A Method for Identifying Urban Renewal Areas Based on Multi-Source Data

Abstract

The present invention belongs to the technical field of urban renewal analysis, and specifically discloses a method for identifying urban renewal areas based on multi-source data. By dividing the target city into geographical units and obtaining a multi-source data set composed of building aging, land use, and remote sensing images, this method solves the problem of single evaluation dimension caused by relying solely on building contour data, can accurately identify renewal needs such as inefficient land use, and avoids one-sided evaluation results; constructs evaluation indicators for building status and land use efficiency, uses a double-threshold warning mechanism and a spatial decay model to dynamically generate an initial renewal potential value, and dynamically corrects it according to the spatial correlation of adjacent geographical units, overcoming the defect of ignoring the linkage of geographical proximity in the prior art, preventing the delineation of isolated renewal areas, and ensuring the integrity of urban functions; finally, through descending order sorting and visual display, scientific and reasonable identification and planning of urban renewal areas are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban renewal analysis. Specifically, it relates to a method for identifying urban renewal areas based on multi-source data. Background Art

[0002] With the advancement of urbanization, urban development has gradually shifted from focusing on scale expansion to intensive development. There are a large number of built-up areas in the city, and some areas have problems such as aging buildings, obsolete facilities, and single functions, which cannot meet the growing living needs of residents. Urban renewal has become an inevitable choice to improve the quality of the city and promote sustainable development.

[0003] The prior art, such as a method for identifying urban renewal areas based on machine learning disclosed in the Chinese invention patent application with the application number 202410964165.4, uses machine learning and building contour data at multiple time nodes for clustering analysis to identify areas that need to be updated, and realizes dynamic tracking and cross-year model reuse.

[0004] Obviously, the above technical solution mainly identifies renewal areas with time series driving as the core, and is good at capturing dynamic evolution laws, but the horizontal dimension is single, and there are still the following problems: 1. Only relying on building contour data, the consideration dimension is single, and it is impossible to identify renewal needs triggered by low land use efficiency, etc., and the evaluation results are one-sided.

[0005] 2. The prior art identifies the relevance of building groups through density clustering, ignoring the linkage of geographical proximity, which may lead to the delineation of isolated renewal areas and damage the integrity of urban functions. Summary of the Invention

[0006] In view of this, a method for identifying urban renewal areas based on multi-source data is proposed to solve the limitations of the prior art in water vapor false alarm, such as poor environmental adaptability, sensitivity to optical pollution, and rough feature analysis.

[0007] The object of the present invention can be achieved by the following technical solutions: The present invention provides a method for identifying urban renewal areas based on multi-source data, which includes: dividing the target city into several geographical units, obtaining building aging data, land use data, and remote sensing image data within each geographical unit, and forming a multi-source data set.

[0008] Construct building state evaluation indicators and land use efficiency evaluation indicators based on the multi-source data set, and dynamically generate an initial renewal potential value through a double-threshold warning mechanism and an attenuation model.

[0009] Dynamically correct the initial renewal potential value of each geographical unit according to the spatial relevance of adjacent geographical units to generate a corrected renewal potential value.

[0010] Sort the corrected update potential values in descending order to generate a priority annotation form, and combine with a geographic information system for visual display.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) By integrating multi-source data such as building aging, land use, and remote sensing images for multi-factor evaluation, the present invention breaks through the limitations of traditional single data dimensions and avoids the one-sidedness of evaluation results. At the same time, based on the spatial correlation of adjacent geographical units for dynamic correction, it effectively overcomes the drawbacks of the prior art that ignores the linkage of geographical proximity, ensures the integrity of urban functions, and realizes scientific and reasonable identification and planning of urban renewal areas.

[0012] (2) Through the fusion of multi-source data, the present invention can capture the current situation of the city from multiple dimensions such as building age, land use efficiency, and urban spatial form, accurately identify hidden renewal needs due to building aging, low land use efficiency, etc., and provide more comprehensive and accurate basic information for subsequent evaluation, avoiding the problem of one-sided evaluation caused by single data.

[0013] (3) By dynamically generating initial update potential values through a dual-threshold warning mechanism and a spatial decay model, the present invention can more scientifically and objectively reflect the update potential of each geographical unit compared with traditional single-factor evaluation, making the update potential evaluation more logical and persuasive, and providing a reliable basis for urban renewal decisions.

