Urban heat risk assessment method based on coupling of social and building dual vulnerability

Abstract

The application relates to the field of urban environment risk assessment, in particular to a city heat risk assessment method based on social and building double-weakness coupling. The method comprises the following steps: obtaining multi-source data of a target region, wherein the multi-source data comprises heat risk dimension indexes, social vulnerability dimension indexes and building vulnerability dimension indexes, the heat risk dimension indexes are a set of indexes representing the intensity of physical hazards of a heat environment, the exposure degree of people and buildings in the heat environment and the adaptation capacity of people and the environment in the heat environment, the social vulnerability dimension indexes are a set of indexes representing the vulnerability degree of people in the heat environment, and the building vulnerability dimension indexes are a set of indexes representing the physical vulnerability of buildings; heat risk indexes, social vulnerability indexes and building vulnerability indexes of each spatial unit in the target region are calculated according to the indexes; and heat risk assessment parameters of the target region are determined based on the indexes, so that the accuracy of heat risk assessment is improved.

Description

Technical Field

[0001] This application relates to the field of urban environmental risk assessment, specifically to an urban thermal risk assessment method based on the weak coupling of social and architectural factors. Background Technology

[0002] In densely built environments, the urban heat island effect is constantly amplified by factors such as impermeable surfaces, high building heights, and limited ventilation, and the differences in heat exposure between different spatial areas and different population groups are becoming increasingly prominent.

[0003] Existing urban heat risk studies typically focus on surface temperature, air temperature, or thermal comfort indicators. For example, surface temperature is obtained through remote sensing imagery, or air temperature indicators are calculated using meteorological monitoring data from weather stations. High-temperature areas are then identified through spatial interpolation or statistical analysis to support urban cooling planning and climate adaptation. These methods are highly efficient in characterizing the spatial distribution of heat islands.

[0004] However, the above methods focus on the physical properties of the thermal environment. It is one-sided to conduct urban thermal risk assessment based solely on the physical properties of the thermal environment, and it is difficult to comprehensively and accurately reflect urban thermal risks. Summary of the Invention

[0005] In view of the above, the embodiments of this application provide an urban thermal risk assessment method based on the weak coupling of social and architectural factors, which can comprehensively reflect urban thermal risks and improve the accuracy of thermal risk assessment.

[0006] This application provides a method for urban thermal risk assessment based on the weak coupling of social and architectural factors, including: Acquire multi-source data for the target area, including thermal risk dimension indicators, social vulnerability dimension indicators, and building vulnerability dimension indicators for each spatial unit in the target area; The thermal risk dimension indicators include hazard indicators, exposure indicators and adaptation indicators. The hazard indicators include surface temperature. The exposure indicators include population density, building coverage and sky visibility factor. The adaptation indicators include normalized vegetation index and medical accessibility index. The social vulnerability dimension index is a set of indicators that characterize the vulnerability of a population to a thermal environment. The building vulnerability dimension indicators include building age, building height, and building visibility factor; The thermal risk index of each spatial unit in the target area is obtained by weighted summation of the surface temperature, population density, building coverage, sky visibility factor, normalized vegetation index and medical accessibility index. The social vulnerability index of each spatial unit in the target region is obtained by weighted summation based on the social vulnerability dimension indicators. The building vulnerability index of each spatial unit in the target area is obtained by weighted summation based on the building age, building height and building visibility factor. The thermal risk assessment parameters for the target area are determined based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit. The thermal risk assessment parameters include: a first concentration index and a second concentration index; the determination of the thermal risk assessment parameters for the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit includes: The spatial units are sorted from high to low according to the social vulnerability index to obtain the first sorting result; The first cumulative spatial unit ratio and the first cumulative thermal risk index ratio are calculated sequentially along the sorting order of the first sorting result; wherein, the first cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the first cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units. Plot the first concentrated curve with the proportion of the first cumulative spatial unit as the horizontal axis and the proportion of the first cumulative thermal risk index as the vertical axis. The first concentration index is determined based on the first concentration curve. The spatial units are sorted from high to low according to the building vulnerability index to obtain a second sorting result; The second cumulative spatial unit ratio and the second cumulative thermal risk index ratio are calculated sequentially according to the sorting order of the second sorting result; wherein, the second cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the second cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units; The second concentrated curve is plotted with the proportion of the second cumulative spatial unit as the horizontal axis and the proportion of the second cumulative thermal risk index as the vertical axis. The second concentration index is determined based on the second concentration curve.

[0007] The multi-source data obtained in this application not only includes comprehensive thermal risk dimension indicators, but also introduces social vulnerability dimension indicators and building vulnerability dimension indicators. That is, thermal risk is comprehensively characterized from three dimensions: physical hazards of the thermal environment, vulnerability of the population, and physical vulnerability of buildings, thereby improving the comprehensiveness of the reference basis for thermal risk assessment. Then, based on these indicators, the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit are calculated by weighted summation. This realizes the quantitative characterization of the thermal risk level, vulnerability of the population, and physical vulnerability of buildings in each spatial unit, and can align them with the space, thereby more realistically reflecting the comprehensive thermal risk level in complex urban environments and ensuring the accuracy of thermal risk assessment results. Furthermore, based on the calculated thermal risk index, social vulnerability index, and building vulnerability index, this application calculates the thermal imbalance measurement model in which the social vulnerability index and building vulnerability index participate. Through the first concentration index and the second concentration index calculated based on this, the degree of imbalance of the social vulnerability index and building vulnerability index in the spatial distribution of thermal risk can be quantified, thereby providing comparable and interpretable quantitative indicators for the differences in high temperature exposure and thermal response among different groups and regions, so as to accurately and comprehensively assess the thermal risk of the target area. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating the steps of an urban thermal risk assessment method based on the weak coupling of social and architectural factors, according to an embodiment of this application.

[0009] Figure 2 This is a schematic diagram of the device structure of an urban thermal risk assessment apparatus according to an embodiment of this application.

