An urban park site selection decision-making method, system, device and medium

Abstract

The present invention belongs to the technical field of urban planning. In order to solve the multiple bottleneck problems faced by existing heat island effect mitigation technologies, a method, system, device and medium for urban park site selection decision-making are proposed. The combined weights are assigned to multi-dimensional indicators respectively based on game theory methods, and hierarchical normalization processing is carried out; according to the conversion heat contribution degrees of different land cover types, the combined weights of surface temperature are decomposed to different land cover types in the target area; the normalized spatial distribution map corresponding to the surface temperature is associated with different land cover types to obtain the normalized heat contribution distribution map of different land cover types in the target area; the above are fused to generate the site selection suitability distribution map of the target area, and screening is carried out to obtain the urban park site selection scheme, avoiding the sensitivity loss of high heat source areas caused by the existing "one-size-fits-all" weighting, and ensuring that the park site selection decision can not only target the mitigation of the heat island core area, but also adapt to the diversity characteristics of the urban spatial pattern.

Description

Technical Field

[0001] The present invention belongs to the technical field related to urban planning, and particularly relates to a method, system, device and medium for urban park site selection decision-making. Background Technique

[0002] The statements in this part only provide background technical information related to the present invention, and do not necessarily constitute prior art.

[0003] In the analysis of the formation mechanism of the urban heat island effect, the thermodynamic property differences of land cover types are considered the core driving factors. There are significant differences in heat absorption efficiency, heat conduction rate, and long-wave radiation release ability among different surface materials such as asphalt, concrete, and vegetation. For example, high-density building clusters form a significant heat accumulation effect through multiple reflections and retention of solar radiation by their three-dimensional surfaces; while the extensive use of metal and glass materials in industrial areas further enhances the complexity of the local thermal environment. However, existing thermal environment assessment models generally adopt a simplified land cover classification system, roughly dividing surface types into two categories: "hardened" and "natural", and failing to accurately quantify the thermodynamic parameter differences of different material combinations. This rough treatment leads to systematic biases in heat flux simulation, especially making it difficult to analyze the gradual impact of the gradual update of land cover, such as the replacement of traditional pavements with permeable pavements, on the heat island pattern.

[0004] Current urban heat island effect mitigation technologies face multiple bottlenecks. At the data acquisition level, the thermal field inversion method relying on a single remote sensing data source has inherent defects: medium-resolution thermal infrared images such as 30-meter-level can depict the macroscopic thermal field distribution, but cannot identify the thermal heterogeneity at the block scale; while high-time-resolution data such as daily scale are severely limited by the spatial resolution and are difficult to support refined thermal environment analysis. In terms of thermodynamic mechanism modeling, existing studies mostly adopt statistical regression models or machine learning black box models based on the vegetation index NDVI. Although they can achieve temperature field prediction, they lack interpretability of the physical process of surface energy exchange. For example, the vegetation cooling effect is often simplified as a linear function of the leaf area index, ignoring the dynamic regulation of canopy transpiration efficiency by micro-meteorological conditions such as wind speed and humidity. In addition, existing planning models mostly regard the urban heat island effect as a homogeneous background field, only using the urban heat island intensity index as a constraint condition, and failing to establish a quantitative mapping relationship between land cover type conversion and thermal environment response, resulting in insufficient targeting of cooling measures.

[0005] The limitations of multi-objective decision-making algorithms further restrict the optimization of heat island mitigation effectiveness. Traditional spatial multi-criteria decision-making models usually adopt static weight allocation strategies, fixing target parameters such as heat island mitigation, service coverage, and economic costs as fixed ratios. However, the differences in urban development stages and regional characteristics require decision-making models to have dynamic response capabilities: in the initial stage of new city construction, heat island mitigation may be given priority, while in mature built-up areas, service fairness needs to be emphasized. Existing static models are difficult to adapt to this dynamic demand, resulting in target conflicts in the implementation of planning schemes. In addition, the subjective intervention of humans in the weight allocation process, such as the fuzzy interval setting of the expert scoring method, may introduce systematic biases, marginalizing areas with high heat regulation potential but high development costs in the comprehensive evaluation.

[0006] In recent years, research in related technical fields has focused on multi-source data fusion and mechanism model optimization. Some studies have attempted to construct a land surface temperature downscaling model by combining optical images and thermal infrared data, but its algorithm lacks robustness to cloud cover and aerosol interference, and the computational complexity increases significantly with the increase in data dimensions. In terms of the analysis of thermodynamic processes, some scholars have proposed a method for decomposing surface fluxes based on the energy balance equation to reveal the internal mechanism of heat island formation by separating sensible heat, latent heat, and storage heat fluxes, but the response sensitivity of the model to the gradual change process of land cover still needs to be improved. In the field of decision support, dynamic weight optimization algorithms have begun to be introduced to enhance multi-objective coordination capabilities, but the convergence efficiency and stability of existing methods under complex constraint conditions have not yet reached practical requirements. These technical explorations show that improvements in a single dimension are difficult to fundamentally solve the systematic disconnection between heat island effect analysis and planning response, and there is an urgent need to construct a full-chain technical system from thermodynamic mechanism analysis to spatial decision optimization to provide an operable decision-making path for the scientific layout of parks in urban environments. Summary of the Invention

[0007] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a method, system, device, and medium for urban park site selection decision-making, ensuring that the park site selection decision can both target the mitigation of the core area of the heat island and adapt to the diversity characteristics of the urban spatial pattern.