[0014] (4) By dynamically correcting the update potential values according to the spatial correlation of adjacent geographical units, the present invention makes up for the defect of the prior art that ignores the linkage of geographical proximity. It avoids the delineation of isolated island-style renewal areas, ensures the integrity of functions and spatial coordination after urban renewal, and makes the urban renewal plan fit the overall development of the city.

[0015] (5) By sorting the corrected update potential values in descending order and visualizing them in combination with a geographic information system, the present invention can intuitively present the priority of the update potential of each region in the city. It is convenient for planners and decision-makers to quickly identify high-potential renewal areas, formulate targeted renewal strategies, and at the same time facilitate the rational allocation of resources and improve the efficiency of urban renewal work. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic flow chart of the implementation steps of the method of the present invention.

[0018] Figure 2 This is a schematic diagram of the construction process for the building state evaluation indicators of the present invention.

[0019] Figure 3 This is a schematic diagram of the construction process for the land use efficiency evaluation indicators of the present invention.

[0020] Figure 4 This is a flowchart of the specific analysis steps for the initial update potential value of the present invention. Detailed implementation manners

[0021] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] Please refer to Figure 1 As shown, the present invention provides a method for identifying urban renewal areas based on multi-source data. The method includes: S1. Divide the target city into several geographical units, and obtain building aging data, land use data, and remote sensing image data within each geographical unit to form a multi-source data set.

[0023] Specifically, the building aging data includes building age, maintenance score, and functional adaptability index. The building age is obtained through comparison and verification of the urban building archives and historical satellite images.

[0024] It should be noted that in the building aging assessment, the functional adaptability index refers to the matching degree between the current use function of the building and its original design purpose or modern urban needs, reflecting the adaptability of the building to the new needs of urban development at the functional level. It is determined by combining the spatial data, facility data, and specification data of the building. For these three types of data, the weight of each type of data is determined by using the expert scoring method or the analytic hierarchy process, and each type of data is quantitatively scored. For example, from aspects such as the use efficiency of the building space, the completeness of facilities, and the advancement of technology, scores from 1 to 10 are assigned according to different standards. Finally, the scores of each type of numerical value are multiplied by the weights and then added together to obtain the functional adaptability index value.

[0025] Specifically, the land use data includes plot ratio, land use mixture, and green coverage rate.

[0026] It should be added that the calculation method of the floor area ratio is: to calculate the ratio of the total building floor area in the geographical unit to the land area. The calculation method of the green coverage rate is: based on the vegetation index analysis of remote sensing images, extract the proportion of the green land area in the total area of the geographical unit as the green coverage rate. The calculation method of the land use mix is: obtain the vector data of land use types such as residential, commercial, industrial, and public services in the unit, calculate the proportion of each type of area and perform normalization processing, use the information entropy model to quantify the base value of the mix, combine with the regional planning policy orientation coefficient, such as the weight of the commercial-residential function synergy degree, for dynamic correction, and finally generate a mix quantification index in the 0-1 interval through range normalization.

[0027] Further, the specific division rules for dividing the target city are as follows: divide the target area into grid units with an area difference within a preset threshold range based on the urban road network structure and administrative division boundaries, and each grid unit contains at least one independent building complex, and use the grid unit as the geographical unit.

[0028] It should be added that the preset threshold range of the area difference can be set as the proportion of the maximum allowable difference, such as ±10%.

[0029] Through the fusion of multi-source data, the embodiments of the present invention can capture the current situation of the city from multiple dimensions such as building age, land use efficiency, and urban spatial form, accurately identify the hidden renewal needs due to building aging, low land use efficiency, etc., provide more comprehensive and accurate basic information for subsequent evaluation, and avoid the problem of one-sided evaluation caused by single data.

[0030] S2. Construct building status evaluation indicators and land use efficiency evaluation indicators based on the multi-source dataset, and dynamically generate an initial renewal potential value through a dual-threshold warning mechanism and a decay model.

[0031] Specifically, please refer to Figure 2 As shown, the specific construction process of the building status evaluation indicators is as follows: A1. Identify the damage degree of the building facade based on remote sensing image data.

[0032] A2. Extract the building age and maintenance score from the building aging data, and calculate the structural stability parameter through a preset weight distribution model.

[0033] A3. Generate a building structure safety index according to the relationship between the structural stability parameter and the corresponding preset qualified threshold.

