ArcGIS Engine and SOM-based city space toughness full-cycle optimization regulation and control method and system

Abstract

The invention provides an urban space toughness full-cycle optimization regulation and control method and system based on ArcGIS Engine and SOM. The method comprises the following steps: 1) multi-dimensional attribute measurement of urban spatial toughness; (2) revealing space-time differentiation characteristics of urban space toughness full-period evolution; 3) identifying influence factors of urban space toughness full-cycle evolution; 4) constructing an urban space toughness full-cycle optimization regulation and control model based on ArcGIS Engine; and 5) searching an optimal solution of urban space toughness full-cycle optimization regulation and control based on SOM. According to the method, a quantitative analysis model and a tool for urban spatial toughness optimization regulation can be provided, and suitable value and threshold range of urban spatial toughness multi-dimensional variables can be identified, so that a full-cycle optimization regulation strategy for urban spatial toughness is supported; therefore, the ability of the planning system to regulate and control the urban space toughness is enhanced from the aspects of space-time integrity and systematicness.

Description

Technical Field

[0001] The present invention relates to the technical field of full-cycle optimization and regulation of urban space resilience, and in particular to a full-cycle optimization and regulation method and system for urban space resilience based on ArcGIS Engine and SOM. Background Art

[0002] Among the multiple dimensions that determine the resilience of urban systems, "spatial resilience" emphasizes the support and contribution of the underlying material spatial form and structure as the carrier of the urban system's operation to the system's resilience, and is crucial to the construction of resilient cities.

[0003] Currently, resilience research still pays insufficient attention to the underlying spatial form and structure of cities, leading to a neglected understanding of the crucial impact of spatial resilience on the security and sustainable development of urban systems. Especially in the context of urban renewal, the physical spatial systems of many cities have undergone a comprehensive development process, spanning establishment, enrichment, and climax. Some urban areas have even undergone a full cycle of decline and reorganization within the context of urban renewal. However, existing research lacks a comprehensive and deductive understanding of the evolutionary mechanisms of spatial resilience throughout its entire lifecycle. This makes it difficult to accurately understand and grasp the underlying historical reasons for the poor performance of urban spatial resilience at different stages of development, further questioning the effectiveness of resilience strategies. Furthermore, due to a lack of understanding of the process-based developmental characteristics of resilience, existing research has also rarely explored models and methods for optimizing and regulating spatial resilience throughout its entire lifecycle, making it difficult to propose resilience regulation strategies that are holistic and systematic across time and space.

[0004] Therefore, it is necessary to develop a full-cycle optimization and regulation model for urban space resilience based on new technologies and methods such as artificial intelligence, break through the bottleneck problem of unclear mechanism and path for full-cycle optimization and regulation of urban space resilience, propose urban space resilience optimization and regulation strategies suitable for different life cycle development stages, and enhance the ability of the planning system to regulate urban space resilience. This is a frontier area that urgently needs to be explored in the current research on urban space resilience. Summary of the Invention

[0005] The purpose of the present invention is to solve the problems in the prior art and propose a method and system for optimizing and controlling urban spatial resilience throughout its entire life cycle based on ArcGIS Engine and SOM. The method and system aim to integrate the Geodesign technical process, construct an ArcGIS Engine-based model for optimizing and controlling urban spatial resilience throughout its entire life cycle, and innovate a method for exploring optimal solutions for optimizing and controlling urban spatial resilience throughout its entire life cycle supported by SOM neural network technology. This method and system provide quantitative models and tools for research on optimizing and controlling urban spatial resilience throughout its entire life cycle, and help resolve the issue of unclear mechanisms and paths for optimizing and controlling urban spatial resilience throughout its entire life cycle.

[0006] The present invention is achieved through the following technical solution. The present invention proposes a full-cycle optimization and control method for urban spatial resilience based on ArcGIS Engine and SOM. The method includes the following steps:

[0007] Step 1: Multidimensional attribute measurement of urban spatial resilience: Identify multi-level variable indicators of urban spatial resilience, construct an urban spatial resilience measurement indicator system, and clarify the calculation formula and superposition calculation method of each indicator;

[0008] Step 2: Revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience: Implementing a full-cycle quantitative measurement of urban spatial resilience for typical sample cities, and revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience based on spatial statistical analysis methods;

[0009] Step 3: Identify factors influencing the evolution of urban spatial resilience throughout its lifecycle: Using a multi-level linear model, analyze the impact of urban spatial elements and organizational characteristics at different development stages on resilience changes, their impact levels, and cross-stage interactions, identifying the internal dominant factors influencing the evolution of spatial resilience throughout its lifecycle at the within-group level. Using a random intercept model and a random coefficient regression model, analyze how socioeconomic environmental variables at different development stages influence the cross-stage changes in urban spatial elements and organizational characteristics, identifying the external dominant factors influencing the evolution of spatial resilience throughout its lifecycle at the between-group level.

[0010] Step 4: Construct an ArcGIS Engine-based full-cycle optimization and regulation model for urban spatial resilience: Based on the Geodesign framework and using ArcGIS Engine technology, through GIS secondary development, a full-cycle optimization and regulation model for urban spatial resilience was constructed, encompassing regulation strategy input, rule modeling, resilience measurement execution, and scenario analysis and evaluation. This model supports full-cycle resilience optimization and regulation, as well as scenario comparative analysis.

[0011] Step 5. Exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: Construct an optimization and regulation model for typical regions at different development stages, set the control factors of urban spatial form and structure that affect multidimensional resilience attributes as parameter variables, carry out spatial design optimization and spatial resilience measurement under single variable and combined variable conditions, and obtain a training data set for non-dominated solution set analysis; integrate the SOM neural network algorithm to construct a multi-development stage and multi-attribute dimension optimization target clustering model for urban spatial resilience, explore the optimal solution for the full-cycle coordinated improvement of the multidimensional attributes of urban spatial resilience through non-dominated solution set analysis, and identify the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages.

