A method, device and equipment for evaluating space thermal effect under heat exposure

Abstract

The application provides a method, device and equipment for evaluating spatial thermal effect under heat exposure, and relates to the technical field of geographic environment data processing. The method comprises the following steps: acquiring green infrastructure patches in a target region; performing spatial feature analysis on the green infrastructure patches to obtain a cooling supply index under different scenarios; acquiring population data and thermal environment data in the target region, obtaining a target model according to the population data and the thermal environment data, and obtaining population data with a second spatial resolution through the target model; obtaining a thermal risk index under different scenarios according to the population data with the second spatial resolution and surface temperature data; and evaluating the heat balance state of the target region according to the cooling supply index and the thermal risk index, identifying a spatial region of a target category, and obtaining a spatial thermal effect evaluation result. The scheme of the application evaluates the heat balance state of the target region, quantifies regional losses caused by high temperature, and provides targeted spatial reconstruction strategies.

Description

Technical Field

[0001] This invention relates to the field of geographic environmental data processing technology, and in particular to a method, apparatus and equipment for assessing spatial thermal effects under thermal exposure. Background Technology

[0002] The urban heat island effect is intensifying, posing a serious threat to public health and urban sustainability. Numerous empirical studies have elucidated the spatiotemporal dynamics of the urban heat island effect, primarily attributing its exacerbation to the expansion of impermeable surfaces and the concentration of anthropogenic heat emissions.

[0003] Although the physical mechanisms of the urban heat island effect are well documented, assessing its socioeconomic liabilities remains a complex challenge, particularly the assessment of lost labor productivity. Existing economic assessments of the urban heat island effect primarily rely on macroeconomic models or aggregated statistical data at the city level.

[0004] These economic loss assessment methods only provide broad statistics at a macro level. They fundamentally lack high-resolution spatial granularity and cannot conduct comprehensive economic loss assessments tailored to specific regions. This methodological disconnect hinders the precise identification of micro-vulnerabilities within macro-regions, thereby impeding the prioritization and implementation of economically feasible and site-specific adaptation strategies. It also fails to quantify the true economic impact of the urban heat island effect and obscures the true scale and spatial differentiation of urban heat inequality. Summary of the Invention

[0005] This invention provides a method, apparatus, and equipment for assessing the thermal effects of space under thermal exposure, which can evaluate the thermal balance of a target area, quantify the regional losses caused by high temperatures, and provide targeted space modification strategies.

[0006] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0007] A method for assessing the thermal effects of space under thermal exposure includes:

[0008] Identify green infrastructure patches within the target area by analyzing land cover data.

[0009] Spatial characteristic analysis was performed on the green infrastructure patches to obtain the cooling supply index within the target area under different scenarios;

[0010] Acquire population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, wherein the first spatial resolution is greater than the second spatial resolution;

[0011] A target model is obtained based on population data at the first spatial resolution and thermal environment data at the second spatial resolution, and population data at the second spatial resolution is obtained through the target model.

[0012] Based on the population data and surface temperature data at the second spatial resolution, the thermal risk index of the target area under different scenarios is obtained;

[0013] Based on the cooling supply index and thermal risk index within the target area, the heat balance status of the target area is assessed, and spatial areas of the target category are identified.

[0014] A spatial thermal effect assessment is performed on the spatial region of the target category to obtain the spatial thermal effect assessment results of the target category spatial region within the target region.

[0015] Optionally, spatial characteristic analysis is performed on the green infrastructure patches to obtain the cooling supply index within the target area under different scenarios, including:

[0016] Morphological spatial pattern analysis was performed on the green infrastructure patches to obtain the morphological spatial pattern analysis results.

[0017] Based on the morphological spatial pattern analysis results, at least three spatial characteristic indicators are extracted for each green infrastructure patch within the target area;

[0018] The at least three spatial feature indicators are normalized or dynamically assigned to obtain the spatial feature indicator data of each spatial feature indicator after normalization or assignment.

[0019] Multiply the spatial characteristic index data with a preset weighting coefficient to obtain the cooling supply index within the target area under different scenarios.

[0020] Optionally, a target model is obtained based on population data at the first spatial resolution and thermal environment data at the second spatial resolution. The population data at the second spatial resolution is obtained through the target model, including:

[0021] Logarithmic transformation is performed on the population data at the first spatial resolution to obtain training labels;

[0022] Based on the thermal environment data at the second spatial resolution, geospatial covariates at the second spatial resolution are obtained;

[0023] The geospatial covariates of the second spatial resolution are transformed by spatial mean or accumulation to obtain the geospatial covariates of the first spatial resolution.

[0024] The training feature set is obtained based on the geospatial covariates of the first spatial resolution;

[0025] The model is trained based on the training labels and training feature set to obtain the target model, which is a random forest model.

[0026] Geospatial covariates are extracted from the thermal environment data at the second spatial resolution, and the geospatial covariates are input into the target model to obtain population data at the second spatial resolution.

[0027] Optionally, based on the population data and surface temperature data at the second spatial resolution, a thermal risk index for the target area under different scenarios is obtained, including:

[0028] When the scenario is an employment scenario or a residential scenario, the population data at the second spatial resolution and the surface temperature data for the target time period corresponding to the scenario are multiplied together to obtain the thermal risk index of each pixel in the target area under the employment scenario or residential scenario.

[0029] When the scenario is a biophysical baseline scenario, the diurnal average surface temperature of each pixel in the target area is used as the thermal risk index of each pixel in the target area.

[0030] Optionally, based on the cooling supply index and thermal risk index within the target area, the heat balance state of the target area is assessed to identify spatial areas of the target category, including:

[0031] The cooling supply index and thermal risk index within the target area are respectively standardized to obtain standardized cooling supply index data and standardized thermal risk index data.

[0032] The standardized cooling supply index data and standardized thermal risk index data are classified according to a preset threshold range to obtain the cooling supply level and thermal risk level of each pixel.

[0033] Based on the cooling supply level and thermal risk level of each pixel, spatial regions of target categories within the target area are identified.

