Urban environment heat risk assessment and early warning method and device based on multi-source data

Abstract

This application discloses a method and apparatus for urban environmental thermal risk assessment and early warning based on multi-source data, relating to the field of data processing technology. The method includes: acquiring multi-source data of the study city in a target year; preprocessing the multi-source data to obtain a standardized multi-source dataset; generating a local climate zone map based on the standardized multi-source dataset, and constructing a future land use simulation model and a thermal risk assessment model; calculating the thermal risk index of different blocks in the local climate zone map and the thermal risk index under future urban land use change scenarios based on the thermal risk assessment model; dividing the study city's areas into corresponding thermal risk levels based on the thermal risk index, thereby generating a thermal risk level distribution map; and triggering a graded early warning mechanism based on a preset risk threshold and the thermal risk level distribution map. This application rapidly and completely identifies the spatial distribution of urban environmental thermal risks and provides thermal risk early warning through multi-source data, which can assist in the formulation of thermal mitigation strategies.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and apparatus for urban environmental thermal risk assessment and early warning based on multi-source data. Background Technology

[0002] With the acceleration of global climate change and urbanization, global warming has intensified significantly, leading to increasingly prominent urban thermal environment deterioration and rising urban environmental thermal risks. Urban environmental thermal risk refers to the potential and extent of adverse effects of high temperatures and abnormal thermal environments on public health and urban system operation within the urban environment. Especially in the context of future urban development, drastic changes in land use types and spatial distribution patterns, the expansion of impervious surfaces, and the reduction of ecological land exacerbate the urban heat island effect, significantly increasing the health risks associated with high temperatures in cities. In today's society, urban environmental thermal risk has become an undeniable challenge in urban development.

[0003] The specific hazards of heat risk manifest in multiple dimensions: For residents' health, extreme heat increases the incidence and mortality risks of heatstroke, cardiovascular and cerebrovascular diseases, posing a significant threat, especially to vulnerable groups such as the elderly and children; at the urban operation level, high temperatures increase the energy consumption of cooling equipment such as air conditioners, exacerbating the pressure on power supply and potentially affecting the stability of transportation facilities and municipal pipelines; from a socio-economic perspective, high temperatures also reduce the efficiency of outdoor work and may even lead to agricultural losses. Currently, urban environmental heat risk assessment is mainly based on single indicators such as surface temperature, population, and economy, and does not quantify the impact of land use changes (e.g., construction land, arable land, forest land, water bodies, grassland, etc.) on key factors such as surface temperature, population, and economy. To address these shortcomings, this invention proposes a method and device for urban environmental heat risk assessment and early warning based on multi-source data, enabling urban environmental heat risk analysis, quantifying the impact of future urban land use changes on heat risk, and providing early warnings. Summary of the Invention

[0004] The main objective of this application is to propose a method and apparatus for urban environmental thermal risk assessment and early warning based on multi-source data, so as to accurately assess urban environmental thermal risks and issue early warnings.

[0005] To achieve the above objectives, one aspect of this application proposes a method for urban environmental thermal risk assessment and early warning based on multi-source data, the method comprising the following steps: Obtain multi-source data for the study city in the target year; The multi-source data is preprocessed to obtain a standardized multi-source dataset; Based on the standardized multi-source dataset, a local climate zone map of the study city is generated, and a future land use simulation model and a thermal risk assessment model are constructed. The thermal risk index of different blocks in the local climate zone map and the thermal risk index under the future urban land use change scenario are calculated based on the thermal risk assessment model. Based on the heat risk index, the area of ​​the study city is divided into corresponding heat risk levels, and a heat risk level distribution map is generated. A graded early warning mechanism is triggered based on a preset risk threshold and the thermal risk level distribution map.

[0006] In some embodiments, obtaining multi-source data for the study city in a target year includes the following steps: The study city's GDP, remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information for the target year are obtained as the multi-source data.

[0007] In some embodiments, preprocessing the multi-source data to obtain a standardized multi-source dataset includes the following steps: Missing and outlier values ​​are detected and removed from the multi-source data, and spatial registration and resampling to a unified coordinate system and the same resolution are completed. Then, normalization and cleaning are performed to obtain the standardized multi-source dataset.

[0008] In some embodiments, the step of generating the local climate zone map based on the standardized multi-source dataset includes the following steps: Extract urban morphology data from the standardized multi-source dataset; Determine the resolution of the local climate zone grid for the studied city; The spatial morphology of the local climate zone grid is evaluated based on the urban morphology data. The local climate zone grid is divided into local climate zone types that include the spatial morphology and climate characteristics using fuzzy classification and majority voting methods, thus obtaining the local climate zone map.

[0009] In some embodiments, the step of constructing the future land use simulation model based on the standardized multi-source dataset includes the following steps: A multi-objective optimization model was adopted, combined with the historical land use transfer matrix, to determine the total land use demand for the target year; A patch-based land use simulation model was used to simulate the spatial distribution pattern of future land use under four urban development scenarios. A land contribution index is constructed to quantify the influence weight of land use type on thermal risk assessment indicators; wherein, the thermal risk assessment indicators include hazard indicators, exposure indicators and vulnerability indicators.

[0010] In some embodiments, determining the total land use demand for a target year based on the multi-objective optimization model and in conjunction with the historical land use transition matrix includes the following steps: Four future urban development scenarios have been identified: economic development, natural development, ecological protection, and coordinated development. The objective function is to maximize the economic value, ecological value, and economic-ecological synergistic value of land, with the amount of arable land, forest coverage, water area, upper limit of construction land, and proportion of ecological land as rigid constraints. The historical land use transition matrix is ​​obtained by calculating the land use type conversion probability in the baseline period using Markov chains, and is used to determine the land use demand for four urban development scenarios.

[0011] In some embodiments, the spatial distribution pattern of future land use under four urban development scenarios is simulated based on the patch-generated land use simulation model, including the following steps: The land use simulation model for patch generation is determined to contain two core modules: a land expansion analysis strategy and a multi-type random patch seed cellular automaton. Influencing factors include slope, average annual temperature, annual precipitation, distance from roads or rivers, population, and regional GDP.

[0012] In some embodiments, based on the constructed land contribution index, the influence weight of land use type on thermal risk assessment indicators is quantified, including the following steps: The formula for calculating the land contribution index is as follows: ; in, The land contribution index. The resolution of the local climate zone grid; Let i be the area of ​​land use category i. is the weighting coefficient for land use types, and n is the total number of land use types; The weighting of land use type on thermal risk assessment indicators is quantified, and the calculation method is as follows: ; in, These are the initial thermal risk assessment indicators, namely, hazard indicators, exposure indicators, or vulnerability indicators; This serves as an indicator for assessing the thermal risks caused by land use changes under future urban development conditions.

[0013] In some embodiments, the step of constructing the thermal risk assessment model based on the standardized multi-source dataset includes the following steps: Thermal risk assessment indicators are constructed based on the standardized multi-source dataset; wherein, the thermal risk assessment indicators include hazard indicators, exposure indicators, and vulnerability indicators; The entropy weight method is used to assign weights to each of the aforementioned thermal risk assessment indicators; The corresponding thermal risk assessment index is calculated by weighted summation based on the assigned weights; The thermal risk assessment model is constructed based on the various thermal risk assessment indicators obtained by weighted summation. The heat risk index under future urban land use change scenarios is calculated based on the land use simulation model and the land contribution index.

