A method for town renewal zoning based on DBSCAN-GM algorithm

Abstract

The application provides a town renewal area delimitation method based on a DBSCAN-GM algorithm, comprising the following steps: performing preliminary clustering on data by using a Gaussian-Means algorithm, determining a clustering center, calculating key parameters EPS and MinPts of a DBSCAN algorithm based on the clustering center, and performing further clustering analysis by using the DBSCAN-GM algorithm. The application not only simplifies the parameter selection process, but also improves the stability and accuracy of the clustering result. By combining the advantages of the DBSCAN and Gaussian-Means algorithms, the parameter selection and clustering stability problem is improved, the accuracy and reliability of the town renewal area delimitation are improved, so that the advantages of big data and intelligent algorithms can be fully utilized, the shortcomings of traditional methods in data processing and analysis are solved, and the renewal area can be accurately and reasonably delimited.

Description

Technical Field

[0001] This invention belongs to the field of urban and rural planning and management technology, specifically relating to a method for delineating urban renewal zones based on the DBSCAN-GM algorithm. Background Technology

[0002] Urban renewal is a crucial means to achieve sustainable urban development and enhance urban functions and environmental quality. The focus of urban development is gradually shifting from large-scale incremental construction to stock renewal and structural adjustment. However, traditional urban renewal planning methods face numerous challenges in practical application. These methods primarily rely on manual surveys and expert experience, which suffer from several major problems: First, data collection and processing efficiency is low, making it difficult to reflect dynamic urban changes in a timely manner; second, they are highly subjective, easily influenced by the experience and knowledge level of planners, leading to inconsistent planning results and insufficient scientific rigor and objectivity; third, traditional methods struggle to handle large-scale, multi-dimensional urban data, making it impossible to comprehensively and accurately assess the actual needs and effects of urban renewal. These problems make traditional urban renewal planning methods ill-suited to address the complex and ever-changing development needs of modern cities.

[0003] To overcome the shortcomings of traditional urban renewal zone delineation methods, and in the context of today's technological revolution, the application of intelligent technologies has enabled urban renewal zone delineation to shift from the traditional reliance on ground surveys and expert experience to a more dynamic, accurate, and efficient process. Among these, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is an important tool for urban renewal zone delineation due to its superior performance in handling noisy data and identifying clusters of arbitrary shapes. However, relying solely on the DBSCAN algorithm for urban renewal zone delineation still presents some problems. The DBSCAN algorithm is sensitive to parameter settings, especially the selection of parameters EPS (neighborhood radius) and MinPts (minimum number of points), which directly affect the clustering results. Inappropriate parameter selection can lead to unstable clustering results, affecting the accurate delineation of the renewal area. Furthermore, the DBSCAN algorithm has high computational complexity when processing high-dimensional data, which can easily lead to low computational efficiency. Summary of the Invention

[0004] This invention discloses a method for delineating urban renewal areas based on the DBSCAN-GM algorithm, which can fully utilize the advantages of big data and intelligent algorithms, solve the shortcomings of traditional methods in data processing and analysis, and accurately and reasonably delineate renewal areas.

[0005] This invention discloses a method for delineating urban renewal zones based on the DBSCAN-GM algorithm, the method comprising the following steps:

[0006] Step 1: Collect vector data related to urban renewal and public opinion survey results in the target study area; preprocess and standardize the collected data; construct extended fields for corresponding land parcels; and establish an urban renewal database.

[0007] Step 2: Perform feature extraction and dimensionality reduction on the data in the urban renewal database to obtain comprehensive indicators; identify data points of urban renewal objects based on the comprehensive indicators, and evaluate the identification results;

[0008] Step 3: Based on the data points of urban renewal objects, use the Gaussian-Means algorithm to perform cluster analysis on the data points, automatically divide the data into several clusters, and determine a center point for each cluster;

[0009] Step 4: Calculate the local EPS value for each cluster, and select the minimum local EPS value among all clusters as the global EPS value. At the same time, calculate the MinPts parameter based on the clustering characteristics, and select the minimum local MinPts parameter among all clusters as the global MinPts parameter.

[0010] Step 5: Based on the global EPS value and the global MinPts parameter, run the DBSCAN algorithm to perform the final cluster analysis to identify potential urban renewal areas.

[0011] Step 6: Distinguish between potential key areas for urban renewal and potential spatial units for urban renewal. Within the potential key areas for urban renewal, repeat steps 3 to 5 to identify potential spatial units for urban renewal.

[0012] Step 7: Based on the vector data collected in Step 1 and the results of the public opinion survey, the boundaries of potential urban renewal areas, including potential key urban renewal areas and potential urban renewal spatial units, are revised to form an urban renewal zone delineation scheme.

[0013] Step 1 further includes:

[0014] Step 1.1: Collect land data, population data, building data, industrial economic data, public service facility data, infrastructure data, administrative boundary data, planning boundary data, and rigid transmission boundary data of the target study area through the planning management department, and supplement the data with field exploration.

