Urban rail transit station development intensity multi-objective optimization method in TOD mode

Abstract

The invention provides an urban rail transit station development intensity multi-objective optimization method in a TOD mode, and relates to the technical field of urban planning and intelligent transportation, and the method comprises the steps: analyzing the spatial relation between various types of land and urban function nodes according to the data after standardization processing, and carrying out the location value evaluation; constructing a development intensity evaluation model according to the location value evaluation, calculating the initial average plot ratio of each type of land, and deducing an initial development intensity parameter in combination with the current situation data; establishing a development intensity optimization target system according to a TOD planning principle, performing iterative optimization on the initial development intensity parameters by adopting a multi-target genetic algorithm, and outputting an optimal solution set; and carrying out comparative analysis on the optimal solution set and a current planning index, and obtaining a plot ratio index in combination with a regional development planning requirement. According to the method, a technical framework of subjective and objective collaborative optimization can be constructed by fusing GIS spatial analysis, an analytic hierarchy process and a non-dominated sorting genetic algorithm.

Description

Technical Field

[0001] This invention relates to the fields of urban planning and intelligent transportation technology, and in particular to a multi-objective optimization method for the development intensity of urban rail transit stations under the TOD (Transit-Oriented Development) model. Background Technology

[0002] Transit-oriented development (TOD) is an important planning concept for alleviating disorderly urban expansion and promoting sustainable urban development. By integrating transportation and land use, it has improved urban spatial efficiency and residents' quality of life. However, in the actual development of TOD station areas, there are still problems such as functional homogeneity, insufficient development intensity, and low integration with the overall urban development. Although the scale of rail transit construction has continued to expand in recent years, existing policies and regulations focus more on mixed land use functions and station connections, and the scientific guidance on development intensity is still insufficient. The lack of development intensity control directly affects the efficiency of intensive land use and the operational benefits of rail transit, becoming a bottleneck restricting the in-depth application of the TOD model.

[0003] In existing research, optimization methods for the development of rail transit station areas are mostly focused on adjusting the land use function layout. Traditional genetic algorithms have drawbacks such as slow convergence speed and easy getting trapped in local optima when solving multi-objective nonlinear programming problems. Although models based on GIS and the analytic hierarchy process can combine spatial data with subjective weight allocation, they are difficult to take into account the dynamic optimization needs under complex constraints when used alone. In addition, current research is mostly based on idealized assumptions and lacks differentiated optimization models for specific spatial environments, making it difficult to adapt to the actual needs of diverse TOD station areas. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a multi-objective optimization method for the development intensity of urban rail transit stations under the TOD model. The method is based on the 5D principle and integrates GIS spatial analysis, hierarchical analysis and non-dominated sorting genetic algorithm to construct a technical framework for collaborative optimization of subjective and objective factors.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows: Firstly, a multi-objective optimization method for the development intensity of urban rail transit stations under the TOD (Transit-Oriented Development) model, the method comprising: S1: Obtain planning data for the area where the target rail transit station is located, including land use, building area indicators, and plot ratio data; S2: Based on the planning data, a circular research area is delineated with the rail transit station as the center, in accordance with the TOD planning standard; S3: Based on the study area, standardized data is obtained by standardizing various types of land use data within the area; S4: Based on the standardized data, analyze the spatial relationship between various land uses and urban functional nodes, and conduct location value assessment; S5: Based on the quantitative evaluation results, construct a development intensity assessment model, calculate the initial average plot ratio of various land uses, and derive the initial development intensity parameters in combination with the current data; S6: Establish a development intensity optimization target system based on the TOD planning principle, use a multi-objective genetic algorithm to iteratively optimize the initial development intensity parameters, and output the optimized solution set; S7: Compare and analyze the optimized solution set with the current planning indicators, and combine them with the requirements of regional development planning to obtain the plot ratio indicator.

[0006] Furthermore, S2: Based on planning data, a circular research area is delineated centered on the rail transit station, according to TOD planning standards, including: S21: Centered on rail transit stations, a circular research area covering the core impact range is automatically generated based on the correlation between pedestrian accessibility and spatial development intensity in TOD planning standards. S22: Based on the circular study area, dynamically match it with the land use properties and transportation network distribution in the planning data, eliminate redundant areas that are irrelevant to the development intensity, and obtain the study area range, radius parameters and boundary coordinates; S23: By standardizing the final defined study area range, radius parameters, and boundary coordinates, a standard defined circular study area is obtained.