[0008] To achieve the above object, the present invention adopts the following technical solutions:

[0009] In the first aspect, the present invention provides a method for urban park site selection decision-making, including:

[0010] Obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of land cover types between multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degree of different land cover types;

[0011] Perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution maps of each indicator in the target area, and assign combined weights to the relative importance among multi-dimensional indicators based on game theory; decompose the combined weight of surface temperature to different ground objects in the target area according to the conversion heat contribution degrees of different ground object categories to obtain the comprehensive weights of different ground objects in the target area.

[0012] Correspond the normalized spatial distribution map corresponding to the surface temperature with different ground objects in the target area to obtain the normalized distribution map of heat contribution of different ground objects in the target area.

[0013] Fuse the comprehensive weights of different ground objects and the normalized distribution maps of heat contribution of corresponding ground objects, as well as the combined weights of each indicator and the normalized spatial distribution maps corresponding to each indicator to generate the site selection suitability distribution map of the target area, extract the hot spots of suitability, construct an OD cost matrix with the residential area POI as the starting point and the hot spots as the ending point, and screen candidate points according to the time cost to obtain the urban park site selection scheme.

[0014] In a second aspect, the present invention provides an urban park site selection decision-making system, including:

[0015] A calculation module, which is configured to: obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of ground object categories among the multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degrees of different ground object categories.

[0016] A weight module, which is configured to: perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution maps of each indicator in the target area, and assign combined weights to the relative importance among multi-dimensional indicators based on game theory; decompose the combined weight of surface temperature to different ground objects in the target area according to the conversion heat contribution degrees of different ground object categories to obtain the comprehensive weights of different ground objects in the target area.

[0017] An allocation module, which is configured to: correspond the normalized spatial distribution map corresponding to the surface temperature with different ground objects in the target area to obtain the normalized distribution map of heat contribution of different ground objects in the target area.

[0018] A site selection module, which is configured to: fuse the comprehensive weights of different ground objects and the normalized distribution maps of heat contribution of corresponding ground objects, as well as the combined weights of each indicator and the normalized spatial distribution maps corresponding to each indicator to generate the site selection suitability distribution map of the target area, extract the hot spots of suitability, construct an OD cost matrix with the residential area POI as the starting point and the hot spots as the ending point, and screen candidate points according to the time cost to obtain the urban park site selection scheme.

[0019] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in the first aspect is completed.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the method described in the first aspect is completed.

[0021] The above one or more technical solutions have the following beneficial effects:

[0022] In the present invention, multi-dimensional indicators are subjected to hierarchical normalization processing to obtain a normalized spatial distribution map of each indicator on the target area, and a combined weight is assigned to the relative importance between multi-dimensional indicators based on the game theory method, breaking through the limitations of traditional subjective weighting or single objective weighting; according to the conversion heat contribution degree of different land cover types, the combined weight of the surface temperature is decomposed to different land covers in the target area, and the normalized spatial distribution map corresponding to the surface temperature is corresponding to different land covers in the target area, obtaining a normalized distribution map of heat contribution of different land covers in the target area, avoiding the sensitivity loss of the existing "one-size-fits-all" type of weighting to the high heat source area, and ensuring that the park site selection decision can not only target to alleviate the heat island core area, but also adapt to the diversity characteristics of the urban spatial pattern.

[0023] The advantages of the additional aspects of the present invention will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The specification drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0025] Figure 1 It is a flow chart of the urban park site selection decision method in the first embodiment of the present invention;

[0026] Figure 2 It is a schematic diagram of the remote sensing data processing process in the first embodiment of the present invention;

[0027] Figure 3 It is a schematic diagram of the framework of the game theory comprehensive weighting method in the first embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0029] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0030] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0031] Term Explanation:

[0032] Residential area POI (Point of Interest) refers to geographical elements closely related to residents' lives, such as communities, apartment buildings, residences, etc. These elements are abstracted as point elements in the geographical information system to enrich the map content and provide the geographical information required by users.

[0033] ‌OD cost matrix (Origin-Destination Cost Matrix)‌ is a network analysis tool used to calculate and store the minimum travel costs between multiple origins and multiple destinations.

