A method for evaluating climate comfort of human settlements based on multi-source data

Abstract

This invention discloses a method for evaluating the climate comfort of human settlements based on multi-source data, relating to the field of environmental climate technology. The method includes: collecting and preprocessing heterogeneous data to generate a standardized multi-source data cube; obtaining an urban microscale climate comfort field based on the standardized multi-source data cube through microclimate simulation that integrates urban three-dimensional building morphology and underlying surface attributes; performing dynamic spatiotemporal overlay analysis of the urban microscale climate comfort field and anonymized group movement location data to identify and quantify persistent exposure hotspots and high-exposure movement corridors; and correlating and analyzing multi-source behavioral feedback data based on these persistent exposure hotspots and high-exposure movement corridors to construct a behavioral feedback-exposure intensity coupling model and assess the urgency level of planning intervention. This invention constructs a behavioral feedback-exposure intensity coupling model that reflects real human feelings, thereby linking physical exposure with psychological perception and assessing the urgency of planning intervention.

Description

Technical Field

[0001] This invention relates to the field of environmental and climate technology, and in particular to a method for evaluating the climate comfort of human settlements based on multi-source data. Background Technology

[0002] The evaluation of climate comfort in human settlements is an important interdisciplinary research direction in the fields of urban climatology, building physics, and public health. It quantifies the comprehensive impact of meteorological conditions on human thermal perception and provides a scientific basis for urban and rural planning, public health risk management, and personalized meteorological services. In existing technologies, by introducing a comprehensive biometeorological index of effective temperature, multiple meteorological elements such as temperature, humidity, wind speed, and sunshine are effectively integrated to construct a relatively unified and continuous evaluation system. This system mainly relies on data provided by a relatively sparse network of fixed meteorological observation stations and generates regional-scale climate comfort distribution maps through spatial interpolation and other techniques.

[0003] When the evaluation objective shifts from macro-level cognition to precise planning and management, the limitations of existing technologies lie in the disconnect between their static environmental assessment perspective and the dynamic needs of human activities. Existing methods can answer whether the climate of a certain place is comfortable, but they cannot answer core planning decisions such as who, when, where, and what kind of discomfort they experience, and where interventions should be prioritized. They cannot quantify the total amount of climate exposure experienced by people during daily movement, nor can they correlate physical environmental data with behavioral feedback data that reflects people's actual feelings. As a result, the conclusions cannot directly support the priority decisions of refined urban climate adaptation plans such as the layout of sunshade facilities and the design of ventilation corridors. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for evaluating the climate comfort of human settlements based on multi-source data to address the problem that existing technologies cannot provide accurate and quantifiable decision-making basis for refined urban climate adaptation planning from the coupled perspective of dynamic human exposure and real behavioral feedback.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for evaluating the climate comfort of human settlements based on multi-source data, which includes collecting and preprocessing heterogeneous data to generate a standardized multi-source data cube.

[0008] Based on standardized multi-source data cubes, a micro-scale climate comfort field of the city is obtained by integrating the microclimate simulation of urban three-dimensional building morphology and underlying surface properties.

[0009] Dynamic spatiotemporal overlay analysis of urban microscale climate comfort field and anonymized group movement location data is performed to identify and quantify continuous exposure hotspots and high-exposure movement corridors.

[0010] Based on the continuous exposure hotspots and high-exposure mobile corridors of the population, we conducted correlation analysis on multi-source behavioral feedback data, constructed a behavioral feedback-exposure intensity coupling model, and assessed the urgency level of planned interventions.

[0011] Based on the urgency level of the planning intervention, a visual planning scheme for the deployment of climate-adaptive facilities is generated.

[0012] The data on the effects of the climate adaptation facility deployment plan after its implementation are monitored and fed back into the behavior feedback-exposure intensity coupled model for adaptive parameter optimization.

[0013] As a preferred embodiment of the human settlement climate comfort evaluation method based on multi-source data described in this invention, the method includes the following steps: collecting and preprocessing heterogeneous data to generate a standardized multi-source data cube:

[0014] Heterogeneous data is collected and then cleaned, coordinate and time unified, and spatiotemporally interpolated and fused to form a structured, standardized multi-source data cube.

[0015] As a preferred embodiment of the human settlement environment climate comfort evaluation method based on multi-source data described in this invention, the method includes the following steps: Based on a standardized multi-source data cube, a micro-scale climate comfort field of the city is obtained by integrating the three-dimensional building morphology and underlying surface properties of the city through micro-climate simulation.

[0016] Meteorological driving fields, three-dimensional urban morphology parameters, and underlying surface physical property parameters are extracted from the standardized multi-source data cube and input into the urban microclimate model to perform dynamic correction and radiation redistribution. Based on grid-based energy balance calculation, the microscale meteorological element correction field is obtained.

[0017] The physical parameters in the microscale meteorological element correction field are converted into grid effective temperature index values ​​for each spatial grid through a pre-defined effective temperature index attribute mapping rule.

[0018] Based on the set standard threshold, the effective temperature index value of the grid is mapped to a comfort level label;

[0019] By combining the effective temperature index value of the grid with the comfort level label, a microscale climate comfort field of the city is obtained.

[0020] As a preferred embodiment of the multi-source data-based human settlement climate comfort evaluation method of the present invention, the method includes the following steps: dynamically and spatiotemporally overlaying and analyzing the urban micro-scale climate comfort field with anonymized group movement location data to identify and quantify persistent exposure hotspots and high-exposure movement corridors:

[0021] On each time slice of the urban microscale climate comfort field, anonymized group movement and location data for the corresponding time period are overlaid.

[0022] Based on the overlaid spatiotemporal matching data, the cumulative exposure duration and frequency of exposure to discomfort levels of the population in each geographic unit within a continuous time period are obtained.

[0023] Based on the urban microscale climate comfort field and anonymized group movement location data, for each preset geographic grid unit, each time slice is traversed and it is determined whether the climate comfort level belongs to the preset set of discomfort levels.

[0024] If it is, the product of the number of people in the geographic grid cell at the current time and the length of the time slice is included in the cumulative exposure time of the people in the geographic grid cell and counted as one uncomfortable event, so as to obtain the cumulative exposure time of the people in each geographic grid cell and the frequency of exposure to the uncomfortable level.

[0025] Based on the cumulative exposure duration and frequency of exposure to discomfort levels, geographical units where people are clustered and continuously exposed to discomfort levels are identified, forming hotspots of continuous exposure to the population.