[0007] Furthermore, based on the standardized data, the spatial relationship between various land uses and urban functional nodes is analyzed to conduct location value assessment, including: S41: Based on the standardized data, automatically obtain the geographic coordinates and attribute data of urban functional nodes, and spatially match them with the standardized land use data to generate a correlation map between land use and functional nodes. S42: Based on the correlation map, combined with the TOD planning objectives and the historical optimization case library, dynamically allocate the weight parameters of service location, transportation location and environmental location factors; S43: Based on the weight parameters, the weight allocation is dynamically optimized through a machine learning model to adjust the weight ratio of each influencing factor in service location, transportation location and environmental location, thereby constructing a multi-dimensional location value assessment model. S44: Based on the multi-dimensional location value assessment model, conduct location value assessments on the accessibility, transportation convenience, and environmental suitability of various types of land use.

[0008] Furthermore, a development intensity assessment model is constructed to calculate the initial average plot ratio for various land uses, including: S51: Real-time integration of location value assessment with current floor area ratio data; and generation of initial average floor area ratio for various land uses by weighted calculation of comprehensive scores for service location, transportation location and environmental location.

[0009] Furthermore, based on the TOD planning principles, a development intensity optimization objective system is established. A multi-objective genetic algorithm is used to iteratively optimize the initial development intensity parameters, outputting an optimized solution set, including: S61: Based on the initial development intensity parameters and the requirements of high-density development, functional integration and transportation accessibility in the TOD planning principles, a set of multi-dimensional objective functions is formed, including the function of maximizing economic benefits, the function of maximizing rail transit passenger volume, the function of optimizing the living environment and the function of land equilibrium. S62: Based on a multi-dimensional set of objective functions, the algorithm parameters are dynamically configured using a multi-objective genetic algorithm framework, based on the initial development intensity parameters and the set of objective functions. S63: Based on the algorithm parameters, the initial parameters are iteratively optimized in multiple rounds using the parallel computing capabilities of the distributed computing cluster to generate a multi-objective balanced Pareto optimal solution set.

[0010] Furthermore, S7: By comparing and analyzing the optimized solution set with the current planning indicators, and combining them with the requirements of regional development planning, the plot ratio indicators are obtained, including: S71: Compare and analyze parameters such as the recommended range of floor area ratio and land use ratio in the optimized solution set with the development intensity indicators in the current control detailed plan in real time, automatically generate a difference map before and after optimization, and mark the quantitative differences of key indicators. S72: Based on the quantitative differences of key indicators and combined with the requirements of regional development planning, the optimization solution set is subjected to secondary constraint verification through the rule engine to eliminate solution set schemes that conflict with the higher-level plan. S73: Based on the development intensity parameters, index comparison results, and constraint verification report of the preferred scheme, the plot ratio index is obtained.

[0011] Secondly, the multi-objective optimization system for urban rail transit station development intensity under the TOD (Transit-Oriented Development) model includes: The acquisition module is used to acquire planning data for the area where the target rail transit station is located, including land use, building area indicators and plot ratio data; based on the planning data, a circular research area is delineated with the rail transit station as the center and in accordance with the TOD planning standard; The assessment module is used to standardize various land use data within the study area to obtain standardized data, including land use classification, area statistics, and coding identification. Based on the standardized data, it analyzes the spatial relationship between various land uses and urban functional nodes, and conducts location value assessment to obtain quantitative evaluation results. Based on the quantitative evaluation results, it constructs a development intensity assessment model, calculates the initial average plot ratio of various land uses, and derives the initial development intensity parameters by combining the current data. The processing module is used to establish a development intensity optimization target system based on the TOD planning principle using initial development intensity parameters, and to iteratively optimize the initial development intensity parameters using a multi-objective genetic algorithm to output an optimized solution set. The optimized solution set is then compared and analyzed with the current planning indicators, and combined with the requirements of regional development planning to obtain the plot ratio index.