[0012] Furthermore, in step 1, by analyzing the mapping relationship between the "spatial form-spatial structure" variable indicators and the multidimensional resilience attributes, the multi-level variable indicators of urban spatial resilience are identified; based on the quantitative analysis methods and tools of urban spatial form and spatial structure, the calculation formulas of various indicators are clarified, and then the quantitative calculation results of each measurement indicator are standardized based on the extreme value method, and the weight of each indicator is calculated based on the linear weighted combination method combining subjective and objective weighting methods.

[0013] Furthermore, in step 2, the full-cycle quantitative measurement of urban spatial resilience is implemented for typical sample cities, specifically: based on the urban life cycle model, the full-cycle development stages of urban spatial resilience in the time dimension are refined and identified, including the development period, maintenance period, decline period, dormancy period and renewal period, and based on potential and connectivity, two important attributes that characterize changes in development stages, spatial visualization measurement of urban spatial resilience is then carried out for each development stage of the typical sample cities.

[0014] Furthermore, in step 2, the spatial statistical analysis method is used to reveal the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience, specifically: based on the high / low clustering analysis tool in ArcGIS, the Geary's c index of the spatial distribution of multidimensional resilience attributes in each development stage is calculated, and the degree of aggregation or dispersion of the multidimensional resilience attributes in space is preliminarily analyzed, and the changes in the high / low clustering distribution areas are analyzed from the time dimension; based on the spatial autocorrelation tool in ArcGIS, the global and local Moran's I index of the multidimensional resilience attributes in each development stage are calculated to reveal the spatial evolution trend and characteristics of urban spatial resilience; then, by identifying the development stage of each research unit and visually presenting the volatility change state of the resilience attribute index between each development stage, the temporal evolution trend and characteristics of urban spatial resilience are summarized and concluded, and based on the Pearson correlation coefficient, the complex trade-offs and synergistic relationships between the changes in each resilience attribute are analyzed, so as to reveal the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience.

[0015] Furthermore, in step 3, the internal dominant influencing factors of the full-cycle evolution of spatial resilience are identified. Specifically, regression models are established for the research units in the five different development stages of the full cycle, namely the development period, maintenance period, decline period, dormancy period and renewal period. Based on the multi-level linear model (HLM), the influence mode, degree of influence and cross-stage interaction effect of the explanatory variables within each development stage, i.e., the measurement indicators, on the dependent variable, i.e., the multidimensional resilience attributes, are analyzed, and the inter-group differences in the influencing factors of the changes in urban spatial resilience are judged, so as to realize the analysis process of the internal dominant influencing factors of the evolution of urban spatial resilience.

[0016] Furthermore, in step 3, the external dominant influencing factors of the full-cycle evolution of spatial resilience are identified. Specifically, regression models are established for the research units in the five different development stages of the full cycle, namely the development period, maintenance period, decline period, dormancy period and renewal period. Based on the random intercept model and random coefficient regression model, the socio-economic environment characteristic variables of the research units in each development stage are analyzed to see how their organizational characteristics affect the cross-stage changes in resilience, and the external dominant influencing factors of the full-cycle evolution of urban spatial resilience are identified.

[0017] Furthermore, in step 5, a multidimensional resilience attribute optimization target clustering model is constructed based on the SOM neural network, and a neuron hierarchical clustering diagram is drawn to represent the resilience optimization target component graph, the non-dominated solution quantity graph within the neuron, and the neuron hierarchical clustering diagram to perform neuron hierarchical clustering screening of urban spatial form and structural variables guided by the resilience optimization target; thereafter, the resilience optimization target guided neuron hierarchical clustering screening results and the SOM neural network are used to reconstruct the resilience optimization target clustering model, and the resilience optimization target guided neuron screening of urban spatial form and structural variables is performed again based on the reconstructed clustering model; based on the resilience optimization target guided neuron screening results, a clustering model of urban spatial form and structural variables is constructed, and based on the clustering model, a neuron matrix diagram representing urban spatial form and structural variables and a neuron matrix diagram representing multidimensional resilience attribute optimization targets are drawn to perform neuron screening guided by urban spatial form and structural variables, and based on the results of this round of screening, it is determined whether the next round of neuron screening guided by urban spatial form and structural variables is needed, until the final urban spatial form and structure optimization and control plan is obtained.

[0018] The present invention also proposes a full-cycle optimization and control system for urban spatial resilience based on ArcGIS Engine and SOM, the system comprising:

[0019] Measurement module, multi-dimensional attribute measurement of urban spatial resilience: Identify multi-level variable indicators of urban spatial resilience, build an urban spatial resilience measurement indicator system, and clarify the calculation formula and superposition calculation method of each indicator;

[0020] Revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of modules and urban spatial resilience: Implementing full-cycle quantitative measurement of urban spatial resilience for typical sample cities, and revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience based on spatial statistical analysis methods;

[0021] Identification module, identification of factors influencing the full-cycle evolution of urban spatial resilience: Based on a multi-level linear model, the impact mode, degree of impact and cross-stage interaction effects of urban spatial elements and organizational characteristics at different development stages on resilience changes are analyzed, and the internal dominant influencing factors of the full-cycle evolution of spatial resilience are identified at the within-group level; based on a random intercept model and a random coefficient regression model, the influence of socio-economic environmental characteristic variables at different development stages on the cross-stage changes of urban spatial elements and organizational characteristics on resilience is analyzed, and the external dominant influencing factors of the full-cycle evolution of spatial resilience are identified at the inter-group level;

[0022] Construction module, construction of a full-cycle optimization and regulation model for urban spatial resilience based on ArcGIS Engine: Based on the Geodesign framework, using ArcGIS Engine technology and through GIS secondary development, a full-cycle optimization and regulation model for urban spatial resilience is constructed, which includes the technical functions of regulation strategy input, rule modeling generation, resilience measurement execution, and scenario analysis and evaluation. This supports full-cycle resilience optimization and regulation and scenario comparative analysis.

