Urban flood emergency material demand space prediction method and related equipment

Abstract

The invention belongs to the technical field of disaster management, discloses an urban flood emergency material demand space prediction method and related equipment, and aims to construct a multi-dimensional risk assessment system by fusing flood disaster-inducing factors and disaster-bearing body vulnerability data so as to significantly improve the accuracy and space directivity of emergency material demand prediction. The subjective limitation of a traditional expert scoring method is broken through by adopting a machine learning weighting mechanism, and objective quantitative evaluation of the flood risk level is realized by dynamically optimizing the influence factor weight through an AdaBoost model. A spatial principal component analysis method is introduced to carry out dimension reduction processing on multi-source social economic indexes, key vulnerability factors are effectively extracted, and data redundancy is eliminated. Spatial coupling of disaster exposure and social vulnerability is realized through an emergency spatial coefficient model, and a spatial association mechanism of disaster risk and population distribution is established, so that the recognition precision of people needing rescue reaches a grid level. The finally formed material demand prediction map can accurately reflect differentiated demands of emergency materials in different geographic units.

Description

Technical Field

[0001] The present invention belongs to the technical field of disaster management, and specifically relates to a spatial prediction method for urban flood emergency material demand and related equipment. Background Art

[0002] Emergency supply dispatch within urban emergency response systems is crucial for ensuring post-disaster rescue efficiency and protecting the lives of affected people. However, traditional methods for forecasting emergency supply demand rely heavily on statistics or expert experience, lacking scientific data support and failing to meet the spatial accuracy and objectivity requirements of practical applications.

[0003] Defects and shortcomings of existing technologies (1) Insufficient spatial accuracy: Most forecasting methods can only forecast the total demand for the entire administrative district or a larger area, and it is difficult to provide detailed spatial distribution information at the street or community level, resulting in insufficient accuracy in the allocation of materials. (2) Strong subjectivity in weights: Traditional risk assessment models are subjective in weight allocation, making it difficult to accurately reflect the importance of each influencing factor, affecting the scientific nature of the forecast results. (3) Lack of a risk and demand integration mechanism: Most models only use risk assessment or population data to predict demand, failing to effectively integrate disaster-causing factors and disaster-bearing body characteristics, and lack a comprehensive weighting mechanism that considers disaster severity and social vulnerability.

[0004] In summary, existing methods are difficult to achieve a refined, objective, and spatially heterogeneous forecast of urban flood emergency material demand. Summary of the Invention

[0005] The present invention provides a method and related equipment for spatial prediction of urban flood emergency material demand, which solves the problem that existing methods are difficult to achieve refined, objective and spatially heterogeneous urban flood emergency material demand prediction.

[0006] To achieve the above object, the present invention provides the following technical solutions: A spatial prediction method for urban flood emergency material demand, comprising: Collect and process multi-source spatial data related to flood risk in the study area, input the processed multi-source spatial data into the trained AdaBoost model, and calculate the weight of each influencing factor; Create a spatial distribution map of flood risk levels based on the weights of each influencing factor; Collect socioeconomic vulnerability indicator data of the study area, perform dimensionality reduction and generate socioeconomic factor maps; The socioeconomic factor map and the flood risk level spatial distribution map are normalized and weighted to obtain the emergency spatial coefficient; Obtain the population spatial distribution grid data of the study area, and obtain the spatial distribution map of the number of people requiring emergency assistance in each grid cell based on the emergency spatial coefficient and the population spatial distribution grid data; According to the preset per capita material demand standard, the demand for emergency materials is calculated based on the spatial distribution map of population, and a spatial distribution forecast map of emergency material demand is obtained.

[0007] Preferably, the multi-source spatial data include flood disaster factors and flood disaster environmental sensitivity factors, the flood disaster factors include cumulative rainfall and average annual rainfall, and the disaster environmental sensitivity factors include digital elevation model, slope, terrain moisture index, road network density, water system density and normalized vegetation index.