[0034] Optionally, a spatial thermal effect assessment is performed on the spatial region of the target category to obtain the spatial thermal effect assessment result of the target category spatial region within the target region, including:

[0035] Determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio;

[0036] Based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculations are performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios;

[0037] Based on the spatial transformation strategy and / or the regional loss results under different scenarios, the spatial thermal effect assessment results of the target category spatial region within the target region are obtained.

[0038] Optionally, determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio, including:

[0039] Based on the extreme surface temperature values ​​within the spatial region of the target category and the preset transformation ratio threshold, the dynamic transformation ratio of the spatial region of the target category is determined.

[0040] Based on the dynamic transformation ratio and the preset spatial transformation measures, the spatial areas of the target category are transformed to obtain a spatial transformation strategy.

[0041] Optionally, based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculations are performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios, including:

[0042] Calculate the ambient temperature based on the surface temperature data within the spatial area of ​​the target category;

[0043] The percentage decrease in labor productivity of the target category spatial region is calculated based on the ambient temperature, and the first region loss result of the target category spatial region under the employment scenario is calculated based on the percentage decrease in labor productivity and the population data of the second spatial resolution.

[0044] The percentage reduction in labor efficiency of the target category spatial area is obtained based on the surface temperature data within the target category spatial area.

[0045] The second regional loss result for the target category spatial region under the residential scenario is obtained based on the next day's labor efficiency reduction ratio and the population data with second spatial resolution.

[0046] The present invention also provides a space thermal effect assessment device under thermal exposure, comprising:

[0047] The acquisition module is used to identify land cover data of the target area and obtain green infrastructure patches within the target area;

[0048] The processing module is used to perform spatial feature analysis on the green infrastructure patches to obtain the cooling supply index of the target area under different scenarios; acquire population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, where the first spatial resolution is greater than the second spatial resolution; obtain a target model based on the population data at the first spatial resolution and the thermal environment data at the second spatial resolution, and obtain population data at the second spatial resolution through the target model; obtain the thermal risk index of the target area under different scenarios based on the population data at the second spatial resolution and the surface temperature data; assess the heat balance state of the target area based on the cooling supply index and the thermal risk index within the target area, and identify spatial areas of the target category; and conduct a spatial thermal effect assessment on the spatial areas of the target category to obtain the spatial thermal effect assessment results of the spatial areas of the target category within the target area.

[0049] The present invention also provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above.

[0050] The above-described solution of the present invention has at least the following beneficial effects:

[0051] The above-described solution of the present invention identifies green infrastructure patches within a target area by identifying land cover data; performs spatial feature analysis on these green infrastructure patches to obtain cooling supply indices for the target area under different scenarios; acquires population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, where the first spatial resolution is greater than the second spatial resolution; obtains a target model based on the first and second spatial resolution population data, and then obtains population data at a second spatial resolution using the target model; obtains thermal risk indices for the target area under different scenarios based on the second spatial resolution population data and surface temperature data; assesses the heat balance state of the target area based on the cooling supply index and thermal risk index, identifying target-category spatial areas; and evaluates the spatial thermal effects of the target-category spatial areas to obtain spatial thermal effect evaluation results for the target-category spatial areas within the target area. This allows for the assessment of the heat balance state of the target area, quantification of regional losses due to high temperatures, and the provision of targeted spatial transformation strategies. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the space thermal effect assessment method under thermal exposure according to an embodiment of the present invention.

[0053] Figure 2This is a schematic diagram of the modules of the space thermal effect assessment method under thermal exposure according to an embodiment of the present invention;

[0054] Figure 3 This is a structural diagram of the space thermal effect assessment device under thermal exposure according to an embodiment of the present invention. Detailed Implementation

[0055] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0056] like Figure 1 As shown, an embodiment of the present invention proposes a method for assessing the thermal effects of space under thermal exposure, comprising:

[0057] Step 11: Identify the land cover data of the target area to obtain green infrastructure patches within the target area;

[0058] Here, high-resolution land cover data of the target area is acquired, preferably 10-meter resolution land cover data. Green infrastructure patches are then identified and extracted.

[0059] Step 12: Perform spatial characteristic analysis on the green infrastructure patches to obtain the cooling supply index (SPI) within the target area under different scenarios;

[0060] Here, morphological spatial pattern analysis is performed on the extracted green infrastructure patches to extract spatial feature indicators. These indicators are then normalized according to preset scenarios to calculate the cooling supply index for each pixel within the target area under each scenario. It should be noted that this application divides the target area into multiple regularly arranged pixels, and various indicators within the target area are determined sequentially on a pixel-by-pixel basis. Three scenarios are preferred: an employment scenario, a residential scenario, and a biophysical baseline scenario. The employment scenario corresponds to high-density commercial office areas, the residential scenario to residential areas, and the biophysical baseline scenario to assess the potential of natural cooling capacity to alleviate surface high temperatures from a physical perspective, without considering short-term population movement, in order to ensure the structural stability and connectivity of the urban ecological network.

[0061] Step 13: Obtain population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, wherein the first spatial resolution is greater than the second spatial resolution;

[0062] Here, preferably, the first spatial resolution is 500 meters, and the second spatial resolution is 30 meters. The population data at the first spatial resolution is population data at a spatial resolution of 500 meters obtained based on mobile signaling data. The thermal environment data at the second spatial resolution is environmental data within the target area at a spatial resolution of 30 meters, characterizing the geospatial features of the target area.

[0063] Step 14: Obtain the target model based on the population data at the first spatial resolution and the thermal environment data at the second spatial resolution, and obtain the population data at the second spatial resolution through the target model;

[0064] Here, a target model, which is a random forest model, is trained using population data at a first spatial resolution and thermal environment data at a second spatial resolution. Feature vectors are extracted from the thermal environment data at the second spatial resolution within the target area to be predicted, and these feature vectors are input into the target model. The target model then predicts the population size and outputs the predicted population size at the second spatial resolution within the target area. The population prediction results output by the model are further corrected to obtain the final population data at the second spatial resolution within the target area.