[0015] Step 1.2: Perform preprocessing on the vector data collected in Step 1.1, including cleaning, organizing, and format conversion. Then, normalize the preprocessed data to the [0,1] interval. The normalization formula is as follows:

[0016]

[0017] Where, x ij It is the value of the i-th sample on the j-th indicator, min(x j ) and max(x j These are the minimum and maximum values ​​of the j-th indicator, respectively.

[0018] Step 1.3: Using the standardized data obtained in Step 1.2, construct extended fields for the corresponding land parcels to establish an urban renewal database.

[0019] As one preferred option, in step 1.1, the land data includes areal vector data of plot ratio, building density, land use compliance, and land attributes; the population data includes population employment data and population density, per capita residential building area, and residential unit type areal vector data; the building data includes areal vector data of construction year, number of floors, building quality, and building structure; the industrial economic data includes areal vector data of economic output, business offices, commercial services, and industrial matching degree; the public service facility data includes areal vector data of scientific research and innovation, culture and education, sports and fitness, medical and health care, social welfare, parks and green spaces, and squares; the infrastructure data includes areal vector data of transportation facilities and public utilities; the administrative boundary data includes the administrative boundaries of cities, counties / districts, and townships / streets; the rigid transmission boundary data includes areal vector data of areas overlapping with historical protection, ecological protection, or other special planning and construction areas already delineated by the overall land space plan and related statutory plans; all areal vector data are based on land parcels.

[0020] Step 2 further includes:

[0021] Step 2.1: Directly include land that faces development strategy adjustments, land with health and safety hazards, land with weak supporting facilities that cannot be improved from the outside, land whose use does not meet the requirements of urban development, and land with urgent needs for historical and cultural protection or historical style enhancement into urban renewal targets.

[0022] Step 2.2: Calculate the weights of each indicator using the entropy weight method to assess the importance of each indicator in urban renewal; the formula for calculating the weight of each indicator is as follows:

[0023]

[0024] Where, p ij This represents the proportion of the i-th sample on the j-th indicator, where m is the total number of samples;

[0025] The formulas for calculating the entropy values ​​of each indicator are as follows:

[0026]

[0027] in, It is a constant used to ensure that the entropy value is in the range [0,1].

[0028] The formula for calculating the weight of each indicator is as follows:

[0029]

[0030] Among them, w j This represents the weight of the j-th indicator, where n is the total number of indicators;

[0031] Step 2.3: Construct a weighted covariance matrix based on the index weights obtained in Step 2.2. Use the PCA method to reduce the dimensionality of the weights determined by the entropy weight method, extract the feature vectors, and reduce the dimensionality of the data. This specifically includes the following sub-steps:

[0032] Construct the weighted covariance matrix:

[0033]

[0034] Where, x i It is the standardized data vector of the i-th sample. is the sample mean vector, where m is the total number of samples;

[0035] Calculate the eigenvalues ​​and eigenvectors of the covariance matrix:

[0036] Cv=λv

[0037] Where λ is the eigenvalue and v is the corresponding eigenvector;

[0038] Select the k largest eigenvalues ​​and their corresponding eigenvectors to form the eigenvector matrix V. k ;

[0039] Using the eigenvector matrix V k Project the original data onto a new low-dimensional space:

[0040] Z = XV k

[0041] Where Z is the data matrix after dimensionality reduction, and X is the original data matrix after standardization;

[0042] Step 2.4: Multiply the principal components extracted by PCA with their corresponding weights to obtain the weighted principal components of each indicator, which will be used as the final comprehensive indicator weight Y.

[0043] Y = ZW

[0044] Where Y is the final comprehensive index weight, Z is the data matrix after dimensionality reduction, and W is the weight vector calculated by the entropy weight method.

[0045] Step 2.5: Calculate the weighted comprehensive index score for each plot area using the comprehensive index weight Y. Based on the weighted comprehensive index score of each plot, use the natural breakpoint analysis method in the geographic information system, combined with expert scoring, to comprehensively determine and set a threshold A. Plot areas exceeding threshold A are included in the urban renewal projects, while plot areas below threshold A are not included in the urban renewal projects.

[0046] Step 3 further includes:

[0047] Step 3.1: Based on the surface data of the urban renewal objects identified in Step 2, establish an envelope rectangle and generate the geometric center point of the envelope rectangle as the data point of the urban renewal object;

[0048] Step 3.2: For the data points of the urban renewal targets, run the Gaussian-Means algorithm to divide the data into the optimal number of clusters C. k Each cluster has a defined center point M. i , i = 1…K.

[0049] Step 4 further includes:

[0050] Step 4.1: For each cluster, calculate the average distance from the cluster center to all points within the cluster as the local EPS value for that cluster.