[0026] Based on the superimposed spatiotemporal matching data, the continuous paths of crowd movement are analyzed, and movement trajectories that exceed the spatial unit and are at an uncomfortable level are identified, forming high-exposure movement corridors.

[0027] For the identified persistent exposure hotspots and high-exposure mobile corridors, the total exposed population, average exposure duration, and exposure intensity index are quantified to form a list of persistent exposure hotspots and high-exposure mobile corridors with spatial range and quantitative attributes.

[0028] As a preferred embodiment of the human settlement climate comfort evaluation method based on multi-source data described in this invention, the method includes the following steps: based on the continuous exposure hotspots and high-exposure movement corridors of the population, multi-source behavioral feedback data are correlated and analyzed to construct a behavioral feedback-exposure intensity coupling model to assess the urgency level of planning interventions:

[0029] For each group, based on the geographical boundaries of continuous exposure hotspots and high-exposure mobile corridors, acquire multi-source behavioral feedback data within the corresponding spatial range and time window;

[0030] By using standardized measurement rules, corresponding exposure intensity quantification values ​​are generated for each identified group's continuous exposure hotspots and high-exposure mobile corridors. Through spatiotemporal matching, each exposure intensity quantification value is associated with multi-source behavioral feedback data within the corresponding spatial range to form sample pairs.

[0031] The machine learning model is trained using sample pairs, with the exposure intensity quantification value as input, to predict the expected intensity of multi-source behavioral feedback data and obtain a behavioral feedback-exposure intensity coupled model.

[0032] The actual multi-source behavioral feedback data of persistent exposure hotspots and high-exposure mobile corridors are compared with the predicted values ​​of the behavioral feedback-exposure intensity coupling model, and the urgency level of planning intervention is assessed based on the degree of deviation.

[0033] As a preferred embodiment of the human settlement climate comfort evaluation method based on multi-source data described in this invention, the method includes the following steps: generating a visualized climate adaptability facility layout plan according to the urgency level of planning intervention.

[0034] The urgency level of planning intervention is rendered on the map layer of the city geographic information system. In areas with a high urgency level of planning intervention, a preset library of climate adaptability facility types is matched.

[0035] Based on the matching climate adaptability facility layout rules and spatial constraints, preliminary facility locations are automatically generated in areas with a high level of urgency for planning intervention.

[0036] The preliminary climate adaptability facility deployment plan is quantified and its coverage relationship with the current exposure sites is mapped to the expected improvement in comfort level according to preset rules.

[0037] By integrating the climate adaptability facility deployment schemes and expected benefit indicators based on simulation assessments, a visualized climate adaptability facility deployment planning scheme map and report is generated.

[0038] As a preferred embodiment of the multi-source data-based human settlement climate comfort evaluation method of the present invention, the following steps are included in monitoring the effect data after the implementation of the climate adaptability facility deployment planning scheme:

[0039] After the implementation of the climate adaptability facility deployment plan, multi-source behavioral feedback data and group movement and positioning data are collected under the same spatial range and meteorological conditions as effect monitoring data.

[0040] As a preferred embodiment of the human settlement climate comfort evaluation method based on multi-source data described in this invention, the adaptive parameter optimization in the behavior feedback-exposure intensity coupled model includes the following steps:

[0041] Based on the effect monitoring data, measure and generate quantitative values ​​of the exposure intensity of the corresponding area after the implementation of the climate adaptation facility deployment plan;

[0042] The quantitative values ​​of exposure intensity in the region after the implementation of the climate adaptation facility deployment plan are correlated with multi-source behavioral feedback data in the same region to form new sample pairs;

[0043] New sample pairs are used as incremental training data and input into the behavior feedback-exposure strength coupling model. The parameters of the behavior feedback-exposure strength coupling model are then updated online.

[0044] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the human settlement climate comfort evaluation method based on multi-source data as described in the first aspect of the present invention.

[0045] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the human settlement climate comfort evaluation method based on multi-source data as described in the first aspect of the present invention.

[0046] The beneficial effects of this invention are as follows: By collecting and standardizing the integration of multi-source heterogeneous data such as meteorology, remote sensing, positioning, and urban morphology, a unified spatiotemporal data base is formed; then, by coupling the three-dimensional morphology of the city with the properties of the underlying surface, the macro-meteorological field is refined into a dynamic comfort distribution map at the street scale, combining static environmental assessment with dynamic human activities: by overlaying anonymous group movement data, hotspots and corridors where people are densely populated and continuously exposed to uncomfortable climates are accurately identified, and their exposure intensity is quantified; by introducing multi-source behavioral feedback data of consumption and social interaction, a behavioral feedback-exposure intensity coupling model that can reflect the real feelings of the human body is constructed, thereby linking physical exposure with psychological perception and assessing the urgency of planning intervention. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a method for evaluating the climate comfort of human settlements based on multi-source data.

[0049] Figure 2 This is a schematic diagram for identifying highly exposed mobile corridors. Detailed Implementation

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0051] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0053] Reference Figures 1-2 This is one embodiment of the present invention, which provides a method for evaluating the climate comfort of human settlements based on multi-source data, including the following steps:

[0054] S1. Collect and preprocess heterogeneous data to generate a standardized multi-source data cube.

[0055] S1.1 Collect heterogeneous data, and after cleaning, unifying coordinates and time, and performing spatiotemporal interpolation fusion on the heterogeneous data, organize it into a structured, standardized multi-source data cube.

[0056] Furthermore, the heterogeneous data collection encompasses meteorological observation data from meteorological stations, remote sensing satellite imagery data, anonymized mobile signaling and positioning data from mobile communication base stations, and 3D building vector and surface material data from urban information models. The data cleaning process addresses the unique error patterns of each data type. For example, outliers caused by instrument drift are removed from meteorological observation data; cloud masking and atmospheric correction are applied to remote sensing imagery data to eliminate noise; and drift points and ping-pong effects are cleaned from anonymized mobile signaling and positioning data based on signal switching and dwell time logic. Coordinate unification transforms all data to the same geographic coordinate system to ensure spatial consistency. Temporal unification aligns data from different acquisition frequencies to a common time reference through resampling, for example, unifying all data to the hour.