[0065] Step 15: Based on the population data and surface temperature data at the second spatial resolution, obtain the thermal risk index (HRI) for the target area under different scenarios;

[0066] Here, surface temperature data of the target area is collected, and the exposure needs of the population are spatially aligned with the thermal environment conditions to obtain thermal risk indices under different scenarios.

[0067] Step 16: Based on the cooling supply index and thermal risk index within the target area, assess the heat balance status of the target area and identify the spatial area of ​​the target category.

[0068] Here, the planning efficiency index is calculated using the difference between the standardized cooling supply index and the population's heat risk exposure demand (i.e., the heat risk index) to assess the heat supply and demand balance in the target area and evaluate the heat balance status of the target area. Furthermore, based on the corresponding levels of the standardized cooling supply index and the heat risk index, the areas corresponding to each pixel within the target area are spatially classified to identify spatial areas of the target category. Preferably, the target category is a "severe deficit area," that is, areas within the target area that have a severe heat exposure risk are identified.

[0069] Step 17: Perform a spatial thermal effect assessment on the spatial region of the target category to obtain the spatial thermal effect assessment results of the target category spatial region within the target region.

[0070] Here, the spatial thermal effect assessment includes two aspects. Firstly, it involves spatial transformation of areas within the target region classified as severely deficit areas to balance heat supply and demand and mitigate the adverse effects caused by severe high temperatures. Secondly, it quantifies the economic losses caused by high temperatures and represents these losses in monetary terms.

[0071] In this embodiment, to systematically assess the spatiotemporal mismatch of urban high temperatures and their socioeconomic consequences, the following approach is adopted: Figure 2 The comprehensive framework shown.

[0072] First, the cooling capacity of green infrastructure is quantified using a cooling supply index. Second, a human thermal exposure map is created using a heat risk index based on population movement. Third, a planning efficiency index is constructed to spatially couple supply and demand, and the indicators are categorized to accurately pinpoint areas of structural heat deficits. Finally, an explicit spatial economic assessment is conducted within the identified deficit areas to monetize diurnal productivity losses and evaluate the ROI of targeted adaptation strategies.

[0073] In an optional embodiment of the present invention, step 12, performing spatial characteristic analysis on the green infrastructure patches to obtain the cooling supply index within the target area under different scenarios, may include:

[0074] Step 121: Perform morphological spatial pattern analysis on the green infrastructure patches to obtain the morphological spatial pattern analysis results;

[0075] Here, the morphological spatial pattern analysis is an image processing method based on mathematical morphology. It reveals the distribution characteristics, interrelationships, and evolutionary patterns of spatial elements (such as buildings, roads, and green spaces) within a specific area through quantitative and qualitative methods. It is used to identify and classify the spatial structure types of landscapes from raster data such as land use. The results of the morphological spatial pattern analysis divide the foreground (such as woodland, wetlands, and grasslands) into seven non-overlapping landscape types, each with a clear ecological meaning, for example:

[0076] Core area: Large-area natural patches with high internal connectivity;

[0077] Bridging Zone: A narrow strip of land connecting two or more core zones, serving as a corridor.

[0078] Peripheral zone: The transition zone between the core area and the background (such as construction land), characterized by high ecological heterogeneity;

[0079] Isolated area: A small, isolated foreground patch that is not connected to any core area;

[0080] Porous areas: The background "voids" within the core area reflect the degree of landscape fragmentation;

[0081] Branch area: Only one end is connected to other foreground types (such as bridges or edges), and the structure is incomplete;

[0082] Ring road area: A closed passageway surrounding the same core area.

[0083] Step 122: Based on the morphological spatial pattern analysis results, extract at least three spatial characteristic indicators for each green infrastructure patch within the target area;

[0084] Here, urban green spaces are structurally deconstructed based on morphological spatial pattern analysis results, and spatial characteristic indicators of green infrastructure patches are extracted. Preferably, three spatial characteristic indicators are selected. A multidimensional evaluation system for the cooling supply index is constructed based on these spatial characteristic indicators. These spatial characteristic indicators include: patch area, shape index, and connectivity.

[0085] Among them, the patch area index is obtained by directly extracting the "core area" category from the morphological spatial pattern analysis results, thereby quantifying the scale of the ecological source area with a stable cooling microclimate, representing the scale of the cold source.

[0086] The shape index focuses on the geometric composition of the core area and the "edge" or "pores," and implements differentiated treatment according to the planning scenario. In the employment scenario, compact and regular patches are given priority to improve cooling efficiency, while in the residential scenario, complex boundaries are encouraged through negative normalization. The "edge effect" with high fractal dimension is used to maximize the accessibility of cooling services, thereby representing the complexity of the cold source.

[0087] The connectivity index is based on the topological logical relationship in the morphological spatial pattern analysis results. It dynamically assigns weights to ecological corridors such as "bridging zones" and "branch lines" to evaluate the transmission continuity and structural stability of cold air in the spatial network, thereby representing the structural continuity of the cold source.

[0088] The aforementioned spatial characteristic indicators enable the quantitative transformation from the physical form of green spaces to the cooling supply capacity across multiple scenarios.

[0089] Step 123: Perform corresponding normalization processing or dynamic assignment on the at least three spatial feature indicators to obtain the spatial feature indicator data of each spatial feature indicator after normalization or assignment.

[0090] Here, spatial characteristic indicators are customized to suit different planning priorities for different scenarios. The planning priorities refer to the preferred land use objectives for different scenarios. For example, in an employment scenario, the planning priorities are "land use efficiency" and "compactness." In high-density commercial office areas, land resources are extremely scarce and development intensity is high; therefore, planning in this scenario prioritizes green space patches with regular boundaries and compact forms. This compact form is considered to better integrate into the spatial layout of the business district, achieving a balance between cooling and efficient land use.