[0023] Exploration module, exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: construct an optimization and regulation model for typical areas at different development stages, set the control factors of urban spatial form and structure that affect multi-dimensional resilience attributes as parameter variables, carry out spatial design optimization and spatial resilience measurement under single variable and combined variable conditions, and obtain a training data set for non-dominated solution set analysis; integrate the SOM neural network algorithm to construct a multi-development stage and multi-attribute dimension optimization target clustering model for urban spatial resilience, explore the optimal solution for the full-cycle coordinated improvement of the multi-dimensional attributes of urban spatial resilience through non-dominated solution set analysis, and identify the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages.

[0024] The present invention also proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the full-cycle optimization and control method of urban space resilience based on ArcGIS Engine and SOM.

[0025] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the full-cycle optimization and control method for urban space resilience based on ArcGIS Engine and SOM.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention's full-cycle optimization and control method and system for urban spatial resilience based on ArcGIS Engine and SOM can effectively reveal the full-cycle evolution trend and spatiotemporal differentiation characteristics of urban spatial resilience, identify the dominant influencing factors of the full-cycle evolution of urban spatial resilience, and reveal the quantitative influence relationship of single or combined variables of urban spatial form and structure on multidimensional resilience attributes. It has significant advantages in identifying the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages, and can support the proposal of urban spatial resilience optimization and control strategies suitable for different life cycle development stages, which is of great significance for enhancing the resilience of urban space to uncertain climate disaster risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0029] Figure 1 This is a flow chart of the full-cycle optimization and control method for urban space resilience based on ArcGIS Engine and SOM described in the present invention. DETAILED DESCRIPTION

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0031] Combine Figure 1 The present invention proposes a full-cycle optimization and control method for urban space resilience based on ArcGIS Engine and SOM, and the method comprises the following steps:

[0032] Step 1: Multidimensional attribute measurement of urban spatial resilience: Identify multi-level variable indicators of urban spatial resilience, construct an urban spatial resilience measurement indicator system, and clarify the calculation formula and superposition calculation method of each indicator;

[0033] In step 1, identify the variable indicators of urban spatial resilience: by analyzing the mapping relationship between the "spatial form-spatial structure" variable indicators and multidimensional resilience attributes, identify the multi-level variable indicators of urban spatial resilience; construct an urban spatial resilience measurement indicator system: based on the expert survey method, invite well-known experts and scholars in the field of resilience at home and abroad through online questionnaires, interviews, or roundtable meetings to screen, supplement, optimize, and evaluate the measurement indicators, and ultimately construct an urban spatial resilience measurement indicator system. Clarify the calculation formulas and superposition calculation methods for each indicator: based on the quantitative analysis methods and tools of urban spatial form and spatial structure such as space matrix, landscape structure index, and space syntax, clarify the calculation formulas for each indicator. Then, standardize the quantitative calculation results of each measurement indicator using the extreme value method, and calculate the weight of each indicator using the linear weighted combination method that combines subjective and objective weighting methods.

[0034] Step 2: Revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience: Implementing a full-cycle quantitative measurement of urban spatial resilience for typical sample cities, and revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience based on spatial statistical analysis methods;

[0035] In step 2, the full-cycle quantitative measurement of urban spatial resilience is implemented for typical sample cities. Specifically, based on the urban life cycle model, the full-cycle development stages of urban spatial resilience in the time dimension are refined and identified, including the development period, maintenance period, decline period, dormancy period and renewal period. Based on the two important attributes of potential and connectivity that characterize the changes in development stages, spatial visualization measurement of urban spatial resilience is then carried out for each development stage of the typical sample cities.

[0036] The spatial statistical analysis method is used to reveal the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience. Specifically, the Geary's c index of the spatial distribution of multidimensional resilience attributes in each development stage is calculated based on the high / low clustering analysis tool in ArcGIS, and the degree of spatial aggregation or dispersion of multidimensional resilience attributes is preliminarily analyzed. The changes in the high / low clustering distribution areas are analyzed from the temporal dimension. The global and local Moran's I indices of the multidimensional resilience attributes in each development stage are calculated based on the spatial autocorrelation tool in ArcGIS to reveal the spatial evolution trends and characteristics of urban spatial resilience. Subsequently, by identifying the development stage of each research unit and visually presenting the fluctuation change state of the resilience attribute index between each development stage, the temporal evolution trends and characteristics of urban spatial resilience are summarized and concluded. The complex trade-offs and synergistic relationships between the changes in various resilience attributes are analyzed based on the Pearson correlation coefficient, thereby revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience.

[0037] Step 3: Identify factors influencing the evolution of urban spatial resilience throughout its lifecycle: Using a multi-level linear model, analyze the impact of urban spatial elements and organizational characteristics at different development stages on resilience changes, their impact levels, and cross-stage interactions, identifying the internal dominant factors influencing the evolution of spatial resilience throughout its lifecycle at the within-group level. Using a random intercept model and a random coefficient regression model, analyze how socioeconomic environmental variables at different development stages influence the cross-stage changes in urban spatial elements and organizational characteristics, identifying the external dominant factors influencing the evolution of spatial resilience throughout its lifecycle at the between-group level.

