capability evaluation method that can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0129] The electronic device can also perform Figure 1 A weighted initialization-based method for evaluating the comprehensive urban flood disaster prevention capacity is proposed and implemented. Figure 1 The functions of the embodiments shown are not described in detail here.

[0130] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, perform any of the aforementioned weight-initialized comprehensive urban flood disaster defense capability evaluation methods.

[0131] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0137] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0139] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization, characterized in that, Includes the following steps: Collect historical data of the study area and preprocess the historical data; Evaluation zones are obtained based on the historical data, and evaluation indicators are obtained by filtering the historical data according to the impact of flood prevention. An evaluation index system is constructed based on the evaluation indexes. The weights of the evaluation index system are initialized using He initialization. The comprehensive flood defense level is obtained according to the evaluation index system and the evaluation zone. A flood control evaluation model is established based on the comprehensive flood control level. The data to be evaluated is input into the flood control evaluation model, and the evaluation results are output. The method for obtaining evaluation partitions based on the historical data includes: Data points were established using point data from the GIS vector data of the study area and their corresponding land use types, land use rights, and industry distribution data. These data points were then clustered. Neighborhood of data points: in, With data point p as the neighborhood core, Let D be the neighborhood of the neighborhood radius, and D be the set of data points. Let q be the local density weight. It is the weight threshold of the neighborhood. This represents the Euclidean distance between data point p and data point q. The core points of the neighborhood: in, For the neighborhood The number of internal data points It is the minimum number of points threshold used to determine whether a data point can be considered a core point. For the neighborhood The noise term, These are the adjustment parameters for the noise term. Formula for calculating cluster center: in, Let x be the center point of cluster j, and let x be a data point within cluster j. The local density weights for data point x. For cluster j, This is the influence term of cluster j, which is the variance of the data points within cluster j. Objective function: in, and These are weight parameters, where K is the number of clusters. It is the weight of the regularization term. Let j be the density of cluster j. Let R be the number of noise points in cluster j, R be the global regularization term, and ρ be the L1 norm. Evaluation partitions of point data in GIS vector data are obtained based on clustering results.

2. The method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization according to claim 1, characterized in that, Methods for collecting historical data on the study area include: Historical data includes basic geographic data, land use data, industry distribution data, socio-economic data, emergency management data, public awareness data, and historical flood event datasets. Basic geographic data includes topographic maps, remote sensing images, and GIS vector data. Land use data includes land use type distribution maps and land use rights information. Industry distribution data includes enterprise directories, industry categories, and industry scale.

3. The method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization as described in claim 1, characterized in that, Methods for obtaining evaluation indicators by filtering historical data based on the impact of flood prevention include: The first feature is obtained by preliminary screening of historical data: in The information gain ratio of feature y. The number of features in historical data. For historical data, For the k-th feature in the historical data, For the amount of historical data, and Each of the historical data and Quantity, It is a subset of features of the m-th eigenvalue in feature y, where m is the index of the eigenvalue in feature y. for The conditional entropy is used to select the first feature using the information gain ratio of historical data. The first feature is converted into a feature vector of the same dimension, with missing values ​​filled with 0. A hierarchical clustering algorithm is then used to cluster the first feature to obtain similar features. The formula for calculating the inter-cluster distance is: in, The first feature and similarity, Represents Euclidean distance. and Composed of the d-th and b-th first features 3D feature vectors Representing vectors The component in the i-th dimension, for and Inter-cluster spacing, and For different clusters, and for and The number of primary features included; Impact of flood prevention on similar characteristics: in The number of similar features, The flood control impact of the o-th similar feature, This refers to data on the impact of floods, which includes data on casualties and economic losses. and For the o-th and r-th similar features, The sum of all distances for similar features. for and Inter-cluster spacing, for and The joint probability distribution, for Marginal probability distribution, for Marginal probability distribution, for and The similarity is given by F, where F is the identity matrix and T denotes the transpose. The similarity characteristic with a flood defense impact greater than 0.632 is used as the evaluation index.

4. The method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization according to claim 1, characterized in that, The method for constructing an evaluation index system based on the aforementioned evaluation indicators includes: The evaluation objective is to assess the city's spatial flood defense capabilities. Based on the evaluation indicators, an evaluation indicator system is constructed using the analytic hierarchy process (AHP), which includes a hierarchical evaluation structure with three levels: criterion level, subcriterion level, and indicator level. The criteria layer includes five primary indicators: infrastructure, natural environment, socio-economic, emergency management, and public awareness. The secondary criteria layer consists of secondary indicators that connect the criteria layer and the indicator layer. The indicator layer consists of tertiary indicators, which are composed of evaluation indicators.

5. The method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization according to claim 1, characterized in that, The method for initializing the weights of the evaluation index system using He initialization includes: A He initialization model was established using historical flood event datasets and their corresponding evaluation indicators. This He initialization model employed a neural network algorithm to predict the impact of flood disasters based on the evaluation indicators. Using the evaluation metrics as input nodes, calculate the standard deviation initialized by He, and extract the initial weight values ​​of the nodes from the Gaussian distribution: Where std represents the standard deviation. Represents the square root. The number of nodes is the input. This indicates that the mean is 0 and the variance is std. 2 The normal distribution The initial weight value for the node; When the predicted loss is less than 1.43%, He initializes the weights of the output nodes of the model as the weights of the evaluation indicators. The weights of the secondary indicators are the sum of the weights of the tertiary indicators they contain, and the weights of the primary indicators are the sum of the weights of the secondary indicators they contain.

6. The method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization according to claim 1, characterized in that, The method for obtaining the comprehensive flood control level based on the evaluation index system and the evaluation zoning includes: Evaluation of flood control capacity index values ​​for different zones: in, This represents the flood control capability index value. The number of primary indicators. As a primary indicator The number of secondary indicators included. Secondary indicator The number of included tertiary indicators. For the first Each primary indicator The weight, For the first Secondary indicators The weight, For the first Three-level indicators The weight, The flood defense capacity index values ​​are sorted from smallest to largest to obtain a flood defense capacity sequence. Based on the flood defense capacity sequence, five flood defense levels are divided into evaluation zones: the first quantile (0, 10%) is low, the first to third quantile (10%, 30%) is relatively low, the third to median (30%, 50%) is medium, the median to seventh quantile (50%, 70%) is high, and the seventh to tenth quantile (70%, 100%) is extremely high. The comprehensive flood defense level of the study area is the median level of the flood defense level of its evaluation zone.

7. The method for evaluating the comprehensive urban flood disaster prevention capability based on weight initialization according to claim 1, characterized in that, The method for establishing a flood defense evaluation model based on the aforementioned comprehensive flood defense level includes: A dataset was established using evaluation indicators and a comprehensive flood control level. The dataset was randomly sampled and divided into a training set and a validation set. The comprehensive flood control level served as the classification label for the evaluation indicators. The training set was used to learn the mapping relationship between the evaluation indicators and the comprehensive flood control level using the SVM algorithm, and a flood control evaluation model was established. The validation set was used to adjust the hyperparameters of the flood control evaluation model.

8. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 7.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 7.

Images