[0091] For residential scenarios, the planning priorities are "resident accessibility" and "quality of interaction." In residential areas, the planning goal is to make it easier for residents to access green spaces. Therefore, this scenario prioritizes patches with complex boundaries (high fractal dimension), as complex edges can generate a stronger "edge effect," increasing residents' opportunities to interact with green landscapes and promoting recreational and social interaction.

[0092] For the biophysical baseline scenario, the planning priorities are "ecological network stability" and "connectivity." This scenario is independent of human activities and assesses cooling capacity purely from a landscape ecology perspective. Its planning focus is on protecting the "core area" and "bridging area," which serve as the core support for ecological corridors, to ensure the structural continuity and stability of the cold island landscape.

[0093] Based on the planning priorities outlined above, for the shape index, positive normalization is applied in the employment scenario. The aim is to prioritize regular, compact patch boundaries, which aligns with the land use efficiency requirements of high-density commercial areas. In the residential and biophysical baseline scenarios, negative normalization is applied. This is because complex boundaries with high fractal dimensions are considered to maximize the "edge effect," thereby enhancing residents' contact opportunities and ecological interaction.

[0094] For connectivity indicators, a uniform metric is not used; instead, dynamic values ​​are assigned based on the categories identified by morphological spatial pattern analysis (e.g., core area, bridging area, isolated area). The biophysical baseline scenario assigns the highest scores to the "core area" and "bridging area" to ensure the stability of the ecological network. For employment and residential scenarios, the weighting is adjusted to prioritize the accessibility of cooling resources and resistance to fragmentation, respectively.

[0095] Step 124: Multiply the spatial characteristic index data with a preset weighting coefficient to obtain the cooling supply index within the target area under different scenarios.

[0096] Here, the formula for the cooling supply index is: ,in, The cooling supply index under scenario k, For the normalized patch area index data, The preset weighting coefficients for the patch area index under scenario k. The shape index data after being processed by the corresponding normalization strategy, The preset weighting coefficients for the shape index under scenario k. For the connectivity index data after assignment, represents the preset weighting coefficients for the connectivity index under scenario k.

[0097] In an optional embodiment of the present invention, step 14, obtaining a target model based on population data at the first spatial resolution and thermal environment data at the second spatial resolution, and obtaining population data at the second spatial resolution through the target model, may include:

[0098] Step 141: Perform logarithmic transformation on the population data at the first spatial resolution to obtain training labels;

[0099] Here, we acquire mobile signaling data of the target area at the first spatial resolution (e.g., 500-meter grid), extract the population base of "main workplace" or "residence", and perform logarithmic transformation on it to generate training labels in order to eliminate systematic errors caused by the spatial distribution skewness of the population.

[0100] Step 142: Based on the thermal environment data at the second spatial resolution, obtain the geospatial covariates at the second spatial resolution;

[0101] Here, the geospatial covariates include:

[0102] Morphological characteristics, using building density within a grid;

[0103] Traffic network characteristics, using road network density and Euclidean distance to major roads;

[0104] Location characteristics, using Euclidean distance to the central business district;

[0105] Social functional characteristics, based on the density of interest points for residential, employment, commercial and recreational categories extracted by kernel density estimation.

[0106] Step 143: The geospatial covariates of the second spatial resolution are transformed by spatial mean or accumulation to obtain the geospatial covariates of the first spatial resolution.

[0107] Here, the geospatial covariates obtained at the second spatial resolution (30 meters) are aggregated to the first spatial resolution (500 meters) scale by means of spatial mean or summation, forming a training feature set containing multiple dimensions.

[0108] Step 144: Obtain the training feature set based on the geospatial covariates of the first spatial resolution;

[0109] Step 145: Train the model based on the training labels and training feature set to obtain the target model, which is a random forest model;

[0110] Here, the random forest model is trained using the constructed training feature set and training label dataset. To ensure model robustness, a 10-fold cross-validation mechanism is used to dynamically adjust the hyperparameters until the model's fitting accuracy in cross-validation is achieved. The target model achieves a preset threshold (e.g., an accuracy of 0.6127 for the residential scenario model and 0.6809 for the employment scenario model). The target model comprises 200 decision trees, and a random seed (random_state=42) is used during training to ensure the repeatability of the results. Multi-core parallel computing (n_jobs=-1) is employed to improve the processing efficiency of large-scale grid data.

[0111] Step 146: Extract geospatial covariates from the thermal environment data at the second spatial resolution, and input the geospatial covariates into the target model to obtain population data at the second spatial resolution.

[0112] Here, the geospatial covariates at a second spatial resolution (30 meters) are input into the trained target model, and the model outputs the corresponding logarithmic population prediction. Subsequently, the prediction is transformed back to the true population scale by performing an inverse logarithmic transformation using an exponential function.

[0113] Furthermore, to eliminate the systematic bias introduced during the inverse logarithmic transform, a mass conservation correction factor is used to globally scale the population values ​​of the second spatial resolution grid after the inverse transform, ensuring that the downscaled population data remains consistent with the original signaling records in terms of regional totals. The calibration coefficient is: Residential Population Calibration Coefficient. Employment population calibration coefficient The logarithmically transformed population predictions output by the target model are multiplied by a calibration coefficient to obtain the final population data. This calibration coefficient is obtained by recording the ratio of the actual total population in the mobile signaling data at the first spatial resolution (e.g., a 500-meter grid) to the sum of all pixel-level population predictions within the study area before calibration, as output by the target model, during training. For example, in a residential scenario, the actual total population in the mobile signaling data is 2,834,880, while the sum of the uncalibrated target model predictions is 1,824,542. Therefore, the final population data is obtained... For the employment scenario, the corresponding values ​​are 3,048,065 and 2,051,732, respectively, from which we can derive... Multiplying the logarithmically transformed population predictions from the target model by a calibration coefficient ensures that the decomposed population surface can be globally integrated into the original total signal, while preserving the relative spatial heterogeneity learned by the target model.