[0034] Embodiment 1

[0035] This embodiment discloses a method for making a decision on the location of an urban park, including:

[0036] Obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of land cover types between the multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degree of different land cover types;

[0037] Perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution maps of each indicator on the target area, and assign combined weights to the relative importance between multi-dimensional indicators based on the game theory method; according to the conversion heat contribution degree of different land cover types, decompose the combined weights of the surface temperature to different land covers in the target area to obtain the comprehensive weights of different land covers in the target area;

[0038] Correspond the normalized spatial distribution map corresponding to the surface temperature with different land covers in the target area to obtain the normalized distribution map of heat contribution of different land covers in the target area;

[0039] Fuse the comprehensive weights of different land covers and the normalized distribution maps of heat contribution of the corresponding land covers, as well as the combined weights of each indicator and the normalized spatial distribution maps corresponding to each indicator to generate the location suitability distribution map of the target area, extract the hot spots of suitability, construct an OD cost matrix with residential area POI as the origin and the hot spots as the destination, and screen candidate points according to the time cost to obtain the location selection plan of the urban park.

[0040] The solution of this embodiment assigns weights to multi-dimensional indicators of the target area based on game theory, breaking through the limitations of traditional subjective weighting or single objective weighting; dynamically adjusts the weights of the urban heat island effect of different land cover types according to the conversion heat contribution degree of different land cover types, avoiding the sensitivity loss of the existing "one-size-fits-all" weighting for high heat source areas, and ensuring that the park site selection decision can not only target the mitigation of the core area of the urban heat island, but also adapt to the diversity characteristics of the urban spatial pattern.

[0041] The following Figure 1 - Figure 2 will detail a method for urban park site selection decision proposed in this embodiment:

[0042] Step 1: Obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of land cover types between the multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degree of different land cover types.

[0043] Obtain multi-temporal remote sensing data of the target area and perform preprocessing, including: radiometric calibration, atmospheric correction, image registration, etc.

[0044] As an implementation method, obtain multi-temporal Sentinel-2 multispectral images of the target area in summer, such as from June to August, with cloud cover < 10% and a spatial resolution of 10 meters; synchronously obtain multi-temporal Landsat 8 images of the same area in summer, with cloud cover < 10% and a resolution of 30 meters.

[0045] Perform atmospheric correction on the Sentinel-2 images using the Sen2Cor tool to obtain surface reflectance data; correct the Landsat 8 images using the FLAASH model to eliminate aerosol and water vapor interference. The formula is:

[0046]

[0047] In the formula, is the radiance at the sensor entrance pupil, DN is the gray value of the original pixel, is the multiplicative coefficient of radiance, is the additive coefficient of radiance, is the solar zenith angle.

[0048] Then, based on the remote sensing data obtained by Sentinel-2, geometrically rectify the remote sensing data obtained by Landsat 8 using the ENVI feature matching method, with a spatial registration error ≤ 1 pixel.

[0049] For example, Sentinel-2 remote sensing images and Landsat 8 remote sensing images with cloud cover < 10% in the summer of two time phases are obtained for the three cities of Shenyang, Xi'an, and Wuhan. And road data, building data, water body surface data, night light data products, etc. of the three cities in the corresponding years are extracted based on OpenStreetMap. Among them, Shenyang is for 2017 and 2020, Xi'an is for 2019 and 2021, and Wuhan is for 2013 and 2016.

[0050] Step 11: Statistically analyze the mutual conversion information of ground object categories between multi-temporal remote sensing data in the target area, calculate the conversion area between ground object categories in the target area, and the net change in conversion temperature between ground object categories.

[0051] Step 111: Based on the multi-temporal remote sensing data in the target area, respectively obtain the ground object category probability maps corresponding to different temporal remote sensing data through the trained semantic segmentation and change detection classification models.

[0052] By inputting the two registered Sentinel-2 remote sensing images into the trained semantic segmentation and change detection classification models respectively, four types of probability maps are obtained, namely buildings, bare land, water bodies, and green spaces.

[0053] Using the DeeplabV3+ framework, the semantic segmentation and change detection classification model includes 4 encoders, namely Block1, Block2, Block3, and Block4, a spatio-temporal feature fusion module, and a decoder.

[0054] Taking the improved ResNet-50 as the Block of the encoder, loading the weights pre-trained on the ImageNet dataset to accelerate the model convergence. Fix the weights of the first 3 convolutional layers of the ResNet-50 network, i.e., Conv1~Conv3, and only fine-tune the deep network, i.e., Conv4 and subsequent modules, to avoid the destruction of shallow general features and reduce the risk of overfitting.

[0055] The improved ResNet-50 is specifically as follows: After the output of the fourth convolutional layer of ResNet-50, i.e., Conv4, add 4 groups of parallel dilated convolutional layers with dilation rates of 6, 12, 18, and 24 respectively to capture the context information of remote sensing data at different scales and obtain multi-scale feature maps; splice the multi-scale feature maps with the original features output by Conv4, and then compress the number of channels to 256 through 1×1 convolution to reduce the computational amount; introduce a channel attention module in the skip connection to automatically learn the importance weights of shallow features of remote sensing data such as building edges and water body boundaries, and suppress background noise such as cloud shadows and seasonal changes of vegetation.

[0056] The specific steps of the spatio-temporal feature fusion module are as follows:

[0057] Differential feature extraction: For the dual-temporal feature maps output by the encoder, the absolute difference is calculated pixel by pixel to generate the initial differential feature map. After the differential feature map is spatially smoothed by a 3×3 convolutional kernel, the initial change features with a channel dimension of 256 are output.