[0038] In step 3, the internal dominant influencing factors of the full-cycle evolution of spatial resilience are identified. Specifically, regression models are established for the research units in the five different development stages of the full cycle, namely the development period, maintenance period, decline period, dormancy period and renewal period. Based on the multi-level linear model (HLM), the influence mode, degree of influence and cross-stage interaction effect of the explanatory variables within each development stage, i.e., the measurement indicators, on the dependent variable, i.e., the multidimensional resilience attributes, are analyzed, and the inter-group differences in the influencing factors of changes in urban spatial resilience are judged, thereby realizing the analysis process of the internal dominant influencing factors of the evolution of urban spatial resilience.

[0039] The identification of external dominant influencing factors of the full-cycle evolution of spatial resilience is as follows: regression models are established for research units in five different development stages of the full cycle, namely the development period, maintenance period, decline period, dormancy period and renewal period. Based on the random intercept model and random coefficient regression model, the author analyzes how the socio-economic environment characteristic variables of the research units in each development stage act on urban spatial elements and their organizational characteristics on the cross-stage changes of resilience, and identifies the external dominant influencing factors of the full-cycle evolution of urban spatial resilience.

[0040] Step 4: Construct an ArcGIS Engine-based full-cycle optimization and regulation model for urban spatial resilience: Based on the Geodesign framework, using ArcGIS Engine, C#, or Python technologies, and through GIS secondary development, construct a full-cycle optimization and regulation model for urban spatial resilience that includes control strategy input, rule modeling, resilience measurement execution, and scenario analysis and evaluation. This model supports full-cycle resilience optimization and regulation and scenario comparative analysis.

[0041] In step 4, based on the Geodesign framework, a technical process for optimizing and regulating urban spatial resilience is proposed, centered around "automatic model generation" and "automatic resilience measurement." Subsequently, the controlling factors affecting the multidimensional resilience attributes of urban spatial form and structure are set as parameter variables. Using five representative research units from different development stages (development, maintenance, decline, dormancy, and renewal) within the full lifecycle as research objects, rule-based modeling of spatial elements such as road networks, blocks, buildings, green spaces, and water bodies is performed within the CityEngine platform to construct a corresponding urban spatial resilience optimization and regulation model. After exporting the model data and corresponding attribute information in shp format, an ArcGIS environment script is created using Python and stored in ArcGIS as a toolbox. This Python script automatically executes the data import, resilience measurement, and result export steps, enabling real-time measurement of resilience performance under different resilience optimization and regulation strategy scenarios.

[0042] Step 5. Exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: Construct an optimization and regulation model for typical regions at different development stages, set the control factors of urban spatial form and structure that affect multidimensional resilience attributes as parameter variables, carry out spatial design optimization and spatial resilience measurement under single variable and combined variable conditions, and obtain a training data set for non-dominated solution set analysis; integrate the SOM neural network algorithm to construct a multi-development stage and multi-attribute dimension optimization target clustering model for urban spatial resilience, explore the optimal solution for the full-cycle coordinated improvement of the multidimensional attributes of urban spatial resilience through non-dominated solution set analysis, and identify the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages.

[0043] In step 5, the training dataset for the non-dominated solution clustering analysis is constructed: according to the technical process of optimizing and regulating urban spatial resilience, based on the optimization and regulation models of the research units in the development period, maintenance period, decline period, dormancy period and renewal period, spatial design optimization, spatial resilience measurement and scheme evaluation analysis are carried out under single variable and combined variable conditions to obtain the training dataset for the non-dominated solution clustering analysis.

[0044] Exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: A multidimensional resilience attribute optimization target clustering model is constructed based on the SOM neural network. By drawing a neuron-representative resilience optimization target component graph, a neuron-representative non-dominated solution quantity graph, and a neuron-level clustering graph, neuron-level clustering screening of urban spatial form and structural variables guided by the resilience optimization target is performed; then, based on the resilience optimization target-guided neuron-level clustering screening results and the SOM neural network, a resilience optimization target clustering model is reconstructed, and based on the reconstructed clustering model, neuron screening of urban spatial form and structural variables guided by the resilience optimization target is performed again; based on the resilience optimization target-guided neuron screening results, a clustering model of urban spatial form and structural variables is constructed, and based on the clustering model, a neuron-representative matrix graph of urban spatial form and structural variables and a neuron-representative matrix graph of multidimensional resilience attribute optimization targets are drawn to perform neuron-oriented screening of urban spatial form and structural variables, and based on the results of this round of screening, it is judged whether the next round of neuron-oriented screening of urban spatial form and structural variables is needed, until the final urban spatial form and structure optimization and regulation plan is obtained. After integrating the SOM neural network algorithm and the non-dominated solution set analysis method to explore the optimal solution for the full-cycle coordinated improvement of the multidimensional attributes of urban spatial resilience, the appropriate values ​​and threshold ranges of urban spatial form and structural variables at different development stages are identified.

[0045] The present invention also proposes a full-cycle optimization and control system for urban spatial resilience based on ArcGIS Engine and SOM, the system comprising:

[0046] Measurement module, multi-dimensional attribute measurement of urban spatial resilience: Identify multi-level variable indicators of urban spatial resilience, build an urban spatial resilience measurement indicator system, and clarify the calculation formula and superposition calculation method of each indicator;

[0047] Revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of modules and urban spatial resilience: Implementing full-cycle quantitative measurement of urban spatial resilience for typical sample cities, and revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience based on spatial statistical analysis methods;

[0048] Identification module, identification of factors influencing the full-cycle evolution of urban spatial resilience: Based on a multi-level linear model, the impact mode, degree of impact and cross-stage interaction effects of urban spatial elements and organizational characteristics at different development stages on resilience changes are analyzed, and the internal dominant influencing factors of the full-cycle evolution of spatial resilience are identified at the within-group level; based on a random intercept model and a random coefficient regression model, the influence of socio-economic environmental characteristic variables at different development stages on the cross-stage changes of urban spatial elements and organizational characteristics on resilience is analyzed, and the external dominant influencing factors of the full-cycle evolution of spatial resilience are identified at the inter-group level;

[0049] Construction module, construction of a full-cycle optimization and regulation model for urban spatial resilience based on ArcGIS Engine: Based on the Geodesign framework, using ArcGIS Engine technology and through GIS secondary development, a full-cycle optimization and regulation model for urban spatial resilience is constructed, which includes the technical functions of regulation strategy input, rule modeling generation, resilience measurement execution, and scenario analysis and evaluation. This supports full-cycle resilience optimization and regulation and scenario comparative analysis.