[0012] Thirdly, a computing device includes: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0013] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0014] The above-described solution of the present invention has at least the following beneficial effects: By building a precise planning foundation through data-driven approaches, leveraging standardized data processing and the delineation of core TOD areas, and employing spatial matching and analytic hierarchy process (AHP) methods for multi-dimensional location value assessment, combined with machine learning to dynamically optimize weights, the scientific and objective nature of development intensity assessment is ensured. The assessment integrates location value and current data, dynamically calibrating deviations through a rule base and historical cases. Utilizing multi-objective function construction and genetic algorithm optimization, a synergistic balance between economic, transportation, and environmental considerations is achieved, avoiding imbalances caused by a single objective. Secondary constraint verification ensures planning compliance, and dynamic weight allocation supports flexible adjustments to functional positioning, balancing policy requirements and regional development differences. Finally, through visualization maps and intelligent decision engines, decision-making costs are reduced and planning efficiency is improved, forming a fully intelligent system covering data collection, assessment modeling, optimization decision-making, and compliance verification. This enhances the scientific rigor and implementation effectiveness of land development intensity planning around rail transit stations under the TOD model. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the multi-objective optimization method for urban rail transit station development intensity under the TOD (Transit-Oriented Development) model provided in an embodiment of the present invention.

[0016] Figure 2 This is a schematic diagram of a multi-objective optimization system for urban rail transit station development intensity under the TOD (Transit-Oriented Development) model provided in an embodiment of the present invention.

[0017] Figure 3 This is a technical flowchart for the research on the optimization of development intensity of TOD rail transit stations based on the 5D principle.

[0018] Figure 4 This is a land and building information raster map of a square study area with a radius of 800m for passenger station A, processed in this embodiment of the invention.

[0019] Figure 5 This is a longitudinal comparison chart of land development intensity in the study area before and after optimization.

[0020] Figure 6 This is a horizontal comparison chart of land development intensity in the study area before and after optimization. Detailed Implementation

[0021] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0022] like Figure 1 As shown, embodiments of the present invention propose a multi-objective optimization method for the development intensity of urban rail transit stations under the TOD (Transit-Oriented Development) model. The method includes the following steps: Step S1: Obtain planning data for the area where the target rail transit station is located, including land use, building area indicators, and plot ratio data; Step S2: Based on the planning data, delineate a circular research area centered on the rail transit station according to the TOD planning standard; Step S3: Based on the study area, standardize the various land use data within the area to obtain standardized data; Step S4: Based on the standardized data, analyze the spatial relationship between various land uses and urban functional nodes, and conduct a location value assessment; Step S5: Based on the location value assessment, construct a development intensity assessment model, calculate the initial average plot ratio for various land uses, and derive the initial development intensity parameters by combining the current data. Step S6: Establish a development intensity optimization target system based on the TOD planning principle, use a multi-objective genetic algorithm to iteratively optimize the initial development intensity parameters, and output the optimized solution set; Step S7: Compare and analyze the optimized solution set with the current planning indicators, and obtain the plot ratio indicator in combination with the requirements of regional development planning.

[0023] In this embodiment of the invention, by acquiring planning data such as land use properties, building area, and plot ratio, and standardizing and coding the land use data, the integrity and consistency of the input data are ensured, avoiding decision-making biases caused by data fragmentation. Based on GIS, a circular research area is delineated, and the location value is quantified by combining the analytic hierarchy process (AHP). The spatial correlation of core elements such as commerce, transportation, and environment is accurately identified, providing high-precision geographic information support for development intensity optimization. According to the TOD planning principle, a multi-dimensional objective function and a land equilibrium function are established for economic benefits, transportation efficiency, and human settlement environment. This breaks through the limitations of traditional single-objective optimization. A multi-objective genetic algorithm is used to iteratively optimize the initial parameters. Through an elite retention strategy and adaptive parameter adjustment, a Pareto optimal solution set is quickly generated, and the development intensity scheme achieves equilibrium among multiple conflicting objectives.