[0058] Temporal modeling: A bidirectional ConvLSTM unit is used to model the initial change features to capture the progressive process of land cover change such as vegetation degradation and sudden events such as building demolition, resulting in a temporal feature map. The hidden layer dimension of the ConvLSTM is set to 512, the time step is set to 2, and the convolutional kernel size is 3×3. The forward and backward LSTMs respectively learn the temporal dependence relationships, and finally the bidirectional hidden states are concatenated into 1024-dimensional features.

[0059] Attention-weighted fusion: Based on the channel attention mechanism, the fused temporal features are dynamically calibrated. Specifically, first, the spatial dimension of the temporal feature map is compressed through global average pooling to obtain channel-level statistics; then two fully connected layers are used to generate the channel weight vector. The weight vector is multiplied with the initial change features in the channel dimension to enhance the response intensity of the key feature channels and suppress the interference of non-significant features. The weighted feature map is compressed to 256 channels by a 1×1 convolution to reduce the computational complexity, and a residual connection is made with the original features output by the encoder, i.e., Block4, to retain the spatial context information of the unchanged regions.

[0060] The specific steps of the decoder are as follows:

[0061] The decoder adopts a four-level upsampling structure to gradually restore the spatial resolution: The first level upsamples the input features (H / 32×W / 32) to H / 16×W / 16 through a 3×3 transposed convolution (stride 2, padding 1), outputs 512 channels, and then fuses the 1024-dimensional features of encoder Block3, and the channels are aligned and added through a 1×1 convolution; The second level repeats the transposed convolution operation to output 256-channel features of H / 8×W / 8 and fuses the Block2 features; The third level upsamples to 128 channels of H / 4×W / 4 and fuses the shallow texture features of Block1; The fourth level finally restores to 64-channel features of the original resolution H×W, and bilinear interpolation is superimposed to refine the local features to ensure the integrity of small-scale land covers.

[0062] Binary mask generation: The 64-dimensional features output by the decoder are compressed to 4 channels, namely buildings, bare land, water bodies, and green spaces, through a 1×1 convolution, and probability maps are generated through the Sigmoid function, and a dynamic threshold segmentation strategy is adopted for processing. The specific dynamic threshold segmentation strategy is as follows: The thresholds for buildings and bare land are set to 0.6 to reduce the misjudgment of vegetation, and the thresholds for water bodies and green spaces are set to 0.4 to improve the sensitivity; In the post-processing stage, salt-and-pepper noise is eliminated through a 5×5 morphological opening operation.

[0063] Confidence estimation. The confidence is jointly calculated by information entropy and spatial consistency, and the formula is as follows:

[0064]

[0065] In the formula, H is the entropy value, which measures the uncertainty of the classification result. The lower the entropy value, the higher the classification certainty; represents the probability that a pixel belongs to the i-th type of ground object (building, bare land, water body, green space).

[0066] When training the semantic segmentation and change detection classification models, the cross-entropy loss function is used to handle the class imbalance problem. Higher weights are assigned to minority classes such as water bodies. For example, the weight of the water body is 1.5, the bare land is 1.2, and the green space is 0.9. The Dice loss is used to optimize the overlap rate of the segmented regions and improve the boundary accuracy, and the weight ratio with the cross-entropy loss is 4:6. The Adam optimizer is used, with β1 = 0.9, β2 = 0.999, the initial learning rate is 0.0001, and the cosine annealing strategy is adopted to dynamically adjust the learning rate, which decays to 10% of the initial value every 50 epochs.

[0067] Step 112: Compare and mark pixel by pixel the pixels with inconsistent classifications in the classification results of remote sensing data in different phases to generate an original difference map, and calculate the conversion area between ground object classes in the target area according to the original difference map.

[0068] Specifically, compare and mark pixel by pixel the pixels with inconsistent classifications in the classification results of two phases to generate an original difference map; construct a 4×4 land use conversion matrix to count the mutual conversions between the four types of ground objects, such as "bare land → building", "green space → bare land", etc., and calculate the area and proportion of each ground object class.

[0069] An example of the land use conversion matrix is as follows:

[0070]

[0071] M in the table i,j represents the number of pixels converted from the previous-phase class i to the next-phase class j.

[0072] Step 12: Calculate the conversion heat contribution degree of different ground object classes according to the net change of the conversion temperature between ground object classes and the conversion area between ground object analogies.

[0073] Based on the thermal infrared bands (Band10 - 11) of Landsat8, the land surface temperature is retrieved. The radiative transfer equation RTE is used to retrieve the land surface temperature LST, and the formula is as follows:

[0074]

[0075] In the formula, .

[0076] Extract the daily average temperatures (T1, T2) of two scenes of images from the meteorological data network, and calculate the background temperature difference: .

[0077] According to the land use type conversion matrix, calculate the average temperature change of each conversion type: ；

[0078] Eliminate meteorological interference, obtain the net heat effect value, and the net temperature change of land use conversion is: , and calculate the net temperature changes of the four land use types respectively.