[0014] In some embodiments, assigning weights to each of the thermal risk assessment indicators using the entropy weight method includes the following steps: The range of each of the aforementioned thermal risk assessment indicators is normalized using the entropy weight method, and the calculation is as follows: ; ; Where X is the original index matrix composed of m research units and n thermal risk assessment indicators; X represents the original value of the i-th research unit and the j-th thermal risk assessment indicator; Y is the standardized value of the original values; The definition of information entropy is as follows: ; ; in, Indicates changes in the size of the indicator; Represents information entropy; The weights and comprehensive index values ​​of each of the aforementioned thermal risk assessment indicators are calculated using the entropy weight method, as follows: ; ; in, The weights of each of the aforementioned thermal risk assessment indicators are: The comprehensive index value is the sum of the various thermal risk assessment indicators.

[0015] In some embodiments, the method further includes analyzing the thermal risk of the study city and the thermal risk under future urban land use change scenarios based on the thermal risk level distribution map, specifically including the following steps: The spatial autocorrelation method was used to analyze the spatial clustering characteristics of thermal risk in the thermal risk level distribution map, and risk clustering areas were identified. The trend of heat risk change under future urban land use change was analyzed using a future land use simulation model and a land contribution index on the heat risk level distribution map. A machine learning algorithm model based on a gradient boosting framework, combined with a game theory-based model interpretation method, is used to identify key influencing factors based on the aforementioned heat risk level distribution map. The nonlinear impact of urban morphology factors on thermal risk is analyzed based on the aforementioned key influencing factors.

[0016] To achieve the above objectives, another aspect of this application proposes an urban environmental thermal risk assessment and early warning device based on multi-source data, the device comprising: The data acquisition unit is used to acquire multi-source data of the study city in the target year. A data preprocessing unit is used to preprocess the multi-source data to obtain a standardized multi-source dataset; The mapping and modeling unit is used to generate local climate zone maps of the study city based on the standardized multi-source dataset, construct a future land use simulation model and a thermal risk assessment model; The thermal risk calculation unit is used to calculate the thermal risk index of different blocks in the local climate zone map and the thermal risk index under the future urban land use change scenario according to the thermal risk assessment model. The thermal risk assessment unit is used to divide the area of ​​the study city into corresponding thermal risk levels according to the thermal risk index, and then generate a thermal risk level distribution map. The thermal risk early warning unit is used to trigger a graded early warning mechanism based on a preset risk threshold and the thermal risk level distribution map.

[0017] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0018] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0019] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0020] The embodiments of this application include at least the following beneficial effects: This application provides a method and apparatus for urban environmental thermal risk assessment and early warning based on multi-source data. The scheme involves acquiring multi-source data of the study city in a target year; preprocessing the multi-source data to obtain a standardized multi-source dataset; generating a local climate zone map of the study city based on the standardized multi-source dataset; constructing a future land use simulation model and a thermal risk assessment model; calculating the thermal risk index of different blocks in the local climate zone map and the thermal risk index under future urban land use change scenarios based on the thermal risk assessment model; dividing the study city into corresponding thermal risk levels based on the thermal risk index, thereby generating a thermal risk level distribution map; and triggering a graded early warning mechanism based on a preset risk threshold and the thermal risk level distribution map. This application rapidly and completely identifies the spatial distribution of urban environmental thermal risks and provides thermal risk early warning through multi-source data, which can assist in urban spatial planning and the formulation of thermal mitigation strategies. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating the urban environmental thermal risk assessment and early warning method based on multi-source data provided in this application embodiment; Figure 2 Example flowchart of the urban environmental thermal risk assessment method based on multi-source data provided in the embodiments of this application; Figure 3 Example diagram of urban local climate zone type results based on Geographic Information System (GIS) method provided for embodiments of this application; Figure 4 Example diagrams showing the spatial distribution of hazard, vulnerability, and exposure under different local climate zone types, as well as the proportions of hazard, vulnerability, and exposure, provided for embodiments of this application; Figure 5 An example diagram illustrating the distribution of thermal risk levels for each local climate zone provided in this application embodiment; Figure 6 Example diagrams illustrating land use type changes under different urban development scenarios provided in the embodiments of this application; Figure 7 Example graphs illustrating the changes in the Heat Risk Index (HRI) under different target years and urban development scenarios provided in this application embodiment; Figure 8 A schematic diagram of the structure of the urban environmental thermal risk assessment and early warning device based on multi-source data provided in this application embodiment; Figure 9 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0024] 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 is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0025] Before providing a detailed description of the embodiments of this application, some related technologies involved in the embodiments of this application will be described first, as follows: The formation of urban environmental thermal risks is closely related to multiple specific factors: on the one hand, there are climate and environmental factors, including regional temperature rise, the heat storage effect of urban underlying surfaces (such as impermeable paving materials like concrete and asphalt), and the lack of cooling spaces such as green spaces or water bodies; on the other hand, there are social and spatial factors, such as population density and aging (high-density areas have more people exposed to heat), urban spatial morphology (such as the "canyon effect" of high-rise buildings that easily traps heat), and socioeconomic level (low-income areas may lack cooling facilities), etc. In addition, traditional thermal environment assessment methods mostly rely on remote sensing surface temperature (LST) or meteorological station data, focusing only on a single thermal environment indicator and ignoring the comprehensive driving effect of multiple factors such as urban spatial morphology, population distribution, and socioeconomic status on thermal risks. This makes it difficult to accurately identify spatial differences and key causes of thermal risks, and fails to meet the actual needs of refined urban planning and the formulation of thermal mitigation strategies.

[0026] Among existing patents related to urban thermal environment, for example, patent application CN202111286897 discloses "A precise and economical method for mobile measurement of street thermal environment," which mainly focuses on mobile measurement and path optimization. It calculates a general thermal climate index by selecting representative measurement points, combining sky-view factor classification, and using a multi-objective optimization algorithm to select an optimized path for mobile observation of the urban thermal environment. However, it lacks a comprehensive assessment and early warning mechanism for urban thermal risks, especially failing to integrate multi-source data (such as remote sensing images, urban morphology data, etc.) for comprehensive analysis, and also failing to provide spatial distribution of thermal risks and identification of key influencing factors; patent application C... N202210963085 discloses "A Method and System for Downscaling Spatiotemporal Analysis and Prediction of Urban Thermal Environment," which mainly focuses on downscaling spatiotemporal analysis and prediction of urban thermal environment. By acquiring image datasets of the target space and combining them with surface temperature and influencing factor data, a relevant prediction model is constructed to achieve high-precision prediction of surface temperature. However, it lacks a comprehensive assessment and spatial distribution identification of urban thermal risk. Although it can predict surface temperature, it fails to further analyze the spatial distribution of thermal risk and key influencing factors, does not reveal the impact of land use change on thermal risk during future urban development, and does not provide an early warning mechanism, thus lacking direct support for urban thermal risk management.

[0027] Therefore, how to quickly and comprehensively identify the spatial distribution and dominant morphological factors of urban environmental thermal risk based on multi-source data and assess the thermal risk to assist in urban spatial planning and the formulation of thermal mitigation strategies is the first technical problem that needs to be solved in thermal risk governance. This is of great significance for basic research and accurate assessment of urban environmental thermal risk, and has important scientific and applied value for building healthy cities in the context of dual carbon emissions. This application constructs a complete urban thermal risk assessment framework, from multi-source data processing and local climate zoning mapping to multi-dimensional thermal risk index assessment, and then to the identification of spatial clustering patterns of thermal risk and the analysis of key influencing factors. With the help of this framework, it is possible to quickly and comprehensively identify the spatial distribution and key influencing factors of urban environmental thermal risk based on multi-source data and assess the thermal risk, thereby assisting in urban spatial planning and the formulation of thermal mitigation strategies. At the same time, it provides a supporting early warning device that can couple multi-source data with weather forecasts to achieve early prediction of urban thermal risk and push graded early warning information to high-risk areas, thereby improving public environmental safety and the level of urban environmental resilience governance.