[0051]

[0052] Where, r j It is the local EPS value of the j-th cluster, N j M is the number of points in the j-th cluster. j It is the center point of the j-th cluster, x ij It is the i-th point in the j-th cluster, distance 2 (M j ,x ij ) is the center point M j Point x ij The Euclidean distance;

[0053] Step 4.2: Select the minimum value from the local EPS values ​​of all clusters as the global EPS value.

[0054] EPS global =min(r1,r2,…,r) k )

[0055] Among them, EPS global This represents the global EPS value, k is the total number of clusters, and r1, r2, ..., r k These are the local EPS values ​​for each cluster;

[0056] Step 4.3: For each cluster, calculate the MinPts parameter:

[0057]

[0058] Among them, MinPts j r is the MinPts parameter of the j-th cluster. j It is the local EPS value of the j-th cluster, N j It is the number of points in the j-th cluster, TotalVolume j It is the total area of ​​the j-th cluster;

[0059] Step 4.4: Select the minimum value from the local MinPts values ​​of all clusters as the global MinPts value:

[0060] MinPts global =min(MinPts1,MinPts2,…,MinPts k )

[0061] Among them, MinPts global This refers to the global MinPts value, where k is the total number of clusters, and MinPts1, MinPts2, ..., MinPts k These are the local MinPts values ​​for each cluster.

[0062] Step 5 further includes:

[0063] Step 5.1: Using the EPS value and MinPts parameter calculated in Step 4, execute the DBSCAN algorithm;

[0064] Step 5.2: Based on the output of the DBSCAN algorithm, generate a cluster label for each data point; where data points with a number of neighbors greater than or equal to the MinPts parameter are marked as core points, data points with a number of neighbors less than the MinPts parameter but within the neighborhood of a core point are marked as boundary points, and data points that do not belong to any cluster are marked as noise points.

[0065] Step 5.3: Evaluate the clustering effect by calculating the silhouette coefficient index;

[0066] Step 5.4: By visualizing the core points and their neighborhood radii, the range of several clusters and their neighborhood radii is superimposed. The superimposed area is used as the high-density area of ​​the identified urban renewal objects and is defined as a potential urban renewal area.

[0067] Step 6 further includes:

[0068] Step 6.1: Use GIS tools to calculate the area of ​​each potential urban renewal area, classify the areas, and update the classification results to the GIS database. Specifically, for cities at the prefecture level and above, areas with an area greater than 1 square kilometer are marked as key potential urban renewal areas; areas with an area less than or equal to 1 square kilometer are marked as potential urban renewal spatial units; for counties, county-level cities, and townships, they are directly marked as potential urban renewal spatial units.

[0069] Step 6.2: Within the potential urban renewal key areas, repeat steps 3 to 5 to identify potential urban renewal spatial units within the potential urban renewal key areas.

[0070] Step 7 further includes:

[0071] Step 7.1: Integrate the vector data collected in Step 1 into a unified geographic information system;

[0072] Step 7.2: In the geographic information system, the boundaries of the secondary planning zones of the overall land space plan, the administrative boundaries of townships and above, and the boundaries of potential key areas for urban renewal are overlaid. Spatial segmentation tools are used to spatially correct the boundaries of potential key areas for urban renewal.

[0073] Step 7.3: Overlay the boundaries of the detailed planning unit, the boundaries of grassroots mass self-governing organizations, and the boundaries of potential urban renewal spatial units. Use spatial segmentation tools to spatially correct the boundaries of potential urban renewal spatial units; overlay and correct the boundaries between potential urban renewal areas and the protection scope of historical and cultural blocks within historical and cultural cities.

[0074] Step 7.4: Organize public participation activities through questionnaires, public meetings and online platforms to present the preliminary boundary adjustment results to residents and stakeholders, collect their feedback and opinions and analyze them, identify the concerns and suggestions of residents and stakeholders regarding the regional boundary adjustment, and further adjust the boundaries of key urban renewal areas and urban renewal spatial units.

[0075] Step 7.5: Update the final corrected regional boundaries to the GIS database to form a GIS data package for the urban updated region.

[0076] The beneficial effects of this invention are as follows:

[0077] By combining the advantages of the DBSCAN and Gaussian-Means algorithms, this invention improves parameter selection and cluster stability, thereby enhancing the accuracy and reliability of urban renewal zone delineation. Specifically, when performing data clustering, the DBSCAN-GM algorithm first uses the Gaussian-Means algorithm for preliminary clustering to determine cluster centers. Then, based on these cluster centers, it calculates the key parameters EPS and MinPts of the DBSCAN algorithm for further cluster analysis. This method not only simplifies the parameter selection process but also improves the stability and accuracy of the clustering results. The urban renewal zone delineation method based on the DBSCAN-GM algorithm of this invention fully leverages the advantages of big data and intelligent algorithms, overcoming the shortcomings of traditional methods in data processing and analysis, and accurately and rationally delineating renewal areas. Attached Figure Description

[0078] Figure 1 This is a flowchart of the urban renewal zone delineation method based on the DBSCAN-GM algorithm of the present invention;

[0079] Figure 2 This diagram illustrates the execution steps of the urban renewal zone delineation method based on the DBSCAN-GM algorithm of the present invention. Detailed Implementation

[0080] The following embodiments are provided to enable those skilled in the art to more fully understand the present invention, but do not limit the invention in any way.