[0010] Figure 3 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0011] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0012] The following description sets forth many specific details to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0014] It should be further noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0015] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0016] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0017] The technical terms used in the embodiments of this application are explained below.

[0018] Thermal risk, also known as high-temperature risk, refers to the potential harm faced by urban areas under high-temperature weather. It is determined by factors such as the intensity of the thermal environment (hazard), the density of disaster-bearing bodies (exposure), and the ability to cool down and provide relief (adaptation). It is a comprehensive measure of urban thermal problems.

[0019] Thermal vulnerability refers to the degree of vulnerability of a specific spatial unit to the risk of high temperatures. It includes two dimensions: social vulnerability caused by physiological, economic and social factors of the population, and architectural vulnerability caused by the physical characteristics of the building.

[0020] Thermal imbalance refers to the uneven distribution of thermal risks among different social groups or different building types, especially the spatial coupling between high-risk areas and highly vulnerable groups.

[0021] In this embodiment of the application, a planning unit refers to a basic geographical zoning unit delineated for urban planning and demographic purposes by the city to be risk-assessed (hereinafter referred to as the target area).

[0022] Spatial registration refers to the process of unifying spatial data from different sources and in different formats to the same geographic coordinate system and the same spatial unit boundary, ensuring that various indicators are comparable and computable within the same spatial unit.

[0023] Spatial unit aggregation refers to the process of statistically summarizing sampling point-level data (such as street view sampling points) according to their spatial units to obtain unit-level index values. Statistical methods such as average, median, or summation are usually used.

[0024] Land surface temperature (LST) refers to the temperature radiated by the Earth's surface in the thermal infrared band, reflecting the thermal state of objects on the Earth's surface.

[0025] Bivariate hierarchical clustering is an unsupervised classification method that performs hierarchical clustering of samples based on the similarity of two variables.

[0026] Ward's join method is a join criterion in hierarchical clustering. It clusters based on the principle of minimizing the increase in the sum of squared deviations within a class after merging, so that samples of the same class are as similar as possible and samples of different classes are as dissimilar as possible.

[0027] The Concentration Index (CI) can be used to quantitatively measure the uneven distribution of thermal risk among different vulnerable groups. Its value ranges from -1 to 1, with positive values ​​indicating a concentration of thermal risk in highly vulnerable areas and negative values ​​indicating a concentration in less vulnerable areas. A larger absolute value indicates a higher degree of unevenness.

[0028] The concentration curve, in this embodiment of the application, is a curve plotted with the cumulative spatial unit proportion as the abscissa and the cumulative thermal risk proportion as the ordinate, used to visually demonstrate the distribution characteristics of thermal risk in spatial units at different vulnerability levels. A curve located above the diagonal indicates that thermal risk is concentrated in vulnerable groups.

[0029] The trapezoidal method, a type of numerical integration method, divides the region under a curve into several smaller trapezoids and approximates the area under the curve by summing the areas of the trapezoids. In the embodiments of this application, it can be used to calculate the area under a curve where thermal risk is concentrated.

[0030] The Generalized Additive Model (GAM) is a nonlinear regression model based on an additive structure, allowing each explanatory variable to fit the explained variable as a smooth function without requiring a predefined specific function form. In the embodiments of this application, it can be used to characterize the nonlinear relationship between various vulnerability factors and thermal risk.

[0031] Smoothing functions are nonparametric functions used in generalized additive models to fit the relationship between explanatory and explained variables. They can adaptively fit local trends in data and identify nonlinear features such as threshold effects and saturation effects.

[0032] Interaction terms are terms in a model used to represent the interaction between two or more explanatory variables, reflecting the synergistic or amplifying effect of the variable combination on the explained variable. In the embodiments of this application, they can be used to identify the interaction between social vulnerability factors and building vulnerability factors.

[0033] The SHapley Additive exPlanations (SHAP) algorithm is an interpretable machine learning algorithm based on game theory. It quantifies the importance of each feature and the direction and magnitude of its influence on the model output by calculating the marginal contribution of each feature to the prediction result.

[0034] Cross-validation is a model evaluation method that divides the sample data into multiple subsets, trains the model with a subset in turn, and validates the model with the remaining subset. The robustness and generalization ability of the model are evaluated through multiple validations.

[0035] Radiometric calibration is the process of converting raw digital values ​​recorded by satellite sensors into physical quantities (such as radiance and reflectivity) to eliminate the influence of sensor response differences on images.

[0036] Atmospheric correction is the process of eliminating the absorption and scattering effects of atmospheric molecules and aerosols on satellite remote sensing images, making the retrieved surface parameters closer to the true values.

[0037] Multi-temporal image synthesis combines multiple images of the same area from different temporal phases, using methods such as average and median to synthesize a representative image, thereby eliminating the impact of abnormal fluctuations in a single temporal phase.

[0038] Semantic segmentation, one of the computer vision tasks, classifies each pixel in an image into a predefined category (such as sky, buildings, vegetation, roads).

[0039] A Point of Interest (POI) is a point-like geographic entity in a geographic information system that has attributes such as name, category, and coordinates, such as a hospital, school, or shop.