[0028] This application provides a method and apparatus for urban environmental thermal risk assessment and early warning based on multi-source data, relating to the field of data processing technology. The method and apparatus provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle-mounted terminal, but is not limited thereto; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application implementing the urban environmental thermal risk assessment and early warning method based on multi-source data, but is not limited to the above forms.

[0029] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0030] Reference Figure 1 This application provides a method for urban environmental thermal risk assessment and early warning based on multi-source data. This method may include, but is not limited to, steps S100 to S150, as follows: S100: Obtain multi-source data for the study city in the target year; S110: Preprocess the multi-source data to obtain a standardized multi-source dataset; S120: Generate a local climate zone map of the study city based on the standardized multi-source dataset, and construct a future land use simulation model and a thermal risk assessment model; S130: Calculate the thermal risk index of different blocks in the local climate zone map and the thermal risk index under the future urban land use change scenario based on the thermal risk assessment model; S140: Based on the heat risk index, the area of ​​the study city is divided into corresponding heat risk levels, and then a heat risk level distribution map is generated; S150: Trigger a graded early warning mechanism based on the preset risk threshold and the thermal risk level distribution map.

[0031] Optionally, obtaining multi-source data for the study city in the target year includes the following steps: The remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information of the study city in the target year are obtained as the multi-source data.

[0032] Optionally, the preprocessing of the multi-source data to obtain a standardized multi-source dataset includes the following steps: Missing and outlier values ​​are detected and removed from the multi-source data, and spatial registration and resampling to a unified coordinate system and the same resolution are completed. Then, normalization and cleaning are performed to obtain the standardized multi-source dataset.

[0033] Optionally, the step of generating the local climate zone map based on the standardized multi-source dataset includes the following steps: Extract urban morphology data from the standardized multi-source dataset; Determine the resolution of the local climate zone grid for the studied city; The spatial morphology of the local climate zone grid is evaluated based on the urban morphology data. The local climate zone grid is divided into local climate zone types that include the spatial morphology and climate characteristics using fuzzy classification and majority voting methods, thus obtaining the local climate zone map.

[0034] Optionally, the step of constructing the future land use simulation model based on the standardized multi-source dataset includes the following steps: A multi-objective optimization model was adopted, combined with the historical land use transfer matrix, to determine the total land use demand for the target year; A patch-based land use simulation model was used to simulate the spatial distribution pattern of future land use under four urban development scenarios. A land contribution index is constructed to quantify the influence weight of land use type on thermal risk assessment indicators; wherein, the thermal risk assessment indicators include hazard indicators, exposure indicators and vulnerability indicators.

[0035] Optionally, the step of using a multi-objective optimization model, combined with a historical land use transition matrix, to determine the total land use demand for the target year includes the following steps: Four future urban development scenarios have been identified: economic development, natural development, ecological protection, and coordinated development. The objective function is to maximize the economic value, ecological value, and economic-ecological synergistic value of land, with the amount of arable land, forest coverage, water area, upper limit of construction land, and proportion of ecological land as rigid constraints. The historical land use transition matrix is ​​obtained by calculating the land use type conversion probability in the baseline period using Markov chains, and is used to determine the land use demand for four urban development scenarios.

[0036] Optionally, the step of using a patch-based land use simulation model to simulate the spatial distribution pattern of future land use under four urban development scenarios includes the following steps: The land use simulation model for patch generation is determined to contain two core modules: a land expansion analysis strategy and a multi-type random patch seed cellular automaton. Influencing factors include slope, average annual temperature, annual precipitation, distance from roads or rivers, population, and regional GDP.

[0037] Optionally, the construction of the land contribution index, which quantifies the influence weight of land use type on thermal risk assessment indicators, includes the following steps: The formula for calculating the land contribution index is as follows: ; in, The land contribution index. The resolution of the local climate zone grid; Let i be the area of ​​land use category i. is the weighting coefficient for land use types, and n is the total number of land use types; The weighting of land use type on thermal risk assessment indicators is quantified, and the calculation method is as follows: ; in, These are the initial thermal risk assessment indicators, namely, hazard indicators, exposure indicators, or vulnerability indicators; This serves as an indicator for assessing the thermal risks caused by land use changes under future urban development conditions.

[0038] Optionally, the step of constructing the thermal risk assessment model based on the standardized multi-source dataset includes the following steps: Thermal risk assessment indicators are constructed based on the standardized multi-source dataset; wherein, the thermal risk assessment indicators include hazard indicators, exposure indicators, and vulnerability indicators; The entropy weight method is used to assign weights to each of the aforementioned thermal risk assessment indicators; The corresponding thermal risk assessment index is calculated by weighted summation based on the assigned weights; The thermal risk assessment model is constructed based on the various thermal risk assessment indicators obtained by weighted summation. The heat risk index under future urban land use change scenarios is calculated based on the land use simulation model and the land contribution index.

[0039] Optionally, assigning weights to each of the thermal risk assessment indicators using the entropy weight method includes the following steps: The range of each of the aforementioned thermal risk assessment indicators is normalized using the entropy weight method, and the calculation is as follows: ; ; Where X is the original index matrix composed of m research units and n thermal risk assessment indicators; X represents the original value of the i-th research unit and the j-th thermal risk assessment indicator; Y is the standardized value of the original values; The definition of information entropy is as follows: ; ; in, Indicates changes in the size of the indicator; Represents information entropy; The weights and comprehensive index values ​​of each of the aforementioned thermal risk assessment indicators are calculated using the entropy weight method, as follows: ; ; in, The weights of each of the aforementioned thermal risk assessment indicators are: The comprehensive index value is the sum of the various thermal risk assessment indicators.

[0040] Optionally, the method further includes analyzing the thermal risk of the studied city and the thermal risk under future urban land use change scenarios based on the thermal risk level distribution map, specifically including the following steps: The spatial autocorrelation method was used to analyze the spatial clustering characteristics of thermal risk in the thermal risk level distribution map, and risk clustering areas were identified. The trend of heat risk change under future urban land use change was analyzed using a future land use simulation model and a land contribution index on the heat risk level distribution map. A machine learning algorithm model based on a gradient boosting framework, combined with a game theory-based model interpretation method, is used to identify key influencing factors based on the aforementioned heat risk level distribution map. The nonlinear impact of urban morphology factors on thermal risk is analyzed based on the aforementioned key influencing factors.

[0041] The following sections will provide a detailed description and explanation of some optional embodiments of this application, using specific application examples.

[0042] This embodiment discloses a method and early warning system for urban environmental thermal risk assessment based on multi-source data. The method includes: acquiring multi-source data of the study city in a target year, including remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information; detecting and removing missing and outlier values ​​from the multi-source data, completing spatial registration, resampling to a unified coordinate system and the same resolution, and performing normalization and cleaning to obtain a standardized multi-source dataset; generating a Local Climate Zone (LCZ) map based on the standardized multi-source dataset, constructing a thermal risk assessment model, including three thermal risk assessment indicators: hazard, exposure, and vulnerability; using the entropy weight method to normalize the range and calculate the weights of each indicator, and fusing them to generate a thermal risk index. The heat risk index (HRI) is used to calculate the risk value of different blocks in the city. Based on the heat risk index, the natural breakpoint method is used to divide the urban area into multiple risk levels, generate a heat risk level distribution map, and use the spatial autocorrelation method to analyze the spatial clustering characteristics of heat risk, identify high-risk clustering areas, and use the gradient boosting framework-based machine learning algorithm (XGBoost) model to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on heat risk.