[0081] This invention discloses a method for delineating urban renewal zones based on the DBSCAN-GM algorithm, the method comprising the following steps:

[0082] Step 1: Collect vector data related to urban renewal and public opinion survey results in the target study area; preprocess and standardize the collected data; construct extended fields for corresponding land parcels; and establish an urban renewal database.

[0083] Step 2: Perform feature extraction and dimensionality reduction on the data in the urban renewal database to obtain comprehensive indicators; identify data points of urban renewal objects based on the comprehensive indicators, and evaluate the identification results;

[0084] Step 3: Based on the data points of urban renewal objects, use the Gaussian-Means algorithm to perform cluster analysis on the data points, automatically divide the data into several clusters, and determine a center point for each cluster;

[0085] Step 4: Calculate the local EPS value for each cluster, and select the minimum local EPS value among all clusters as the global EPS value. At the same time, calculate the MinPts parameter based on the clustering characteristics, and select the minimum local MinPts parameter among all clusters as the global MinPts parameter.

[0086] Step 5: Based on the global EPS value and the global MinPts parameter, run the DBSCAN algorithm to perform the final cluster analysis to identify potential urban renewal areas.

[0087] Step 6: Distinguish between potential key areas for urban renewal and potential spatial units for urban renewal. Within the potential key areas for urban renewal, repeat steps 3 to 5 to identify potential spatial units for urban renewal.

[0088] Step 7: Based on the vector data collected in Step 1 and the results of the public opinion survey, the boundaries of potential urban renewal areas, including potential key urban renewal areas and potential urban renewal spatial units, are revised to form an urban renewal zone delineation scheme.

[0089] See Figure 1 and Figure 2 The method for delineating urban renewal zones of the present invention specifically includes the following steps:

[0090] S1. First, conduct data collection and build an urban renewal database.

[0091] Data was collected by searching various information departments through computer networks. Data that could not be collected through manual questionnaires and big data analysis using Python 3.12 was obtained. Then, the data of each indicator was standardized by the entropy weight method to normalize them to the [0,1] interval. The data was then imported into the geographic information platform and extended fields were constructed for the corresponding land parcels to establish a town renewal database.

[0092] S2. Then, based on comprehensive indicators, identify urban renewal targets and evaluate the identification results.

[0093] The proportion, entropy value, and weight of each indicator are calculated using the entropy weight method to assess the importance of each indicator in urban renewal. Based on these indicator weights, a weighted covariance matrix is ​​further constructed. The PCA method is then used to reduce the dimensionality of the weights determined by the entropy weight method, extracting feature vectors and reducing the dimensionality of the data.

[0094] The principal components extracted by PCA are multiplied by their corresponding weights to obtain the weighted principal components of each indicator, which are used as the final comprehensive indicator Y. Based on this, combined with the classification of urban renewal objects, the corresponding types of urban renewal objects are identified and the urban renewal threshold A is evaluated, thus identifying the surface data of urban renewal objects.

[0095] S3. Cluster analysis based on urban renewal object data points.

[0096] The Gaussian-Means algorithm is used to perform preliminary cluster analysis on the data points, determine the cluster centers, test the Gaussian distribution hypothesis, and finally optimize the location of the cluster centers.

[0097] S4. Calculate and select the key parameters EPS and MinPts for the DBSCAN algorithm.

[0098] Calculate the local EPS value for each cluster, and select the minimum local EPS value among all clusters as the global EPS value. At the same time, calculate the MinPts parameter based on the clustering characteristics.

[0099] S5. Run the DBSCAN algorithm and label the clustering results.

[0100] Based on the calculated EPS and MinPts parameters, the DBSCAN algorithm is run to perform cluster analysis, and core points, boundary points, and noise points are marked to evaluate the clustering effect.

[0101] S6. Use GIS tools to classify regions and repeat cluster analysis in key regions.

[0102] The area of ​​each potential urban renewal area is calculated and classified into key areas and spatial units. Cluster analysis is repeated within the key areas to further identify renewal spatial units.

[0103] S7. Integrate data to correct boundaries and make further adjustments through public participation.

[0104] The collected vector data was integrated into the GIS system for spatial segmentation and boundary correction. Public feedback was collected through questionnaires, public meetings, and online platforms to further adjust the regional boundaries.

