CN-121981561-A - Space form optimization method, device and equipment based on urban hot air risk network

CN121981561ACN 121981561 ACN121981561 ACN 121981561ACN-121981561-A

Abstract

The invention relates to the field of urban planning and management, in particular to a space form optimization method, device and equipment based on an urban hot air risk network, wherein the method comprises the steps of obtaining multisource remote sensing data of cities and constructing a space basic data set; the method comprises the steps of identifying a risk surface, a gallery and barrier points based on a space basic data set, constructing a high/low high hot air risk network, extracting multi-dimensional landscape features of each network component, training an optimal prediction model, extracting key form thresholds of each landscape feature in different network components, and generating space form optimization strategies corresponding to different network components in the high/low hot air risk network. According to the invention, the spatial structure of urban thermal risk is accurately identified through a geographic information system and landscape ecology, an independent high/low hot air risk network is constructed, meanwhile, an abstract thermal environment improvement target is converted into an operable planning design index by combining an interpretable machine learning quantitative morphological control threshold, and the accurate treatment of different components in the high/low hot air risk network is realized.

Inventors

XIANG YANG
PENG JING
HUANG CHUNBO
ZHU YI
WANG XIAOSHUANG
ZHANG YANGYANG

Assignees

中国地质大学（武汉）

Dates

Publication Date: 20260505
Application Date: 20260408

Claims (10)