[0008] Preferably, the AdaBoost model iteratively trains weak classifiers, dynamically adjusts sample weights to increase attention to difficult-to-classify samples, and obtains the objective weight of each influencing factor through feature importance calculation.

[0009] Preferably, the generation of the socioeconomic factor map is specifically to select the top k principal components whose cumulative variance contribution rate exceeds a preset threshold through spatial principal component analysis, and perform weight calculation based on the eigenvalues or variance contribution rates of the principal components, and perform weighted superposition of the k principal component raster layers according to their weights to generate a comprehensive socioeconomic factor spatial distribution map.

[0010] Preferably, the calculation of the emergency space coefficient is as follows:

[0011] in, is the normalized flood risk level, is the normalized comprehensive socioeconomic factor, and is the weight coefficient and satisfies α+β=1.

[0012] Preferably, the spatial distribution map of flood risk levels is divided into levels using the natural breakpoint method, and the visualization results are output in the form of raster data.

[0013] Preferably, the emergency supplies include at least one of drinking water, food, clothing and medicine, and the per capita demand standard is set according to disaster emergency guidelines.

[0014] A spatial prediction system for urban flood emergency material demand, comprising: Weight calculation module: used to collect and process multi-source spatial data related to flood risk in the study area, input the processed multi-source spatial data into the trained AdaBoost model, and calculate the weight of each influencing factor; Mapping module: used to produce a spatial distribution map of flood risk levels based on the weights of various influencing factors; Image generation module: used to collect socioeconomic vulnerability indicator data of the study area, perform dimensionality reduction and generate socioeconomic factor maps; Coefficient acquisition module: used to normalize and weight the socioeconomic factor map and the flood risk level spatial distribution map to obtain the emergency spatial coefficient; Image acquisition module: used to obtain the population spatial distribution grid data of the study area, and obtain the spatial distribution map of the number of people requiring emergency assistance in each grid cell based on the emergency spatial coefficient and the population spatial distribution grid data; Forecasting module: used to calculate the demand for emergency supplies based on the preset per capita demand standard for supplies and the spatial distribution map of population, and obtain a spatial distribution forecast map of the demand for emergency supplies.

[0015] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor implements the steps of a method for spatial prediction of urban flood emergency material demand.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for spatial prediction of urban flood emergency material demand.

[0017] Compared with existing technologies, the present invention has the following advantages: It provides a spatial forecasting method for urban flood emergency supply demand. By integrating flood hazard factors with vulnerability data of hazard-bearing objects, it constructs a multidimensional risk assessment system, significantly improving the accuracy and spatial specificity of emergency supply demand forecasts. A machine learning weighting mechanism overcomes the subjective limitations of traditional expert scoring methods. The AdaBoost model dynamically optimizes the weights of influencing factors, achieving an objective quantitative assessment of flood risk levels. Spatial principal component analysis is introduced to reduce the dimensionality of multi-source socioeconomic indicators, effectively extracting key vulnerability factors and eliminating data redundancy. An emergency spatial coefficient model is used to spatially couple disaster exposure and social vulnerability, establishing a spatial correlation mechanism between disaster risk and population distribution, enabling grid-level identification of the population in need of assistance. The resulting demand forecast map accurately reflects the differentiated demand for emergency supplies within different geographic units, providing a spatial basis for decision-making in the site selection of supply reserves and transportation route planning. It also avoids the demand distortion caused by traditional administrative division statistics, significantly improving the efficiency of emergency resource allocation and the speed of disaster response.

[0018] Furthermore, the AdaBoost machine learning model is used to adaptively learn the contribution weights of various influencing factors to flood risk, avoiding the subjectivity of traditional methods (such as AHP and expert scoring) and improving the accuracy of risk assessment (such as AUC value verification) and the objectivity of subsequent demand forecasting through a data-driven approach.

[0019] Furthermore, grid-based spatial analysis (for example, 1km x 1km units) can generate high-resolution risk level maps, emergency spatial coefficient maps, and spatial distribution maps of the demand for various types of materials, providing a spatial basis for the precise deployment and zoning management of emergency resources, which is superior to traditional methods that only provide total amount forecasts.