[0105] Example

[0106] The following will use the urban renewal zone delineation based on the DBSCAN-GM algorithm in a certain ancient city as an example to illustrate the technical solution of the present invention in detail.

[0107] Step 1: Collect and standardize data from the target study area through the planning management department, construct extended fields for corresponding land parcels, and establish an urban renewal database. This specifically includes:

[0108] Step 1.1 Collect data from various information departments through computer networks. If data cannot be collected manually, it can be obtained through manual questionnaires and big data analysis using Python 3.12. Import the collected land data, population data, building data, industrial economic data, public service facility data, infrastructure data, administrative boundary data, planning boundary data, and rigidly transmitted boundary data of a certain ancient city into the geographic information system.

[0109] Land data includes areal vector data such as plot ratio, building density, land use compliance, and land attributes. Population data includes population employment data such as employment population density, per capita residential building area, and residential unit type.

[0110] Building data includes planar vector data such as year of construction, number of floors, building quality, and building structure; industrial and economic data includes planar vector data such as economic output, business offices, commercial services, and industry matching degree.

[0111] Public service facility data includes area vector data of scientific research and innovation, culture and education, sports and fitness, medical and health care, social welfare, parks and green spaces, squares, etc.

[0112] Infrastructure data includes areal vector data of transportation facilities, public utilities, and ecological and environmental impacts.

[0113] Administrative boundary data includes township-level administrative boundaries and boundaries of grassroots mass self-governing organizations (communities).

[0114] The planning boundary data includes vector data of ecological protection red lines, permanent basic farmland, and urban development boundaries.

[0115] The rigid transmission boundary includes the regional areal vector data that overlaps with historical protection, ecological protection or other special planning and construction areas already delineated in the overall national spatial plan and related statutory plans.

[0116] The collected vector data is cleaned, organized, and converted to ensure its accuracy and consistency.

[0117] Step 1.2: Standardize the data of each indicator using the entropy weight method, normalizing it to the [0,1] interval. The standardization formula is as follows:

[0118]

[0119] Where, x ij It is the value of the i-th sample on the j-th indicator, min(x j ) and max(x j ) are the minimum and maximum values ​​of the j-th indicator, respectively.

[0120] Step 1.3: Import the obtained statistical data, vector information, and interview data into the geographic information platform with the CGS-WGS-1984 coordinate system, construct extended fields for the corresponding land parcels, and establish an urban renewal database. The spatial elements in the database meet the requirements of TD / T1057-2020 and are incorporated into the national land space basic data platform.

[0121] Step 2: Urban renewal targets are screened using a direct screening method. For other areas, the entropy weight method is used to calculate the weights of each indicator and construct a weighted covariance matrix. PCA is then used to reduce the dimensionality of the weights determined by the entropy weight method, extracting feature vectors and reducing the data dimensionality to obtain comprehensive indicators. Urban renewal targets are identified based on these comprehensive indicators, and the identification results are evaluated. Specifically, this includes:

[0122] Step 2.1: Directly include land that is facing development strategy adjustments, land with health and safety hazards, land with weak supporting facilities that cannot be improved from the outside, land whose use does not meet the requirements of urban development, and land with urgent needs for historical and cultural protection or historical appearance enhancement into urban renewal targets.

[0123] Step 2.2: Calculate the weights of each indicator using the entropy weight method to assess the importance of each indicator in urban renewal. The formula for calculating the weight of each indicator is as follows:

[0124]

[0125] Where, p ij Let m represent the proportion of the i-th sample on the j-th indicator, and m be the total number of samples.

[0126] The formulas for calculating the entropy values ​​of each indicator are as follows:

[0127]

[0128] in, It is a constant used to ensure that the entropy value is in the range [0,1].

[0129] The formula for calculating the weight of each indicator is as follows:

[0130]

[0131] Among them, w j This represents the weight of the j-th indicator, where n is the total number of indicators.

[0132] Step 2.3: Construct a weighted covariance matrix based on the index weights obtained in Step 2.2. Use the PCA method to reduce the dimensionality of the weights determined by the entropy weight method, extract the feature vectors, and reduce the dimensionality of the data.

[0133] Construct the weighted covariance matrix:

[0134]

[0135] Where, x i It is the standardized data vector of the i-th sample. It is the sample mean vector, and m is the total number of samples.

[0136] Calculate the eigenvalues ​​and eigenvectors of the covariance matrix by solving the eigenvalue decomposition problem.

[0137] Cv=λv

[0138] Where λ is the eigenvalue and v is the corresponding eigenvector.

[0139] Principal component selection: Select the k largest eigenvalues ​​and their corresponding eigenvectors to form the eigenvector matrix V. k .

[0140] Data dimensionality reduction: using the eigenvector matrix V k Project the original data into a new low-dimensional space:

[0141] Z = XV k

[0142] Where Z is the data matrix after dimensionality reduction, and X is the original data matrix after standardization.