[0114] In an optional embodiment of the present invention, step 15, obtaining the thermal risk index of the target area under different scenarios based on the population data and surface temperature data at the second spatial resolution, may include:

[0115] Step 151: When the scenario is an employment scenario or a residential scenario, multiply the population data of the second spatial resolution with the surface temperature data of the target time period corresponding to the scenario to obtain the thermal risk index of each pixel in the target area under the employment scenario or residential scenario.

[0116] Step 152: When the scenario is a biophysical baseline scenario, the diurnal average surface temperature of each pixel in the target area is used as the thermal risk index of each pixel in the target area.

[0117] In this embodiment, ,

[0118] in, For the heat risk index of pixels in scenario k, Population data with second spatial resolution in scenario k This refers to the surface temperature data for the target time period corresponding to scenario k. For example, the employment scenario corresponds to daytime surface temperature, and the residential scenario corresponds to nighttime surface temperature. The diurnal average surface temperature is the target pixel. For the biophysical baseline scenario, the aim is to assess the intrinsic physical thermal conditions independent of population distribution, therefore the requirement is defined solely by the diurnal average surface temperature.

[0119] In an optional embodiment of the present invention, step 16, assessing the heat balance state of the target area based on the cooling supply index and heat risk index within the target area, and identifying the spatial area of ​​the target category, may include:

[0120] Step 161: Perform data standardization processing on the cooling supply index and thermal risk index within the target area to obtain standardized cooling supply index data and standardized thermal risk index data.

[0121] Here, because the physical units and numerical magnitudes of the cooling supply index and the heat risk index are completely different, they cannot be calculated directly. Therefore, through standard score standardization, the two spatial raster layers of the cooling supply index and the heat risk index are converted into dimensionless standard normal distribution data with a mean of 0 and a standard deviation of 1. Based on the difference between the standardized cooling supply index data and the standardized heat risk index data, the planning efficiency index of each pixel in the target area is obtained.

[0122] Here, through the formula Calculate the planning efficiency index, where, For the planning efficiency index under scenario k, Provide standardized cooling supply index data for scenario k. This provides standardized thermal risk index data under scenario k. The efficiency index is then used for planning. This represents the spatial balance difference between cooling supply and thermal risk demand within the target grid. To spatially represent this supply-demand balance, a bivariate classification scheme with a fixed threshold can be used to identify the spatial regions of target categories within the target area. The threshold range is set to Z. [-0.5, 0.5].

[0123] Step 162: Classify the standardized cooling supply index data and standardized thermal risk index data according to a preset threshold range to obtain the cooling supply level and thermal risk level of each pixel.

[0124] Step 163: Identify the spatial region of the target category within the target area based on the cooling supply level and thermal risk level of each pixel.

[0125] Set preset threshold range A bivariate classification scheme based on a fixed threshold is used to ensure that regardless of the skewness of the data, All pixels will be absolutely and strictly classified into the "low" category. Based on the preset threshold range, the standardized cooling supply index data will be... and standardized thermal risk index data They are divided into three levels: "low", "medium", and "high".

[0126] Low: Z < -0.5;

[0127] In the case of -0.5 ≤ Z ≤ 0.5;

[0128] Height: Z > 0.5;

[0129] Based on the cross-combination (3×3) of the above 3 cooling supply levels and 3 thermal risk levels, each pixel in the target area will be strictly determined to be one of the following 9 spatial classification results:

[0130] Category 0: Low-level equilibrium zone, judgment criteria: and (Low supply, low demand);

[0131] Category 1: Low supply, medium demand zone; Criteria for determination: and (Low supply, medium demand);

[0132] Category 2: Severe Deficit Area, Criteria for Judgment: and (Low supply, high demand);

[0133] Category 3: Medium supply and low demand area, determination criteria: and (Medium supply, low demand);

[0134] Category 4: Medium Matching Zone, Judgment Criteria: and (Medium supply, medium demand);

[0135] Category 5: Medium-supply, high-demand region; criteria for determination: and (Medium supply, high demand);

[0136] Category 6: Ecological Surplus Zone, Determination Criteria: and (High supply, low demand);

[0137] Category 7: High supply and medium demand zone, criterion: and (High supply, medium demand);

[0138] Category 8: Highly Matching Region, Judgment Criteria: and (High supply, high demand).

[0139] Preferably, the spatial region of the above-mentioned "Category 2, Severe Deficit Area" is determined as the target category.

[0140] In an optional embodiment of the present invention, step 17, which involves evaluating the spatial thermal effect of the target category's spatial region to obtain the evaluation result of the spatial thermal effect of the target category's spatial region within the target region, may include:

[0141] Step 171: Determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio;

[0142] Here, the cost-effectiveness of mitigating residual heat risks in identified areas of severe deficit is quantified by simulating spatially targeted engineering modification strategies (such as cold roofs) and estimating costs.

[0143] Step 172: Based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculation is performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios.

[0144] Here, we conduct monetization assessments of daytime productivity losses and nighttime implicit costs related to regional losses caused by severe heat exposure. We quantify the direct economic impact of daytime heat exposure on the working population to estimate heat stress-induced labor productivity losses within target spatial areas. We also quantify the indirect economic impact of severe heat exposure, focusing on the productivity decline caused by nighttime heat stress. Unlike daytime high temperatures that directly affect physical labor, nighttime heat primarily impacts productivity the following day by impairing sleep quality and thus leading to cognitive fatigue.

[0145] Step 173: Obtain the spatial thermal effect assessment result of the target category spatial region within the target region based on the spatial modification strategy and / or the regional loss result. That is, the spatial modification strategy can be used as the spatial thermal effect assessment result, or the regional loss result can be used as the spatial thermal effect assessment result, or both the spatial modification strategy and the regional loss result can be used as the spatial thermal effect assessment result.

[0146] In an optional embodiment of the present invention, step 171, determining the dynamic modification ratio of the spatial region of the target category, and determining a spatial modification strategy for the spatial region of the target category based on the dynamic modification ratio, may include:

[0147] Step 1711: Determine the dynamic transformation ratio of the spatial area of ​​the target category based on the extreme surface temperature value within the spatial area of ​​the target category and the preset transformation ratio threshold.