[0020] Furthermore, an emergency spatial coefficient (ESC) was constructed, which integrates the "flood risk level (disaster intensity)" determined by disaster factors and disaster environment, and the "socio-economic vulnerability (disaster-bearing body characteristics)" composed of population, economy, infrastructure, etc., to more comprehensively and scientifically reflect the actual urgency of needs in different regions under disasters.

[0021] Furthermore, the forecast results are intuitively displayed in the form of spatial distribution maps, which can clearly identify high-risk areas and high-demand areas, making it easier for emergency management departments to quickly formulate material allocation plans, optimize logistics routes, set up temporary shelters and material distribution points, and improve the efficiency and pertinence of emergency responses. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of a spatial prediction method for urban flood emergency material demand according to the present invention; Figure 2 is a weight diagram of various influencing factors according to an embodiment of the present invention; Figure 3 This is a spatial distribution map of flood risk levels according to an embodiment of the present invention; Figure 4 This is a socioeconomic factor graph according to an embodiment of the present invention; Figure 5 This is a spatial distribution prediction diagram of an embodiment of the present invention; Figure 6 This is a flow chart of spatial prediction of emergency material demand according to an embodiment of the present invention; Figure 7 This is a block diagram of a spatial prediction system for urban flood emergency material demand according to the present invention. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0026] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0027] like Figure 1 As shown, the present invention provides a method for spatial prediction of urban flood emergency material demand, comprising: Collect and process multi-source spatial data related to flood risk in the study area, input the processed multi-source spatial data into the trained AdaBoost model, and calculate the weight of each influencing factor; Create a spatial distribution map of flood risk levels based on the weights of each influencing factor; Collect socioeconomic vulnerability indicator data of the study area, perform dimensionality reduction and generate socioeconomic factor maps; The socioeconomic factor map and the flood risk level spatial distribution map are normalized and weighted to obtain the emergency spatial coefficient; Obtain the population spatial distribution grid data of the study area, and obtain the spatial distribution map of the number of people requiring emergency assistance in each grid cell based on the emergency spatial coefficient and the population spatial distribution grid data; According to the preset per capita material demand standard, the demand for emergency materials is calculated based on the spatial distribution map of population, and a spatial distribution forecast map of emergency material demand is obtained.

[0028] The multi-source spatial data include flood disaster factors and flood disaster environmental sensitivity factors. The flood disaster factors include cumulative rainfall and average annual rainfall, and the disaster environmental sensitivity factors include digital elevation model, slope, terrain moisture index, road network density, water system density and normalized difference vegetation index.

[0029] The AdaBoost model iteratively trains weak classifiers, dynamically adjusts sample weights to increase attention to difficult-to-classify samples, and obtains the objective weight of each influencing factor through feature importance calculation.

[0030] The generation of the socioeconomic factor map is specifically as follows: the top k principal components whose cumulative variance contribution rate exceeds the preset threshold are selected through spatial principal component analysis, and weights are calculated according to the eigenvalues or variance contribution rates of the principal components. The k principal component raster layers are weighted and superimposed according to their weights to generate a comprehensive spatial distribution map of socioeconomic factors.

[0031] The calculation of the emergency space coefficient is as follows:

[0032] in, is the normalized flood risk level, is the normalized comprehensive socioeconomic factor, and is the weight coefficient and satisfies α+β=1.

[0033] The spatial distribution map of flood risk levels is divided into levels using the natural breakpoint method, and the visualization results are output in the form of raster data.

[0034] Emergency supplies include at least one of drinking water, food, clothing and medicine, and the per capita demand standard is set according to the disaster emergency guidelines.