[0057] Specifically, a dynamically weighted heterogeneous data fusion framework is constructed. Instead of pre-fixing the priority of various types of data, the weights are dynamically allocated during the fusion process based on the spatiotemporal representativeness of the data, the reliability of the measurement principle, and real-time quality indicators. For example, in areas with sparse meteorological stations, surface temperature data retrieved from remote sensing has a higher weight in spatial interpolation; while in densely built-up urban areas, detailed three-dimensional geometric data from urban information models dominate the corrective interpolation of wind speed and radiation, so that the generated standardized multi-source data cube achieves a better balance between spatial integrity and physical consistency.

[0058] S2. Based on standardized multi-source data cubes, a micro-scale climate comfort field for the city is obtained by integrating the microclimate simulation of urban three-dimensional building morphology and underlying surface properties.

[0059] S2.1 Extract meteorological driving fields, three-dimensional urban morphology parameters and underlying surface physical property parameters from the standardized multi-source data cube, input them into the urban microclimate model to perform dynamic correction and radiation redistribution, and obtain the microscale meteorological element correction field based on grid-based energy balance calculation.

[0060] Furthermore, a hierarchical urban microclimate model framework with clear physical mechanisms was constructed. It is not a single complex numerical model, but rather decouples the city's impact on climate into three sub-processes with clear physical causal relationships for sequential processing. Dynamic correction ensures that the blocking and guiding effect of urban geometry on the background wind field is quantified. Using morphological parameters such as building windward area density and street height-to-width ratio, rapid and reasonable correction of wind speed and direction within the canopy is achieved through empirical functions. The radiation redistribution process specifically handles the interception, reflection, and re-emission effects of solar and long-wave radiation in the three-dimensional space of the city. The application of sky visibility factors and multiple reflection enhancement factors allows the complex radiation exchange in the building shadow area and street canyon to be explicitly expressed.

[0061] Specifically, grid-based energy balance calculations use the local meteorological conditions, corrected for the aforementioned dynamics and radiation, as the driving boundary for each grid cell. Combined with underlying surface properties such as vegetation cover and surface resistance, the surface energy budget for each grid is calculated, yielding corrected near-surface temperature, humidity, and other parameters. This hierarchical sequential processing decomposes the complex urban climate problem into multiple independently verifiable and optimizable physical steps. The output of each step serves as the input for the next, forming a physically self-consistent chain. This approach overcomes the shortcomings of traditional single models, such as overly tight parameter coupling, high computational complexity, and difficulty in interpreting intermediate processes when dealing with the multidimensional heterogeneity of cities. It ensures that the generation of the microscale meteorological element correction field possesses both physical reliability and a balance between computational efficiency and process transparency.

[0062] The dynamic correction formula is:

[0063] ;

[0064] in, To correct the wind speed within the canopy, For reference altitude wind speed, This is the drag coefficient. For the building's windward area density, The height-to-width ratio of the street, The angle between the wind direction and the street axis. The average building height This represents the average width of the street.

[0065] Radiation redistribution formula:

[0066] ;

[0067] in, The mean radiation temperature. Total solar radiation. It is the surface albedo. For sky visibility factor, As a multiple reflection enhancement factor, This is atmospheric back radiation. To reflect long-wave radiation to the environment, It is the Stefan-Boltzmann constant. It represents the surface emissivity.

[0068] Grid energy balance formula:

[0069] ;

[0070] in, Net radiation, air density, The specific heat of air at constant pressure. For surface temperature, For air temperature, For aerodynamic drag, For latent heat of vaporization, The surface saturation and air specific humidity are considered. The specific humidity of air. For surface resistance, For deep soil temperature, It is the thermal conductivity of the soil.

[0071] Formula for corrected field of microscale meteorological elements:

[0072] ;

[0073] in, For microscale meteorological element correction fields, Temperature at reference altitude Relative humidity at reference altitude This refers to vegetation coverage.

[0074] S2.2. The physical parameters in the microscale meteorological element correction field are converted into the grid effective temperature index value of each spatial grid through the preset effective temperature index attribute mapping rules.

[0075] Furthermore, the concept of attribute mapping rules is proposed. The microscale meteorological element correction field provides multiple physical parameters, such as corrected air temperature, humidity, wind speed, and mean radiant temperature. The pre-defined effective temperature index attribute mapping rule defines a set of deterministic transformation logic. Taking the above-mentioned multivariate physical parameters as input, it directly outputs the grid effective temperature index value of each spatial grid through a standardized and reproducible nonlinear relationship. The ingenuity of this approach is to achieve decoupling and standardization, abstracting the complex human thermal comfort model from specific geospatial grid calculations and encapsulating it into a universal mapping rule. Regardless of the data source or spatial resolution of the microscale meteorological element correction field, as long as the same mapping rule is applied, it can ensure that the generated grid effective temperature index values ​​remain consistent in standard and meaning, have cross-temporal and spatial comparability, and avoid the inconsistency problem caused by different empirical formulas used in different regions. Thus, it efficiently and consistently transforms physical environmental parameters into human-centered comfort quantification indicators.

[0076] S2.3 Based on the set standard threshold, map the effective temperature index value of the grid to a comfort level label.

[0077] Furthermore, the standard threshold is used for discretized classification mapping. The grid effective temperature index value is a continuous variable, but for intuitive understanding and subsequent spatial analysis and management decisions, it needs to be converted into a limited set of discrete comfort level labels such as cold, cool, comfortable, hot, and extremely hot. The set standard threshold is based on statistical induction from a large number of human thermal sensation experiments and questionnaire survey data. It divides the grid effective temperature index value range corresponding to different human thermal sensation intervals. The mapping process is a simple interval judgment logic. Each grid effective temperature index value is assigned a corresponding comfort level label according to the threshold interval it falls into, solidifying the statistical conclusions into a stable classification standard. This ensures the objectivity and repeatability of the evaluation results and avoids the bias caused by subjective arbitrary division. By applying a unified standard threshold, regardless of which city or time period the analysis is conducted on, the same grid effective temperature index value will correspond to the same comfort level. This allows for standardized comparison and summary analysis of comfort conditions in different regions and at different times.

[0078] S2.4 Combine the effective temperature index value of the grid with the comfort level label to obtain the urban microscale climate comfort field.