[0040] This application provides a method, apparatus, electronic device, and computer-readable storage medium for urban thermal risk assessment based on the weak coupling of social and building factors. The urban thermal risk assessment method based on the weak coupling of social and building factors may include: Acquire multi-source data for the target area, including thermal risk dimension indicators, social vulnerability dimension indicators, and building vulnerability dimension indicators; The thermal risk dimension indicators include hazard indicators, exposure indicators and adaptation indicators. The hazard indicators include surface temperature. The exposure indicators include population density, building coverage and sky visibility factor. The adaptation indicators include normalized vegetation index and medical accessibility index. The social vulnerability dimension index is a set of indicators that characterize the vulnerability of a population to a thermal environment. The building vulnerability dimension indicators include building age, building height, and building visibility factor; The thermal risk index of each spatial unit in the target area is obtained by weighted summation of the surface temperature, population density, building coverage, sky visibility factor, normalized vegetation index and medical accessibility index. The social vulnerability index of each spatial unit in the target region is obtained by weighted summation based on the social vulnerability dimension indicators. The building vulnerability index of each spatial unit in the target area is obtained by weighted summation based on the building age, building height, and building view factor. The thermal risk assessment parameters for the target area are determined based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit. The thermal risk assessment parameters include: a first concentration index and a second concentration index; the determination of the thermal risk assessment parameters for the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit includes: The spatial units are sorted from high to low according to the social vulnerability index to obtain the first sorting result; The first cumulative spatial unit ratio and the first cumulative thermal risk index ratio are calculated sequentially along the sorting order of the first sorting result; wherein, the first cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the first cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units. Plot the first concentrated curve with the proportion of the first cumulative spatial unit as the horizontal axis and the proportion of the first cumulative thermal risk index as the vertical axis. The first concentration index is determined based on the first concentration curve. The spatial units are sorted from high to low according to the building vulnerability index to obtain a second sorting result; The second cumulative spatial unit ratio and the second cumulative thermal risk index ratio are calculated sequentially according to the sorting order of the second sorting result; wherein, the second cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the second cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units; The second concentrated curve is plotted with the proportion of the second cumulative spatial unit as the horizontal axis and the proportion of the second cumulative thermal risk index as the vertical axis. The second concentration index is determined based on the second concentration curve.

[0041] The multi-source data obtained in this application not only includes thermal risk dimension indicators, but also introduces social vulnerability dimension indicators and building vulnerability dimension indicators. That is, thermal risk is comprehensively characterized from three dimensions: physical hazards of the thermal environment, vulnerability of the population, and physical vulnerability of buildings, thereby improving the comprehensiveness of the reference basis for thermal risk assessment. Then, by calculating the thermal risk index, social vulnerability index, and building vulnerability index, the thermal risk level, the degree of vulnerability of the population, and the degree of physical vulnerability of buildings are quantitatively characterized, which can more realistically reflect the comprehensive thermal risk level in complex urban environments and ensure the accuracy of thermal risk assessment results. Furthermore, based on the calculated thermal risk index, social vulnerability index, and building vulnerability index, this application calculates the thermal imbalance measurement model in which the social vulnerability index and building vulnerability index participate. The first concentration index and the second concentration index calculated based on this can quantify the degree of imbalance of the social vulnerability index and building vulnerability index in the spatial distribution of thermal risk, thereby providing comparable and interpretable quantitative indicators for the differences in high temperature exposure and thermal response among different groups and regions, so as to accurately and comprehensively assess the thermal risk of the target area.

[0042] The urban thermal risk assessment method based on the weak coupling of social and architectural factors proposed in this application can be applied to one or more electronic devices. The electronic device is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, processors, microprogrammed control units (MCUs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc. For example, the electronic device can be a server or a personal computer, but is not limited to these.

[0043] The urban thermal risk assessment method based on the dual weak coupling of society and architecture proposed in this application can be applied to related technical fields such as urban climate risk assessment, urban thermal environment analysis and environmental imbalance identification, and is especially suitable for technical application scenarios of thermal risk differences and vulnerable group identification in high-density built-up areas and cities with high population density.

[0044] Figure 1 This is a flowchart illustrating an embodiment of the urban thermal risk assessment method based on the weak coupling of social and architectural factors, as described in this application. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0045] See Figure 1 As shown, the urban thermal risk assessment method based on the dual weak coupling of society and architecture may include the following steps.

[0046] Step 101: Obtain multi-source data for the target area.

[0047] The target area refers to the urban area where a thermal risk assessment will be conducted. The target area may include multiple spatial units, and the division of these spatial units can be set according to actual application requirements.

[0048] Electronic devices can acquire multi-source data related to urban thermal environment and population carrying capacity characteristics within the target area.

[0049] This multi-source data includes thermal risk, social vulnerability, and building vulnerability indicators for each spatial unit within the target area. The following is an explanation of each indicator in the multi-source data: 1. Thermal risk dimension indicators: The thermal risk dimension index is a set of indicators that characterize the intensity of physical hazards in the thermal environment (hereinafter referred to as hazard index), the degree of exposure of people and buildings in the thermal environment (hereinafter referred to as exposure index), and the adaptability of people and the environment in the thermal environment (hereinafter referred to as adaptation index).

[0050] The hazard indicators may include land surface temperature (LST), which is used to characterize the intensity of high-temperature environments.

[0051] Exposure metrics may include population density (PD), building coverage ratio (BCR), and sky view factor (SVF).

[0052] Population density (PD) refers to the number of people per unit area, usually expressed as people per square kilometer or people per hectare. It reflects the degree of population concentration in a region and is a core indicator for measuring the size of the population exposed to high temperatures.

[0053] Building Coverage Ratio (BCR) refers to the ratio of the building footprint area to the total area of ​​a given region. It reflects the density of the built environment and is closely related to the surface heat storage capacity and ventilation conditions. SVF is used to characterize the visibility of the sky when looking up at the sky from an observation point, reflecting ventilation and heat dissipation conditions. The higher the SVF value, the more open the sky is and the better the ventilation and heat dissipation conditions are; the lower the SVF value, the more enclosed the building is and the easier it is for heat to accumulate.

[0054] Adaptation indicators may include the Normalized Difference Vegetation Index (NDVI) and the Healthcare Accessibility Index (HAI).

[0055] NDVI is used to characterize vegetation cover and growth status, reflecting the cooling capacity of the environment. The higher the NDVI value, the denser the vegetation and the more significant the cooling effect.

[0056] HAI is used to characterize the ease of access to medical services in a target area. It can be spatially analyzed and calculated based on medical facility point of interest data, usually considering factors such as the density, distance or accessibility of medical facilities, and reflects the treatment capacity for heat-related diseases.