[0050] Exploration module, exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: construct an optimization and regulation model for typical areas at different development stages, set the control factors of urban spatial form and structure that affect multi-dimensional resilience attributes as parameter variables, carry out spatial design optimization and spatial resilience measurement under single variable and combined variable conditions, and obtain a training data set for non-dominated solution set analysis; integrate the SOM neural network algorithm to construct a multi-development stage and multi-attribute dimension optimization target clustering model for urban spatial resilience, explore the optimal solution for the full-cycle coordinated improvement of the multi-dimensional attributes of urban spatial resilience through non-dominated solution set analysis, and identify the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages.

[0051] Example

[0052] The present invention proposes a full-cycle optimization and control method and system for urban spatial resilience based on ArcGIS Engine and SOM. The specific implementation method of the technical solution of the present invention will be further explained below using a city in my country as an example. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The specific application of the present invention includes the following steps:

[0053] Step 1: Multidimensional attribute measurement of urban spatial resilience:

[0054] (1) Identify variable indicators of urban spatial resilience. Eight resilience attribute characteristics that are crucial to urban spatial resilience were identified, namely “robustness-redundancy-flexibility-multifunctionality-multi-layeredness-diversity-connectivity-polycentricity”. By analyzing the mapping relationship between the variable indicators of “spatial form-spatial structure” and the multidimensional resilience attributes of “robustness-redundancy-flexibility-multifunctionality-multi-layeredness-diversity-connectivity-polycentricity”, the variable indicators of urban spatial resilience were identified.

[0055] (2) Construct an urban spatial resilience measurement indicator system. Based on the expert survey method, well-known experts and scholars in the field of resilience at home and abroad were invited to screen, supplement, optimize, and evaluate the measurement indicators through online questionnaires, interviews, or roundtable meetings. This will ultimately construct an urban spatial resilience measurement indicator system. In the indicator system, each resilience attribute is measured and represented by at least one variable indicator. Among them, the measurement indicators of robustness include the robustness index of ecosystems (A1) and the robustness index of artificial systems (A2); the measurement indicator of redundancy is the spatial capacity redundancy index (B1); the measurement indicator of flexibility is the land use white space index (C1); the measurement indicator of multifunctionality is the spatial functional variability index (D1); the measurement indicators of multi-levelness include the functional hierarchy structure index (E1) and the population hierarchy structure index (E2); the measurement indicator of diversity is the land use function diversity index (F1); the measurement indicators of connectivity include the street network accessibility index (G1) and the important facilities accessibility index (G2); the measurement indicators of polycentricity include the travel centrality index (H1) and the density centrality index (H2).

[0056] (3) Clarify the calculation formula and superposition calculation method of each indicator. Based on the quantitative analysis methods and tools of urban spatial form and spatial structure such as Space matrix, Landscape structure index, Space syntax, etc., clarify the calculation formula of each indicator. Afterwards, implement the quantitative calculation of each measurement indicator for the case city, standardize the quantitative calculation results of each measurement indicator based on the extreme value method, and calculate the weight of each indicator based on the linear weighted combination method combining subjective and objective weighting methods. Based on the obtained weight calculation results, the superposition calculation formula of spatial resilience in the embodiment is:

[0057] ∑R=W1A1+W2A2+W3B1+W4C1+W5D1+W6E1+W7E2+W8F1+W9G1+W 10 G2+W 11 H1+W 12 H2

[0058] Where: W i (i=1,2,…,12) is the weight of the i-th measurement indicator. According to the weight calculation results of the case cities, W1 is 18.15%, W2 is 9.06%, W3 is 9.37%, W4 is 5.64%, W5 is 6.82%, W6 is 7.71%, W7 is 7.23%, W8 is 9.37%, W9 is 4.15%, and W 10 9.71%, W 11 is 6.69%, W 12 It is 6.10%.

[0059] Step 2: The spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience reveal:

[0060] (1) Quantitative measurement of spatial resilience over the entire life cycle of typical sample cities: Based on the urban life cycle model, the full life cycle development process of the case cities was analyzed, and the potential and connectivity characteristics of the research units in each period were analyzed. In this way, the typical eras corresponding to the development period, maintenance period, decline period, dormancy period, and renewal period of the case cities were identified, namely, the 1920s, 1950s, 1970s, 1990s, and 2020s. Subsequently, under the guidance of the urban spatial resilience measurement method, spatial visualization measurement of urban spatial resilience was carried out for the typical development stages of the case cities. According to the measurement results, among all 279 research units in the five development stages, the spatial resilience index was the highest at 0.86 and the lowest at 0.11.