[0143] Step 2.4: Multiply the principal components extracted by PCA with their corresponding weights to obtain the weighted principal components of each indicator, which will be used as the final comprehensive indicator. The formula is as follows:

[0144] Y = ZW

[0145] Where Y is the final comprehensive index weight, Z is the data matrix after dimensionality reduction, and W is the weight vector calculated by the entropy weight method.

[0146] Step 2.5: Calculate the weighted comprehensive index score for each region using the comprehensive index weight Y. Based on the scores, use the natural breakpoint analysis method in Geographic Information System (GIS) combined with expert judgment to establish a judgment threshold A. Regions exceeding this threshold are included in the urban renewal project, while regions below this threshold are not included.

[0147] Step 2.6: Evaluate the recognition results, including the evaluation of indicators such as accuracy and stability, to verify the effectiveness and reliability of the weight recognition system.

[0148] Step 3: Determine the final number of clusters and cluster centers by performing preliminary clustering, Gaussian distribution hypothesis testing, and calculating and optimizing cluster centers using the description length criterion.

[0149] Step 3.1: Based on the surface data of the ancient city town update object identified in Step 2, establish an envelope rectangle and generate the geometric center point of the envelope rectangle so that it can be used for subsequent analysis based on such data points.

[0150] Step 3.2: Perform preliminary cluster analysis using the Gaussian-Means (G-Means) algorithm to determine the optimal number and structure of clusters: Input the dataset, run the Gaussian-Means algorithm, and divide the data into the optimal number of clusters C. k Each cluster has a defined center point M. i (where i = 1…K), the obtained clusters and centroids will be used to determine the parameters EPS and Minpts of the DBSCAN algorithm.

[0151] Step 4: Calculate and select the key parameters EPS and MinPts for the DBSCAN algorithm.

[0152] 4.1 For each cluster, calculate the average distance from the cluster center to all points within the cluster as the local EPS value for that cluster:

[0153]

[0154] Step 4.2: Select the minimum value from the local EPS values ​​of all clusters as the global EPS value.

[0155] EPS global =min(r1,r2,…,r) k )

[0156] Step 4.3: For each cluster, calculate the MinPts parameter:

[0157]

[0158] Step 4.4: Select the minimum value from the local MinPts values ​​of all clusters as the global MinPts value:

[0159] MinPts global =min(MinPts1,MinPts2,…,MinPts k )

[0160] Step 5: Run the DBSCAN algorithm using the calculated EPS and MinPts parameters, label the clustering results, and evaluate the clustering effect through visualization.

[0161] Step 5.1: Using the EPS value and MinPts parameter calculated in Step 4, run the DBSCAN algorithm to perform cluster analysis.

[0162] Step 5.2: Based on the output of the DBSCAN algorithm, the data points are labeled as core points, boundary points, and noise points, and a cluster label is generated for each data point to identify which cluster the data point belongs to or to identify it as a noise point.

[0163] Step 5.3: Evaluate the clustering effect by calculating the silhouette coefficient. The silhouette coefficient reflects the compactness and separation of clusters, ensuring the quality of the clustering results.

[0164] Step 5.4: By visualizing the core points and their neighborhood radii, the sets of several clusters and their neighborhood radii are superimposed. These areas are the high-density areas of a certain ancient city's urban renewal object identified by the DBSCAN algorithm, i.e., potential urban renewal areas.

[0165] Step 6: Use GIS tools to calculate and classify the area of ​​potential urban renewal areas, and repeat cluster analysis in key areas to identify renewal spatial units.

[0166] Step 6.1: Use GIS tools to calculate the area of ​​each potential urban renewal area, thereby classifying the areas:

[0167] Areas with a floor area greater than 1 square kilometer are designated as potential key areas for urban renewal.

[0168] Areas with a floor area of ​​1 square kilometer or less are designated as potential urban renewal spatial units.

[0169] Step 6.2: Within the potential urban renewal key areas, repeat steps 3 to 5 to identify potential urban renewal spatial units within the potential urban renewal key areas.

[0170] Step 7: Integrate vector data for spatial segmentation and boundary correction, and further adjust the boundaries of the urban renewal area of ​​a certain ancient city through public participation.

[0171] Step 7.1: Integrate the vector data collected in Step 1, including administrative boundary data, planning boundary data, rigid transmission boundary data, etc., into a unified Geographic Information System (GIS).

[0172] Step 7.2: In the geographic information system, the boundaries of the secondary planning zones of the overall land space plan, the administrative boundaries of townships and above, and the boundaries of potential key areas for urban renewal are overlaid. Spatial segmentation tools are used to spatially correct the boundaries of potential key areas for urban renewal.

[0173] Step 7.3: Overlay the boundaries of the detailed planning unit, the boundaries of the grassroots mass self-governing organizations (communities), and the boundaries of the potential urban renewal spatial units. Use spatial segmentation tools to spatially correct the boundaries of the potential urban renewal spatial units.