[0024] By transforming subjective factors such as policy guidance into quantitative indicators and combining them with GIS spatial data, this approach avoids purely technical models that are divorced from actual planning needs. Initial parameters are derived based on the current plot ratio and development intensity level, ensuring that the optimized scheme conforms to both theoretical models and actual development conditions. From data collection and area delineation to optimization solutions, the process is automated through standardized modules, significantly shortening the planning cycle. Visual results such as development intensity heat maps and 3D models are generated through the GIS platform, intuitively displaying the spatial distribution and target achievement of the optimized scheme. This facilitates quick understanding and interactive optimization by planners and decision-makers. The method can be applied to various scenarios such as urban renewal, new area development, and transportation hub planning, supporting differentiated functional positioning. It can also access new transportation lines, environmental monitoring data, or policy adjustment signals in real time, automatically triggering model parameter updates to ensure the forward-looking and sustainable nature of the planning scheme. By scientifically allocating development intensity, it maximizes the economic value of land while avoiding traffic congestion or environmental degradation caused by over-development. The optimized scheme balances the improvement of rail transit passenger capacity and the guarantee of green space coverage, achieving a win-win situation for urban development and residents' well-being.

[0025] In a preferred embodiment of the present invention, step S1 above may include: Step S11: Obtain planning data for the area where the target rail transit station is located, including five categories: land use, building survey, transportation system, socio-economic, and POI.

[0026] In this embodiment of the invention, the planning data for the area where the target rail transit station is located covers five core categories: Land use data, including the nature of land use (such as residential, commercial, and industrial) in the current and planning stages, the proportion of land area, the status of land ownership and the assessment of development potential. Building survey data includes parameters such as building density, plot ratio, height, building area, construction year, functional type (such as residential, office buildings, commercial complexes) and vacancy rate; Traffic system data includes road network layout (grade, width, traffic flow), public transportation lines (subway, bus, BRT) and station distribution, and rail transit passenger flow data (current traffic flow, peak flow coefficient). Socioeconomic data, covering population density, age structure, employment distribution, regional GDP, per capita income, industrial structure, and residents' travel characteristics (commuting mode and travel distance). POI data includes spatial distribution and attribute information of commercial facilities (shopping malls, supermarkets), educational facilities (schools, kindergartens), medical facilities (hospitals, clinics), recreational facilities (parks, squares), and public service facilities (government agencies, fire stations).

[0027] Categorized data acquisition technology path: Obtain existing cadastral maps and overall land use planning maps from the natural resources department. Interpret existing land use types using remote sensing imagery (such as high-resolution satellite data), and combine this with the planned land use nature in the control planning documents to form existing and planned layers. Use software such as ENVI / ArcGIS to extract land use boundaries, and verify the accuracy of remote sensing interpretation through on-site sampling to ensure that the error rate is controlled within 5%. At the same time, mark the areas where existing and planned conflicts occur.

[0028] Information such as building area, height, and age from the housing and construction department's building survey database was integrated. Missing data was supplemented through drone aerial photography and on-site measurements using handheld GPS devices. Building function types were clarified by combining property registration data. Three-dimensional building outlines were obtained using drone oblique photography technology. Individual building parameters were integrated through a BIM platform. The consistency between on-site measurements and the database was verified through sampling to ensure that the plot ratio error was ≤3%, with a focus on supplementing information on older buildings.

[0029] The coordinates of points of interest (POIs) were obtained in batches through the POI interfaces of Gaode and Baidu Maps. Data on publicly available facilities was supplemented from government public service platforms, and undisclosed, niche facilities (such as community convenience stores) were recorded through on-site surveys. Web crawling technology was used to process map data in batches, and facilities were categorized and coded by type through a GIS platform. The accuracy of POI coordinates was verified on-site (error ≤ 50 meters), and the density was checked for reasonableness based on service radius (e.g., service radius of kindergartens ≤ 500 meters).

[0030] Based on the City Information Modeling (CIM) or ArcGIS Pro platform, establish a multi-source data sharing database to achieve: Spatial correlation between land use data and building data (e.g., matching land use with building function); overlay analysis of traffic data and POI data (e.g., correlation between POI density around stations and passenger flow); rasterization transformation of socioeconomic data (e.g., generating heat maps from population density).

[0031] Standardization processes follow these rules: Unify the spatial coordinate system (such as CGCS2000) and the accuracy of the 1:5000 scale; establish standardized field naming (such as unifying "floor area ratio" as "FAR") and value range in the data dictionary; use ETL tools to regularly synchronize and update data to ensure timeliness.