[0079] Furthermore, a comprehensive data field was constructed, possessing both continuous quantitative and discrete semantic features. The urban microscale climate comfort field is not a single data layer, but rather each spatial grid cell contains two attributes simultaneously: the grid effective temperature index value and a comfort level label. The grid effective temperature index value provides accurate and continuous quantitative measurement, facilitating numerical calculations, trend analysis, and spatial statistics. The comfort level label provides intuitive and discrete semantic classification, enabling rapid map reading, region identification, and category-based spatial queries. Together, they meet multi-level application needs. For example, in visualization, color gradients can represent the continuous changes in the grid effective temperature index value, while contour lines or zoning colors highlight the regional range of different comfort levels. In spatial statistical analysis, this combined approach overcomes the limitations of a single representation form, preserving data granularity while enhancing the interpretability and practicality of the results, thus making the final urban microscale climate comfort field more comprehensive.

[0080] S3. Dynamically overlay and analyze the urban microscale climate comfort field with anonymized group movement location data to identify and quantify continuous exposure hotspots and high-exposure movement corridors.

[0081] S3.1. Overlay anonymized group movement and location data for the corresponding time period onto each time slice of the urban microscale climate comfort field.

[0082] Furthermore, the urban microscale climate comfort field provides dynamic spatial climate conditions in units of time slices, while the anonymized group movement location data provides dynamic population distribution in units of the same time granularity. The overlay operation is not a simple layer overlay, but rather uses a unified geographic grid coordinate system and a unified time axis as a benchmark to accurately correlate the number of people in the same geographic grid unit at the same time with the climate comfort level, constructing a spatiotemporally aligned data cube. Each time-space unit contains two dimensions: environmental state and population state. This overcomes the limitations of traditional evaluations that treat the population as static or homogeneous and the climate as a uniform background, providing an accurate data foundation for subsequent analysis of the population's exposure in a real dynamic environment. This transforms exposure assessment from an evaluation of the land to a measurement of the spatiotemporal co-occurrence relationship between people and the land.

[0083] S3.2 Based on the overlaid spatiotemporal matching data, obtain the cumulative exposure duration and frequency of exposure to discomfort levels for each geographic unit within a continuous time period.

[0084] Furthermore, two complementary core exposure metrics were defined and measured: cumulative exposure duration, which measures the total population size affected by uncomfortable weather, and cumulative exposure duration, which measures the total number of people in each geographic unit at the discomfort level within each time slice, multiplied by the length of the time slice. The result reflects the overall person-time burden caused by uncomfortable weather. The frequency of exposure to the discomfort level measures the persistence of uncomfortable weather conditions, which is the proportion of time slices at the discomfort level for a geographic unit within the analysis period to the total number of slices.

[0085] Specifically, these two indicators quantify exposure characteristics from two orthogonal dimensions: the breadth and depth of the impact and the frequency of occurrence. This provides a more comprehensive characterization of exposure risk. A region may have a high cumulative exposure duration due to a large number of people gathering in a short period of time, or it may have a high frequency due to long-term discomfort but low population flow. Distinguishing between these two modes is crucial for understanding the causes of risk and developing intervention strategies, overcoming the problem that a single indicator may mask the true risk pattern.

[0086] S3.3 Based on the urban microscale climate comfort field and anonymized group movement location data, for each preset geographic grid unit, traverse each time slice and determine whether the climate comfort level belongs to the preset set of discomfort levels.

[0087] Furthermore, by traversing each preset geographic grid cell and each time slice, a complete scan of the spatiotemporal data domain is achieved. The judgment operation is based on a preset set of discomfort levels, which is predefined, such as including heat and extreme heat levels. This decomposes the complex spatiotemporal pattern recognition problem into a large number of independent, isomorphic atomic logical operations. Each atomic operation answers only one simple question: at a specific time and place, is the climate uncomfortable? This method is logically very clear and easy to implement, verify, and parallelize.

[0088] S3.4 If it belongs to the category, the product of the number of people in the geographic grid cell at the current time and the length of the time slice is included in the cumulative exposure time of the people in the geographic grid cell and counted as an uncomfortable event, so as to obtain the cumulative exposure time of the people in each geographic grid cell and the frequency of exposure to the uncomfortable level.

[0089] Furthermore, when the judgment condition is true, two parallel quantification actions are executed. The first action multiplies the number of people in the geographic grid cell at the current moment by the length of the time slice as a contribution value, which is added to the cumulative exposure time of the population in that geographic grid cell. The physical meaning of this product is person-hour, which is the basic unit of exposure dose. The second action counts the event as an uncomfortable event, establishing a bridge between micro-instantaneous events and macro-cumulative indicators. It ensures that each uncomfortable moment and its corresponding population size can contribute to the total exposure in an additive manner, accurately recording the frequency of event occurrence.

[0090] S3.5 Based on the cumulative exposure duration and frequency of exposure to discomfort levels, identify geographical units where people are clustered and continuously exposed to discomfort levels, thus forming hotspots of continuous exposure to the population.

[0091] Furthermore, defining and identifying spatial entities with clear public health and planning significance as hotspots of sustained exposure to the population involves setting joint thresholds for two indicators: cumulative exposure duration and frequency of exposure to discomfort levels. A geographical unit must simultaneously meet two thresholds to be identified as a hotspot of sustained exposure to the population. This approach captures the two key elements of sustainability and population. Sustainability is reflected in high frequency, indicating that the location is under prolonged climatic stress; population is reflected in high cumulative exposure duration, indicating that a large number of people are experiencing this discomfort at the location. This dual-condition identification overcomes the one-sidedness of judging a hotspot solely based on high temperature or high population density. It accurately locates key areas that are both climatically unfavorable and densely populated, thus posing the highest health risks and improvement needs, such as unshaded bus hubs or open plazas on a hot summer afternoon.

[0092] S3.6. Based on the superimposed spatiotemporal matching data, analyze the continuous paths of crowd movement, identify movement trajectories on the path that exceed the spatial unit and are at an uncomfortable level, and form a high-exposure movement corridor.

[0093] Furthermore, the analysis extends from static hotspot analysis to dynamic corridor identification, focusing on the linear exposure of people during movement. It analyzes the individual or group movement trajectories reconstructed from anonymized group movement location data. For each trajectory, it examines the climate comfort level corresponding to the sequence of continuous spatial units it passes through. The identification rule is that when the number (or length ratio) of spatial units at the discomfort level in a movement trajectory exceeds a preset threshold, the trajectory is marked as a high-exposure movement trajectory. All these trajectories converge in space to form a common path, which constitutes a high-exposure movement corridor.

[0094] Specifically, it reveals dynamic, linear climate risk channels in cities, identifying not necessarily the final gathering places of people, but rather the sections of road with harsh climate conditions that people have to endure on their way to their destinations, such as sidewalks lacking shade connecting subway stations and large residential areas.