[0061] (2) The spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience are revealed: After obtaining the full-cycle quantitative measurement results of the spatial resilience of the case city, the Geary's c index of the spatial distribution of multidimensional resilience attributes in each development stage is calculated based on the high / low clustering analysis tool in ArcGIS. The degree of spatial aggregation or dispersion of multidimensional resilience attributes is preliminarily analyzed, and the changes in the high / low clustering distribution areas are analyzed from the temporal dimension. According to the analysis results of the embodiment, the research units with high resilience in the development period are mainly concentrated in the city center; the research units with high resilience in the maintenance period are scattered throughout the city; the research units with high resilience in the decline and dormancy periods are distributed in the peripheral areas of the city; and in the renewal period, the research units in the city center regain high resilience performance. Subsequently, the global and local Moran's I index of the multidimensional resilience attributes in each development stage are calculated based on the spatial autocorrelation tool in ArcGIS to reveal the spatial evolution trend and characteristics of urban spatial resilience. The results of the example analysis show that during the development phase, the comprehensive resilience values ​​of almost all research units generally remain high, with approximately 82.36% of research units exhibiting medium-to-high resilience. During the maintenance phase, research units with fully developed artificial systems maintain their high resilience, while research units with underdeveloped artificial systems and damaged ecosystems experience a decline in their comprehensive resilience index, with approximately 68.37% of research units exhibiting medium-to-high resilience. During the decline and dormancy phases, over 80% of research units experience a downward trend in their comprehensive resilience values, with approximately 21.26% exhibiting medium-to-high resilience. During the renewal phase, the comprehensive resilience index of most research units re-emerges on an upward trend, with approximately 37.53% exhibiting medium-to-high resilience. Finally, by identifying the development stage of each research unit and visualizing the fluctuations in the resilience attribute index across development stages, we summarize and summarize the temporal evolution trends and characteristics of urban spatial resilience. Using the Pearson correlation coefficient, we analyze the complex trade-offs and synergies between changes in various resilience attributes, thereby revealing the spatiotemporal differentiation of urban spatial resilience over its full cycle.

[0062] Step 3: Identify factors influencing the full-cycle evolution of urban spatial resilience:

[0063] (1) Identification of the internal dominant influencing factors of the full-cycle evolution of spatial resilience: Regression models are established for the research units in the 1920s, 1950s, 1970s, 1990s, and 2020s during the full life cycle of the implementation example. The multi-level linear model is used to analyze the influence of the explanatory variables in each development stage on the dependent variables, and to determine the inter-group differences in the factors affecting the changes in urban spatial resilience at different development stages, so as to realize the analysis process of the internal dominant influencing factors of the evolution of urban spatial resilience. According to the analysis results of the embodiment, in the development period, the three indicators of ecosystem robustness index A1 (influence coefficient 0.708), street network accessibility index G1 (influence coefficient 0.685), and density centrality index H2 (influence coefficient 0.679) are the dominant influencing factors of urban spatial resilience; in the maintenance period, the three indicators of ecosystem robustness index A1 (influence coefficient 0.813), land function diversity index F1 (influence coefficient 0.672), and street network accessibility index G1 (influence coefficient 0.665) are the dominant influencing factors of urban spatial resilience; in the decline and dormant periods, the two indicators of artificial system robustness index A2 (influence coefficient 0.732) and important facility accessibility index G2 (influence coefficient 0.659) are the dominant influencing factors of urban spatial resilience; in the renewal period, the two indicators of land blank index C1 (influence coefficient 0.632) and spatial function variability index D1 (influence coefficient 0.611) are the dominant influencing factors of urban spatial resilience.

[0064] (2) Identification of external dominant influencing factors of the full-cycle evolution of spatial resilience: Regression models are established for research units in the five different development stages of the full cycle, namely the development stage, maintenance stage, decline stage, dormancy stage and renewal stage. Based on the random intercept model and random coefficient regression model, the influence of the socio-economic environment characteristic variables of the research units in each development stage on the urban spatial elements and their organizational characteristics on the cross-stage changes of resilience are analyzed to identify the external dominant influencing factors of the full-cycle evolution of urban spatial resilience. According to the results of the example analysis, the "economic development level" indicator has little effect on the cross-stage changes of urban spatial resilience, with an influence coefficient of only 0.201; the "planning policy orientation" indicator has a significant impact on the cross-stage changes of urban spatial resilience, with an influence coefficient of 0.794; the "planning management personnel scale" and "resilience management experience" indicators also have a relatively significant impact on the cross-stage changes of urban spatial resilience, with influence coefficients of 0.687 and 0.659 respectively.

[0065] Step 4: Construct a full-cycle optimization and regulation model for urban spatial resilience based on ArcGIS Engine:

[0066] According to the technical process of optimizing and regulating urban spatial resilience, this paper takes typical research units in five different development stages, namely the development period, maintenance period, decline period, dormancy period and renewal period, as the research objects. The dominant influencing factors affecting the multidimensional resilience attributes are set as parameter variables, and rule modeling of multiple types of spatial elements is carried out in the CityEngine platform to construct a corresponding urban spatial resilience optimization and regulation model.

[0067] Step 5: Explore the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM:

[0068] (1) Construction of training data set for non-dominated solution clustering analysis: The comprehensive resilience of the research units in the development period, maintenance period, decline period, dormancy period and renewal period is taken as the optimization target, and eight dominant influencing factors, namely the robustness index of ecosystem (A1), the robustness index of artificial system (A2), the land use white space index (C1), the spatial function variability index (D1), the land use function diversity index (F1), the street network accessibility index (G1), the important facility accessibility index (G2), and the density centrality index (H2), are selected as control variables. Spatial design optimization, spatial resilience measurement and scheme evaluation analysis under single variable and combined variable conditions are carried out to obtain the comprehensive resilience value of the research unit in each period corresponding to each group of variables. In the embodiment, a total of 300 sets of training data sets for non-dominated solution clustering analysis are output.