[0079] The formula for calculating the heat contribution degree of land use type conversion is:

[0080]

[0081] Among them, is the heat contribution degree of land use type i , is the net temperature change of land use type j converted to land use type i , is the conversion area of land use type j converted to land use type i .

[0082] For example, on August 15, 2017 in Shenyang , on August 18, 2020 , .

[0083] Step 2: Perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution maps of each indicator in the target area, and assign combined weights to the relative importance among multi-dimensional indicators based on game theory; according to the conversion heat contribution degrees of different land use types, decompose the combined weights of surface temperature to different land uses in the target area to obtain the comprehensive weights of different land uses in the target area; correspond the normalized spatial distribution map corresponding to surface temperature with different land uses in the target area to obtain the heat contribution normalized distribution map of different land uses in the target area.

[0084] Step 21: Classify the multi-dimensional indicators respectively using the natural break point method, and perform normalization processing on the classification results to obtain the normalized spatial distribution maps of each indicator in the target area.

[0085] The multi - dimensional indicators for urban park site selection, namely land surface temperature, NDVI, traffic accessibility, and night - light index, are classified using the natural break method respectively. For example: the land surface temperature is divided into 5 levels according to the severity of the heat island, 1 = very inappropriate → 5 = very appropriate; NDVI is divided into 5 levels according to the vegetation scarcity degree, 1 = very appropriate → 5 = very inappropriate; traffic accessibility is divided into 5 levels according to the value, 1 = very inappropriate → 5 = very appropriate; night - light index is divided into 5 levels according to the value, 1 = very inappropriate → 5 = very appropriate.

[0086] Normalize the classification results into 0 - 1 scores. For example, level 1 = 0.2, level 2 = 0.4, …, level 5 = 1.0.

[0087] Step 22: Use the analytic hierarchy process (AHP) to determine the subjective weights of the multi - dimensional indicators, use the independent weight coefficient method (IWCM) to determine the objective weights of the multi - dimensional indicators, and take the minimization of the difference between the subjective weight and the objective weight as the goal, and use the Nash equilibrium to solve for the combined weights of the multi - dimensional indicators.

[0088] As Figure 3 shown, using the analytic hierarchy process (AHP), through pairwise comparison of the relative importance between indicators by experts, construct a judgment matrix by quantifying and scoring based on the 1 - 9 scale method, obtain the subjective weights of the four indicators, and pass the consistency test, CR < 0.1;

[0089] Using the independent weight coefficient method (IWCM), based on the information entropy to calculate the index dispersion to determine the objective weights of the multi - dimensional indicators. The formula is:

[0090]

[0091] In the formula, The j objective weight of the th j indicator, is the information entropy of the th

[0092] indicator,

[0093]

[0094]

[0095] where, is the subjective weight, is the objective weight, , is the optimal coefficient, is the combined weight.

[0096] The analytic hierarchy process is adopted to determine the subjective weights of multi-dimensional indicators, combined with the independent weight coefficient method to quantify the objective weights, and the game theory is used to optimize the synergistic relationship between the two types of weights, so that the weighting of the four core indicators of land surface temperature, vegetation coverage, accessibility, and night light index can adapt to the spatial heterogeneity characteristics of different regions.

[0097] Step 23: Decompose the comprehensive weight of the land surface temperature to each land use type, namely buildings, bare land, water bodies, and green spaces, to achieve spatial heterogeneity weighting. Specifically:

[0098] According to the heat contribution degrees of the four types of ground objects (buildings, bare land, water bodies, and green spaces) calculated in Step 1 Allocate the comprehensive weight of the land surface temperature to each land use type proportionally:

[0099]

[0100] In the formula, is the comprehensive weight of the four types of ground objects after decomposition, and the subscript respectively takes , is the combined weight of the land surface temperature, is the heat contribution degree of the four types of ground objects, i ranges from 1 to 4.

[0101] Step 24: Split the normalized distribution map of the land surface temperature obtained in Step 21 into four types of ground objects according to the four types of probability maps of the later phase obtained in Step 111, that is, use the spatial distribution of the four types of ground objects in the later phase to clip the normalized distribution map of the land surface temperature to obtain the normalized distribution map of the heat contribution corresponding to the four types of ground objects.

[0102] Step 3: Integrate the comprehensive weights of different ground objects and the normalized distribution maps of the heat contributions of the corresponding ground objects, as well as the combined weights of each indicator and the normalized spatial distribution maps corresponding to each indicator, to generate a suitability distribution map for site selection in the target area, extract the hot spots of suitability, construct an OD cost matrix with the residential area POI as the starting point and the hot spots as the end point, and screen the candidate points according to the time cost to obtain the urban park site selection plan.

[0103] Overlay the land surface temperature, vegetation scarcity degree, night light index, and residential accessibility indicators of the four types of ground objects to generate a suitability distribution map for site selection, and screen the candidate points in combination with the road network topology constraints and the non-hardened surface protection rules; through the analysis of the heat island mitigation potential and the public service coverage blind area, output the optimal park site selection plan.