[0032] In a specific embodiment of the present invention, the specific steps include: Step S12: Identify the rail transit stations requiring planning analysis. Target stations can be located using unique identifiers such as station name, number, or geographic coordinates. Connect with the planning management systems of departments such as the Natural Resources and Planning Bureau and the Housing and Construction Bureau to obtain authoritative data such as the overall land use plan and detailed control plan. These systems typically store legal planning indicators such as regional land use nature and plot ratio. Using a city-level GIS platform, retrieve the spatial data layer containing the target station area, extracting land use polygon data and its attribute information, such as land use type code and building area fields. From the land use layer of the GIS platform, filter out the plots in the target station area, extracting the corresponding land use nature codes. Prioritize obtaining the plot ratio indicators from the planning department's control plan documents. If missing, the plot ratio can be estimated by dividing the total building area by the land area. Integrate the collected data into structured tables or database tables, ensuring consistency in field names and data types (e.g., numeric, text) to obtain the planning data.

[0033] In a preferred embodiment of the present invention, step S2 above may include: Step S21: Taking the rail transit station as the center, automatically generate a circular study area covering the core impact range based on the correlation between walkability and spatial development intensity in the TOD planning standard; Step S22: Based on the circular study area, dynamically match it with the land use properties and transportation network distribution in the planning data, eliminate redundant areas that are irrelevant to the development intensity, and obtain the study area range, radius parameters and boundary coordinates; Step S23: By standardizing the final defined study area range, radius parameters and boundary coordinates, a standard defined circular study area is obtained.

[0034] In this embodiment of the invention, based on the core principle of the 5-10 minute walking circle in the TOD standard, a circular research area with a radius of 800 meters is automatically generated with rail transit stations as the center. This avoids resource waste caused by an excessively large area or functional deficiencies caused by an excessively small area. By analyzing the correlation between walkability and spatial development intensity, the area boundary is automatically generated, ensuring that the research area is highly consistent with the high-density development goals of TOD. The generated circular area is matched in real time with the land use properties and transportation networks in the planning database. Irrelevant areas such as ecological reserves and undevelopable roads are automatically filtered to avoid invalid data interference. Through dynamic matching, deviations in the area boundary caused by terrain or existing construction are corrected, ensuring that the research area boundary is strictly aligned with the TOD planning goals. The final delineated area, radius, and boundary coordinates are standardized and encoded to generate a data package that can be directly imported into the optimization model, reducing manual intervention and avoiding data conversion errors. The automatic generation and matching process replaces traditional manual drawing and data filtering, reducing labor costs and the risk of subjective errors. By accurately eliminating undevelopable areas, the efficiency of planning implementation is improved.

[0035] In a specific embodiment of the present invention, the specific steps include: Step S21: According to the TOD planning standards, clarify the relationship between pedestrian accessibility and spatial development intensity. Generally, the area covered by a 5-10 minute walk is considered the core influence range of the rail station area, with a corresponding radius of about 800m. Using the geographical location of the rail transit station as the center, and according to the radius determined by the above relationship, automatically draw a circular area covering the core influence range through the geographic information system.

[0036] Step S22: Using the spatial overlay tool of GIS software, the circular study area generated in Step S21 is overlaid with the land use data in the planning data. A common overlay method is Intersect, which identifies the overlapping part between the circular area and the land use patches, and identifies different land use types within the circular area, such as residential land, commercial land, public service land, road and transportation land, and ecological reserve land. At the same time, the circular area is matched with the transportation network distribution data, including information on roads at all levels, transportation stations, and ramps. Based on the influencing factors of development intensity, the effects of various land use and transportation elements on development intensity are analyzed. Areas with minimal or no direct correlation to development intensity, such as ecological reserves and some remote and inconveniently located plots, are identified as redundant areas and removed. Through the above operations, the actual range of the study area is accurately determined, the radius parameter of the area is measured and recorded, and the boundary coordinates of the area are obtained.

[0037] Step S23: Standardize the format of the study area range, radius parameters, and boundary coordinates obtained in Step S22. All data must conform to specific geographic information data format requirements, such as the common Shapefile format and GeoJSON format. Set the spatial reference system for the study area, select the map projection method and coordinate system, so that the study area data can be accurately matched and overlaid with other relevant geographic data in space. Standardize the attribute information of the study area, such as clearly marking the area type and unifying the naming rules, to form a standard circular study area.