[0035] Another embodiment of the present invention provides a method for spatially predicting demand for urban flood emergency supplies, comprising the following steps: Step 1: Spatial assessment of flood risk based on machine learning Define the study area and divide it into unified spatial analysis units (1km x 1km grids). Collect and process multi-source spatial data related to flood risk, including at least two categories: Hazard Factors: Data reflecting the intensity and characteristics of the flood event itself, such as the cumulative rainfall of a specific rainstorm event (such as the "23.7" event) and the average annual rainfall in the study area. Disaster Environment Sensitivity Factors: Data reflecting the sensitivity of the geographic environment to flood impacts, such as digital elevation models (DEMs), slope, terrain wetness index (TWI), road network density, water system (drainage) density, and normalized difference vegetation index (NDVI).

[0036] Historical waterlogging points in the study area served as positive samples (labeled 1), and an equal number of points were randomly generated in non-waterlogging areas as negative samples (labeled 0). The sampling points consisted of 456 waterlogging points and 456 non-waterlogging points. Waterlogging points were obtained from the official website of the Beijing Water Authority. Non-waterlogging points were randomly generated in ArcGIS and distinguished from waterlogging points. 426 waterlogging risk points were designated as waterlogging points, and an equal number of non-waterlogging points, distinguished from waterlogging points, were randomly selected in ArcGIS to form a total of 852 sample points. The data for each influencing factor were normalized. Where Fij is the normalized value, Xij is the original value, and Xmax and Xmin are the maximum and minimum values of the indicator, respectively.

[0037] The normalization formula for positive indicators is:

[0038] The normalization formula for negative indicators is:

[0039] Model training and weight determination: The sample data is divided into a training set and a test set (for example, 70% training and 30% testing). The AdaBoost (adaptive boosting algorithm) ensemble learning model is used. AdaBoost iteratively trains weak classifiers (such as decision tree stumps). After each round of iteration, the weight of incorrectly classified samples is increased and the weight of correctly classified samples is reduced, so that the subsequent model pays more attention to difficult-to-classify samples. Using the trained AdaBoost model, the feature importance (Eigenimportance Values) of each influencing factor for flood risk (whether waterlogging occurs) is calculated, and these importance values are normalized to obtain the weight of each influencing factor, such as Figure 2 shown.

[0040] Risk level calculation and mapping: The normalized spatial raster data of each influencing factor are weighted and superimposed according to the weights determined by the AdaBoost model. The comprehensive flood risk index of each grid cell is calculated. The risk index is graded using an appropriate classification method (such as the natural breakpoint method) (for example, into five levels: very low, low, medium, high, and very high). The spatial distribution map of the flood risk level (DL, Disaster Level) of the study area is generated, such as Figure 3 shown.

[0041] Step 2: Constructing emergency spatial coefficients based on spatial principal component analysis Socioeconomic data preparation: Collect and process indicators reflecting regional socioeconomic vulnerability or disaster resilience, and normalize them to the same spatial resolution as the risk assessment (e.g., 1km grid). These indicators include at least: vulnerable population (e.g., the sum of population under 14 and over 65), GDP per unit area (GDP per unit area), school density density (SNDA), hospital density density (HNDA), and nighttime light intensity. All socioeconomic indicator data are normalized. Spatial principal component analysis (SPCA) and factor generation: Leveraging the spatial analysis capabilities of a GIS platform, we performed spatial principal component analysis (SPCA) on normalized raster data of multiple socioeconomic indicators. SPCA transforms the originally highly correlated multidimensional indicators into a small number of uncorrelated, comprehensive principal components while retaining most of the original information.

[0042] Collect indicators reflecting socioeconomic vulnerability (such as vulnerable population, GDP per capita, school / hospital density analysis, nighttime light intensity, etc.), use spatial principal component analysis (SPCA) to reduce dimensionality and generate a socioeconomic factor map. Select the first k principal components whose cumulative variance contribution reaches a threshold (for example, >90%). Calculate the weight of each selected principal component based on its eigenvalue (Eigenvalue) or variance contribution. Overlay the k principal component raster layers according to their weights to generate a comprehensive socioeconomic factor spatial distribution map (SF), such as Figure 4 shown.