[0034] A4. Generate a maintenance status score according to the maintenance frequency and capital investment within a preset time window in the maintenance record.

[0035] A5. Extract functional adaptability indicators from the building aging data, and comprehensively obtain the calculated building status evaluation score value by weighted summation of the building structure safety index, maintenance status score, and functional adaptability indicators.

[0036] It should be added that the weights of the building structure safety index, maintenance status score, and functional adaptability indicators can be set to 0.4, 0.3, and 0.3 respectively.

[0037] Understandably, the specific process of identifying the damage degree of the building facade in step A1 includes: performing preprocessing of radiometric correction and geometric registration on the high-resolution visible light image, using edge enhancement algorithms such as the Canny operator to extract the building contour and segment the facade area. Secondly, through multi-scale texture analysis, such as calculating the contrast and entropy values using the gray-level co-occurrence matrix and combining with the HSV color space conversion, the degree of fading and pollution of the facade material is quantified. Finally, for structural damages such as cracks and peeling, after segmentation by the U-Net neural network model, the number of pixels in the crack / peeling category in the segmentation result is counted, divided by the total number of pixels of the building facade, to obtain the crack ratio and peeling ratio, and the damage degree of the building facade is obtained by weighted summation. Among them, the weights of cracks and peeling can be set to 0.55 and 0.45 respectively.

[0038] Understandably, the specific calculation of calculating the structural stability parameter in step A2 is as follows: taking the building age, maintenance score, and the damage degree of the building facade as input parameters, based on the expert experience database and historical safety assessment reports, determine the weight coefficients of each input parameter, and obtain the structural stability parameter by weighted summation.

[0039] Understandably, the preset qualified threshold in step A3 is obtained according to the building safety code and historical accident data statistics, and the specific generation process of the building structure safety index is as follows: if the structural stability parameter is greater than the preset qualified threshold, assign the building structure safety index as 1; if the structural stability parameter is less than the preset qualified threshold and the difference from the preset qualified threshold is within the set safety range, take the ratio of the structural stability parameter to the preset qualified threshold as the structural safety index; if the structural stability parameter is less than the preset qualified threshold and the difference from the preset qualified threshold exceeds the set safety range, assign the structural safety index as 0.

[0040] In a specific embodiment, a fast determination of safety / non-safety is achieved based on a threshold. When the parameter meets the standard, it is directly assigned a value of 1, simplifying the evaluation process for high-safety-level buildings. For buildings that do not meet the standard but are still within the set safety range, the risk level is quantified by a ratio, which not only retains the accuracy of the evaluation but also differentiates safety hazards of different degrees. For buildings beyond the safety range, a value of 0 is directly assigned, and they are forcibly marked as high-risk objects to ensure that extreme dangerous situations are identified first. This avoids misjudgment or missed judgment caused by a single standard and provides accurate and efficient quantitative basis for the safety assessment of building structures in urban renewal through differential assignment.

[0041] Specifically, please refer to Figure 3 shown, the specific construction process of the land use efficiency evaluation index is as follows: B1. Extract the floor area ratio, land use mix, and green coverage rate from the land use data and perform standardization processing.

[0042] B2. Perform weighted fusion calculation on the standardized indicators to obtain the land use efficiency evaluation score value.

[0043] Among them, when the green coverage rate is lower than the set threshold, the update of the land use efficiency evaluation score is triggered, and the update rule of the comprehensive land use efficiency score is as follows: If the ratio of the number of consecutive monitoring periods when the green coverage rate is lower than the set threshold to the total monitoring periods exceeds the limit, a deduction ratio threshold is triggered, and the land use efficiency evaluation score value is correspondingly deducted according to the deduction ratio threshold.

[0044] Otherwise, divide the ladder interval according to the gap between the green coverage rate and the set threshold, and deduct according to the increasing ratio, with the upper limit of the deduction being the set deduction ratio threshold.

[0045] It should be added that the weights of the floor area ratio, land use mix, and green coverage rate can be respectively taken as 0.3, 0.3, and 0.4.

[0046] In a specific embodiment, assuming that the deduction ratio threshold is 30%, based on the threshold, with a 5% gap as one gear, the increasing ratio is set to 5%. That is, when 25% ≤ green coverage rate < 30%, a deduction of 10% of the initial land use efficiency score is made. When 20% ≤ green coverage rate < 25%, the deduction ratio is increased to 15%. When 15% ≤ green coverage rate < 20%, a deduction of 20% is made. When the green coverage rate < 15%, a deduction of 30% is made.