[0057] The LST and NDVI values ​​mentioned above can be processed on the Google Earth Engine platform. For example, radiometric calibration and atmospheric correction can be performed on all Landsat 8 imagery, LST can be retrieved based on the thermal infrared band, and a representative LST distribution can be obtained by averaging multiple temporal images from summer 2021-2024. NDVI can be calculated from remote sensing imagery. HAI can be calculated based on medical facility POI data through spatial analysis. PD and BCR are directly calculated from census and building data. SVF is obtained through image processing of the target area.

[0058] 2. Social Vulnerability Dimension Indicators: The social vulnerability dimension index is a set of indicators characterizing the vulnerability of a population to thermal environments. The target area can include multiple spatial units, and the social vulnerability dimension index of each spatial unit can reflect the differences in the sensitivity and adaptability of the population to high-temperature risks within that unit.

[0059] The social vulnerability dimension indicators can include multiple vulnerability factors (referred to as social vulnerability factors). For example, the social vulnerability dimension indicators may include: The Children Ratio (CHILD) refers to the proportion of the population below the first preset age (e.g., 15 years old) in each spatial unit within the target area.

[0060] The Old Age Ratio (OLD) refers to the proportion of the population aged 65 and above in each spatial unit within the target area.

[0061] The Poverty Ratio (POVR) can refer to the proportion of households with incomes below a set threshold within each spatial unit of a target area.

[0062] The Low Education Population Ratio (LEP) refers to the proportion of the population in each spatial unit of a target area whose education level is below a set level.

[0063] The People Living Alone Ratio (PLA) can refer to the proportion of people living alone in a target area out of the total population.

[0064] 3. Building vulnerability dimension indicators: The building vulnerability dimension index is a set of indicators characterizing the physical vulnerability of a building. In this embodiment, the building vulnerability dimension index may include multiple vulnerability factors (hereinafter referred to as building vulnerability factors). For example, the building vulnerability dimension index may include: Building Year (BY) refers to the year a building was constructed or its age. Older buildings typically have poor insulation, building materials with high heat storage capacity, lack modern energy-saving designs, and are physically more vulnerable.

[0065] Building height (BH) refers to the vertical height of a building, usually measured in meters. Building height affects the duration of sunlight exposure, ventilation conditions, and heat radiation capture effect; heat accumulation may occur within certain height ranges.

[0066] The Building View Factor (BVF) is used to characterize the proportion of building pixels when looking up at the sky from the observation point. It reflects the degree of enclosure of the building space. The higher the BVF value, the higher the degree of building enclosure, the worse the ventilation and heat dissipation conditions, and the greater the risk of heat accumulation.

[0067] In some embodiments, the building vulnerability dimension index may further include: the proportion of public rental housing building area, whereby the proportion of public rental housing building area in a certain spatial unit is used to characterize the proportion of public rental housing area to the total building area of ​​the spatial unit.

[0068] Refer to Table 1 below, which explains the use of multi-source data and their meaning.

[0069] Table 1 The above data sources are merely examples and can be configured according to requirements in actual use. This application does not limit them.

[0070] In the aforementioned multi-source data, the thermal risk dimension index includes the sky view factor, and the building vulnerability dimension index includes the building view factor. The steps for obtaining the sky view factor and the building view factor may include: First, the electronic device acquires images of the target area. For example, based on the road network of the target area, street view sampling points are generated at 100-meter intervals, and 360° panoramic street view images of each sampling point are obtained through the street view map application interface. The image resolution can be set to 640×640 pixels, but is not limited to this.

[0071] Then, the electronic device identifies sky pixels and building pixels in the image (such as a street view image) based on a preset semantic segmentation model. For example, a deep learning-based semantic segmentation model is used to perform pixel-level classification of the street view image, distinguishing elements such as sky, buildings, vegetation, and roads.

[0072] Next, the electronic device can determine the sky view factor based on the proportion of the sky pixels in the image; and determine the building view factor based on the proportion of the building pixels in the image.

[0073] In some embodiments, after collecting multi-source data, the electronic device can divide the target area into multiple spatial units based on a preset spatial planning unit; perform spatial registration and unitization processing on the multi-source data, aggregate the multi-source data into each spatial unit, and construct a multi-dimensional index database for each spatial unit, that is, determine the thermal risk dimension index, social vulnerability dimension index and building vulnerability dimension index corresponding to each spatial unit.

[0074] Taking city A as the target area as an example, electronic devices can use the planning units of city A as spatial units.

[0075] The planning unit of city A is a basic geographical zoning unit delineated based on the urban planning and population statistics of city A. Each basic geographical zoning unit can be regarded as a spatial unit of city A.

[0076] Assuming city A is divided into approximately 290 units, geographic information system (GIS) technology is used to spatially register the aforementioned multi-source data and aggregate various indicators into each spatial unit, constructing a multi-dimensional indicator database for each spatial unit. For example, through spatial unit aggregation, multi-source data such as sky view factors and building view factors from each sampling point are mapped to corresponding spatial units, thereby determining the thermal risk dimension indicators, social vulnerability dimension indicators, and building vulnerability dimension indicators for each spatial unit in city A.

[0077] Step 102: Calculate the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit in the target area based on the thermal risk dimension index, social vulnerability dimension index, and building vulnerability dimension index, respectively.

[0078] For example, electronic devices can calculate the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit based on the multidimensional index database constructed in step 101.

[0079] Step 102 may include the following steps: weighted summation of the surface temperature, population density, building coverage, sky visibility factor, normalized vegetation index and medical accessibility index to obtain the thermal risk index of each spatial unit in the target area.

[0080] Based on the social vulnerability dimension indicators, such as the proportion of young people, the proportion of old people, the proportion of low-income people, the proportion of people with low education levels, and the proportion of people living alone, a weighted sum is performed to obtain the social vulnerability index of each spatial unit in the target area.

[0081] The building vulnerability index of each spatial unit in the target area is obtained by weighted summation based on the building age, building height, building view factor, and the proportion of public rental housing building area.