[0095] S3.7. For the identified persistent exposure hotspots and high-exposure mobile corridors, quantify the total exposed population, average exposure duration, and exposure intensity index to form a list of persistent exposure hotspots and high-exposure mobile corridors with spatial range and quantitative attributes.

[0096] Furthermore, the identified spatial entities are assigned multi-dimensional quantitative attributes to form a structured and operable list. For each group, continuous exposure hotspots are identified, including the total exposed population and average exposure duration. An exposure intensity index can also be calculated. For each high-exposure mobile corridor, similar quantification is performed, such as calculating the total exposed population passing through the corridor and the average single exposure duration. The exposure intensity index is a comprehensive indicator that aims to integrate information such as the size of the exposed population, duration, and spatial range. The final list not only includes the spatial boundaries of each hotspot and corridor but also includes these quantitative attributes.

[0097] Specifically, the spatial identification results are transformed into data products that can be used for prioritization and decision support. The quantitative attributes in the list enable comparisons between different hotspots and corridors, providing objective data support for answering which areas have more serious problems and require priority intervention.

[0098] S4. Based on the continuous exposure hotspots and high-exposure mobile corridors of the group, conduct correlation analysis on multi-source behavioral feedback data, construct a behavioral feedback-exposure intensity coupling model, and assess the urgency level of planned interventions.

[0099] S4.1. For each group, continuously expose hotspots and high-exposure mobile corridors at their geographical boundaries, and obtain multi-source behavioral feedback data within the corresponding spatial range and time window.

[0100] Furthermore, by precisely linking subjective feelings and behavioral responses with physical exposure spaces through quantifiable external data proxy indicators, multi-source behavioral feedback data is generated. The root causes are closely related to the actual discomfort and adaptive behaviors of the population in specific times and spaces. Data acquisition is carried out on the geographical boundaries and time windows of continuous exposure hotspots and high-exposure mobile corridors for each group. This means that information fragments related to target spatial entities and target time periods can be selectively retrieved from the ocean of behavioral big data. It realizes the mapping from macroscopic and anonymous digital footprints of the group to microscopic and specific spatial problems. It overcomes the limitations of traditional evaluation methods that rely on small sample questionnaires or interviews in terms of spatiotemporal coverage and real-time performance, making it possible to measure the thermal comfort perception of the population on a large scale, dynamically and objectively.

[0101] S4.2. Through standardized measurement rules, generate corresponding exposure intensity quantification values ​​for each identified group's continuous exposure hotspots and high-exposure mobile corridors. Through spatiotemporal matching, associate each exposure intensity quantification value with multi-source behavioral feedback data within the corresponding spatial range to form sample pairs.

[0102] Furthermore, a standardized paired data unit for physical exposure and behavioral feedback is constructed. The quantified exposure intensity value is an objective and standardized measure of the climate risk intensity of persistent exposure hotspots and high-exposure movement corridors for a population, based on physical models and observational data. The quantification on the physical side involves processing the multi-source behavioral feedback data, such as cleaning, aggregation, and normalization, to form a comprehensive index representing the behavioral response. Through spatiotemporal matching, the quantified exposure intensity value of the same persistent exposure hotspot or the same high-exposure movement corridor is paired with its corresponding multi-source behavioral feedback data (behavioral response index) within the same spatiotemporal range, forming a sample pair. Each sample pair contains one independent variable and one dependent variable.

[0103] Specifically, the complex urban climate-human response relationship is discretized into individual, independently learnable data points, enabling the model to automatically learn the statistical correlation pattern between exposure intensity and behavioral feedback from historical data. This overcomes the difficulty of accurately characterizing complex nonlinear socio-climate interactions by relying on prior theoretical models.

[0104] S4.3. Use sample pairs to train a machine learning model, taking the exposure intensity quantification value as input, to predict the expected intensity of multi-source behavioral feedback data and obtain a behavioral feedback-exposure intensity coupled model.

[0105] Furthermore, a mapping function from physical exposure to behavioral feedback can be directly learned and constructed from the data. The sample set provides a large number of input-output observation instances. The exposure intensity quantification value is used as the model input feature, and multi-source behavioral feedback data (behavioral response indicators) is used as the model prediction target. A machine learning model, such as a gradient boosting decision tree or a neural network, is trained. The training process allows the model to continuously adjust its internal parameters to minimize the difference between its predicted values ​​and the actually observed multi-source behavioral feedback data. The resulting model is the behavioral feedback-exposure intensity coupled model, which is a mathematical function that can predict the expected intensity of multi-source behavioral feedback data (i.e., the intensity of population behavioral response) under a given exposure intensity quantification value.

[0106] Specifically, it achieves automated relationship analysis and data-driven quantification. The model can capture the complex nonlinear relationships and interaction effects that may exist between exposure intensity and behavioral feedback, without requiring manual pre-setting of specific function forms, making the model predictions more adaptive and accurate.

[0107] S4.4 Compare the actual multi-source behavioral feedback data of the group's continuous exposure hotspots and high-exposure mobile corridors with the predicted values ​​of the behavioral feedback-exposure intensity coupling model, and assess the urgency level of the planned intervention based on the degree of deviation.

[0108] Furthermore, using the prediction-actual deviation as the core criterion for assessing the urgency of planning interventions, for each group to be assessed, continuous exposure hotspots or high-exposure mobile corridors, their current actual multi-source behavioral feedback data is obtained. The quantified value of the spatial entity's exposure intensity is input into a pre-trained behavioral feedback-exposure intensity coupling model to obtain the model's predicted intensity of multi-source behavioral feedback data expected to occur under that exposure intensity. The actual observation value is compared with the model's predicted value. The assessment logic is as follows: if the actual observed behavioral feedback intensity is higher than the model's predicted value, it indicates that under the current physical exposure level, the population exhibits a stronger adverse response or adaptive behavior than historical experience patterns. This suggests that the existing environmental conditions or facilities in the area may no longer meet the population's adaptive needs, and the population is experiencing more discomfort than expected. Therefore, the urgency level of planning interventions should be rated as high. Conversely, if the actual feedback matches the prediction or is even lower, the urgency is relatively low.