[0043] Calculation of the Emergency Spatial Coefficient (ESC): The flood risk level map (DL) obtained in step 1 and the socioeconomic factor map (SF) obtained in step 2 are normalized (for example, to a range of 0-1). The normalized DL and SF are weighted and combined to construct the Emergency Spatial Coefficient (ESC). In this embodiment, an equal-weighted combination is used:

[0044] The value of ESC ranges from 0 to 1, reflecting the urgency or demand intensity of emergency response in each grid cell under flood disaster, taking into account the disaster intensity and socioeconomic vulnerability.

[0045] Step 3: Spatial forecast of emergency material demand based on emergency space coefficient Estimating the number of people requiring assistance: Obtain high-resolution spatial population distribution raster data (e.g., LandScan data) for the study area. Multiply the Emergency Spatial Coefficient (ESC) raster layer obtained in Step 2 by the population spatial distribution raster layer (cell by cell multiplication). This yields a spatial distribution map of the number of people requiring emergency assistance within each grid cell. An ESC value of 1 indicates that all residents within that grid cell require assistance, while an ESC value of 0.5 indicates that half the population requires assistance, and so on.

[0046] Calculation and mapping of material demand: Determine the types of key emergency materials that need to be predicted, such as drinking water, food, clothing, and medicines (such as antibiotics). According to relevant emergency standards or guidelines, determine the per capita demand standards for each type of material (for example, 2.5L / person / day for drinking water, 1.6kg / person / day for food, etc.). Multiply the number of people in need of assistance in each grid by the per capita demand standard for the corresponding material. Generate a spatial distribution forecast map of the demand for various emergency materials (drinking water, food, clothing, medicine, etc.), such as Figure 5 shown.

[0047] like Figure 6 As shown, another embodiment of the present invention provides a spatial forecasting method for urban flood emergency supply demand, using the "23.7" torrential rain event in Beijing as an example for validation. A 1km x 1km grid was used as the analysis unit. In step 1, the AdaBoost model determined that factors such as DEM, rainfall, and NDVI had high weights, and a flood risk level map was generated, showing that areas such as Fangshan and Mentougou were at higher risk. In step 2, SPCA was performed based on five indicators: vulnerable population, GDP, school and hospital density, and nighttime lighting. This was then integrated with the risk level map to generate an ESC map. In step 3, the ESC map was multiplied by the population distribution map and combined with per capita supply standards (e.g., 2.5L for water, 1.6kg for food). This ultimately yielded a spatial distribution map of demand for various emergency supplies, showing that demand was primarily concentrated in the densely populated central urban area and southeastern regions, rather than in the southwestern mountainous areas, where risk was highest.

[0048] like Figure 7 As shown, the present invention provides a spatial prediction system for urban flood emergency material demand, comprising: Weight calculation module: used to collect and process multi-source spatial data related to flood risk in the study area, input the processed multi-source spatial data into the trained AdaBoost model, and calculate the weight of each influencing factor; Mapping module: used to produce a spatial distribution map of flood risk levels based on the weights of various influencing factors; Image generation module: used to collect socioeconomic vulnerability indicator data of the study area, perform dimensionality reduction and generate socioeconomic factor maps; Coefficient acquisition module: used to normalize and weight the socioeconomic factor map and the flood risk level spatial distribution map to obtain the emergency spatial coefficient; Image acquisition module: used to obtain the population spatial distribution grid data of the study area, and obtain the spatial distribution map of the number of people requiring emergency assistance in each grid cell based on the emergency spatial coefficient and the population spatial distribution grid data; Forecasting module: used to calculate the demand for emergency supplies based on the preset per capita demand standard for supplies and the spatial distribution map of population, and obtain a spatial distribution forecast map of the demand for emergency supplies.

[0049] An embodiment of the present invention provides a terminal device. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of each of the aforementioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in each of the aforementioned device embodiments are implemented.

[0050] The computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to accomplish the present invention.

[0051] The terminal device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0052] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0053] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0054] If the module / unit integrated in the terminal device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signal and telecommunication signal.

[0055] Although the embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments and application fields. The above-mentioned specific embodiments are merely illustrative and instructive, and are not restrictive. A person skilled in the art, guided by the description, may devise various forms without departing from the scope of protection of the claims of the present invention, all of which fall within the scope of protection of the present invention.