[0082] The calculation methods for the thermal risk index, social vulnerability index, and building vulnerability index are explained below: 1. Calculation of the heat risk index: The thermal risk index is a quantitative parameter calculated based on the aforementioned thermal risk dimension indicators. It is used to characterize the overall thermal risk level of each spatial unit, with a higher value indicating a greater thermal risk.

[0083] For example, electronic devices can perform weighted summation of the thermal risk dimension indicators of the spatial unit to obtain the thermal risk index of the spatial unit. That is, electronic devices can perform weighted summation based on the surface temperature, population density, building coverage, sky visibility factor, normalized vegetation index and medical accessibility index to obtain the thermal risk index of each spatial unit in the target area.

[0084] For example, electronic devices can use weighted summation (such as the equal weight method) to comprehensively calculate the hazard index LST, exposure index PD, BCR, SVF and adaptation index NDVI, HAI to obtain the thermal risk index.

[0085] 2. Calculation of the Social Vulnerability Index: The social vulnerability index is a quantitative parameter calculated based on the social vulnerability dimension indicators. It is used to characterize the vulnerability of the population in each spatial unit. The higher the value, the more severe the vulnerability of the population.

[0086] Electronic devices can perform weighted summation of the social vulnerability dimension indicators of the spatial units described in Table 1 to obtain the Social Disadvantage Index (SDI) of the spatial units.

[0087] For example, electronic devices can perform a weighted summation based on the proportions of young people, older people, low-income people, people with low levels of education, and people living alone to obtain a social vulnerability index for each spatial unit in the target area. For instance, an equal-weighting method can be used to comprehensively calculate the above indicators to obtain the social vulnerability index.

[0088] 3. Calculation of the building vulnerability index: The building vulnerability index is a quantitative parameter calculated based on the building vulnerability dimension indicators. It is used to characterize the physical vulnerability of each spatial unit. The higher the value, the more severe the building vulnerability.

[0089] Electronic devices can perform weighted summation of the building vulnerability dimension indicators of the spatial unit to obtain the building vulnerability index (BDI) of the spatial unit.

[0090] In other words, the electronic device can perform a weighted summation based on the building's age, height, and field of view factor to obtain the building vulnerability index for each spatial unit in the target area. For example, the electronic device can use an equal-weighting method to comprehensively calculate the above indicators to obtain the building vulnerability index.

[0091] Furthermore, the electronic device can perform a weighted summation based on the building's age, building height, building field of view factor, and the proportion of public rental housing building area to obtain the building vulnerability index of each spatial unit in the target area.

[0092] Step 103: Determine the thermal risk assessment parameters for the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit.

[0093] In some embodiments, thermal risk assessment parameters can be used to assess the thermal risk of a target area, and may include any one or a combination thereof: thermal imbalance characteristics of different spatial units in the target area, uneven distribution characteristics of thermal risk in the target area among different socially vulnerable and architecturally vulnerable groups, and the relationship between vulnerability factors and thermal risk index in the target area.

[0094] The following sections explain each thermal risk assessment parameter: 1. Thermal imbalance characteristics of different spatial units in the target region: The thermal imbalance characteristics of different spatial units in the target area can be determined by the first spatial type and the second spatial type to which each spatial unit belongs.

[0095] The first spatial type is a spatial type that is divided based on the combination of thermal risk level and social vulnerability level, and is used to indicate the spatial coupling type of thermal risk and social vulnerability to which each spatial unit belongs.

[0096] For example, based on the degree of thermal risk, spaces can be divided into high-thermal spaces and low-thermal spaces, where the thermal risk index of high-thermal spaces is greater than that of geothermal spaces. Based on the degree of social vulnerability, spaces can be divided into high-vulnerability spaces and low-vulnerability spaces, where the social vulnerability index of high-vulnerability spaces is greater than that of low-vulnerability spaces. The space types corresponding to the combination of thermal risk degree and social vulnerability degree can include first high-thermal-high-vulnerability space, first high-thermal-low-vulnerability space, first low-thermal-high-vulnerability space, and first low-thermal-low-vulnerability space.

[0097] The second space type is a space type that is divided according to the combination of thermal risk level and building vulnerability level, and is used to indicate the space coupling type of thermal risk and building vulnerability to which each space unit belongs.

[0098] For example, spaces can be classified into high-heat spaces and low-heat spaces based on their thermal risk level. The thermal risk index of high-heat spaces is greater than that of geothermal spaces. Similarly, spaces can be classified into high-vulnerability spaces and low-vulnerability spaces based on their building vulnerability level. The building vulnerability index of high-vulnerability spaces is greater than that of low-vulnerability spaces. The space types corresponding to the combination of thermal risk level and building vulnerability level can include second-high-heat-high-vulnerability spaces, second-high-heat-low-vulnerability spaces, second-low-heat-high-vulnerability spaces, and second-low-heat-low-vulnerability spaces.

[0099] In some embodiments, the step of determining the first spatial type to which each spatial unit belongs includes: performing range standardization and normalization on the thermal risk index, social vulnerability index, and building vulnerability index; and then performing bivariate hierarchical clustering analysis on the thermal risk index and the social vulnerability index of each spatial unit to obtain a first clustering result. For example, the thermal risk index and the social vulnerability index of the spatial unit can be used as bivariate inputs, and hierarchical clustering can be performed using the Ward join method.

[0100] Then, based on the first clustering result, the first spatial type to which each spatial unit belongs is determined. For example, based on the clustering partitioning threshold, each spatial unit is divided into a first high-heat high-vulnerability space, a first high-heat low-vulnerability space, a first low-heat high-vulnerability space, and a first low-heat low-vulnerability space.

[0101] In some embodiments, the step of determining the second space type to which each space unit belongs may include: The thermal risk index of each spatial unit and the social vulnerability index are subjected to bivariate hierarchical clustering analysis to obtain the second clustering result. For example, the thermal risk index of the spatial unit and the building vulnerability index can be used as bivariate inputs, and the Ward connection method can be used for hierarchical clustering.