[0104] Specifically, integrate the 7 indicators of the land surface temperature, NDVI, night light index, and accessibility of the four types of ground objects, and perform weighted overlay to output the suitability spatial distribution map of the target area with a resolution of 30 meters. The formula is:

[0105]

[0106] In the formula, represents the comprehensive weight of the heat contribution of the building land type, represents the comprehensive weight of the heat contribution of the bare land type, represents the comprehensive weight of the heat contribution of the green land type, represents the comprehensive weight of the heat contribution of the water body land type; represents the combined weight of the index NDVI; represents the combined weight of the index night light index; represents the combined weight of the index accessibility; is the normalized spatial distribution map of the heat contribution of the building land type, is the normalized spatial distribution map of the heat contribution of the bare land type, is the normalized spatial distribution map of the heat contribution of the green land type, is the normalized spatial distribution map of the heat contribution of the water body land type, is the normalized spatial distribution map of NDVI, is the normalized spatial distribution map of the night light index, is the normalized spatial distribution map of accessibility; S represents the spatial distribution map of the suitability of urban park locations.

[0107] The Getis-Ord Gi* hot spot analysis is used to extract the significant areas of the heat island intensity and vegetation scarcity, with Z-score > 2.58 and confidence level > 99%.

[0108] Based on the OpenStreetMap building and water surface vector data, the existing building areas and permanent water bodies are excluded.

[0109] Taking the residential area POI as the starting point and the hot spot area as the ending point, an OD cost matrix is constructed. Using the 15-minute walking isochrone as the time cost, the accessibility distribution map is generated by superimposing the water body blockage and terrain impedance. Specifically:

[0110] Data preparation and processing: Obtain the residential area POI point data, the vector boundary of the suitability hot spot area, the road network data, and the high-precision water system layer;

[0111] Establish traffic rules: Taking the traffic road network as the path, set the water body area as an impassable area;

[0112] Generate cost raster: Integrate the road network distribution and water body blockage factors to construct comprehensive traffic cost raster data;

[0113] Calculate the shortest path: Using the path planning algorithm, with the residential area as the starting point and the suitability hot spot area as the ending point, iteratively calculate the minimum cumulative travel time to generate the accessibility distribution map;

[0114] Extraction of isochrones: Segment the accessibility grid based on a 15 - minute walking threshold to generate continuous isochrone surface areas;

[0115] Construction of OD matrix: Spatially connect the residential area POIs with the suitability hotspots, establish a start - end reachability time relationship table, and output the candidate point locations and path topological structures.

[0116] Screen candidate point locations that simultaneously meet the conditions of "suitability > set value such as 0.8", "reachable time < set time such as 15 minutes", and "proportion of non - hardened surfaces such as bare land / green land > 70%"; Sort in descending order according to the suitability score, and output the coordinates and attribute table of the top - ranked candidates such as Top15.

[0117] In this embodiment, by fusing Sentinel - 2 high - resolution multi - spectral data and the thermal infrared band of Landsat 8, a sub - pixel - level geometric registration framework is constructed, overcoming the problems of insufficient resolution of traditional single - data sources and rough land cover classification. When using the radiative transfer equation to invert the land surface temperature, meteorological parameters are innovatively introduced for dynamic correction to strip the interference of background air temperature fluctuations on the attribution of the heat island effect, and achieve accurate mapping of land cover types and temperature changes. Through the semantic segmentation and change detection classification model, combined with multi - scale dilated convolution and attention mechanism to enhance the feature extraction ability, significantly improve the recognition accuracy of the boundaries of key land features such as buildings and bare land, construct a two - temporal land cover type conversion matrix to analyze the difference in heat contribution, and provide a spatially explicit quantitative basis for tracing the source of the heat island effect.

[0118] This embodiment is based on a multi - dimensional index dynamic weighting method for urban park location selection coupled with game theory, breaking through the limitations of traditional subjective weighting or single - objective weighting. By fusing the analytic hierarchy process and the independent weight coefficient method through the Nash equilibrium theory, the weight distribution of core indicators such as temperature and vegetation index is both scientific and adaptable. An innovative weight decomposition mechanism for land surface temperature is proposed, dynamically adjusting the influence weights of types such as buildings and green spaces in the global evaluation according to the heat contribution of different land cover type conversions, avoiding the sensitivity loss of the "one - size - fits - all" weighting method for high - heat source areas. This embodiment realizes the local optimization of weight parameters through spatial heterogeneity analysis, ensuring that the park location selection decision can not only target and alleviate the core area of the heat island but also adapt to the diversity characteristics of the urban spatial pattern.

[0119] The decision-making method for park site selection based on multi-constraint network analysis in this embodiment constructs a multi-objective collaborative optimization framework of "thermal environment governance - ecological service supply and demand - resident accessibility", uses spatial statistical methods to identify suitable hotspots for park site selection, and combines road network topological analysis and walking isochrone modeling. Through multi-dimensional index weighted overlay and spatial exclusion rules such as non-hardened surface protection and avoidance of existing construction, the optimal solution set that simultaneously meets the potential for heat island mitigation, ecological restoration needs, and public service fairness is screened out. This method breaks through the limitations of traditional single-objective optimization, realizes the deep coupling of ecological benefits and people's livelihood needs with network analysis technology, and provides an operable decision-making path for the scientific layout of parks in high-density urban environments.