[0047] Furthermore, please refer to Figure 4 shown, the specific analysis process of the initial update potential value is: C1. Set the early warning thresholds for the building status evaluation index and the land use efficiency evaluation index.

[0048] C2. If any evaluation index of a certain geographical unit is lower than the set early warning threshold, assign its initial update potential value as 1.

[0049] C3. If there are indicators higher than the set warning threshold, calculate the initial update potential value through the attenuation function based on the building status evaluation indicators and the land use efficiency evaluation indicators.

[0050] It should be added that the specific calculation formula of the spatial attenuation function is supplemented as follows: , and are the weights corresponding to the preset building status indicators and land use efficiency indicators respectively, and are the building status evaluation indicators and the land use efficiency evaluation indicators respectively, and are the warning thresholds of the building status evaluation indicators and the land use efficiency evaluation indicators respectively, is the natural constant.

[0051] In a specific embodiment, through the dual-track mechanism of dynamic cycle monitoring + stepped differential deduction, it not only highlights the systematic problems of long-term non-compliance with greening standards but also accurately reflects the actual impact of short-term fluctuations. By triggering mandatory deductions through the proportion of consecutive monitoring cycles exceeding the limit, it can effectively identify and restrict areas that have long neglected greening construction and whose ecology has continued to deteriorate. The stepped deduction rule, for the situation where mandatory deductions are not triggered, conducts gradient deductions according to the gap degree between the greening coverage rate and the threshold, which can not only reflect the differential impact of different greening levels on land use efficiency but also avoid excessive punishment by setting a deduction ceiling, ensuring that the evaluation results have both a warning effect and reasonableness.

[0052] In the embodiment of the present invention, the initial update potential value is dynamically generated through the dual-threshold warning mechanism and the spatial attenuation model. Compared with the traditional single-factor evaluation, it can more scientifically and objectively reflect the update potential of each geographical unit, making the update potential evaluation more logical and persuasive, and providing a reliable basis for urban renewal decisions.

[0053] S3. Dynamically correct the initial update potential values of each geographical unit according to the spatial relevance of adjacent geographical units to generate the corrected update potential values.

[0054] Specifically, the specific implementation steps of the dynamic correction include: S31. Randomly select a geographical unit as the target geographical unit and obtain the initial update potential values of all its adjacent geographical units.

[0055] S32. Generate the final spatial distance index value based on the shortest travel time and the spatial straight-line distance between the target geographical unit and the adjacent geographical units.

[0056] S33. Generate the functional complementary index value by matching and associating the land use types of the adjacent geographical units and the target geographical unit.

[0057] S34. Allocate a correction coefficient based on the final spatial distance index value and the functional complementarity index value.

[0058] S35. Weight and correct the initial update potential value of the target geographical unit based on the correction coefficient to generate a corrected update potential value.

[0059] S36. Traverse all geographical units to complete the correction in turn, and output the corrected update potential values corresponding to all geographical units.

[0060] Furthermore, the specific generation process of the spatial distance index value in step S32 includes: J1. Calculate the traffic convenience degree through a path analysis algorithm according to the shortest travel time between the target geographical unit and adjacent geographical units.

[0061] Among them, the specific calculation formula for calculating the traffic convenience degree is: , represents the traffic convenience degree, represents the set actual sensitivity coefficient, and the value range is [0.05, 0.2]. The specific value can be combined with the experience of experts in aspects such as urban traffic and space utilization. For example, in urban renewal research, if past experience shows that traffic travel time has a relatively sensitive impact on regional development, the time sensitivity coefficient can be appropriately close to the upper limit of the value range, such as 0.2. If the impact is relatively less sensitive, a value closer to the lower limit, such as 0.05, can be selected. And The larger the value, the more obvious the decline in traffic accessibility when the travel time increases. represents the shortest travel time between the target geographical unit and adjacent geographical units.

[0062] J2. Calculate the geographical proximity through an inverse distance weighting model according to the spatial straight-line distance between the target geographical unit and adjacent geographical units.