[0109] Specifically, a dynamic assessment framework based on the relative distress index was established. Instead of viewing the absolute value of physical exposure or the absolute value of behavioral feedback in isolation, it focuses on the degree of deviation of behavioral feedback from the historical exposure-response relationship baseline. This allows the urgency assessment to dynamically reflect the true tolerance and adaptation status of the population, providing an intelligent and contextualized decision-making basis for identifying the most prominent current contradictions and the most urgent intervention points.

[0110] S5. Generate a visualized climate adaptation facility deployment plan based on the urgency level of the planning intervention.

[0111] S5.1 Render the urgency level of planning intervention on the map layer of the city geographic information system, and match the preset climate adaptability facility type library in areas where the urgency level of planning intervention is high.

[0112] Furthermore, the urgency level of planning intervention is rendered as a map layer, transforming abstract priority assessment conclusions into an intuitive and visual spatial distribution pattern. High-urgency areas are highlighted on the map. The pre-defined climate-adaptive facility type library is a knowledge base that defines the basic attributes, applicable scenarios, and mitigation goals of different types of facilities. For example, sunshades are suitable for partial shading in open squares, while street trees are suitable for continuous shading and cooling on linear streets. The matching operation automatically selects the most suitable combination of facility types from the facility type library based on the spatial characteristics and exposure problem nature of high-urgency areas. For example, for a highly exposed transportation hub square, sunshades and misting cooling facilities might be matched; for a highly exposed pedestrian walkway on a main urban road, street trees or connecting corridors would be prioritized.

[0113] Specifically, it achieves standardized and contextualized recommendations for intervention measures, avoids the arbitrariness of planning scheme generation, overcomes the limitations of traditional planning that relies too much on the personal experience of planners and is difficult to quickly form a list of targeted measures from massive amounts of diagnostic information, ensures that the subsequent planning scheme generation is highly consistent with the problem diagnosis from the starting point, and provides a clear technical path for automated generation.

[0114] S5.2 Based on the matching climate adaptability facility layout rules and spatial constraints, the initial facility locations are automatically generated in areas with a high level of urgency for planning intervention.

[0115] Furthermore, professional design rules and spatial constraints are encoded into executable algorithms to achieve automated spatial optimization of planning schemes. In the matching library of climate-adaptive facility types, each facility is accompanied by its layout rules and spatial constraints. The layout rules define how facilities should be laid out to achieve optimal efficiency. For example, sunshades should cover the main pedestrian paths and the spacing should meet the requirements for continuous shading, and street trees should meet the requirements for planting spacing and setback. The spatial constraints are the real limitations on whether facilities can be laid out in physical space, including unoccupiable spaces such as road red lines, underground pipelines, fire lanes, and existing structures. The system automatically generates preliminary facility locations. In areas with a high level of urgency for planning intervention, candidate locations are generated based on the facility layout rules. These candidate locations are then screened, adjusted, and optimized according to the spatial constraints. Finally, a set of facility location coordinates that meets all constraints, conforms to the layout rules, and covers high-exposure areas as much as possible is generated.

[0116] Specifically, the complex, experience-dependent facility layout work is transformed into a constrained spatial optimization problem, overcoming the shortcomings of low efficiency, difficulty in simultaneously considering multiple complex constraints, and poor consistency of results of manual site selection. This enables the rapid generation of a large number of technically feasible and spatially reasonable preliminary solutions in complex urban environments.

[0117] S5.3. For the generated preliminary climate adaptability facility deployment plan, quantify the coverage relationship with the current exposure sites, and map it to the expected improvement in comfort level according to preset rules.

[0118] Furthermore, it provides a rapid and standardized method for pre-assessing the expected benefits of planning schemes without the need for complex microclimate simulations. Quantifying coverage relationships refers to calculating the effective coverage area of ​​the preliminary facility deployment scheme and the spatial overlap with the identified persistent exposure hotspots and high-exposure mobile corridors in the current exposure field. The preset rules are established based on expert knowledge or historical case data, defining the correspondence between the expected microclimate improvement and comfort level enhancement under different facility types and coverage levels. For example, a pedestrian path with a continuous shading rate of 80% is expected to reduce the thermal discomfort level of its covered section by one level. According to the preset rules, the quantified coverage relationship data is input into this set of rules, and the output is an assessment of the expected comfort level enhancement for each covered area.

[0119] S5.4 Integrate the climate adaptability facility deployment plan and expected benefit indicators after simulation and evaluation to generate a visualized climate adaptability facility deployment plan map and report.

[0120] Furthermore, the results of technical analysis, spatial design, and benefit assessment are integrated into a professional and comprehensive decision support product. The simulated and assessed climate adaptability facility deployment plan includes spatial and attribute information such as facility location, type, and specifications, as well as benefit indicators such as the expected improvement in comfort level. The integration process involves organizing, symbolizing, and annotating this spatial information, attribute information, and assessment indicators according to standard cartographic specifications for urban planning maps. The generated planning scheme map consists of one or more professional maps that clearly show the facility layout, coverage area, and urgency level zoning, presenting the expected benefits through legends and annotations. The report is a textual summary of the entire scheme generation process, its basis, technical indicators, investment estimates, and implementation recommendations.

[0121] Specifically, it achieves the final step in the transformation from data analysis to planning results. The output is not intermediate data or analysis charts, but formal planning documents that conform to industry standards and can be directly used for reporting, review, and subsequent in-depth design. This overcomes the format gap and information loss that often exist between technical analysis results and application implementation, ensuring that the depth and value of technical analysis can be completely and accurately conveyed to decision-makers and implementers, and improving the feasibility and practicality of research results.

[0122] S6. Monitor the effectiveness data of the climate adaptability facility deployment plan after its implementation.

[0123] S6.1 After the implementation of the climate adaptability facility deployment plan, collect multi-source behavioral feedback data and group movement positioning data under the same spatial range and meteorological conditions as effect monitoring data.

[0124] Furthermore, the core of effect monitoring lies in acquiring data that reflects the post-intervention state and is comparable to the pre-intervention diagnostic phase. Data collection should be conducted within the same spatial area, specifically within the persistent exposure hotspots and high-exposure movement corridors covered by the climate adaptation facility deployment plan. Crucially, data collection must be carried out under comparable meteorological conditions. This means selecting a period similar to the historical analysis period in terms of season, typical weather types, and macro-meteorological driving field to control for confounding effects from meteorological fluctuations. Multi-source behavioral feedback data and population movement location data should be collected again. Multi-source behavioral feedback data measures changes in the population's actual perceptions and behavioral responses after the facility's presence, while population movement location data observes whether the spatial distribution and movement patterns of the population have changed due to environmental improvements.