[0120] Embodiment 2

[0121] The purpose of this embodiment is to provide an urban park site selection decision-making system, including:

[0122] A calculation module, which is configured to: obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of ground object categories between the multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degree of different ground object categories;

[0123] A weight module, which is configured to: perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution map of each indicator on the target area, and assign combined weights to the relative importance between multi-dimensional indicators based on game theory; according to the conversion heat contribution degree of different ground object categories, decompose the combined weight of the surface temperature to different ground objects in the target area to obtain the comprehensive weight of different ground objects in the target area;

[0124] An allocation module, which is configured to: correspond the normalized spatial distribution map corresponding to the surface temperature to different ground objects in the target area to obtain the normalized distribution map of heat contribution of different ground objects in the target area;

[0125] A site selection module, which is configured to: fuse the comprehensive weights of different ground objects and the normalized distribution map of heat contribution of the corresponding ground objects, as well as the combined weights of each indicator and the normalized spatial distribution map corresponding to each indicator, generate a site selection suitability distribution map of the target area, extract suitable hotspots, construct an OD cost matrix with the residential area POI as the starting point and the hotspot as the end point, and screen candidate points according to time cost to obtain the urban park site selection plan.

[0126] In more embodiments, there is also provided:

[0127] An electronic device, including a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in Embodiment 1 is completed. For the sake of brevity, it will not be repeated here.

[0128] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or the processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0129] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0130] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the method described in the first embodiment.

[0131] The method in the first embodiment can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0132] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with this embodiment can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0133] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, they do not limit the protection scope of the present invention. Those skilled in the art should understand that based on the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A decision-making method for the location selection of urban parks, characterized in that, Including: Obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of land cover types among the multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degree of different land cover types. Perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution maps of each indicator on the target area, and assign combined weights to the relative importance among multi-dimensional indicators based on the game theory method; according to the conversion heat contribution degree of different land cover types, decompose the combined weights of surface temperature to different land covers in the target area to obtain the comprehensive weights of different land covers in the target area. Correspond the normalized spatial distribution map corresponding to the surface temperature with different land covers in the target area to obtain the normalized distribution map of heat contribution of different land covers in the target area. Fuse the comprehensive weights of different land covers and the normalized distribution maps of heat contribution of the corresponding land covers, as well as the combined weights of each indicator and the normalized spatial distribution maps corresponding to each indicator to generate the suitability distribution map for site selection in the target area, extract the hot spots of suitability, construct an OD cost matrix with residential area POIs as the starting point and hot spots as the end point, and screen candidate points according to time cost to obtain the site selection plan for urban parks. Among them, counting the mutual conversion information of land cover types among the multi-temporal remote sensing data of the target area and calculating the conversion heat contribution degree of different land cover types are specifically as follows: Count the mutual conversion information of land cover types among the multi-temporal remote sensing data of the target area, calculate the conversion area between land cover types in the target area, and the net change in temperature during the conversion between land cover types. According to the net change in temperature during the conversion between land cover types and the conversion area between land cover types, calculate the conversion heat contribution degree of different land cover types. Among them, counting the mutual conversion information of land cover types among the multi-temporal remote sensing data of the target area and calculating the conversion area between land cover types in the target area are specifically as follows: Based on the multi-temporal remote sensing data of the target area, respectively obtain the land cover type probability maps corresponding to different temporal remote sensing data through the trained semantic segmentation and change detection classification models. Compare and mark pixel by pixel the pixels with inconsistent classifications in the classification results of different temporal remote sensing data to generate the original difference map. Calculate the conversion area between land cover types in the target area according to the original difference map.

2. The urban park location decision-making method according to claim 1, characterized in that, The semantic segmentation and change detection classification model includes an encoder, a spatio-temporal feature fusion module and a decoder. The encoder uses an improved ResNet-50 network. The improved ResNet-50 network is specifically: add multiple groups of parallel dilated convolutions after the fourth layer of convolution in the ResNet-50 network to capture the context information of remote sensing data at different scales and obtain multi-scale feature maps; splice the multi-scale feature maps with the output features of the fourth layer of convolution to obtain spliced features; introduce channel attention in the skip connection to learn the shallow features of remote sensing data. Based on the spatio-temporal feature fusion module, calculate the initial change features for the bi-temporal feature maps output by the encoder, model the initial change features using a bidirectional ConvLSTM unit to obtain the temporal feature maps, and perform dynamic calibration on the temporal feature maps using a channel attention mechanism.