[0069] (2) Exploration of the optimal solution for the full-cycle optimization and regulation of urban spatial resilience based on SOM: 300 groups of sample data were randomly divided into a training data set and a validation data set. The SOM neural network prediction model was modeled and trained with the optimization objectives of minimizing the mean square error between the predicted value and the simulated value of the neural network training data and maximizing the linear correlation coefficient between the predicted value and the simulated value of the validation data. In order to obtain the non-dominated solution for the trade-off between the goals of urban spatial resilience throughout the life cycle, 218 non-dominated solutions for the full-life cycle optimization of spatial resilience were first extracted from a large number of solutions, and a SOM neural network with a size of 16×8 was constructed. Iterative training was performed using the normalized full-life cycle optimization of spatial resilience target data until the network converged, resulting in a SOM clustering model that can demonstrate the distribution of non-dominated solution data. Afterward, the next round of neuron screening was conducted, extracting the spatial resilience full-lifecycle optimization target data for the 144 non-dominated solutions obtained after the first round of screening. A new 12×6 SOM neural network was constructed and iteratively trained using the normalized spatial resilience full-lifecycle optimization target data to obtain a new SOM clustering model. Considering that there is still room for improvement in the spatial resilience full-lifecycle optimization target of the non-dominated solutions, a new 3×3 SOM neural network was constructed and iteratively trained using the normalized spatial resilience full-lifecycle optimization target data to obtain the final SOM clustering model. The corresponding non-dominated solution can be found by indexing the neuron number, and this non-dominated solution is the optimal solution for the spatial resilience full-lifecycle optimization control. Judging from the optimal solution exploration results of the embodiment, when the threshold of the robustness index (A1) of the ecosystem is between 0.43 and 0.56, the threshold of the robustness index (A2) of the artificial system is between 0.31 and 0.36, the threshold of the land blank index (C1) is between 0.09 and 0.11, the threshold of the spatial function variability index (D1) is between 0.17 and 0.19, the threshold of the land function diversity index (F1) is between 0.81 and 0.87, the threshold of the street network accessibility index (G1) is between 0.64 and 0.77, the threshold of the important facility accessibility index (G2) is between 0.57 and 0.62, and the threshold of the density centrality index (H2) is between 0.49 and 0.51, the comprehensive performance of the spatial resilience of the embodiment research unit can perform well in the development process of the whole life cycle.

[0070] The present invention also proposes an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the full-cycle optimization and control method of urban space resilience based on ArcGIS Engine and SOM.

[0071] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the full-cycle optimization and control method for urban space resilience based on ArcGIS Engine and SOM.

[0072] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DRRAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0073] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disc (SSD)).

[0074] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it will not be described in detail here.

[0075] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0076] The above is a detailed introduction to the full-cycle optimization and control method and system for urban spatial resilience based on ArcGIS Engine and SOM proposed in the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A full-cycle optimization and control method for urban spatial resilience based on ArcGIS Engine and SOM, characterized by: The method comprises the following steps: Step 1: Multidimensional attribute measurement of urban spatial resilience: Identify multi-level variable indicators of urban spatial resilience, construct an urban spatial resilience measurement indicator system, and clarify the calculation formula and superposition calculation method of each indicator; Step 2: Revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience: Implementing a full-cycle quantitative measurement of urban spatial resilience for typical sample cities, and revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience based on spatial statistical analysis methods; Step 3: Identify factors influencing the evolution of urban spatial resilience throughout its lifecycle: Using a multi-level linear model, analyze the impact of urban spatial elements and organizational characteristics at different development stages on resilience changes, their impact levels, and cross-stage interactions, identifying the internal dominant factors influencing the evolution of spatial resilience throughout its lifecycle at the within-group level. Using a random intercept model and a random coefficient regression model, analyze how socioeconomic environmental variables at different development stages influence the cross-stage changes in urban spatial elements and organizational characteristics, identifying the external dominant factors influencing the evolution of spatial resilience throughout its lifecycle at the between-group level. Step 4: Construct an ArcGIS Engine-based full-cycle optimization and regulation model for urban spatial resilience: Based on the Geodesign framework and using ArcGIS Engine technology, through GIS secondary development, a full-cycle optimization and regulation model for urban spatial resilience was constructed, encompassing regulation strategy input, rule modeling, resilience measurement execution, and scenario analysis and evaluation. This model supports full-cycle resilience optimization and regulation, as well as scenario comparative analysis. Step 5. Exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: Construct an optimization and regulation model for typical regions at different development stages, set the control factors of urban spatial form and structure that affect multidimensional resilience attributes as parameter variables, carry out spatial design optimization and spatial resilience measurement under single variable and combined variable conditions, and obtain a training data set for non-dominated solution set analysis; integrate the SOM neural network algorithm to construct a multi-development stage and multi-attribute dimension optimization target clustering model for urban spatial resilience, explore the optimal solution for the full-cycle coordinated improvement of the multidimensional attributes of urban spatial resilience through non-dominated solution set analysis, and identify the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages.

2. The method according to claim 1, characterized in that In step 1, the multi-level variable indicators of urban spatial resilience are identified by analyzing the mapping relationship between the "spatial form-spatial structure" variable indicators and multidimensional resilience attributes. Based on the quantitative analysis methods and tools of urban spatial form and spatial structure, the calculation formulas of each indicator are clarified. Then, the quantitative calculation results of each measurement indicator are standardized using the extreme value method, and the weight of each indicator is calculated using the linear weighted combination method that combines subjective and objective weighting methods.

3. The method according to claim 1, characterized in that In step 2, the full-cycle quantitative measurement of urban spatial resilience is implemented for typical sample cities. Specifically, based on the urban life cycle model, the full-cycle development stages of urban spatial resilience in the time dimension are refined and identified, including the development period, maintenance period, decline period, dormancy period and renewal period. Based on the two important attributes of potential and connectivity that characterize the changes in development stages, spatial visualization measurement of urban spatial resilience is then carried out for each development stage of the typical sample cities.