[0125] Specifically, a quasi-experimental observation framework with before-and-after comparisons and controlled variables was constructed. This overcomes the problems in traditional post-planning evaluations, where a single post-test is conducted and cannot be effectively attributed to the planning intervention itself, or where conclusions are unreliable due to inconsistent comparison benchmarks. Through standardized monitoring data collection, a solid, reliable, and causal inference potential data foundation can be provided for accurately assessing the actual effectiveness of facilities, verifying the accuracy of previous predictions, and optimizing subsequent models.

[0126] S7. Feedback is fed into the behavioral feedback-exposure intensity coupled model for adaptive parameter optimization.

[0127] S7.1 Based on effect monitoring data, measure and generate quantitative values ​​of exposure intensity in the corresponding areas after the implementation of the climate adaptability facility deployment plan.

[0128] Furthermore, this quantifies the changes in exposure resulting from the intervention. The effectiveness monitoring data includes post-intervention population movement and location data, along with climate comfort field data under comparable meteorological conditions for the corresponding period. Based on this data, a quantitative value for exposure intensity is generated. This means using the exact same standardized measurement rules as before the intervention, for the same spatial area, under comparable meteorological conditions, but in a new state after the intervention, to remeasure indicators such as the cumulative exposure duration and frequency of exposure to discomfort levels. This process generates a new quantitative value for exposure intensity that reflects the actual exposure level after the intervention. The potential reduction in this value directly reflects the degree of mitigation of physical climate risks.

[0129] Specifically, the core diagnostic indicator of exposure intensity quantification is also used as a unified metric for effect evaluation, enabling precise quantification of changes before and after intervention. This overcomes the problem of ambiguity in traditional effect evaluations caused by the separation of physical environment measurement and population exposure measurement or the use of inconsistent indicators. It provides key physical-side quantitative input for causal chain analysis from exposure change to behavioral feedback change.

[0130] S7.2. Correlate the quantitative values ​​of exposure intensity in the region after the implementation of the climate adaptability facility deployment plan with multi-source behavioral feedback data in the same region to form new sample pairs;

[0131] Furthermore, the quantitative value of exposure intensity in the area after the implementation of the climate adaptation facility deployment plan represents the new physical exposure level after the intervention, while the multi-source behavioral feedback data collected in the same area at the same time represents the actual behavioral response of the population in the new environment. Pairing these two data points spatiotemporally creates a new sample pair. This new sample pair has the same structure as the sample pair used to train the model before the intervention, both containing a quantitative value of exposure intensity and a multi-source behavioral feedback data value, reflecting the new state of urban space after human modification and the commissioning of facilities.

[0132] Specifically, each planning implementation is treated as a natural experiment, and its results—that is, the new exposure-feedback relationships after the intervention—are captured and recorded, becoming the latest data evidence reflecting the current real-world relationships. This overcomes the common problem of performance degradation of machine learning models due to environmental changes after deployment. By continuously collecting new sample pairs that reflect the latest reality, it makes it possible for the dynamic updating and adaptation of the model, ensuring that the model can learn and reflect the evolution of urban environment and human behavior caused by planning intervention.

[0133] S7.3. Use the new sample pairs as incremental training data and input them into the behavior feedback-exposure intensity coupling model. Use online updates to update the parameters of the behavior feedback-exposure intensity coupling model.

[0134] Furthermore, the new sample pairs represent the latest, validated exposure-behavior relationship data. These new sample pairs are used as incremental training data and input into the existing behavior feedback-exposure intensity coupling model. Online learning or incremental learning algorithms are then used to update the model parameters. Online updates mean that the model is not retrained with all the data, but rather its existing parameters are fine-tuned based on the new data. This allows the model to absorb new knowledge and adapt to new relationships without forgetting important historical patterns. After this update, the behavior feedback-exposure intensity coupling model internally learns the mapping relationship between exposure intensity and expected behavior feedback, incorporating the actual effects observed after the planned intervention. If the intervention effectively reduces actual exposure and changes behavior feedback, the updated model will be able to predict a lower expected behavior feedback intensity at a similarly reduced exposure level.

[0135] Specifically, it endows the entire evaluation system with the ability to learn from and evolve in practice, enabling the behavior feedback-exposure intensity coupling model to evolve synchronously with the continuous improvement of the city. Its predictions and assessments will become increasingly aligned with the latest realities, thereby providing a more accurate and reliable intelligent core for the next round of diagnosis, planning, and priority assessment, and realizing the intelligent and self-reinforcing process of improving the climate adaptability of the human settlement environment.

[0136] This embodiment also provides a computer device applicable to the human settlement climate comfort evaluation method based on multi-source data, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the human settlement climate comfort evaluation method based on multi-source data as proposed in the above embodiment.

[0137] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0138] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for evaluating the climate comfort of human settlements based on multi-source data as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0139] In summary, this invention forms a unified spatiotemporal data foundation by collecting and standardizing heterogeneous data from multiple sources, including meteorology, remote sensing, positioning, and urban morphology. Furthermore, by coupling urban three-dimensional morphology with underlying surface attributes into a microclimate physical model, the macro-meteorological field is refined into a dynamic comfort distribution map at the street level, combining static environmental assessment with dynamic population activity. By overlaying anonymous population movement data, hotspots and corridors where people are densely populated and continuously exposed to uncomfortable climates are accurately identified, and their exposure intensity is quantified. By introducing multi-source behavioral feedback data from consumption and social interactions, a behavioral feedback-exposure intensity coupling model that reflects real human feelings is constructed, thereby linking physical exposure with psychological perception and assessing the urgency of planning interventions.