[0174] Since the ancient city is a famous historical and cultural city, it is also necessary to overlap and correct the boundary between the potential urban renewal area and the historical and cultural block.

[0175] Step 7.4: Organize public participation activities through questionnaires, public meetings, and online platforms to present the preliminary boundary adjustment results to residents and stakeholders, collect their feedback and opinions, and analyze them. By identifying the main concerns and suggestions of residents and stakeholders regarding the regional boundary adjustment, further adjustments will be made to the boundaries of key urban renewal areas and urban renewal spatial units.

[0176] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A method for delineating urban renewal zones based on the DBSCAN-GM algorithm, characterized in that, The method includes the following steps: Step 1: Collect vector data related to urban renewal and public opinion survey results for the target study area; preprocess and standardize the collected data; construct extended fields for corresponding land parcels; and establish an urban renewal database. Step 2: Perform feature extraction and dimensionality reduction on the data in the urban renewal database to obtain comprehensive indicators; identify data points of urban renewal objects based on the comprehensive indicators, and evaluate the identification results; Step 3: Based on the data points of urban renewal objects, use the Gaussian-Means algorithm to perform cluster analysis on the data points, automatically divide the data into several clusters, and determine a center point for each cluster; Step 4: Calculate the local EPS value for each cluster, and select the minimum local EPS value among all clusters as the global EPS value. At the same time, calculate the MinPts parameter based on the clustering characteristics, and select the minimum local MinPts parameter among all clusters as the global MinPts parameter. Step 4 further includes: Step 4.1: For each cluster, calculate the average distance from the cluster center to all points within the cluster as the local EPS value for that cluster. Where, r j It is the local EPS value of the j-th cluster, N j M is the number of points in the j-th cluster. j It is the center point of the j-th cluster, x ij It is the i-th point in the j-th cluster, distance 2 (M j ,x ij ) is the center point M j Point x ij The Euclidean distance; Step 4.2: Select the minimum value from the local EPS values ​​of all clusters as the global EPS value. EPS global =min(r1,r2,…,r k ) Among them, EPS global This represents the global EPS value, k is the total number of clusters, and r1, r2, ..., r k These are the local EPS values ​​for each cluster; Step 4.3: For each cluster, calculate the MinPts parameter: Among them, MinPts j r is the MinPts parameter of the j-th cluster. j It is the local EPS value of the j-th cluster, N j It is the number of points in the j-th cluster, TotalVolume j It is the total area of ​​the j-th cluster; Step 4.4: Select the minimum value from the local MinPts values ​​of all clusters as the global MinPts value: MinPts global =min(MinPts1,MinPts2,…,MinPts k ) Among them, MinPts global These are the global MinPts values, MinPts1, MinPts2, ..., MinPts k These are the local MinPts values ​​for each cluster; Step 5: Based on the global EPS value and the global MinPts parameter, run the DBSCAN algorithm to perform the final cluster analysis to identify potential urban renewal areas; the urban renewal areas include potential key urban renewal areas and potential urban renewal spatial units. Step 6: Distinguish between potential key areas for urban renewal and potential spatial units for urban renewal. Within the key areas for urban renewal, repeat steps 3 to 5 to identify potential spatial units for urban renewal. Step 7: Based on the vector data collected in Step 1 and the results of the public opinion survey, the regional boundaries of the potential key areas for urban renewal and the potential spatial units for urban renewal in the potential urban renewal areas are revised to form an urban renewal zone delineation scheme.

2. The method for delineating urban renewal zones based on the DBSCAN-GM algorithm according to claim 1, characterized in that, Step 1 further includes: Step 1.1: Collect land data, population data, building data, industrial economic data, public service facility data, infrastructure data, administrative boundary data, planning boundary data, and rigid transmission boundary data of the target study area through the planning management department, and supplement the data with field exploration. Step 1.2: Perform preprocessing on the vector data collected in Step 1.1, including cleaning, organizing, and format conversion. Then, normalize the preprocessed data to the [0,1] interval. The normalization formula is as follows: Where, x i′ j ′ It is the i-th ′ The sample at the jth ′ The value of each indicator, min(x) j′ ) and max(x j′ ) are respectively the j-th ′ The minimum and maximum values ​​of each indicator; Step 1.3: Using the standardized data obtained in Step 1.2, construct extended fields for the corresponding land parcels to establish an urban renewal database.

3. The method for delineating urban renewal zones based on the DBSCAN-GM algorithm according to claim 2, characterized in that, In step 1.1, land data includes isometric vector data of plot ratio, building density, land use compliance, and land attributes; population data includes isometric vector data of employment population density, per capita residential building area, and residential unit type; building data includes isometric vector data of construction year, number of floors, building quality, and building structure; industrial economic data includes isometric vector data of economic output, business offices, commercial services, and industry matching degree; public service facility data includes isometric vector data of scientific research and innovation, culture and education, sports and fitness, medical and health care, social welfare, parks and green spaces, and squares; infrastructure data includes isometric vector data of transportation facilities and public utilities; and administrative boundary data includes administrative boundaries of cities, counties / districts, and townships / streets. All isometric vector data are based on land parcels.