[0102] Then, the second spatial type to which each spatial unit belongs is determined based on the second clustering result. For example, each spatial unit is divided into a second high-temperature high-vulnerability space, a second high-temperature low-vulnerability space, a second low-temperature high-vulnerability space, and a second low-temperature low-vulnerability space according to the clustering partitioning threshold.

[0103] This embodiment divides the clustering results into high thermal and high vulnerability, high thermal and low vulnerability, low thermal and high vulnerability, and low thermal and low vulnerability, which can intuitively present the thermal imbalance characteristics of different spatial units, thereby obtaining significant sub-regions with thermal imbalance in the target region.

[0104] 2. The uneven distribution of thermal risk in the target area among different socially vulnerable and architecturally vulnerable groups: This uneven distribution can be represented by the first concentration index and the second concentration index.

[0105] The first concentration index and the second concentration index are quantitative parameters used to quantitatively measure the uneven distribution of thermal risk among different vulnerable groups.

[0106] The process for determining the index in the first concentration is as follows: The electronic device sorts the spatial units from highest to lowest according to the social vulnerability index, obtaining a first sorting result; and calculates the first cumulative spatial unit ratio and the first cumulative thermal risk index ratio sequentially along the sorting order of the first sorting result. The first cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units; the first cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units.

[0107] Then, the first concentrated curve is plotted with the proportion of the first cumulative spatial unit as the horizontal axis and the proportion of the first cumulative thermal risk index as the vertical axis.

[0108] Next, the first concentration index is determined based on the first concentration curve. For example, the area under the first concentration curve (AUC) is calculated using the trapezoidal rule, and then the first concentration index CI is calculated using the formula CI=2×(AUC-0.5).

[0109] The process of determining the second concentration index may include: The electronic device sorts the spatial units from highest to lowest according to the building vulnerability index, obtaining a second sorting result; and calculates the second cumulative spatial unit ratio and the second cumulative thermal risk index ratio sequentially along the sorting order of the second sorting result. The second cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units; the second cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units.

[0110] Then, a second concentration curve is plotted with the proportion of the second cumulative spatial unit as the abscissa and the proportion of the second cumulative thermal risk index as the ordinate; the second concentration index is determined based on the second concentration curve. For example, the area under the second concentration curve (AUC) is calculated using the trapezoidal rule, and then the second concentration index CI is calculated using the formula CI=2×(AUC-0.5).

[0111] The positive or negative sign of the concentration index and the magnitude of its absolute value can reflect the direction of concentration and the degree of imbalance of thermal risk in the vulnerability ranking, thereby enabling a quantitative characterization of the unevenness of urban thermal risk.

[0112] 3. The relationship between vulnerability factors and thermal risk index in the target area: This relationship can be modeled using a nonlinear model. Vulnerability factors are individual indicators from the social vulnerability dimension indicators and the building vulnerability dimension indicators, such as CHILD, OLD, POVR, LEP, PLA, BY, BH, BVF, PH, etc., as shown in Table 1.

[0113] In some embodiments, the step of determining a nonlinear model of a target region by an electronic device may include: constructing a smoothing function for each vulnerability factor, wherein the smoothing function represents the nonlinear relationship between the vulnerability factor and the thermal risk index. For example, a nonlinear modeling method based on additive structure (Generalized Additive Model GAM) is used to introduce a smoothing term for each vulnerability factor, adaptively fitting the changing trend of the vulnerability factor change in response to the thermal risk without pre-setting the function form.

[0114] The electronic device can also combine the vulnerability factors of the social vulnerability dimension index and the vulnerability factors of the building vulnerability dimension index in pairs to obtain various vulnerability factor combinations (including social vulnerability factors and building vulnerability factors). Then, based on each vulnerability factor combination, a two-factor interaction term is constructed, which represents the nonlinear relationship between the vulnerability factor combination and the heat risk index.

[0115] Next, the nonlinear model is determined based on the smoothing function and the two-factor interaction term. For example, the smoothing function and the two-factor interaction term are added together to determine the nonlinear model. By comparing the modeling results of different factor combinations, factor combinations with significant synergistic or amplifying effects in the formation of thermal risks are identified.

[0116] This application employs a nonlinear modeling method based on additive structures, constructing smoothing functions for each vulnerability factor to characterize the potential nonlinear relationship between a single vulnerability factor and thermal risk. By introducing smoothing terms, the nonlinear model can adaptively fit the changing trend of the vulnerability factor's response to thermal risk without pre-setting the function form, thereby avoiding the problem of traditional linear models failing to adequately characterize complex relationships.

[0117] Furthermore, in order to identify the interaction effect between social vulnerability factors and building vulnerability factors, this application embodiment combines the vulnerability factor set in pairs to construct a nonlinear model containing two-factor interaction terms. By comparing the modeling results of different factor combinations, it identifies factor combinations that have significant synergistic or amplifying effects in the process of thermal risk formation, thereby revealing the composite driving mechanism of thermal imbalance formation.

[0118] After determining the nonlinear model, the electronic device can interpret the nonlinear model based on the Shapley additive interpretation algorithm (SHAP) to obtain the model interpretation result.

[0119] The model interpretation results are used to indicate the degree of contribution of each vulnerability factor and combination of vulnerability factors to the model output of the nonlinear model, thereby clarifying the strength of each vulnerability factor in the thermal risk formation mechanism and its relative order of influence.

[0120] In other words, at the model interpretation level, this application introduces a model interpretation method to quantitatively evaluate the relative importance of single-factor and two-factor combinations in the model fitting process.

[0121] Furthermore, to evaluate the robustness and generalization ability of the constructed model, multi-fold cross-validation was performed on the model results. By dividing the sample data into multiple subsets and alternating between model training and validation, the model's fitting stability under different data partitioning conditions was examined, thereby improving the reliability of the thermal imbalance mechanism identification results.

[0122] Compared to a single dimension in characterizing population vulnerability, this application constructs indicators for social vulnerability and building vulnerability as two independent and parallel core dimensions, and performs systematic coupling analysis with thermal risk. By separately characterizing the vulnerability characteristics of the population level and the amplification effect of built environment conditions on thermal exposure, it achieves dual identification of urban thermal vulnerability. This breaks through the traditional analysis methods that ignore or implicitly treat the vulnerability of the built environment, and more realistically and comprehensively reveals the formation mechanism of uneven thermal risk in high-density cities.