3. The method for making a decision on the location of an urban park according to claim 1, characterized in that, Perform hierarchical normalization processing on multi-dimensional indicators to obtain the normalized spatial distribution maps of each indicator in the target area. Assign combined weights to the relative importance among multi-dimensional indicators based on game theory methods, specifically as follows: Classify the multi-dimensional indicators of the target area using the natural break method respectively, and perform normalization processing on the classification results to obtain the normalized spatial distribution maps of each indicator in the target area; Determine the subjective weights of multi-dimensional indicators using the analytic hierarchy process, determine the objective weights of multi-dimensional indicators using the independent weight coefficient method, and use the Nash equilibrium solution to obtain the combined weights of multi-dimensional indicators with the goal of minimizing the difference between subjective weights and objective weights.

4. The method for making a decision on the location of an urban park as described in claim 3, wherein, Fuse the comprehensive weights of different ground objects and the normalized distribution maps of the heat contributions of the corresponding ground objects, as well as the combined weights of each indicator and the normalized spatial distribution maps corresponding to each indicator to generate the suitability distribution map for site selection in the target area, specifically as follows: ， Among them, represents the comprehensive weight of the heat contribution of the building land type, represents the comprehensive weight of the heat contribution of the bare land type, represents the comprehensive weight of the heat contribution of the green land type, represents the comprehensive weight of the heat contribution of the water body land type; represents the combined weight of the indicator NDVI; represents the combined weight of the indicator night light index; represents the combined weight of the indicator accessibility; is the normalized spatial distribution map of the heat contribution of the building land type, is the normalized spatial distribution map of the heat contribution of the bare land type, is the normalized spatial distribution map of the heat contribution of the green land type, is the normalized spatial distribution map of the heat contribution of the water body land type, is the normalized spatial distribution map of NDVI, is the normalized spatial distribution map of the night light index, is the normalized spatial distribution map of accessibility; S represents the spatial distribution map of the suitability of urban park sites.

5. The method for making a decision on the location of an urban park as described in claim 1, wherein, According to the suitability distribution map for site selection in the target area, extract the suitability hot spots. Construct an OD cost matrix with residential areas' POIs as the starting point and the hot spots as the ending point, and screen candidate points according to the time cost to obtain the urban park site selection plan, specifically as follows: Use Getis-Ord Gi* hot spot analysis to identify significant areas of heat island intensity and vegetation scarcity; Exclude the existing building areas and permanent water bodies based on OSM building vector data; Construct an OD cost matrix with residential areas as the starting point and the urban park hot spots as the ending point, and calculate the walking cost from residential areas to the hot spots; Screen candidate points that meet the preset conditions of suitability and accessible time and are non-hardened surfaces; Sort the candidate points according to the heat island mitigation potential and the coverage rate of the residents' service blind areas to obtain the urban park site selection plan.

6. An urban park site selection decision-making system, characterized in that, Including: A calculation module, which is configured to: obtain multi-temporal remote sensing data of the target area, count the mutual conversion information of ground object categories among the multi-temporal remote sensing data of the target area, and calculate the conversion heat contribution degrees of different ground object categories; among them, counting the mutual conversion information of ground object categories among the multi-temporal remote sensing data of the target area and calculating the conversion heat contribution degrees of different ground object categories, specifically as follows: Count the mutual conversion information of ground object categories among the multi-temporal remote sensing data of the target area, calculate the conversion area between ground object categories in the target area, and the net change in temperature between ground object categories; Calculate the conversion heat contribution degrees of different ground object categories according to the net change in temperature between ground object categories and the conversion area between ground object categories; Among them, counting the mutual conversion information of ground object categories among the multi-temporal remote sensing data of the target area and calculating the conversion area between ground object categories in the target area, specifically as follows: Based on the multi-temporal remote sensing data of the target area, respectively obtain the ground object category probability maps corresponding to different temporal remote sensing data through the trained semantic segmentation and change detection classification models; Compare and mark pixel by pixel the pixels with inconsistent categories in the classification results of different temporal remote sensing data to generate the original difference map; Calculate the conversion area between ground object categories in the target area according to the original difference map; A weight module, which is configured to: perform hierarchical normalization processing on multi-dimensional indicators to obtain a normalized spatial distribution map of each indicator in the target area, and assign a combined weight to the relative importance among the multi-dimensional indicators based on game theory; decompose the combined weight of the surface temperature to different ground objects in the target area according to the conversion heat contribution degree of different ground object categories to obtain the comprehensive weight of different ground objects in the target area; An allocation module, which is configured to: correspond the normalized spatial distribution map corresponding to the surface temperature with different ground objects in the target area to obtain a normalized distribution map of heat contribution of different ground objects in the target area; A site selection module, which is configured to: fuse the comprehensive weights of different ground objects and the normalized distribution map of heat contribution of the corresponding ground objects, as well as the combined weights of each indicator and the normalized spatial distribution map corresponding to each indicator, generate a site selection suitability distribution map of the target area, extract the suitability hot spots, construct an OD cost matrix with the residential area POI as the starting point and the hot spots as the end point, and screen candidate points according to the time cost to obtain a site selection plan for urban parks.

7. An electronic device, characterized in that, It includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method according to any one of claims 1-5 is completed.

8. A computer-readable storage medium, characterized in that, For storing computer instructions, when the computer instructions are executed by the processor, the method according to any one of claims 1-5 is completed.

Images