[0063] Among them, the specific calculation formula for calculating the traffic convenience degree is: , represents the geographical proximity, represents the distance decay coefficient, and the value range is between 0.1 and 0.5. The specific value can be determined comprehensively by combining theory and experience. For example, in the city center or areas with high functional agglomeration, the distance has a more significant impact on geographical proximity, can approach 0.5. In the edge or areas with weak connections, a smaller value, such as close to 0.1, can be selected to reflect the actual intensity difference of distance decay. And The value determines the decay speed of the impact of distance on geographical proximity, The larger the value, the faster the geographical proximity decreases when the distance increases. Indicates the spatial straight-line distance between the target geographical unit and adjacent geographical units.

[0064] J3. The comprehensive traffic convenience degree and geographical proximity are weighted and fused to obtain the generated spatial distance index value, and a compensation coefficient is set according to the proximity type of adjacent geographical units.

[0065] Among them, the weighted fusion weights of the traffic convenience degree and geographical proximity can be determined by methods such as the expert scoring method, the analytic hierarchy process, the entropy weight method, or the combined weighting method, and can be flexibly adjusted in combination with the research objectives and scenarios. Taking the expert scoring method as an example, it is evaluated based on professional experience in the fields of planning and transportation. For example, in the urban central area, the traffic convenience is emphasized, the weight is set to 0.6 - 0.7, and the geographical proximity is taken as 0.3 - 0.4.

[0066] J4. The corresponding compensation is performed on the spatial distance index value through the compensation coefficient to obtain the final spatial distance index value.

[0067] Among them, setting the compensation coefficient according to the proximity type satisfies the following rules: if the proximity type is directly adjacent, the first compensation coefficient value is given; if the proximity type is separated by one geographical unit, the second compensation coefficient value is given, and the first compensation coefficient value is greater than the second compensation coefficient value.

[0068] It should be added that the specific process of performing the corresponding compensation on the spatial distance index value through the compensation coefficient to obtain the final spatial distance index value is as follows: , is the final spatial distance index value, is the spatial distance index value before compensation, is the compensation coefficient, and exemplarily, for the sake of reasonable compensation, in a specific embodiment, the first compensation coefficient value and the second compensation coefficient value can be set in combination with empirical data. For example, the first compensation value can be set to 0.1, and the second compensation coefficient value can be set to 0.05.

[0069] Furthermore, the specific generation process of the functional complementarity index value in step S33 includes: extracting the dominant land use types of adjacent geographical units and matching them with the land use type of the target geographical unit.

[0070] If it belongs to a preset complementary type combination, the functional complementarity index value is calculated according to the matched land use types and the preset weights of the corresponding land use types.

[0071] If it does not belong to the complementary combination, the correlation index is calculated based on the land use compatibility specification, and the functional complementarity index value is obtained by mapping through a preset mapping function according to the correlation index.

[0072] It should be added that land use types include but are not limited to residential land, commercial land, educational land, medical land, recreational land, transportation land, public service land, industrial land, garden land, agricultural land, greening land, etc. They are defined based on urban planning standards. And by way of example, the complementary type combinations of residential land include commercial land, educational land, medical land, and greening land. The complementary type combinations of commercial land include residential land, transportation land, recreational land, industrial land, and public service land. The complementary type combinations of industrial land include transportation land, greening land, residential land, and agricultural land.

[0073] It should be added that the specific method for calculating the functional complementary index value according to the number of matched land use types and the preset weights of the corresponding land use types is as follows: Sum up the matched land use types and the preset weights of the corresponding land use types to obtain the total matched weight, and divide it by the total sum of the preset weights of all land use types within the corresponding complementary type combination. Take the ratio as the functional complementary index value.

[0074] It also should be added that the mapping function mapping can be a Sigmoid function, and the input parameter is the correlation index.

[0075] Preferably, the specific calculation process of the correlation index is as follows: E1. Obtain the historical regional update dataset and then count the co-occurrence frequency of the corresponding land use types of the target geographical unit and adjacent geographical units.

[0076] It should be noted that the statistics of the co-occurrence frequency need to meet the following conditions: Only include the historical data of the same climate zone and economic development level zone of the target city, and exclude the interference of cross-regional statistics. Apply a time decay factor to the old urban area data to reduce the weight of expired data. The specific calculation formula of the time decay factor is: , is the data year, represents the time decay factor set in the data year. Through exponential decay, the older the data of the old urban area, the lower the weight, reducing the interference of expired data on the statistics of the co-occurrence frequency and ensuring that the analysis is more in line with the current actual situation. For example, the weight of data 10 years ago is reduced to about 36.79%, highlighting the reference value of relatively new data.