[0123] This application's embodiments achieve interpretable modeling of the thermal risk formation mechanism, overcoming the black-box problem of traditional models. By introducing a model interpretation algorithm based on SHAP values, this application's embodiments decompose the contribution of thermal risk prediction results into spatial units, achieving a quantitative characterization of the impact of different vulnerability factors and their interactions on thermal risk. Compared to traditional methods based on correlation analysis or regression coefficients, this application's embodiments can clarify the direction and magnitude of the marginal contribution of each factor under nonlinear and multi-factor coupling conditions, effectively solving the problem of insufficient interpretability in thermal risk assessment models.

[0124] Furthermore, the embodiments of this application can characterize the spatial amplification effect of multi-factor interactions on thermal risk. These embodiments not only analyze the impact of a single vulnerability factor on thermal risk, but also reveal the synergistic amplification or inhibition effect of social vulnerability characteristics and built environment vulnerability characteristics in different regions through spatial analysis of the SHAP values ​​of two-factor and multi-factor interaction terms. Compared to methods that ignore the spatial effects of factor interactions, the embodiments of this application can more realistically reflect the intrinsic mechanism of thermal risk formation in complex urban environments.

[0125] The embodiments of this application have good versatility and scalability. The model interpretation and spatial mapping methods used in the embodiments of this application do not depend on specific cities or specific indicator systems. Input factors or spatial analysis units can be flexibly replaced according to the research object. It is applicable to thermal risk and environmental imbalance analysis at different scales and in different city types, and has strong technical adaptability.

[0126] Based on the same idea as the urban thermal risk assessment method based on the weak coupling of social and architectural factors in the above embodiments, this application also provides an urban thermal risk assessment device, which can be used to perform the above-described urban thermal risk assessment method based on the weak coupling of social and architectural factors. For ease of explanation, the structural schematic diagram of the thermal risk assessment device embodiment only shows the parts related to the embodiments of this application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation on the device, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0127] like Figure 2 As shown, the thermal risk assessment device includes a data acquisition module 201, an index calculation module 202, and a risk assessment module 203. In some embodiments, the above modules can be programmable software instructions stored in memory and executable by a processor. It is understood that in other embodiments, the above modules can also be program instructions or firmware embedded in the processor.

[0128] The data acquisition module 201 is used to acquire multi-source data of the target area, including thermal risk dimension indicators, social vulnerability dimension indicators and building vulnerability dimension indicators of each spatial unit in the target area. The thermal risk dimension indicators include hazard indicators, exposure indicators, and adaptation indicators. The hazard indicators include surface temperature. The exposure indicators include population density, building coverage, and sky visibility factor. The adaptation indicators include normalized difference vegetation index and medical accessibility index. The social vulnerability dimension indicators are a set of indicators that characterize the vulnerability of a population to the thermal environment. The building vulnerability dimension indicators include building age, building height, and building visibility factor. The index calculation module 202 is used to obtain the thermal risk index of each spatial unit in the target area by weighted summation based on the surface temperature, population density, building coverage, sky view factor, normalized vegetation index, and medical accessibility index; to obtain the social vulnerability index of each spatial unit in the target area by weighted summation based on the social vulnerability dimension index; and to obtain the building vulnerability index of each spatial unit in the target area by weighted summation based on the building age, building height, and building view factor. Risk assessment module 203 is used to determine the thermal risk assessment parameters of the target area based on the thermal risk index, social vulnerability index and building vulnerability index of each spatial unit; The thermal risk assessment parameters include: a first concentration index and a second concentration index; the determination of the thermal risk assessment parameters for the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit includes: The spatial units are sorted from high to low according to the social vulnerability index to obtain the first sorting result; The first cumulative spatial unit ratio and the first cumulative thermal risk index ratio are calculated sequentially along the sorting order of the first sorting result; wherein, the first cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the first cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units. Plot the first concentrated curve with the proportion of the first cumulative spatial unit as the horizontal axis and the proportion of the first cumulative thermal risk index as the vertical axis. The first concentration index is determined based on the first concentration curve. The spatial units are sorted from high to low according to the building vulnerability index to obtain a second sorting result; The second cumulative spatial unit ratio and the second cumulative thermal risk index ratio are calculated sequentially according to the sorting order of the second sorting result; wherein, the second cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the second cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units; The second concentrated curve is plotted with the proportion of the second cumulative spatial unit as the horizontal axis and the proportion of the second cumulative thermal risk index as the vertical axis. The second concentration index is determined based on the second concentration curve.

[0129] Figure 3 This is a schematic diagram of an embodiment of the electronic device of this application.

[0130] The electronic device 100 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and executable on the processor 30. When the processor 30 executes the computer program 40, it implements the steps described in the above-described embodiment of the urban thermal risk assessment method based on the dual weak coupling of social and architectural factors, for example... Figure 1 Steps 101 to 103 are shown.

[0131] For example, computer program 40 can also be divided into one or more modules / units, which are stored in memory 20 and executed by processor 30. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 40 in electronic device 100.

[0132] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 100 and does not constitute a limitation on the electronic device 100. It may include more or fewer components than shown in the diagram, or combine certain components, or different components. For example, the electronic device 100 may also include input / output devices, network access devices, buses, etc.

[0133] Processor 30 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors, single-chip microcomputers, or any conventional processor.

[0134] The memory 20 can be used to store computer programs 40 and / or modules / units. The processor 30 implements various functions of the electronic device 100 by running or executing the computer programs and / or modules / units stored in the memory 20 and by calling data stored in the memory 20. The memory 20 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0135] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed 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 do not include electrical carrier signals and telecommunication signals.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the electronic device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and other division methods may be used in actual implementation.