[0148] The dynamic transformation ratio is: ,in, For the dynamic modification ratio of pixel i, The preset minimum modification ratio threshold, The preset maximum modification ratio threshold, For the surface temperature of pixel i, The minimum surface temperature value within the spatial region of the target category. The maximum surface temperature value within the spatial region of the target category.

[0149] Step 1712: Modify the spatial area of ​​the target category according to the dynamic modification ratio and the preset spatial modification measures to obtain the spatial modification strategy.

[0150] The spatial transformation measure is "converting the roof into a cold roof." Buildings within the target category's spatial area are transformed according to a dynamic transformation ratio. Furthermore, the pixel-level investment cost of implementing the spatial transformation strategy is calculated: ,in, For the engineering renovation investment cost of pixel i, For pixel area, The cost per unit area for renovation is set, for example, the unit cost of high-reflectivity coating is set at 60.0 yuan / m². 2 Furthermore, the investment payback period is calculated based on the aforementioned engineering renovation investment cost. ,in, For the investment payback period of pixel i, The recurring economic losses that can be avoided annually through redevelopment of a single pixel, stemming from the second-zone loss outcomes under residential scenarios. .

[0151] In an optional embodiment of the present invention, step 172, based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, performs loss calculations according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios, which may include:

[0152] Step 1721: Calculate the ambient temperature based on the surface temperature data within the spatial region of the target category;

[0153] Here, the surface temperature (LST) is converted to ambient air temperature, which directly affects labor productivity. The regression slope of summer daytime surface temperature on air temperature is determined to be 0.0955. When the ambient air temperature reaches the occupational heat stress threshold of 31°C, the corresponding surface temperature (LST) in high-density urban areas is approximately 35°C. Conversion formula:

[0154]

[0155] in, For the ambient temperature of pixel i, 31 represents the daytime surface temperature of pixel i, 31 represents the set critical temperature threshold for occupational heat stress, 35 represents the average surface temperature baseline value corresponding to the critical temperature in a high-density urban environment, and 0.0955 represents the empirical regression slope of surface temperature on ambient temperature, which reflects the degree of attenuation of heat transfer from the heated surface to the near-surface air.

[0156] Step 1722: Calculate the percentage decrease in labor productivity of the spatial region of the target category based on the ambient temperature, and calculate the first regional loss result of the spatial region of the target category under the employment scenario based on the percentage decrease in labor productivity and the population data of the second spatial resolution. The first regional loss result is the regional economic loss result.

[0157]

[0158] in, Let be the percentage decrease in labor productivity for pixel i, and 0.02 be the marginal loss coefficient, meaning that for every 1°C increase in temperature above the comfort threshold, work efficiency decreases by 2%.

[0159]

[0160] in, For the loss results in the first region, The number of working people during the daytime within pixel i at the second spatial resolution. Economic value per unit of time, such as average hourly wage. For effective daytime heat exposure duration, The total number of days for summer assessment.

[0161] Step 1723: Obtain the next-day labor efficiency reduction ratio of the spatial region of the target category based on the surface temperature data within the spatial region of the target category;

[0162]

[0163] in, The percentage reduction in the next day's labor productivity of pixel i The coefficient for sleep-related productivity decline is derived by coupling the sensitivity of labor efficiency to temperature with the regression slope of nighttime temperature, and its value is 0.002. For the nighttime surface temperature of pixel i, This represents the critical surface temperature threshold for heat-induced sleep disorders.

[0164] Step 1724: Based on the next day's labor efficiency reduction ratio and the population data with second spatial resolution, obtain the second regional loss result of the target category spatial region under the residential scenario. The second regional loss result is the regional economic loss result.

[0165]

[0166] in, For the loss results in the second region, Let i be the number of nighttime residents within the second spatial resolution of pixel i.

[0167] The embodiments of this invention couple a spatial morphology-based supply index with a population flow-based thermal risk index to construct a planning efficiency index, thereby accurately identifying "heat crisis zones" characterized by diurnal heat deficits in space. By integrating remote sensing inversion, human flow data, and local labor productivity loss functions, the limitations of traditional heat exposure loss assessments are overcome. Through comparative analysis of biophysical benchmarks, daytime employment, and nighttime residential scenarios, not only are the implicit economic costs of urban heat exposure quantified, but also a rigorous cost-benefit basis is provided for targeted engineering adaptation strategies.

[0168] like Figure 3 As shown, embodiments of the present invention also provide a space thermal effect assessment device 30 under thermal exposure, comprising:

[0169] The acquisition module 31 is used to identify land cover data of the target area and obtain green infrastructure patches within the target area;

[0170] Processing module 32 is used to perform spatial feature analysis on the green infrastructure patches to obtain the cooling supply index of the target area under different scenarios; acquire population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, where the first spatial resolution is greater than the second spatial resolution; obtain a target model based on the population data at the first spatial resolution and the thermal environment data at the second spatial resolution, and obtain population data at the second spatial resolution through the target model; obtain the thermal risk index of the target area under different scenarios based on the population data at the second spatial resolution and the surface temperature data; assess the heat balance state of the target area based on the cooling supply index and the thermal risk index within the target area, and identify spatial areas of the target category; and conduct a spatial thermal effect assessment on the spatial areas of the target category to obtain the spatial thermal effect assessment results of the spatial areas of the target category within the target area.

[0171] Optionally, spatial characteristic analysis is performed on the green infrastructure patches to obtain the cooling supply index within the target area under different scenarios, including:

[0172] Morphological spatial pattern analysis was performed on the green infrastructure patches to obtain the morphological spatial pattern analysis results.

[0173] Based on the morphological spatial pattern analysis results, at least three spatial characteristic indicators are extracted for each green infrastructure patch within the target area;

[0174] The at least three spatial feature indicators are normalized or dynamically assigned to obtain the spatial feature indicator data of each spatial feature indicator after normalization or assignment.