[0077] It also should be added that the co-occurrence frequency reflects the probability that the land use types of the target geographical unit and adjacent geographical units appear simultaneously in historical data or spatial distribution. It is obtained by calculating the ratio of the number of times the dominant land use type of the adjacent geographical unit appears adjacent to the land use type of the target geographical unit to the total number of times adjacent to all other types of the target geographical unit in the historical dataset.

[0078] E2. Query the initial value of the functional dependence weight of the land use types corresponding to the target geographical unit and the adjacent geographical unit according to the land use type functional dependence weight table.

[0079] In a specific embodiment, the land use type functional dependence weight table can be referred to as shown in Table 1, where the target type in the table refers to the land use type of the target geographical unit, and the adjacent type refers to the dominant land use type of the adjacent geographical unit.

[0080] Table 1 Compatibility Specification Table

[0081]

[0082] E3. Calculate the compatibility coefficient between the target geographical unit and the adjacent geographical unit according to the land use compatibility rules of the target city.

[0083] Understandably, specific examples of the land use compatibility rules are as follows: If the land use types of the target geographical unit and the adjacent geographical unit belong to the same compatibility type, the compatibility coefficient between the two is set to 1. If the land use types of the target geographical unit and the adjacent geographical unit belong to the conditional compatibility type, the compatibility coefficient between the two satisfies the formula: , is the environmental isolation compliance coefficient, , if the land use types of the target geographical unit and the adjacent geographical unit belong to the prohibited compatibility type, the compatibility coefficient between the two is set to 0. Among them, by setting the zeroing mechanism, it can ensure that the output result strictly complies with the legal land use specifications and avoid planning compliance risks.

[0084] Preferably, the specific calculation formula of the environmental isolation compliance coefficient is: , and respectively represent the weights corresponding to the isolation belt width and the monitoring pollution index, and the initial default values are 0.6 and 0.4 respectively. represents the actual isolation belt width, represents the minimum width required by the specification, and respectively represent the monitoring pollution index and the national standard limit value. represents the isolation belt width term. The increase of this term reflects the advantage of the isolation belt width. is the pollution index term. The smaller the pollution index and the larger the national standard limit value, the larger this term as a whole. Conversely, if the pollution is serious, it is assigned a value of 0 to suppress the value of the environmental isolation compliance coefficient.

[0085] It should be added that the same major compatibility category refers to a combination of land use types that meet the high functional synergy and no negative interference defined in the urban planning technical standards, mainly based on the urban land classification and the standard of planned construction land. If there are special provisions in local regulations, such as the urban renewal technical guidelines, local rules shall be preferred. Analyze the spatial distribution density of land use in the same major category through GIS tools. If the density similarity ≥ 70%, it shall be automatically classified into the same major compatibility category, such as commercial - business, residential - education.

[0086] Judgment process for conditionally compatible types, triggering conditions: When the land use type combination of the target geographical unit and the adjacent geographical unit meets any of the following scenarios, it is judged as conditionally compatible: 1) Environment - sensitive type, such as an industrial area adjacent to a residential area, where an isolation belt needs to be set up. Exemplarily, such as a green belt, a buffer zone.

[0087] 2) Time - period restriction type, such as a commercial area adjacent to a cultural relics protection area, where commercial activities need to be restricted during certain time periods. Exemplarily, such as banning noisy business forms at night.

[0088] 3) Capacity - control type, such as a high - density residential area adjacent to a park green space, where the development intensity needs to be restricted. Exemplarily, such as the floor area ratio ≤ 2.0.

[0089] For the sake of easy understanding, the prohibited compatibility types specifically involve historical buildings or cultural heritage protection areas, etc.

[0090] E4. Constrain the initial value of the functional dependence weight according to the compatibility coefficient to obtain the corrected functional dependence weight value.

[0091] It can be understood that the corrected functional dependence weight value is the product of the compatibility coefficient and the functional dependence weight.

[0092] E5. Calculate the association index through weighted summation by comprehensively considering the corrected functional dependence weight value and the co - occurrence frequency.

[0093] Furthermore, the specific distribution process of the correction coefficient in step S34 is as follows: Obtain the renewal planning categories of the target city, and set the spatial distance weight and the functional complementarity weight according to the renewal planning categories.