[0137] Furthermore, the functional units in the various embodiments of this application can be integrated into the same processing unit, or each unit can exist physically separately, or two or more units can be integrated into the same unit. The integrated units described above can be implemented in hardware or in the form of hardware plus software functional modules.

[0138] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and not restrictive in all respects. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or electronic devices recited in the electronic device claims may also be implemented by the same unit or electronic device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for urban thermal risk assessment based on the dual weak coupling of social and architectural factors, characterized in that, include: Acquire multi-source data for the target area, including thermal risk dimension indicators, social vulnerability dimension indicators, and building vulnerability dimension indicators for each spatial unit in the target area; The thermal risk dimension indicators include hazard indicators, exposure indicators, and adaptation indicators. The hazard indicators include surface temperature. The exposure indicators include population density, building coverage, and sky visibility factor. The adaptation indicators include normalized difference vegetation index and medical accessibility index. The social vulnerability dimension indicators are a set of indicators that characterize the vulnerability of a population to the thermal environment. The building vulnerability dimension indicators include building age, building height, and building visibility factor. The thermal risk index of each spatial unit in the target area is obtained by weighted summation of the surface temperature, population density, building coverage, sky visibility factor, normalized vegetation index and medical accessibility index. The social vulnerability index of each spatial unit in the target region is obtained by weighted summation based on the social vulnerability dimension indicators. The building vulnerability index of each spatial unit in the target area is obtained by weighted summation based on the building age, building height, and building view factor. The thermal risk assessment parameters for the target area are determined based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit. The thermal risk assessment parameters include: a first concentration index and a second concentration index; the determination of the thermal risk assessment parameters for the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit includes: The spatial units are sorted from high to low according to the social vulnerability index to obtain the first sorting result; The first cumulative spatial unit ratio and the first cumulative thermal risk index ratio are calculated sequentially along the sorting order of the first sorting result; wherein, the first cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the first cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units. Plot the first concentrated curve with the proportion of the first cumulative spatial unit as the horizontal axis and the proportion of the first cumulative thermal risk index as the vertical axis. The first concentration index is determined based on the first concentration curve. The spatial units are sorted from high to low according to the building vulnerability index to obtain a second sorting result; The second cumulative spatial unit ratio and the second cumulative thermal risk index ratio are calculated sequentially according to the sorting order of the second sorting result; wherein, the second cumulative spatial unit ratio is the proportion of the current cumulative number of spatial units to the total number of spatial units, and the second cumulative thermal risk index ratio is the proportion of the sum of the thermal risk indices of the current cumulative spatial units to the sum of the thermal risk indices of all spatial units; The second concentrated curve is plotted with the proportion of the second cumulative spatial unit as the horizontal axis and the proportion of the second cumulative thermal risk index as the vertical axis. The second concentration index is determined based on the second concentration curve.

2. The urban thermal risk assessment method based on the weak coupling of social and architectural factors as described in claim 1, characterized in that, The thermal risk assessment parameters also include the first spatial type to which each spatial unit belongs; the first spatial type is a spatial type classified based on the combination of thermal risk level and social vulnerability level; The method for determining the thermal risk assessment parameters of the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit also includes: The thermal risk index of each spatial unit and the social vulnerability index are subjected to bivariate hierarchical cluster analysis to obtain the first clustering result. The first spatial type to which each spatial unit belongs is determined based on the first clustering result.

3. The urban thermal risk assessment method based on the dual weak coupling of social and architectural factors as described in claim 1, characterized in that, The thermal risk assessment parameters also include the second spatial type to which each spatial unit belongs; the second spatial type is a spatial type classified based on the combination of thermal risk level and building vulnerability level; The method for determining the thermal risk assessment parameters of the target area based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit also includes: A bivariate hierarchical cluster analysis was performed on the thermal risk index of each spatial unit and the building vulnerability index to obtain the second clustering result. Based on the second clustering result, the second spatial type to which each spatial unit belongs is determined.

4. The urban thermal risk assessment method based on the dual weak coupling of social and architectural factors as described in claim 1, characterized in that, The thermal risk assessment parameters also include a nonlinear model representing the relationship between each vulnerability factor and the thermal risk index, wherein the vulnerability factor is a single indicator among the social vulnerability dimension index and the building vulnerability dimension index. Based on the thermal risk index, social vulnerability index, and building vulnerability index of each spatial unit, the thermal risk assessment parameters of the target area are determined, including: A smoothing function is constructed for each vulnerability factor, and the smoothing function represents the nonlinear relationship between the vulnerability factor and the thermal risk index; The vulnerability factors of the social vulnerability dimension index and the vulnerability factors of the building vulnerability dimension index are combined in pairs to obtain the various vulnerability factor combinations. Two-factor interaction terms are constructed based on each combination of vulnerability factors, and the two-factor interaction terms represent the nonlinear relationship between the combination of vulnerability factors and the thermal risk index. The nonlinear model is determined based on the smoothing function and the two-factor interaction term.

5. The urban thermal risk assessment method based on the dual weak coupling of social and architectural factors as described in claim 4, characterized in that, After determining the nonlinear model based on the smoothing function and the two-factor interaction term, the method further includes: The nonlinear model is interpreted based on the Shapley additive interpretation algorithm to obtain the model interpretation result, which is used to indicate the degree of contribution of each vulnerability factor and combination of vulnerability factors to the model output of the nonlinear model.

6. The urban thermal risk assessment method based on the dual weak coupling of social and architectural factors as described in any one of claims 1 to 5, characterized in that, The steps for obtaining the sky view factor include: Acquire images of the target area; The sky pixels in the image are identified based on a preset semantic segmentation model; The sky view factor is determined based on the proportion of the sky pixels in the image.

7. The urban thermal risk assessment method based on the dual weak coupling of social and architectural factors as described in any one of claims 1 to 5, characterized in that, The steps for obtaining the building view factor include: Acquire images of the target area; The building pixels in the image are identified based on a preset semantic segmentation model; The building view factor is determined based on the proportion of the building pixels in the image.

Images