[0175] Multiply the spatial characteristic index data with a preset weighting coefficient to obtain the cooling supply index within the target area under different scenarios.

[0176] Optionally, a target model is obtained based on population data at the first spatial resolution and thermal environment data at the second spatial resolution. The population data at the second spatial resolution is obtained through the target model, including:

[0177] Logarithmic transformation is performed on the population data at the first spatial resolution to obtain training labels;

[0178] Based on the thermal environment data at the second spatial resolution, geospatial covariates at the second spatial resolution are obtained;

[0179] The geospatial covariates of the second spatial resolution are transformed by spatial mean or accumulation to obtain the geospatial covariates of the first spatial resolution.

[0180] The training feature set is obtained based on the geospatial covariates of the first spatial resolution;

[0181] The model is trained based on the training labels and training feature set to obtain the target model, which is a random forest model.

[0182] Geospatial covariates are extracted from the thermal environment data at the second spatial resolution, and the geospatial covariates are input into the target model to obtain population data at the second spatial resolution.

[0183] Optionally, based on the population data and surface temperature data at the second spatial resolution, a thermal risk index for the target area under different scenarios is obtained, including:

[0184] When the scenario is an employment scenario or a residential scenario, the population data at the second spatial resolution and the surface temperature data for the target time period corresponding to the scenario are multiplied together to obtain the thermal risk index of each pixel in the target area under the employment scenario or residential scenario.

[0185] When the scenario is a biophysical baseline scenario, the diurnal average surface temperature of each pixel in the target area is used as the thermal risk index of each pixel in the target area.

[0186] Optionally, based on the cooling supply index and thermal risk index within the target area, the heat balance state of the target area is assessed to identify spatial areas of the target category, including:

[0187] The cooling supply index and thermal risk index within the target area are respectively standardized to obtain standardized cooling supply index data and standardized thermal risk index data.

[0188] The standardized cooling supply index data and standardized thermal risk index data are classified according to a preset threshold range to obtain the cooling supply level and thermal risk level of each pixel.

[0189] Based on the cooling supply level and thermal risk level of each pixel, spatial regions of target categories within the target area are identified.

[0190] Optionally, a spatial thermal effect assessment is performed on the spatial region of the target category to obtain the spatial thermal effect assessment result of the target category spatial region within the target region, including:

[0191] Determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio;

[0192] Based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculations are performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios;

[0193] Based on the spatial transformation strategy and / or regional loss results, the spatial thermal effect assessment results of the target category spatial region within the target region are obtained.

[0194] Optionally, determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio, including:

[0195] Based on the extreme surface temperature values ​​within the spatial region of the target category and the preset transformation ratio threshold, the dynamic transformation ratio of the spatial region of the target category is determined.

[0196] Based on the dynamic transformation ratio and the preset spatial transformation measures, the spatial areas of the target category are transformed to obtain a spatial transformation strategy.

[0197] Optionally, based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculations are performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios, including:

[0198] Calculate the ambient temperature based on the surface temperature data within the spatial area of ​​the target category;

[0199] The percentage decrease in labor productivity of the target category spatial region is calculated based on the ambient temperature, and the first region loss result of the target category spatial region under the employment scenario is calculated based on the percentage decrease in labor productivity and the population data of the second spatial resolution.

[0200] The percentage reduction in labor efficiency of the target category spatial area is obtained based on the surface temperature data within the target category spatial area.

[0201] The second regional loss result for the target category spatial region under the residential scenario is obtained based on the next day's labor efficiency reduction ratio and the population data with second spatial resolution.

[0202] It should be noted that this device is the same as the method described above. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0203] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0204] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0205] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0206] In the embodiments provided by this invention, 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 units 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 devices or units may be electrical, mechanical, or other forms.

[0207] The units described 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.

[0208] In addition, the functional units in the various embodiments of the present invention 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.

[0209] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion 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 several 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 described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0210] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0211] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0212] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for assessing the thermal effects of space under thermal exposure, characterized in that, include: Identify green infrastructure patches within the target area by analyzing land cover data. Spatial characteristic analysis was performed on the green infrastructure patches to obtain the cooling supply index within the target area under different scenarios; Acquire population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, wherein the first spatial resolution is greater than the second spatial resolution; A target model is obtained based on population data at the first spatial resolution and thermal environment data at the second spatial resolution, and population data at the second spatial resolution is obtained through the target model. Based on the population data and surface temperature data at the second spatial resolution, the thermal risk index of the target area under different scenarios is obtained; Based on the cooling supply index and thermal risk index within the target area, the heat balance status of the target area is assessed, and spatial areas of the target category are identified. A spatial thermal effect assessment is performed on the spatial region of the target category to obtain the spatial thermal effect assessment results of the target category spatial region within the target region. Specifically, spatial characteristic analysis of the green infrastructure patches yields cooling supply indices within the target area under different scenarios, including: Morphological spatial pattern analysis was performed on the green infrastructure patches to obtain the morphological spatial pattern analysis results. Based on the morphological spatial pattern analysis results, at least three spatial characteristic indicators are extracted for each green infrastructure patch within the target area; The at least three spatial feature indicators are normalized or dynamically assigned to obtain the spatial feature indicator data of each spatial feature indicator after normalization or assignment. Multiply the spatial characteristic index data by a preset weighting coefficient to obtain the cooling supply index within the target area under different scenarios; The process of obtaining a target model based on population data at the first spatial resolution and thermal environment data at the second spatial resolution, and obtaining population data at the second spatial resolution through the target model, includes: Logarithmic transformation is performed on the population data at the first spatial resolution to obtain training labels; Based on the thermal environment data at the second spatial resolution, geospatial covariates at the second spatial resolution are obtained; The geospatial covariates of the second spatial resolution are transformed by spatial mean or accumulation to obtain the geospatial covariates of the first spatial resolution. The training feature set is obtained based on the geospatial covariates of the first spatial resolution; The model is trained based on the training labels and training feature set to obtain the target model, which is a random forest model. Geospatial covariates are extracted from the thermal environment data at the second spatial resolution, and the geospatial covariates are input into the target model to obtain population data at the second spatial resolution. Among them, based on the population data and surface temperature data of the second spatial resolution, the thermal risk index of the target area under different scenarios is obtained, including: When the scenario is an employment scenario or a residential scenario, the population data at the second spatial resolution and the surface temperature data for the target time period corresponding to the scenario are multiplied together to obtain the thermal risk index of each pixel in the target area under the employment scenario or residential scenario. When the scenario is a biophysical baseline scenario, the diurnal average surface temperature of each pixel in the target area is used as the thermal risk index of each pixel in the target area.