[0140] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for evaluating the climate comfort of human settlements based on multi-source data, characterized in that: include, Collect and preprocess heterogeneous data to generate standardized multi-source data cubes; Based on standardized multi-source data cubes, a micro-scale climate comfort field of the city is obtained by integrating the microclimate simulation of urban three-dimensional building morphology and underlying surface properties. Dynamic spatiotemporal overlay analysis of urban microscale climate comfort field and anonymized group movement location data is performed to identify and quantify continuous exposure hotspots and high-exposure movement corridors. Based on the continuous exposure hotspots and high-exposure mobile corridors of the population, we conducted correlation analysis on multi-source behavioral feedback data, constructed a behavioral feedback-exposure intensity coupling model, and assessed the urgency level of planned interventions. Based on the urgency level of the planning intervention, a visual planning scheme for the deployment of climate-adaptive facilities is generated. The effectiveness data of the climate adaptation facility deployment plan after its implementation is monitored and fed back into the behavior feedback-exposure intensity coupled model for adaptive parameter optimization; Based on persistent exposure hotspots and high-exposure movement corridors, multi-source behavioral feedback data are correlated and analyzed to construct a behavioral feedback-exposure intensity coupling model. This model is used to assess the urgency level of planned interventions, including the following steps: For each group, based on the geographical boundaries of continuous exposure hotspots and high-exposure mobile corridors, acquire multi-source behavioral feedback data within the corresponding spatial range and time window; By using standardized measurement rules, corresponding exposure intensity quantification values ​​are generated for each identified group's continuous exposure hotspots and high-exposure mobile corridors. Through spatiotemporal matching, each exposure intensity quantification value is associated with multi-source behavioral feedback data within the corresponding spatial range to form sample pairs. A machine learning model is trained using sample pairs, with the exposure intensity quantification value as input, to predict the expected intensity of multi-source behavioral feedback data and obtain a behavioral feedback-exposure intensity coupled model. The actual multi-source behavioral feedback data of persistent exposure hotspots and high-exposure mobile corridors are compared with the predicted values ​​of the behavioral feedback-exposure intensity coupling model, and the urgency level of planning intervention is assessed based on the degree of deviation.

2. The method for evaluating the climate comfort of human settlements based on multi-source data as described in claim 1, characterized in that: Collecting and preprocessing heterogeneous data to generate a standardized multi-source data cube includes the following steps: Heterogeneous data is collected and then cleaned, coordinate and time unified, and spatiotemporally interpolated and fused to form a structured, standardized multi-source data cube.

3. The method for evaluating the climate comfort of human settlements based on multi-source data as described in claim 2, characterized in that: Based on standardized multi-source data cubes, a microclimate simulation integrating urban 3D building morphology and underlying surface properties is used to obtain an urban microscale climate comfort field, including the following steps: Meteorological driving fields, three-dimensional urban morphology parameters, and underlying surface physical property parameters are extracted from the standardized multi-source data cube and input into the urban microclimate model to perform dynamic correction and radiation redistribution. Based on grid-based energy balance calculation, the microscale meteorological element correction field is obtained. The physical parameters in the microscale meteorological element correction field are converted into grid effective temperature index values ​​for each spatial grid through a pre-defined effective temperature index attribute mapping rule. Based on the set standard threshold, the effective temperature index value of the grid is mapped to a comfort level label; By combining the effective temperature index value of the grid with the comfort level label, a microscale climate comfort field of the city is obtained.

4. The method for evaluating the climate comfort of human settlements based on multi-source data as described in claim 3, characterized in that: Dynamic spatiotemporal overlay analysis of urban microscale climate comfort fields and anonymized population movement location data is performed to identify and quantify persistent exposure hotspots and high-exposure movement corridors, including the following steps: On each time slice of the urban microscale climate comfort field, anonymized group movement and location data for the corresponding time period are overlaid. Based on the overlaid spatiotemporal matching data, the cumulative exposure duration and frequency of exposure to discomfort levels of the population in each geographic unit within a continuous time period are obtained. Based on the urban microscale climate comfort field and anonymized group movement location data, for each preset geographic grid unit, each time slice is traversed and it is determined whether the climate comfort level belongs to the preset set of discomfort levels. If it is, the product of the number of people in the geographic grid cell at the current time and the length of the time slice is included in the cumulative exposure time of the people in the geographic grid cell and counted as one uncomfortable event, so as to obtain the cumulative exposure time of the people in each geographic grid cell and the frequency of exposure to the uncomfortable level. Based on the cumulative exposure duration and frequency of exposure to discomfort levels, geographical units where people are clustered and continuously exposed to discomfort levels are identified, forming hotspots of continuous exposure to the population. Based on the superimposed spatiotemporal matching data, the continuous paths of crowd movement are analyzed, and movement trajectories that exceed the spatial unit and are at an uncomfortable level are identified, forming high-exposure movement corridors. For the identified persistent exposure hotspots and high-exposure mobile corridors, the total exposed population, average exposure duration, and exposure intensity index are quantified to form a list of persistent exposure hotspots and high-exposure mobile corridors with spatial range and quantitative attributes.

5. The method for evaluating the climate comfort of human settlements based on multi-source data as described in claim 1, characterized in that: Based on the urgency level of the planned intervention, a visualized climate adaptation facility deployment plan is generated, including the following steps: The urgency level of planning intervention is rendered on the map layer of the city geographic information system. In areas with a high urgency level of planning intervention, a preset library of climate adaptability facility types is matched. Based on the matching climate adaptability facility layout rules and spatial constraints, preliminary facility locations are automatically generated in areas with a high level of urgency for planning intervention. The preliminary climate adaptability facility deployment plan is quantified and its coverage relationship with the current exposure sites is mapped to the expected improvement in comfort level according to preset rules. By integrating the climate adaptability facility deployment schemes and expected benefit indicators based on simulation assessments, a visualized climate adaptability facility deployment planning scheme map and report is generated.

6. The method for evaluating the climate comfort of human settlements based on multi-source data as described in claim 5, characterized in that: Monitoring the effectiveness data of climate adaptability facility deployment plans after implementation includes the following steps: After the implementation of the climate adaptability facility deployment plan, multi-source behavioral feedback data and group movement and positioning data are collected under the same spatial range and meteorological conditions as effect monitoring data.

7. The method for evaluating the climate comfort of human settlements based on multi-source data as described in claim 6, characterized in that, The adaptive parameter optimization in the behavior feedback-exposure intensity coupled model includes the following steps: Based on the effect monitoring data, measure and generate quantitative values ​​of the exposure intensity of the corresponding area after the implementation of the climate adaptation facility deployment plan; The quantitative values ​​of exposure intensity in the region after the implementation of the climate adaptation facility deployment plan are correlated with multi-source behavioral feedback data in the same region to form new sample pairs; New sample pairs are used as incremental training data and input into the behavior feedback-exposure strength coupling model. The parameters of the behavior feedback-exposure strength coupling model are then updated online.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the human settlement climate comfort evaluation method based on multi-source data as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the human settlement climate comfort evaluation method based on multi-source data as described in any one of claims 1 to 7.

Images