1. The space form optimization method based on the urban hot air risk network is characterized by comprising the following steps of: step 1, acquiring multi-source remote sensing data of a city, preprocessing and standardizing the multi-source remote sensing data, and constructing a space basic data set; Step 2, performing morphological space pattern analysis based on the space basic data set to identify a risk surface, calculating a comprehensive resistance surface, identifying a corridor and an obstacle point based on a minimum accumulated resistance model and a circuit theory, and constructing an independent high-hot air risk network and a low-hot air risk network; Step 3, extracting multidimensional landscape features of each network component, and training an optimal prediction model, wherein the input of the optimal prediction model is multidimensional landscape features, and the output of the optimal prediction model is the surface temperature; Step 4, calculating the feature contribution degree of each landscape feature in the optimal prediction model by adopting a SHAP model, and establishing a SHAP local dependency graph to extract key morphological thresholds of each landscape feature in different network components; And 5, generating space morphology optimization strategies corresponding to different network components in the high/low hot air risk network based on the key morphology threshold.
2. The space morphology optimization method based on the urban hot air risk network according to claim 1, wherein the multi-source remote sensing data comprises surface temperature data, socioeconomic data and environmental characteristic data, the constructing of the space basic data set in the step 1 comprises the following steps: step 101, screening an initial thermal infrared band image meeting preset conditions in Google EARTH ENGINE, and filling a missing region in the thermal infrared band image through a preset interpolation strategy to obtain continuous surface temperature data; Step 102, obtaining social and economic data and environmental characteristic data, and integrating the surface temperature data, the social and economic data and the environmental characteristic data into a fishing net grid in a unified way by adopting a spatial registration, resampling and region statistics method to construct a spatial basic data set.
3. The urban hot air risk network-based space morphology optimization method according to claim 2, wherein the socioeconomic data comprises road density data, heat exposure data and/or heat vulnerability data; the environmental characteristic data includes at least one of terrain data, local climate zone map, building morphology data, three-dimensional tree data, albedo data, land cover data, and spectral index.
4. The urban hot air risk network-based space morphology optimization method according to claim 1, characterized in that the identification of the surface of the high/low hot air risk network comprises the following steps: step 201, constructing two groups of spatial association relations of thermal hazard-thermal exposure and thermal hazard-thermal vulnerability, and generating a local bivariate cluster map; step 202, identifying a potential high heat risk area and a potential low heat risk area through the local bivariate cluster map, wherein the potential high heat risk area is an intersection area of 'high heat damage-high heat exposure' and 'high heat damage-high heat fragility', and the potential low heat risk area is an intersection area of 'low heat damage-low heat exposure' and 'low heat damage-low heat fragility'; Step 203, converting the potential high-risk areas and the potential low-risk areas into binary grid patterns respectively, analyzing and extracting core plaques through morphological space patterns, filtering interference plaques in the core plaques through an area screening mechanism, extracting preferable core plaques through a possible connectivity index and/or an overall connectivity index, and generating a high-risk surface and a low-risk surface.
5. The urban hot air risk network-based space morphology optimization method according to claim 4, characterized in that identifying galleries and obstacle points of the high/low hot air risk network comprises the following steps: Step 204, constructing an evaluation framework based on heat hazard-heat exposure-heat fragility, and calculating the resistance value of the high/low hot air risk surface through weighted superposition to generate a high/low hot air risk comprehensive resistance surface; Step 205, calculating a minimum cost path on a corresponding comprehensive resistance surface based on the minimum accumulated resistance model, and identifying a low hot air risk gallery connected with a high hot air risk gallery and a low hot air risk gallery connected with the low hot air risk surface; Step 206, identifying obstacle points of the high hot air risk surface and the low hot air risk surface based on BarrierMapper tools.
6. The spatial morphology optimization method based on the urban hot air risk network according to claim 1, wherein the training of the optimal prediction model in the step 3 comprises the following steps: Step 301, extracting multidimensional landscape features of surfaces, galleries and barrier points in a high/low hot air risk network by adopting a fishing net tool, wherein the multidimensional landscape features comprise two-dimensional landscape indexes and three-dimensional city morphological indexes; Step 302, respectively constructing a plurality of machine learning prediction models based on the surfaces, galleries and obstacle points in the high/low hot air risk network, performing super-parameter tuning, traversing corresponding preset parameter spaces through grid search and cross-validation methods to screen out the optimal super-parameter combination of each machine learning model on a specific data set, and selecting the machine learning model with the highest precision as the optimal prediction model based on preset evaluation indexes, wherein the input of the optimal prediction model is multi-dimensional landscape characteristics, and the output of the optimal prediction model is the surface temperature.
7. The spatial morphology optimization method based on the urban hot air risk network according to claim 1, wherein the step 4 of extracting key morphology threshold values of each landscape feature in different network components comprises the following steps: Step 401, calculating SHAP values of all landscape features in the optimal prediction model, namely feature contribution degrees, by adopting a SHAP model; Step 402, summarizing the SHAP absolute value average values of all samples to show the global importance ranking and local interpretation of each landscape feature in different network components; Step 403, a SHAP local dependency graph is established, and key form thresholds of landscape features in different network components are analyzed based on the SHAP local dependency graph, wherein the key form thresholds are inflection points of the landscape features for influencing the surface temperature from positive to negative or from negative to positive.
8. The spatial morphology optimization method based on the urban hot air risk network according to claim 1 is characterized in that the spatial morphology optimization strategy is generated in the step 5, specifically, based on the key morphology threshold and combining action mechanisms of different landscape features in physical thermodynamics and urban ecology, a differential spatial morphology optimization strategy is formulated for the surfaces, galleries and obstacle points of the high hot air risk network and the low hot air risk network by following a treatment path of 'spatial recognition-factor diagnosis-threshold control'.
9. A space form optimizing device based on urban hot air risk network, which is based on the method of any one of claims 1-8 and is characterized by comprising a data acquisition module, a network construction module, a model optimization module, an analysis module and a strategy generation module, The data acquisition module is used for acquiring multi-source remote sensing data of a city, preprocessing and standardizing the multi-source remote sensing data, and constructing a space basic data set; The network construction module is used for executing morphological space pattern analysis based on the space basic data set to identify a risk surface, calculating a comprehensive resistance surface, identifying a corridor and an obstacle point based on a minimum accumulated resistance model and a circuit theory, and constructing an independent high-hot air risk network and a low-hot air risk network; The model optimization module is used for extracting multidimensional landscape features of each network component and training an optimal prediction model, wherein the input of the optimal prediction model is multidimensional landscape features, and the output of the optimal prediction model is ground surface temperature; The analysis module is used for calculating the feature contribution degree of each landscape feature in the optimal prediction model by adopting a SHAP model, and establishing a SHAP local dependency graph so as to extract key morphological thresholds of each landscape feature in different network components; the strategy generation module is used for generating space morphology optimization strategies corresponding to different network components in the high/low hot air risk network based on the key morphology threshold.
10. A spatial morphology optimization device based on a city hot air risk network, comprising a computer readable storage medium and a processor, characterized in that the processor, when executing a computer program on the computer readable storage medium, implements the steps of the spatial morphology optimization method based on a city hot air risk network as claimed in any one of the preceding claims 1-8.