[0043] The early warning system in this embodiment includes: a data acquisition module, a data processing module, a model building module, a spatial distribution module, and a risk early warning module. This embodiment can rapidly and comprehensively identify the spatial distribution and key influencing factors of urban environmental thermal risks based on multi-source data and assess these risks, assisting in urban spatial planning and the formulation of heat mitigation strategies. It also provides a supporting early warning device that can couple multi-source data with weather forecasts to achieve early prediction of urban thermal risks and push tiered early warning information to high-risk areas, thereby improving public environmental safety and the level of urban environmental resilience governance.

[0044] This embodiment provides a method for urban environmental thermal risk assessment based on multi-source data, including the following steps: Acquire multi-source data for the study city in the target year. The multi-source data includes remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information. Missing and outlier values ​​are detected and removed from multi-source data. Spatial registration and resampling to a unified coordinate system and the same resolution are completed, and normalization and cleaning are performed to obtain a standardized multi-source dataset. Based on standardized multi-source datasets, local climate zone maps are generated, and a thermal risk assessment model is constructed, which includes three thermal risk assessment indicators: hazard, exposure, and vulnerability. The entropy weight method is used to normalize the range and calculate the weight of each indicator, and the thermal risk index is generated by fusion. The risk value of different blocks in the city is calculated. Based on the thermal risk index, the urban area is divided into multiple risk levels using the natural breakpoint method, generating a thermal risk level distribution map. The spatial autocorrelation method is used to analyze the spatial clustering characteristics of thermal risk and identify high-risk clustering areas. Furthermore, the XGBoost model, a machine learning algorithm based on the gradient boosting framework, combined with the Shapley Additive Explanations (SHAP) method based on game theory, can be used to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk.

[0045] Furthermore, multi-source data for the study city in the target year was obtained. This multi-source data included remote sensing imagery, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information. Specifically: Surface infrared image data is used to retrieve summer surface temperature; Artificial heat flux raster data at a certain resolution; Building vector data, including building base outline and building height; Population density data and population density data for those aged 65 and over, estimated by grid population at a certain resolution; Nighttime light and shadow effects are used to represent the economic level of a neighborhood; Land cover data at a certain resolution is used to identify green spaces, water bodies, and impermeable surfaces.

[0046] Furthermore, the multi-source data undergoes data processing, including detecting and removing missing, outlier, or isolated values; spatial registration; resampling to a unified coordinate system and the same resolution; and normalization and cleaning to obtain a standardized multi-source dataset. This process specifically includes the following steps: Data extraction and standardization, along with outlier handling, were performed. First, the acquired raw multi-source data was extracted to identify valid data relevant to urban environmental thermal risk assessment. Next, outlier identification was conducted. Based on the data distribution characteristics, a 95% confidence interval was set, and data exceeding this interval were identified as outliers and recorded. Then, standardization methods were used to uniformly preprocess the raw multi-source data. By scaling the data proportionally, it was made to fall within a specific numerical range, thus eliminating differences between different units of measurement. After standardization, the previously recorded outliers were further processed. Depending on the importance and practical significance of the data, they were either removed or filled using appropriate interpolation methods to effectively improve the accuracy and consistency of subsequent analyses. Perform data quality inspection and cleaning, check the consistency of standardized data, identify and remove outliers and invalid data, and correct errors. For missing data, use appropriate strategies to impute it, and implement tiered management based on data quality levels to ensure the integrity and reliability of the final dataset. Data loading and centralized management are performed, and the cleaned and processed data is imported into the target data warehouse in batches. Then, large-scale data is efficiently loaded and centrally stored to provide a high-quality, structured data foundation for the subsequent construction of thermal risk assessment models.

[0047] Furthermore, unified preprocessing is performed on the original multi-source data, specifically including: ① After atmospheric correction and strip restoration, the surface infrared image data is inverted using the radiative transfer equation to obtain the surface temperature (LST) at a certain resolution. ② The building vectors need to undergo topology checks, height assignments, and uniform projection; ③ The population density grid needs to be resampled to the same resolution; ④ Vegetation, water bodies, and nighttime lights are resampled and masked using the same grid system to ensure that all layers have the same number of rows and columns.

[0048] Furthermore, based on standardized multi-source datasets, local climate zone maps are generated, and a thermal risk assessment model is constructed, including three thermal risk assessment indicators: hazard, exposure, and vulnerability. The entropy weight method is used to normalize the range and calculate the weights of each indicator, and the results are fused to generate a thermal risk index. The risk values ​​for different urban blocks are then calculated, specifically including: A thermal risk assessment model was constructed, including indicators of hazard, exposure, and vulnerability, and risk indicators for different regional units in the city were calculated respectively. Hazard indicators include: land surface temperature (LST) and anthropogenic heat emissions (AHF); Vulnerability indicators include: elderly population density (OPD) and nighttime light intensity (NTL); Exposure indicators include: population density (PD), normalized difference vegetation index (NDVI), and enhanced water body index (EWI).

[0049] Furthermore, the multi-source data required to generate local climate zone maps includes: urban morphology data such as building height, building density, sky visibility factor (SVF), ground roughness (HRE), and permeable / impermeable surface ratio (PSF / ISF).

[0050] Furthermore, the local climate zone types are divided into 17 categories, covering morphological characteristics and microclimate variations, including 10 built-up areas (LCZ 1 to LCZ 10) and 7 land cover areas (LCZ A to LCZ G).

[0051] Furthermore, the key steps in mapping local climate zones specifically include: (1) Determine the grid resolution for local climate zones; (2) Assess urban spatial morphology; (3) Use fuzzy classification and majority voting methods to divide the urban area and obtain a local climate zone map.

[0052] Furthermore, the formula for calculating the Heat Risk Index (HRI) is as follows: ; Furthermore, the formula for range normalization and weight calculation of each indicator using the entropy weight method is as follows: ; ; Where X is the original index matrix consisting of m research units and n indicators; X represents the original value of the i-th research unit and the j-th indicator; and Y is the standardized value; The definition of information entropy is as follows: ; ; Where P represents the change in the size of the indicator; E represents the information entropy; The formulas for calculating the weights and the comprehensive index values ​​for each layer are as follows: ; ; Where W represents the indicator weight and S represents the comprehensive indicator value.

[0053] Furthermore, when using the entropy weight method to calculate weights, indicators with information redundancy ≥ 0.9 are forcibly reduced in weight by 20% to avoid overfitting.

[0054] Furthermore, the hazard value includes land surface temperature (LST) and anthropogenic heat emissions (AHF) indicators, which are standardized to a range of 0.1 to 0.9. The standardized indicators are multiplied by their corresponding weights to obtain the thermal hazard value. The calculation formula is as follows: .

[0055] Furthermore, the vulnerability value includes Older Population Density (OPD) and Nighttime Light Intensity (NTL) indicators, which are standardized to a range of 0.1 to 0.9. The vulnerability value is obtained by multiplying the standardized indicators by their corresponding weights. The calculation formula is as follows: .

[0056] Furthermore, the exposure value includes population density (PD), normalized difference vegetation index (NDVI), and enhanced water quality index (EWI). These three indicators are standardized to a range of 0.1 to 0.9. The exposure value is obtained by multiplying the standardized indicators by their corresponding weights. The calculation formula is as follows: ; The formulas for calculating the Normalized Difference Vegetation Index (NDVI) and the Enhanced Water Index (EWI) are as follows: ; ; Wherein, NIR is the near-infrared band; R is the red band; Green is the green band; and SWIR1 is the short-wave infrared band.