[0094] Obtain the correction coefficient according to the set weights, the final spatial distance index value, and the functional complementarity index value.

[0095] Exemplarily, the renewal planning categories include but are not limited to spatial structure optimization and functional quality improvement optimization. When the renewal planning category is spatial structure optimization, the spatial distance weight and the functional complementarity weight can be respectively set as 0.8 and 0.2. When the renewal planning category is functional quality improvement optimization, the spatial distance weight and the functional complementarity weight can be respectively set as 0.3 and 0.7.

[0096] Among them, exemplarily, the spatial structure optimization aims to relieve congestion and densify the road network, while the functional quality improvement optimization aims at industrial upgrading and mixed development.

[0097] Another exemplarily, the trigger design of the spatial structure optimization type is as follows: in the regulatory planning area where the target geographical unit is located, if the proportion of newly planned road area ≥ 10% or the 500-meter coverage rate of bus stops increases by ≥ 30%, the trigger design of the spatial structure optimization type is: in the area where the target geographical unit is located, it is clearly required in the plan that the mixed ratio of commercial-residential-public service land ≥ 1:1:1.

[0098] S4. Sort the corrected update potential values in descending order to generate a priority annotation form, and perform visual display in combination with the geographic information system.

[0099] In the embodiment of the present invention, multi-factor evaluation is carried out by integrating multi-source data such as building aging, land use and remote sensing images, breaking through the limitations of the traditional single data dimension and avoiding the one-sidedness of the evaluation results. At the same time, dynamic correction is carried out based on the spatial correlation of adjacent geographical units, effectively overcoming the drawbacks of the existing technology that ignores the linkage of geographical proximity, ensuring the integrity of urban functions, and realizing scientific and reasonable identification and planning of urban renewal areas.

[0100] It should be added that the priority annotation form is overlaid with the geographic information system layer, the update potential distribution is displayed in the form of a heat map, and the spatial coordinates and corrected update potential values of the high-priority areas are marked.

[0101] In the embodiment of the present invention, by sorting the corrected update potential values in descending order and performing visual display in combination with the geographic information system, the priority of the update potential of each area in the city can be intuitively presented. It is convenient for planners and decision-makers to quickly identify high-potential renewal areas, formulate targeted renewal strategies, and at the same time facilitate the reasonable allocation of resources and improve the efficiency of urban renewal work.

[0102] The above formulas are all dimensionless and take their numerical calculations. The formula is a formula obtained by collecting a large amount of data for software simulation to get the closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0103] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0104] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed 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 for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0105] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0106] As described above, this is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all such changes or substitutions should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0107] Finally, the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying urban renewal areas based on multi-source data, characterized in that: The method includes: Divide the target city into several geographic units, obtain the building aging data, land use data and remote sensing image data in each geographic unit, and form a multi-source data set; Construct building status evaluation indicators and land use efficiency evaluation indicators based on multi-source data sets, and dynamically generate initial renewal potential values ​​through a dual threshold early warning mechanism and attenuation model; The specific analysis process of the initial update potential value is as follows: Set warning thresholds for building status assessment indicators and land use efficiency assessment indicators; If any evaluation indicator of a geographical unit is lower than the set warning threshold, its initial update potential value is assigned a value of 1; If there are indicators that are higher than the set warning threshold, the initial renewal potential value is calculated through the attenuation function based on the building status evaluation indicators and the land use efficiency evaluation indicators; Dynamically correct the initial renewal potential value of each geographic unit according to the spatial correlation of adjacent geographic units to generate a corrected renewal potential value; The specific execution steps of the dynamic correction include: A geographical unit is randomly selected as the target geographical unit, and the initial update potential values ​​of all its adjacent geographical units are obtained; Generate the final spatial distance index value based on the shortest travel time and spatial straight-line distance between the target geographic unit and the adjacent geographic unit; By matching and associating the land use types of adjacent geographic units with the target geographic unit, the functional complementarity index value is generated; Allocate correction coefficients according to the final spatial distance index value and functional complementarity index value; Performing weighted correction on the initial renewal potential value of the target geographic unit based on the correction coefficient to generate a corrected renewal potential value; Traverse all geographic units and complete the correction in turn, and output the corresponding corrected update potential values ​​of all geographic units; The revised renewal potential values ​​are sorted in descending order, a priority labeling form is generated, and a visual display is performed in conjunction with the geographic information system.