Description

Space form optimization method, device and equipment based on urban hot air risk network Technical Field The invention relates to the field of urban planning and management, in particular to a space form optimization method, device and equipment based on an urban hot air risk network. Background At present, related researches for relieving urban heat islands are focused on cooling effect analysis of single landscape elements (such as water bodies and greenbelts) or constructing a cold island network based on a plaque-gallery-matrix theory. However, the existing method still has obvious limitations that firstly, the construction of the traditional cold island network depends on the physical index of surface temperature, comprehensive consideration of population dimension is lacking, thermal hazard and thermal exposure and thermal vulnerability are not organically combined, so that a release strategy possibly generates ' resource mismatch ' - ' namely, a cooling measure is excessively configured in a low population thermal exposure area, but an actual high risk area with higher temperature and high population density is ignored, secondly, the existing driving mechanism analysis assumes that urban thermal environment driving factors are in a homogeneous and linear relationship in space, the heterogeneous influence of different spatial functions is ignored, and the essential difference of dominant driving factors and thresholds in surfaces serving as thermal risks, galleries serving as thermal transmission channels and barrier points serving as thermal barriers cannot be effectively distinguished. Therefore, a comprehensive evaluation framework capable of integrating thermal hazard, thermal exposure and thermal vulnerability is urgently needed, a high/low hot air risk network is constructed based on the framework, and meanwhile, a technical method for accurately analyzing nonlinear morphological thresholds under different network functions is provided, so that the accuracy and efficiency of urban hot air risk regulation are supported. Disclosure of Invention The invention provides a space form optimization method, device and equipment based on an urban hot air risk network, which solve the technical problems of lack of consideration of population dimension, neglecting spatial heterogeneity of space functions on dominant factors and thresholds and the like in the prior art when a hot island or a cold island network is constructed, and realize accurate treatment of different components in the high hot air risk network and the low hot air risk network, including surfaces, galleries, obstacle points and the like, by constructing the high and low hot air risk networks and combining interpretable machine learning. The first aspect of the embodiment of the invention provides a space morphology optimization method based on an urban hot air risk network, which comprises the following steps: step 1, acquiring multi-source remote sensing data of a city, preprocessing and standardizing the multi-source remote sensing data, and constructing a space basic data set; Step 2, performing morphological space pattern analysis based on the space basic data set to identify a risk surface, calculating a comprehensive resistance surface, identifying a corridor and an obstacle point based on a minimum accumulated resistance model and a circuit theory, and constructing an independent high-hot air risk network and a low-hot air risk network; Step 3, extracting multidimensional landscape features of each network component, and training an optimal prediction model, wherein the input of the optimal prediction model is multidimensional landscape features, the output is surface temperature, and the network components comprise surfaces, galleries and obstacle points of a high/low hot air risk network; Step 4, calculating the feature contribution degree of each landscape feature in the optimal prediction model by adopting a SHAP model, and establishing a SHAP local dependency graph to extract key morphological thresholds of each landscape feature in different network components; And 5, generating space morphology optimization strategies corresponding to different network components in the high/low hot air risk network based on the key morphology threshold. A second aspect of the embodiments of the present invention provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the above-described spatial morphology optimization method based on a urban hot air risk network. A third aspect of the embodiments of the present invention provides a spatial morphology optimization device based on an urban hot air risk network, including a computer readable storage medium and a processor, where the processor implements the steps of the spatial morphology optimization method based on an urban hot air risk network when executing a computer program on the computer readable storage medium. The fourth a