[0057] Furthermore, based on the thermal risk index, the urban area is divided into multiple risk levels using the natural discontinuity method, generating a thermal risk level distribution map. Spatial autocorrelation methods are then used to analyze the spatial clustering characteristics of thermal risk, identifying high-risk clusters. Additionally, the XGBoost model combined with the SHAP interpretation method can be used to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk, specifically including: Based on the heat risk index, the level of urban heat risk is divided into different levels, including but not limited to extremely low risk, low risk, medium risk, high risk, and extremely high risk. Based on spatial autocorrelation analysis, the local Moran index is used to quantify and identify the spatial distribution and clustering patterns of thermal risk, such as high-high clustering areas and low-low clustering areas. Based on the XGBoost model, with urban morphology indicators as input variables and thermal risk index as output variables, the SHAP method is used to explain the contribution and threshold effect of each variable.

[0058] Furthermore, XGBoost model training can analyze the nonlinear impact of urban morphology factors on thermal risk, using urban morphology indicators as input variables, such as building surface ratio, sky visibility factor, and permeable surface ratio, and the thermal risk index as the output variable. The model training process specifically includes: (1) The learning rate is set to 0.1 to balance training speed and convergence accuracy; (2) The maximum tree depth is 3 to prevent overfitting and ensure that the model effectively learns the data features; (3) The data is divided into training set and test set in a 7:3 ratio to ensure that the model is trained sufficiently and performs reliably.

[0059] Furthermore, by using the SHAP method to explain the contribution and threshold effect of each variable, the contribution and threshold effect of each urban morphology indicator on thermal risk can be clarified. When the permeable surface ratio exceeds 0.6, it has a significant effect on reducing thermal risk; when the sky visibility factor exceeds 0.75, the thermal risk shows a more obvious decreasing trend.

[0060] This embodiment also provides an early warning system for urban environmental thermal risk assessment based on multi-source data, including: The system comprises five modules: data acquisition, data processing, model building, spatial distribution, and risk early warning. Data is first transferred from the data acquisition module to the data processing module, where it acquires multi-source data for the target year. The data processing module then performs processing such as detection, filtering, and spatial registration to obtain a standardized multi-source dataset. Next, the data flows from the data processing module to the model building module, which generates local climate zone maps and constructs a thermal risk assessment model to calculate risk values. Following this, the data flows from the model building module to the spatial distribution module, which classifies risk levels, analyzes clustering characteristics, and identifies key influencing factors. Finally, the spatial distribution module connects to the risk early warning module, which receives information to trigger an early warning mechanism, pushes early warning information, and performs risk prediction, establishing an early warning response feedback channel. Specifically, this includes: The data acquisition module is used to acquire multi-source data of the study city in the target year. The multi-source data includes remote sensing image data, vegetation cover, water cover, land cover information, and statistical yearbook information. The data processing module is used to detect and remove missing and outlier values ​​from multi-source data, complete spatial registration, resample to a unified coordinate system and the same resolution, and perform normalization and cleaning to obtain a standardized multi-source dataset. The model building module is used to generate local climate zone maps based on standardized multi-source datasets, build a thermal risk assessment model, which includes three thermal risk assessment indicators: hazard, exposure, and vulnerability. The entropy weight method is used to normalize the range and calculate the weight of each indicator, and the models are integrated to generate a thermal risk index to calculate the risk value of different blocks in the city. The spatial distribution module is used to divide urban areas into multiple risk levels based on the thermal risk index using the natural breakpoint method, generate a thermal risk level distribution map, and analyze the spatial clustering characteristics of thermal risk using the spatial autocorrelation method to identify high-risk clustering areas. It can also use the XGBoost model combined with the SHAP interpretation method to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk.

[0061] The risk warning module receives thermal risk level distribution maps and information on high-risk clusters generated by the spatial distribution module. It automatically sets risk thresholds and triggers a tiered warning mechanism. By coupling urban population density grid data with building function type data, it accurately identifies exposed populations and sensitive locations (such as schools, hospitals, and elderly care facilities) within high-risk areas. Based on risk levels, it dynamically and automatically generates differentiated warning information, including risk levels, health advice, protective measures, and refuge location guidance, which is pushed to multiple channels such as SMS platforms, mobile applications, smart terminals, and public displays. Combining 24-hour weather forecast data with XGBoost prediction models, it extrapolates the spatiotemporal evolution trend of thermal risk, achieving forward-looking risk prediction, establishing a warning response feedback channel, and linking urban emergency management departments with grassroots community grids to improve public environmental safety and urban environmental resilience governance.

[0062] The optional embodiments of this application are as follows: It should be noted that, depending on the actual application requirements, the original multi-source data (such as remote sensing imagery, building vectors, population grids, etc.) can be replaced with other open / commercial data sources of equal or higher resolution, and the same applies to the method of this application. This embodiment takes a city as the study area and uses multi-source data such as Landsat-8 surface thermal infrared imagery, Google Earth building vector data, and WorldPop population data as examples to conduct urban environmental thermal risk assessment research based on a thermal risk assessment model that includes three thermal risk assessment indicators: hazard, exposure, and vulnerability.

[0063] First embodiment: Figure 2 An example flowchart of the urban environmental thermal risk assessment method based on multi-source data provided in the first embodiment of this application.

[0064] A method for urban environmental thermal risk assessment based on multi-source data includes the following steps: Acquire multi-source data for the study city in the target year. The multi-source data includes remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information.

[0065] In this embodiment, the thermal risk assessment method, based on a preset surface temperature inversion unit, local climate zone mapping unit, risk index calculation unit, spatial autocorrelation unit, and XGBoost-SHAP interpretation unit, can quickly, accurately, and interpretably output the spatial distribution of thermal risk levels in different urban areas, providing a scientific basis for decision-making by urban renewal, planning control, and emergency management departments.

[0066] The specific research data included in this embodiment are as follows: Surface infrared image data is used to retrieve summer surface temperature; Artificial heat flux raster data at a certain resolution; Building vector data, including building base outline and building height; Population density data and population density data for those aged 65 and over, estimated by grid population at a certain resolution; Nighttime light and shadow effects are used to represent the economic level of a neighborhood; Land cover data at a certain resolution is used to identify green spaces, water bodies, and impermeable surfaces.

[0067] The missing and outlier values ​​of the multi-source data are detected and removed. Spatial registration and resampling to a unified coordinate system and the same resolution are completed, and normalization and cleaning are performed to obtain a standardized multi-source dataset.

[0068] In this embodiment, to ensure the accuracy of subsequent risk indicators, the original multi-source data needs to be preprocessed uniformly: ① After atmospheric correction and strip restoration, the surface infrared image data is inverted using the radiative transfer equation to obtain the surface temperature (LST) at a certain resolution. ② The building vectors need to undergo topology checks, height assignments, and uniform projection; ③ The population density grid needs to be resampled to the same resolution; ④ Vegetation, water bodies, and nighttime lights are resampled and masked using the same grid system to ensure that all layers have the same number of rows and columns.

[0069] Based on standardized multi-source datasets, local climate zone maps are generated, and a thermal risk assessment model is constructed, which includes three thermal risk assessment indicators: hazard, exposure, and vulnerability. The entropy weight method is used to normalize the range and calculate the weights of each indicator, and the thermal risk index is generated by fusion. The risk values ​​of different blocks in the city are then calculated.