2. The method for assessing the thermal effects of space under thermal exposure according to claim 1, characterized in that, Based on the cooling supply index and thermal risk index within the target area, the heat balance status of the target area is assessed, and spatial areas of the target category are identified, including: The cooling supply index and thermal risk index within the target area are respectively standardized to obtain standardized cooling supply index data and standardized thermal risk index data. The standardized cooling supply index data and standardized thermal risk index data are classified according to a preset threshold range to obtain the cooling supply level and thermal risk level of each pixel. Based on the cooling supply level and thermal risk level of each pixel, spatial regions of target categories within the target area are identified.

3. The method for assessing the thermal effects of space under thermal exposure according to claim 1, characterized in that, A spatial thermal effect assessment is performed on the spatial region of the target category to obtain the spatial thermal effect assessment results of the target category spatial region within the target region, including: Determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio; Based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculations are performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios; Based on the spatial transformation strategy and / or the regional loss results under different scenarios, the spatial thermal effect assessment results of the target category spatial region within the target region are obtained.

4. The method for assessing the thermal effects of space under thermal exposure according to claim 3, characterized in that, Determine the dynamic transformation ratio of the spatial area of ​​the target category, and determine the spatial transformation strategy for the spatial area of ​​the target category based on the dynamic transformation ratio, including: Based on the extreme surface temperature values ​​within the spatial region of the target category and the preset transformation ratio threshold, the dynamic transformation ratio of the spatial region of the target category is determined. Based on the dynamic transformation ratio and the preset spatial transformation measures, the spatial areas of the target category are transformed to obtain a spatial transformation strategy.

5. The method for assessing the thermal effects of space under thermal exposure according to claim 3, characterized in that, Based on the surface temperature data and second spatial resolution population data of the spatial region of the target category, loss calculations are performed according to different scenarios to obtain the regional loss results of the spatial region of the target category under different scenarios, including: Calculate the ambient temperature based on the surface temperature data within the spatial area of ​​the target category; The percentage decrease in labor productivity of the target category spatial region is calculated based on the ambient temperature, and the first region loss result of the target category spatial region under the employment scenario is calculated based on the percentage decrease in labor productivity and the population data of the second spatial resolution. The percentage reduction in labor efficiency of the target category spatial area is obtained based on the surface temperature data within the target category spatial area. The second regional loss result for the target category spatial region under the residential scenario is obtained based on the next day's labor efficiency reduction ratio and the population data with second spatial resolution.

6. A device for assessing the thermal effects of space under thermal exposure, characterized in that, include: The acquisition module is used to identify land cover data of the target area and obtain green infrastructure patches within the target area; The processing module is used to perform spatial feature analysis on the green infrastructure patches to obtain the cooling supply index in the target area under different scenarios. Acquire population data at a first spatial resolution and thermal environment data at a second spatial resolution within the target area, where the first spatial resolution is greater than the second spatial resolution; obtain a target model based on the population data at the first spatial resolution and the thermal environment data at the second spatial resolution, and obtain population data at the second spatial resolution through the target model; obtain a thermal risk index within the target area under different scenarios based on the population data at the second spatial resolution and surface temperature data; assess the heat balance state of the target area based on the cooling supply index and thermal risk index within the target area, and identify spatial areas of the target category; A spatial thermal effect assessment is performed on the spatial region of the target category to obtain the spatial thermal effect assessment results of the target category spatial region within the target region. Specifically, spatial characteristic analysis of the green infrastructure patches yields cooling supply indices within the target area under different scenarios, including: Morphological spatial pattern analysis was performed on the green infrastructure patches to obtain the morphological spatial pattern analysis results. Based on the morphological spatial pattern analysis results, at least three spatial characteristic indicators are extracted for each green infrastructure patch within the target area; The at least three spatial feature indicators are normalized or dynamically assigned to obtain the spatial feature indicator data of each spatial feature indicator after normalization or assignment. Multiply the spatial characteristic index data by a preset weighting coefficient to obtain the cooling supply index within the target area under different scenarios; The process of obtaining a target model based on population data at the first spatial resolution and thermal environment data at the second spatial resolution, and obtaining population data at the second spatial resolution through the target model, includes: Logarithmic transformation is performed on the population data at the first spatial resolution to obtain training labels; Based on the thermal environment data at the second spatial resolution, geospatial covariates at the second spatial resolution are obtained; The geospatial covariates of the second spatial resolution are transformed by spatial mean or accumulation to obtain the geospatial covariates of the first spatial resolution. The training feature set is obtained based on the geospatial covariates of the first spatial resolution; The model is trained based on the training labels and training feature set to obtain the target model, which is a random forest model. Geospatial covariates are extracted from the thermal environment data at the second spatial resolution, and the geospatial covariates are input into the target model to obtain population data at the second spatial resolution. Among them, based on the population data and surface temperature data of the second spatial resolution, the thermal risk index of the target area under different scenarios is obtained, including: When the scenario is an employment scenario or a residential scenario, the population data at the second spatial resolution and the surface temperature data for the target time period corresponding to the scenario are multiplied together to obtain the thermal risk index of each pixel in the target area under the employment scenario or residential scenario. When the scenario is a biophysical baseline scenario, the diurnal average surface temperature of each pixel in the target area is used as the thermal risk index of each pixel in the target area.

7. A computing device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 5.

Images