4. The method according to claim 3, characterized in that In step 2, the spatial statistical analysis method is used to reveal the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience. Specifically, the Geary's c index of the spatial distribution of multidimensional resilience attributes in each development stage is calculated based on the high / low clustering analysis tool in ArcGIS, and the degree of aggregation or dispersion of the multidimensional resilience attributes in space is preliminarily analyzed. The changes in the high / low clustering distribution areas are analyzed from the time dimension; the global and local Moran's I index of the multidimensional resilience attributes in each development stage are calculated based on the spatial autocorrelation tool in ArcGIS to reveal the spatial evolution trend and characteristics of urban spatial resilience; then, by identifying the development stage of each research unit and visually presenting the volatility change state of the resilience attribute index between each development stage, the temporal evolution trend and characteristics of urban spatial resilience are summarized and concluded, and the complex trade-offs and synergistic relationships between the changes in each resilience attribute are analyzed based on the Pearson correlation coefficient, so as to reveal the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience.

5. The method according to claim 1, characterized in that In step 3, the internal dominant influencing factors of the full-cycle evolution of spatial resilience are identified. Specifically, regression models are established for the research units in the five different development stages of the full cycle, namely the development period, maintenance period, decline period, dormancy period and renewal period. Based on the multi-level linear model (HLM), the influence mode, degree of influence and cross-stage interaction effect of the explanatory variables within each development stage, i.e., the measurement indicators, on the dependent variable, i.e., the multidimensional resilience attributes, are analyzed, and the inter-group differences in the influencing factors of changes in urban spatial resilience are judged, thereby realizing the analysis process of the internal dominant influencing factors of the evolution of urban spatial resilience.

6. The method according to claim 1, characterized in that In step 3, the external dominant influencing factors of the full-cycle evolution of spatial resilience are identified. Specifically, regression models are established for research units in the five different development stages of the full cycle, namely the development period, maintenance period, decline period, dormancy period and renewal period. Based on the random intercept model and random coefficient regression model, the socio-economic environment characteristic variables of the research units in each development stage are analyzed to see how their organizational characteristics affect the cross-stage changes in resilience, and the external dominant influencing factors of the full-cycle evolution of urban spatial resilience are identified.

7. The method according to claim 1, characterized in that In step 5, a multidimensional resilience attribute optimization target clustering model is constructed based on the SOM neural network. By drawing a neuron-representative resilience optimization target component graph, a neuron-representative non-dominated solution quantity graph, and a neuron-level clustering graph, a neuron-level clustering screening of urban spatial form and structural variables guided by the resilience optimization target is performed. Afterwards, based on the resilience optimization target-guided neuron-level clustering screening results and the SOM neural network, a resilience optimization target clustering model is reconstructed, and based on the reconstructed clustering model, a neuron-level clustering model of urban spatial form and structural variables guided by the resilience optimization target is again performed. Based on the resilience optimization target-guided neuron screening results, a clustering model of urban spatial form and structural variables is constructed, and based on the clustering model, a neuron-representative matrix graph of urban spatial form and structural variables and a neuron-representative multidimensional resilience attribute optimization target matrix graph are drawn to perform neuron-level screening of urban spatial form and structural variables. Based on the results of this round of screening, it is determined whether the next round of neuron-level screening of urban spatial form and structural variables is needed, until the final urban spatial form and structure optimization and control plan is obtained.

8. A full-cycle optimization and control system for urban spatial resilience based on ArcGIS Engine and SOM, characterized by: The system comprises: Measurement module, multi-dimensional attribute measurement of urban spatial resilience: Identify multi-level variable indicators of urban spatial resilience, build an urban spatial resilience measurement indicator system, and clarify the calculation formula and superposition calculation method of each indicator; Revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of modules and urban spatial resilience: Implementing full-cycle quantitative measurement of urban spatial resilience for typical sample cities, and revealing the spatiotemporal differentiation characteristics of the full-cycle evolution of urban spatial resilience based on spatial statistical analysis methods; Identification module, identification of factors influencing the full-cycle evolution of urban spatial resilience: Based on a multi-level linear model, the impact mode, degree of impact and cross-stage interaction effects of urban spatial elements and organizational characteristics at different development stages on resilience changes are analyzed, and the internal dominant influencing factors of the full-cycle evolution of spatial resilience are identified at the within-group level; based on a random intercept model and a random coefficient regression model, the influence of socio-economic environmental characteristic variables at different development stages on the cross-stage changes of urban spatial elements and organizational characteristics on resilience is analyzed, and the external dominant influencing factors of the full-cycle evolution of spatial resilience are identified at the inter-group level; Construction module, construction of a full-cycle optimization and regulation model for urban spatial resilience based on ArcGIS Engine: Based on the Geodesign framework, using ArcGIS Engine technology and through GIS secondary development, a full-cycle optimization and regulation model for urban spatial resilience is constructed, which includes the technical functions of regulation strategy input, rule modeling generation, resilience measurement execution, and scenario analysis and evaluation. This supports full-cycle resilience optimization and regulation and scenario comparative analysis. Exploration module, exploration of the optimal solution for full-cycle optimization and regulation of urban spatial resilience based on SOM: construct an optimization and regulation model for typical areas at different development stages, set the control factors of urban spatial form and structure that affect multi-dimensional resilience attributes as parameter variables, carry out spatial design optimization and spatial resilience measurement under single variable and combined variable conditions, and obtain a training data set for non-dominated solution set analysis; integrate the SOM neural network algorithm to construct a multi-development stage and multi-attribute dimension optimization target clustering model for urban spatial resilience, explore the optimal solution for the full-cycle coordinated improvement of the multi-dimensional attributes of urban spatial resilience through non-dominated solution set analysis, and identify the appropriate values ​​and threshold ranges of urban spatial form and structure variables at different development stages.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images