[0070] In this embodiment, based on preprocessed building vectors, vegetation, water bodies, and land cover data, a local climate zone map of a certain size is generated using fuzzy classification and majority voting methods. The morphological indices of each grid are calculated: Sky Visibility Factor (SVF), Building Surface Fraction (BSF), Roughness Element Height (HRE), Permeable Surface Fraction (PSF), Impermeable Surface Fraction (ISF), and Terrain Roughness (TRC). Subsequently, the local climate zone type is spatially correlated with the morphological indices to obtain a local climate zone classification map of the city.

[0071] In this embodiment, it should be noted that the overall accuracy of the local climate zone division based on the Geographic Information System (GIS) method in this study is 85.5%, which meets the high accuracy requirements for assessing thermal risk.

[0072] Figure 3 This is the result of the urban block type based on the Geographic Information System (GIS) method in the first embodiment of this application. For example... Figure 3 As shown, land cover areas account for 84.4% of all local climate zones. LCZ AB and LCZ CD are the most common land cover types, accounting for 66.6% and 20.5% respectively, mainly concentrated in the northern hilly areas. Built-up areas account for 15.6% of all local climate zones. LCZ 5 and LCZ 2 are the main types, accounting for 24.7% and 20.8% respectively, concentrated in the city center area. The remaining local climate zone types and their proportions are, in descending order: LCZ 10, LCZ 9, LCZ 4, LCZ 6, LCZ 8, LCZ 1, and LCZ 3.

[0073] In this embodiment, a thermal risk assessment model is constructed based on hazard, exposure, and vulnerability indicators, namely: land surface temperature (LST) and anthropogenic heat emissions (AHF), old-age population density (OPD) and nighttime light intensity (NTL), population density (PD), normalized difference vegetation index (NDVI), and enhanced water quality index (EWI). The entropy weight method is used to determine the weight of each indicator, and after normalization, the indicators are multiplied to obtain the urban area thermal risk index HRI. The natural breakpoint method is then used to divide the thermal risk index into seven levels: extremely low, low, relatively low, medium, relatively high, high, and extremely high.

[0074] Figure 4 This illustrates the spatial distribution of hazard, vulnerability, and exposure under different local climate zone types in the first embodiment of this application, as well as the ratio of hazard, vulnerability, and exposure. Figure 4As shown, the hazard values ​​range from 0.13 to 0.79. High-risk areas (i.e., high and relatively high levels) are mainly concentrated in the west, while they are more scattered in the east. These high-risk areas have impermeable and exposed surfaces that receive a large amount of solar radiation, leading to a rapid increase in surface temperature. Vulnerability values ​​range from 0.10 to 0.90. A high-risk area appears around a certain region. This region has a dense elderly population and is vulnerable to the adverse effects of high temperatures. In addition, the exposure value ranges from 0.10 to 0.75. This region also has a high risk because it also consists of many built-up areas and a lack of tree-lined green spaces. Similarly, a riverside area also shows a similar risk. The remaining areas show a mixture of low and relatively low risk.

[0075] Based on the thermal risk index, the urban area is divided into multiple risk levels using the natural discontinuity method, generating a thermal risk level distribution map. The spatial autocorrelation method is used to analyze the spatial clustering characteristics of thermal risk, identify high-risk clustering areas, and the XGBoost model combined with the SHAP interpretation method can be used to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk.

[0076] Figure 5 This shows the distribution of heat risk levels for each local climate zone in the first embodiment of this application. For example... Figure 5 As shown, the heat risk level in urban centers is higher than in suburbs. Extremely high-risk and extremely low-risk areas are mainly distributed in the central and northern parts of the city, with the extremely high-risk areas concentrated in the city center. This can be attributed to the high population density and large elderly population in this area. Furthermore, the high-temperature risk in built-up areas is higher than other land cover types. For example, LCZ 4 has the highest risk type, with extremely high-risk and high-risk areas accounting for 15.48% and 21.07% respectively. Conversely, low-risk areas are most prevalent in LCZ A and B, at 93.81% and 57.98% respectively, followed by LCZ F. LCZ 4 has the widest risk distribution, with an average high-temperature risk value of 0.21, followed by LCZ 1 and LCZ 8. Overall, LCZs 1 to 4, with their higher building and population densities, are more susceptible to high-temperature risks.

[0077] In this embodiment, based on the spatial autocorrelation analysis method, the local Moran index method is used to identify high-high and low-low clustering areas of thermal risk and their spatial distribution patterns.

[0078] In this embodiment, based on the XGBoost model, with urban morphology indicators as input variables and thermal risk index as output variables, the SHAP method is used to explain the contribution and threshold effect of each variable.

[0079] It is important to note that urban morphology influences regional temperature, population, and economy. Studying the impact of urban morphology indicators on thermal risk can provide valuable insights for future urban planning and development. The XGBoost-SHAP model helps in understanding the influence of urban morphology on thermal risk.

[0080] In this embodiment, among urban morphology indicators, vegetation surface fraction (PSF) is the primary factor influencing thermal risk, followed by high-density area ratio (HRE), building surface fraction (BSF), sky visibility factor (SVF), impervious surface fraction (ISF), and ground roughness (TRC). It is speculated that the presence of 84.4% of the study area with low thermal risk land cover increases the impact of PSF on model training. The effects of HRE and BSF are almost identical, and they correlate more strongly with land surface temperature (LST). This result can be attributed to the fact that taller buildings and denser layouts block solar radiation, reducing heat absorption by the land surface.

[0081] For example, Figure 6 Example diagrams illustrating changes in land use types under different urban development scenarios; Figure 7 Example graph showing the changes in the Heat Risk Index (HRI) under different target years and urban development scenarios.

[0082] This application provides a method for urban environmental thermal risk assessment based on multi-source data, comprising: acquiring multi-source data of the study city in a target year, including remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information; detecting and removing missing and outlier values ​​from the multi-source data, completing spatial registration, resampling to a unified coordinate system and the same resolution, and performing normalization and cleaning to obtain a standardized multi-source dataset; generating a local climate zone map based on the standardized multi-source dataset, constructing a thermal risk assessment model, including three thermal risk assessment indicators: hazard, exposure, and vulnerability; using the entropy weight method to normalize the range and calculate the weights of each indicator, fusing them to generate a thermal risk index, and calculating the risk value of different blocks in the city; based on the thermal risk index, dividing the urban area into multiple risk levels using the natural breakpoint method, generating a thermal risk level distribution map, and using the spatial autocorrelation method to analyze the spatial clustering characteristics of thermal risk, identifying high-risk clustering areas, and using the XGBoost model combined with the SHAP interpretation method to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk. This application's early warning device includes: a data acquisition unit, a data processing unit, a model building unit, a spatial distribution unit, and a risk early warning unit. This application enables rapid and comprehensive identification of the spatial distribution and key influencing factors of urban environmental thermal risks based on multi-source data, and facilitates the assessment of thermal risks, thus aiding in urban spatial planning and the formulation of thermal mitigation strategies.

[0083] Second embodiment of this application: The second embodiment of this application provides an urban environmental thermal risk assessment and early warning system based on multi-source data, including: The data acquisition module is used to acquire multi-source data of the study city in the target year. The multi-source data includes remote sensing image data, vegetation cover, water cover, land cover information, and statistical yearbook information.

[0084] In this embodiment, the thermal risk assessment method, based on a preset surface temperature inversion module, local climate zone mapping module, risk index calculation module, spatial autocorrelation module, and XGBoost-SHAP interpretation module, can quickly, accurately, and interpretably output the spatial distribution of thermal risk levels in different urban areas, providing a scientific basis for decision-making by urban renewal, planning control, and emergency management departments.