2. The urban renewal area identification method based on multi-source data according to claim 1 is characterized by: The specific division rules of the target cities are as follows: The target area is divided into grid units with area differences within a preset threshold range based on the urban road network structure and administrative division boundaries, each grid unit contains at least one independent building complex, and the grid units are used as geographical units.

3. The urban renewal area identification method based on multi-source data according to claim 1 is characterized by: The specific construction process of the building status assessment index is as follows: Identify the degree of damage to building facades based on remote sensing image data; Extract building age and maintenance score from building aging data, and calculate structural stability parameters through a preset weight distribution model; Generate a building structure safety index based on the relationship between the structural stability parameter and the corresponding preset qualified threshold value; Generate a maintenance status score based on the maintenance frequency and capital investment in the maintenance record within a preset time window; Functional adaptability indicators are extracted from building aging data, and the building status assessment score is calculated by integrating the building structure safety index, maintenance status score and functional adaptability indicators.

4. The urban renewal area identification method based on multi-source data according to claim 1 is characterized by: The specific construction process of the land use efficiency evaluation index is as follows: Extract the volume ratio, land use mix and green coverage from the land use data and perform standardization; The weighted fusion calculation of each index after standardization is performed to obtain the land use efficiency evaluation score; Among them, when the green coverage rate is lower than the set threshold, the land use efficiency evaluation score is updated. The land use efficiency comprehensive score update rules are as follows: If the ratio of the number of consecutive monitoring cycles during which the green coverage rate is lower than the set threshold to the total monitoring cycle exceeds the limit, the deduction ratio threshold is set, and the land use efficiency assessment score is deducted accordingly according to the deduction ratio threshold; Otherwise, the step intervals are divided according to the gap between the green coverage rate and the set threshold, and deductions are made in increasing proportion, with the upper limit of the deduction being the set deduction proportion threshold.

5. The urban renewal area identification method based on multi-source data according to claim 1 is characterized in that: The specific generation process of the spatial distance index value includes: Calculate the degree of travel convenience based on the shortest travel time between the target geographical unit and the adjacent geographical units; Calculate geographic proximity based on the spatial straight-line distance between the target geographic unit and the adjacent geographic unit; The spatial distance index value is generated by weighted fusion of comprehensive travel convenience and geographical proximity, and the compensation coefficient is set according to the proximity type of adjacent geographical units; The spatial distance index value is compensated accordingly by the compensation coefficient to obtain a final spatial distance index value; Among them, the compensation coefficient is set according to the adjacent type to meet the following rules: If the proximity type is directly adjacent, a first compensation coefficient value is assigned; if the proximity type is one geographic unit apart, a second compensation coefficient value is assigned, and the first compensation coefficient value is greater than the second compensation coefficient value.

6. The method for identifying urban renewal areas based on multi-source data according to claim 1, characterized in that: The specific process of generating the functional complementarity index value includes: Match the dominant land use type of the adjacent geographic unit with the land use type of the target geographic unit; If it belongs to the preset complementary type combination, the functional complementary index value is calculated according to the matched land use types and the preset weights of the corresponding land use types; If it is not a complementary combination, the correlation index is calculated based on the land compatibility specification, and the functional complementary index value is obtained by mapping the correlation index through a preset mapping function.

7. The method for identifying urban renewal areas based on multi-source data according to claim 6, characterized in that: The specific calculation process of the correlation index is as follows: Obtain historical regional update data sets and then count the co-occurrence frequencies of corresponding land use types of target geographic units and adjacent geographic units; According to the land use type functional dependency weight table, query the initial value of the functional dependency weight of the corresponding land use type of the target geographical unit and the adjacent geographical unit; Calculate the compatibility coefficient between the target geographical unit and the adjacent geographical units according to the land use compatibility rules of the target city; According to the compatibility coefficient, the initial value of the functional dependency weight is constrained to obtain the modified functional dependency weight value; The comprehensive correction function relies on the weight value and the co-occurrence frequency to calculate the association index.

8. The method for identifying urban renewal areas based on multi-source data according to claim 1, characterized in that: The specific allocation process of the correction coefficient is as follows: Obtain the renewal planning category of the target city, and set the spatial distance weight and functional complementarity weight according to the renewal planning category; The correction coefficient is obtained according to the set weight, the final spatial distance index value and the functional complementarity index value.

Images