Claims

1. A spatial prediction method for urban flood emergency material demand, characterized by: include: Collect and process multi-source spatial data related to flood risk in the study area, input the processed multi-source spatial data into the trained AdaBoost model, and calculate the weight of each influencing factor; Create a spatial distribution map of flood risk levels based on the weights of each influencing factor; Collect socioeconomic vulnerability indicator data of the study area, perform dimensionality reduction and generate socioeconomic factor maps; The socioeconomic factor map and the flood risk level spatial distribution map are normalized and weighted to obtain the emergency spatial coefficient; Obtain the population spatial distribution grid data of the study area, and obtain the spatial distribution map of the number of people requiring emergency assistance in each grid cell based on the emergency spatial coefficient and the population spatial distribution grid data; According to the preset per capita material demand standard, the demand for emergency materials is calculated based on the spatial distribution map of population, and a spatial distribution forecast map of emergency material demand is obtained.

2. A spatial prediction method for urban flood emergency material demand according to claim 1, characterized in that: The multi-source spatial data include flood disaster factors and flood disaster environmental sensitivity factors. The flood disaster factors include cumulative rainfall and average annual rainfall, and the disaster environmental sensitivity factors include digital elevation model, slope, terrain moisture index, road network density, water system density and normalized difference vegetation index.

3. The spatial prediction method for urban flood emergency material demand according to claim 1 is characterized in that: The AdaBoost model iteratively trains weak classifiers, dynamically adjusts sample weights to increase attention to difficult-to-classify samples, and obtains the objective weight of each influencing factor through feature importance calculation.

4. The spatial prediction method for urban flood emergency material demand according to claim 1 is characterized in that: The generation of the socioeconomic factor map is specifically as follows: the top k principal components whose cumulative variance contribution rate exceeds the preset threshold are selected through spatial principal component analysis, and weights are calculated according to the eigenvalues or variance contribution rates of the principal components. The k principal component raster layers are weighted and superimposed according to their weights to generate a comprehensive spatial distribution map of socioeconomic factors.

5. The spatial prediction method for urban flood emergency material demand according to claim 1 is characterized in that: The calculation of the emergency space coefficient is as follows: in, is the normalized flood risk level, is the normalized comprehensive socioeconomic factor, and is the weight coefficient and satisfies α+β=1.

6. The spatial prediction method for urban flood emergency material demand according to claim 1 is characterized in that: The spatial distribution map of flood risk levels is divided into levels using the natural breakpoint method, and the visualization results are output in the form of raster data.

7. The spatial prediction method for urban flood emergency material demand according to claim 1 is characterized in that: The emergency supplies include at least one of drinking water, food, clothing and medicine, and the per capita demand standard is set according to the disaster emergency guidelines.

8. A spatial prediction system for urban flood emergency material demand, characterized by: include: Weight calculation module: used to collect and process multi-source spatial data related to flood risk in the study area, input the processed multi-source spatial data into the trained AdaBoost model, and calculate the weight of each influencing factor; Mapping module: used to produce a spatial distribution map of flood risk levels based on the weights of various influencing factors; Image generation module: used to collect socioeconomic vulnerability indicator data of the study area, perform dimensionality reduction and generate socioeconomic factor maps; Coefficient acquisition module: used to normalize and weight the socioeconomic factor map and the flood risk level spatial distribution map to obtain the emergency spatial coefficient; Image acquisition module: used to obtain the population spatial distribution grid data of the study area, and obtain the spatial distribution map of the number of people requiring emergency assistance in each grid cell based on the emergency spatial coefficient and the population spatial distribution grid data; Forecasting module: used to calculate the demand for emergency supplies based on the preset per capita demand standard for supplies and the spatial distribution map of population, and obtain a spatial distribution forecast map of the demand for emergency supplies.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for spatial prediction of urban flood emergency material demand as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for spatial prediction of urban flood emergency material demand as claimed in any one of claims 1 to 7 are implemented.

Images