4. The method for delineating urban renewal zones based on the DBSCAN-GM algorithm according to claim 1, characterized in that, Step 2 further includes: Step 2.1: Determine the land directly included in urban renewal projects; Step 2.2: Calculate the weights of each indicator using the entropy weight method to assess the importance of each indicator in urban renewal; the formula for calculating the weight of each indicator is as follows: Where, p i′ j ′ Indicates the i-th ′ The sample at the jth ′ The proportion of each indicator, where m is the total number of samples; The formulas for calculating the entropy values ​​of each indicator are as follows: in, It is a constant used to ensure that the entropy value is in the range [0,1]. The formula for calculating the weight of each indicator is as follows: Among them, w j′ Indicates the j-th ′ The weight of each indicator, where n is the total number of indicators; Step 2.3: Construct a weighted covariance matrix based on the index weights obtained in Step 2.

2. Use the PCA method to reduce the dimensionality of the weights determined by the entropy weight method, extract the feature vectors, and reduce the dimensionality of the data. This specifically includes the following sub-steps: Construct the weighted covariance matrix: Where, x i′ It is the i-th ′ A standardized data vector of each sample. is the sample mean vector, where m is the total number of samples; Calculate the eigenvalues ​​and eigenvectors of the covariance matrix: Cv=λv Where λ is the eigenvalue and v is the corresponding eigenvector; Select the first ξ largest eigenvalues ​​and their corresponding eigenvectors to form the eigenvector matrix V. ξ ; Using the eigenvector matrix V ξ Project the original data into a new low-dimensional space: Z=XV ξ Where Z is the data matrix after dimensionality reduction, and X is the original data matrix after standardization; Step 2.4: Multiply the principal components extracted by PCA with their corresponding weights to obtain the weighted principal components of each indicator, which will be used as the final comprehensive indicator weight Y. Y = ZW Where Y is the final comprehensive index weight, Z is the data matrix after dimensionality reduction, and W is the weight vector calculated by the entropy weight method. Step 2.5: Calculate the weighted comprehensive index score for each plot area using the comprehensive index weight Y. Based on the weighted comprehensive index score of each plot, use the natural breakpoint analysis method in the geographic information system, combined with expert scoring, to comprehensively determine and set a threshold A. Plot areas exceeding threshold A are included in the urban renewal projects, while plot areas below threshold A are not included in the urban renewal projects.

5. The method for delineating urban renewal zones based on the DBSCAN-GM algorithm according to claim 1, characterized in that, Step 3 further includes: Step 3.1: Based on the surface data of the urban renewal objects identified in Step 2, establish an envelope rectangle and generate the geometric center point of the envelope rectangle as the data point of the urban renewal object; Step 3.2: For the data points of the urban renewal targets, run the Gaussian-Means algorithm to divide the data into the optimal number of clusters C. k Each cluster has a defined center point M. j , j = 1…k.

6. The method for delineating urban renewal zones based on the DBSCAN-GM algorithm according to claim 1, characterized in that, Step 5 further includes: Step 5.1: Using the EPS value and MinPts parameter calculated in Step 4, execute the DBSCAN algorithm; Step 5.2: Based on the output of the DBSCAN algorithm, generate a cluster label for each data point; where data points with a number of neighbors greater than or equal to the MinPts parameter are marked as core points, data points with a number of neighbors less than the MinPts parameter but within the neighborhood of a core point are marked as boundary points, and data points that do not belong to any cluster are marked as noise points. Step 5.3: Evaluate the clustering effect by calculating the silhouette coefficient index; Step 5.4: By visualizing the core points and their neighborhood radii, the range of several clusters and their neighborhood radii is superimposed. The superimposed area is used as the high-density area of ​​the identified urban renewal objects and is defined as a potential urban renewal area.

7. The method for delineating urban renewal zones based on the DBSCAN-GM algorithm according to claim 1, characterized in that, Step 6 further includes: Step 6.1: Use GIS tools to calculate the area of ​​each potential urban renewal area, classify the areas, and update the classification results to the GIS database. Specifically, for cities at the prefecture level and above, areas with an area greater than 1 square kilometer are marked as key potential urban renewal areas; areas with an area less than or equal to 1 square kilometer are marked as potential urban renewal spatial units; for counties, county-level cities, and townships, they are directly marked as potential urban renewal spatial units. Step 6.2: Within the potential urban renewal key areas, repeat steps 3 to 5 to identify potential urban renewal spatial units within the potential urban renewal key areas.

Images