[0085] The specific research data included in this embodiment are as follows: Surface infrared image data is used to retrieve summer surface temperature; Artificial heat flux raster data at a certain resolution; Building vector data, including building base outline and building height; Population density data and population density data for those aged 65 and over, estimated by grid population at a certain resolution; Nighttime light and shadow effects are used to represent the economic level of a neighborhood; Land cover data at a certain resolution is used to identify green spaces, water bodies, and impermeable surfaces.

[0086] The data processing module is used to detect and remove missing and outlier values ​​from multi-source data, complete spatial registration, resample to a unified coordinate system and the same resolution, and perform normalization and cleaning to obtain a standardized multi-source dataset.

[0087] In this embodiment, to ensure the accuracy of subsequent risk indicators, the original multi-source data needs to be preprocessed uniformly: ① After atmospheric correction and strip restoration, the surface infrared image data is inverted using the radiative transfer equation to obtain the surface temperature (LST) at a certain resolution. ② The building vectors need to undergo topology checks, height assignments, and uniform projection; ③ The population density grid needs to be resampled to the same resolution; ④ Vegetation, water bodies, and nighttime lights are resampled and masked using the same grid system to ensure that all layers have the same number of rows and columns.

[0088] The model building module is used to generate local climate zone maps based on standardized multi-source datasets, construct a thermal risk assessment model, which includes three thermal risk assessment indicators: hazard, exposure, and vulnerability. The entropy weight method is used to normalize the range and calculate the weight of each indicator, and the models are integrated to generate a thermal risk index to calculate the risk value of different blocks in the city.

[0089] In this embodiment, based on preprocessed building vectors, vegetation, water bodies, and land cover data, a local climate zone map of a certain size is generated using fuzzy classification and majority voting methods. The morphological indices of each grid are calculated: Sky Visibility Factor (SVF), Building Surface Fraction (BSF), Roughness Element Height (HRE), Permeable Surface Fraction (PSF), Impermeable Surface Fraction (ISF), and Terrain Roughness (TRC). Subsequently, the local climate zone type is spatially correlated with the morphological indices to obtain a local climate zone classification map of the city.

[0090] In this embodiment, a thermal risk assessment model is constructed based on hazard, exposure, and vulnerability indicators, namely: land surface temperature (LST) and anthropogenic heat emissions (AHF), old-age population density (OPD) and nighttime light intensity (NTL), population density (PD), normalized difference vegetation index (NDVI), and enhanced water quality index (EWI). The entropy weight method is used to determine the weight of each indicator, and after normalization, the indicators are multiplied to obtain the urban area thermal risk index HRI. The natural breakpoint method is then used to divide the thermal risk index into seven levels: extremely low, low, relatively low, medium, relatively high, high, and extremely high.

[0091] The spatial distribution module is used to divide urban areas into multiple risk levels based on the thermal risk index using the natural breakpoint method, generating a thermal risk level distribution map; it also uses the spatial autocorrelation method to analyze the spatial clustering characteristics of thermal risk, identify high-risk clustering areas, and can use the XGBoost model combined with the SHAP interpretation method to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk.

[0092] In this embodiment, based on the spatial autocorrelation analysis method, the local Moran index method is used to identify high-high and low-low clustering areas of thermal risk and their spatial distribution patterns.

[0093] In this embodiment, based on the XGBoost model, with urban morphology indicators as input variables and thermal risk index as output variables, the SHAP method is used to explain the contribution and threshold effect of each variable.

[0094] It is important to note that urban morphology influences regional temperature, population, and economy. Studying the impact of urban morphology indicators on thermal risk can provide valuable insights for future urban planning and development. The XGBoost-SHAP model helps in understanding the influence of urban morphology on thermal risk.

[0095] In this embodiment, among urban morphology indicators, vegetation surface fraction (PSF) is the primary factor influencing thermal risk, followed by high-density area ratio (HRE), building surface fraction (BSF), sky visibility factor (SVF), impervious surface fraction (ISF), and ground roughness (TRC). It is speculated that the presence of 84.4% of the study area with low thermal risk land cover increases the impact of PSF on model training. The effects of HRE and BSF are almost identical, and they correlate more strongly with land surface temperature (LST). This result can be attributed to the fact that taller buildings and denser layouts block solar radiation, reducing heat absorption by the land surface.

[0096] The risk warning module receives thermal risk level distribution maps and information on high-risk clusters generated by the spatial distribution module. It automatically sets risk thresholds and triggers a tiered warning mechanism. By coupling urban population density grid data with building function type data, it accurately identifies exposed populations and sensitive locations (such as schools, hospitals, and elderly care facilities) within high-risk areas. Based on risk levels, it dynamically and automatically generates differentiated warning information, including risk levels, health advice, protective measures, and refuge location guidance, which is pushed to multiple channels such as SMS platforms, mobile applications, smart terminals, and public displays. Combining 24-hour weather forecast data with XGBoost prediction models, it extrapolates the spatiotemporal evolution trend of thermal risk, achieving forward-looking risk prediction, establishing a warning response feedback channel, and linking urban emergency management departments with grassroots community grids to form a closed-loop management system of assessment, warning, response, and optimization.

[0097] This application provides an urban environmental thermal risk assessment and early warning device based on multi-source data, comprising: acquiring multi-source data of the study city in a target year, including remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information; detecting and removing missing and outlier values ​​from the multi-source data, completing spatial registration, resampling to a unified coordinate system and the same resolution, and performing normalization and cleaning to obtain a standardized multi-source dataset; generating a local climate zone map based on the standardized multi-source dataset, constructing a thermal risk assessment model, including three thermal risk assessment indicators: hazard, exposure, and vulnerability; using the entropy weight method to normalize the range and calculate the weights of each indicator, fusing them to generate a thermal risk index, and calculating the risk value of different blocks in the city; based on the thermal risk index, dividing the urban area into multiple risk levels using the natural breakpoint method, generating a thermal risk level distribution map, and using the spatial autocorrelation method to analyze the spatial clustering characteristics of thermal risk, identifying high-risk clustering areas, and using the XGBoost model combined with the SHAP interpretation method to identify key influencing factors and analyze the nonlinear impact of urban morphology factors on thermal risk. The early warning device proposed in this application includes: a data acquisition unit, a data processing unit, a model building unit, a spatial distribution unit, and a risk early warning unit. This application provides a supporting early warning device that couples multi-source data with weather forecasts to achieve forward-looking prediction of thermal risks, and pushes tiered early warning information to high-risk populations in a targeted manner, forming a closed-loop management system of assessment-early warning-response.

[0098] Reference Figure 8 This application also provides an urban environmental thermal risk assessment and early warning device based on multi-source data, which can realize the above-mentioned urban environmental thermal risk assessment and early warning method based on multi-source data. The device includes: The data acquisition unit is used to acquire multi-source data of the study city in the target year. A data preprocessing unit is used to preprocess the multi-source data to obtain a standardized multi-source dataset; The mapping and modeling unit is used to generate local climate zone maps of the study city and construct a thermal risk assessment model based on the standardized multi-source dataset. A thermal risk calculation unit is used to calculate the thermal risk index of different blocks in the local climate zone map according to the thermal risk assessment model. The thermal risk assessment unit is used to divide the area of ​​the study city into corresponding thermal risk levels according to the thermal risk index, and then generate a thermal risk level distribution map. The thermal risk early warning unit is used to trigger a graded early warning mechanism based on a preset risk threshold and the thermal risk level distribution map.

[0099] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0100] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method of this application. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0101] It is understood that the content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the methods of this application, and the beneficial effects achieved are the same as those achieved by the methods of this application.

[0102] Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 101 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 102 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 102 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 102 and is called and executed by the processor 101. Input / output interface 103 is used to implement information input and output; The communication interface 104 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 105 transmits information between various components of the device (e.g., processor 101, memory 102, input / output interface 103, and communication interface 104); The processor 101, memory 102, input / output interface 103 and communication interface 104 are connected to each other within the device via bus 105.

[0103] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of this application.

[0104] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0105] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0106] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0107] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0108] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0109] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0111] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0112] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0114] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for urban environmental thermal risk assessment and early warning based on multi-source data, characterized in that, The method includes the following steps: Obtain multi-source data for the study city in the target year; The multi-source data is preprocessed to obtain a standardized multi-source dataset; Based on the standardized multi-source dataset, a local climate zone map of the study city is generated, and a future land use simulation model and a thermal risk assessment model are constructed. The thermal risk index of different blocks in the local climate zone map and the thermal risk index under the future urban land use change scenario are calculated based on the thermal risk assessment model. Based on the heat risk index, the area of ​​the study city is divided into corresponding heat risk levels, and a heat risk level distribution map is generated. A graded early warning mechanism is triggered based on a preset risk threshold and the thermal risk level distribution map.

2. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 1, characterized in that, The acquisition of multi-source data for the study city in the target year includes the following steps: The study city's GDP, remote sensing image data, urban morphology data, vegetation cover, water cover, land cover information, and statistical yearbook information for the target year are obtained as the multi-source data.

3. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 1, characterized in that, The preprocessing of the multi-source data to obtain a standardized multi-source dataset includes the following steps: Missing and outlier values ​​are detected and removed from the multi-source data, and spatial registration and resampling to a unified coordinate system and the same resolution are completed. Then, normalization and cleaning are performed to obtain the standardized multi-source dataset.

4. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 1, characterized in that, The steps for generating the local climate zone map based on the standardized multi-source dataset include the following steps: Extract urban morphology data from the standardized multi-source dataset; Determine the resolution of the local climate zone grid for the studied city; The spatial morphology of the local climate zone grid is evaluated based on the urban morphology data. The local climate zone grid is divided into local climate zone types that include the spatial morphology and climate characteristics using fuzzy classification and majority voting methods, thus obtaining the local climate zone map.

5. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 1, characterized in that, The steps for constructing the future land use simulation model based on the standardized multi-source dataset include the following steps: A multi-objective optimization model was adopted, combined with the historical land use transfer matrix, to determine the total land use demand for the target year; A patch-based land use simulation model was used to simulate the spatial distribution pattern of future land use under four urban development scenarios. A land contribution index is constructed to quantify the influence weight of land use type on thermal risk assessment indicators; wherein, the thermal risk assessment indicators include hazard indicators, exposure indicators and vulnerability indicators.

6. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 5, characterized in that, The method of using a multi-objective optimization model, combined with a historical land use transition matrix, to determine the total land use demand for the target year includes the following steps: Four future urban development scenarios have been identified: economic development, natural development, ecological protection, and coordinated development. The objective function is to maximize the economic value, ecological value, and economic-ecological synergistic value of land, with the amount of arable land, forest coverage, water area, upper limit of construction land, and proportion of ecological land as rigid constraints. The historical land use transition matrix is ​​obtained by calculating the land use type conversion probability in the baseline period using Markov chains, and is used to determine the land use demand for four urban development scenarios.

7. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 5, characterized in that, The method employs a patch-based land use simulation model to simulate the spatial distribution patterns of future land use under four urban development scenarios, including the following steps: The land use simulation model for patch generation is determined to contain two core modules: a land expansion analysis strategy and a multi-type random patch seed cellular automaton. Influencing factors include slope, average annual temperature, annual precipitation, distance from roads or rivers, population, and regional GDP.

8. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 5, characterized in that, The construction of the land contribution index, which quantifies the influence weight of land use type on thermal risk assessment indicators, includes the following steps: The formula for calculating the land contribution index is as follows: ； in, The land contribution index. The resolution of the local climate zone grid; Let i be the area of ​​land use category i. is the weighting coefficient for land use types, and n is the total number of land use types; The weighting of land use type on thermal risk assessment indicators is quantified, and the calculation method is as follows: ； in, These are the initial thermal risk assessment indicators, namely, hazard indicators, exposure indicators, or vulnerability indicators; This serves as an indicator for assessing the thermal risks caused by land use changes under future urban development conditions.

9. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 1, characterized in that, The steps for constructing the thermal risk assessment model based on the standardized multi-source dataset include the following steps: Thermal risk assessment indicators are constructed based on the standardized multi-source dataset; the entropy weight method is used to assign weights to each of the thermal risk assessment indicators. The corresponding thermal risk assessment index is calculated by weighted summation based on the assigned weights; The thermal risk assessment model is constructed based on the various thermal risk assessment indicators obtained by weighted summation. The heat risk index under future urban land use change scenarios is calculated based on the land use simulation model and the land contribution index.

10. The urban environmental thermal risk assessment and early warning method based on multi-source data according to claim 9, characterized in that, The process of assigning weights to each of the thermal risk assessment indicators using the entropy weight method includes the following steps: The range of each of the aforementioned thermal risk assessment indicators is normalized using the entropy weight method, and the calculation is as follows: ； ； Where X is the original index matrix composed of m research units and n thermal risk assessment indicators; X represents the original value of the i-th research unit and the j-th thermal risk assessment indicator; Y is the standardized value of the original values; The definition of information entropy is as follows: ； ； in, Indicates changes in the size of the indicator; Represents information entropy; The weights and comprehensive index values ​​of each of the aforementioned thermal risk assessment indicators are calculated using the entropy weight method, as follows: ； ； in, The weights of each of the aforementioned thermal risk assessment indicators are: The comprehensive index value is the sum of the various thermal risk assessment indicators.

11. The urban environmental thermal risk assessment and early warning method based on multi-source data according to any one of claims 1 to 10, characterized in that, The method also includes analyzing the thermal risk of the studied city and the thermal risk under future urban land use change scenarios based on the thermal risk level distribution map, specifically including the following steps: The spatial autocorrelation method was used to analyze the spatial clustering characteristics of thermal risk in the thermal risk level distribution map, and risk clustering areas were identified. The trend of heat risk change under future urban land use change was analyzed using a future land use simulation model and a land contribution index on the heat risk level distribution map. A machine learning algorithm model based on a gradient boosting framework, combined with a game theory-based model interpretation method, is used to identify key influencing factors based on the aforementioned heat risk level distribution map. The nonlinear impact of urban morphology factors on thermal risk is analyzed based on the aforementioned key influencing factors.

12. A device for urban environmental thermal risk assessment and early warning based on multi-source data, characterized in that, The device includes: The data acquisition unit is used to acquire multi-source data of the study city in the target year. A data preprocessing unit is used to preprocess the multi-source data to obtain a standardized multi-source dataset; The mapping and modeling unit is used to generate local climate zone maps of the study city based on the standardized multi-source dataset, and to construct a future land use simulation model and a thermal risk assessment model. The thermal risk calculation unit is used to calculate the thermal risk index of different blocks in the local climate zone map and the thermal risk index under the future urban land use change scenario according to the thermal risk assessment model. The thermal risk assessment unit is used to divide the area of ​​the study city into corresponding thermal risk levels according to the thermal risk index, and then generate a thermal risk level distribution map. The thermal risk early warning unit is used to trigger a graded early warning mechanism based on a preset risk threshold and the thermal risk level distribution map.

13. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 11.

Images