[0038] In a preferred embodiment of the present invention, step S3 above may include: Step S31: Based on the designated area, integrate the land use nature, building area and plot ratio data of the study area in real time, and automatically classify the raw data into the corresponding land use type through the preset land use classification rule library, including five categories: land use, building survey, transportation system, socio-economic and POI. Step S32: Based on the corresponding land use type and according to the preset coding logic, perform area statistics and unique coding identification on the classified land use data to obtain the coded land use data; Step S33: Encapsulate the coded land use data and statistical results into a structured data package to obtain standardized data.

[0039] In this embodiment of the invention, a pre-defined land use classification rule base automatically categorizes complex and diverse original land use data into corresponding land use types such as residential, commercial, and public service, unifying land use classification standards and effectively eliminating obstacles to data understanding and analysis caused by classification differences. Simultaneously, it integrates multi-source data such as land use properties, building area, and plot ratio in real time to form a complete land use dataset, facilitating comprehensive analysis of the current state of land development and improving the scientific nature of planning. Regarding data management and querying, the classified land use data is statistically analyzed and uniquely coded according to a pre-defined coding logic, improving data management and query efficiency. Furthermore, the coded land use data and statistical results are uniformly encapsulated into a structured data package, making data storage and transmission more orderly, facilitating computer program reading, analysis, and processing, and enhancing data backup, recovery, and sharing capabilities, thereby strengthening data security and availability.

[0040] In a specific embodiment of the present invention, the specific steps include: Step S31: Based on the defined area, integrate the data from different formats and sources to form a comprehensive dataset. During the integration process, ensure the accuracy and integrity of the data, and mark and process any missing or erroneous data.

[0041] Step S32: Using the categorized land use data, calculate the area of ​​each plot. Utilize the spatial analysis function of GIS to calculate the area of ​​each plot within each land use category. For example, for polygonal plots, determine the plot size by calculating the area enclosed by its boundary coordinates. Then, summarize and statistically analyze the areas of all plots within the same land use category to obtain the total area data for each category. Generate a unique code identifier for each plot, forming the coded land use data.

[0042] Step S33: Organize the coded land use data and the statistical results of various land use areas obtained previously, and arrange them according to specific structured data format requirements. For example, use JSON format to build a dataset structure containing fields such as land use type, code, and area. Use data encapsulation tools or data structure operation methods in programming languages ​​to encapsulate the organized data into a structured data package to obtain standardized data.

[0043] In a preferred embodiment of the present invention, step S4 above may include: Step S41: Based on the standardized data, automatically obtain the geographic coordinates and attribute data of urban functional nodes, and perform spatial matching with the standardized land use data to generate a correlation map between land use and functional nodes. Step S42: Based on the correlation map, combined with the TOD planning objectives and historical optimization case library, dynamically allocate the weight parameters of service location, transportation location and environmental location factors. The weights of each factor in the GIS intensity model and the weights of the benchmark model can be seen in Table 1 below. Table 1

[0044] Step S43: Based on the weight parameters, dynamically optimize the weight allocation through a machine learning model, adjust the weight ratio of each influencing factor in service location, transportation location and environmental location, thereby constructing a multi-dimensional location value assessment model. Step S44: Based on the multi-dimensional location value assessment model, conduct location value assessments on the accessibility, transportation convenience, and environmental suitability of various types of land use.

[0045] In this embodiment of the invention, by automatically acquiring urban functional node data and spatially matching it with land use data to generate a correlation map, the relationship between land use and functional nodes is clearly presented. Combining TOD planning objectives and a historical optimization case library, weight parameters are dynamically allocated, fully considering actual planning needs and past experience, making the weight allocation more reasonable. A machine learning model is used to dynamically optimize the weight allocation and construct a multi-dimensional location value assessment model. Based on constantly changing data and actual conditions, the weight ratio of each influencing factor can be flexibly adjusted, improving the accuracy and adaptability of the assessment model. This model dynamically quantifies and scores the accessibility, transportation convenience, and environmental suitability of various types of land use. The resulting quantitative evaluation results provide strong support for accurately assessing the location value of land use, helping to more scientifically determine the development intensity of land surrounding urban rail transit stations under the TOD model and achieve the rational utilization of land resources.

[0046] In a specific embodiment of the present invention, the specific steps include: Step S41: Import the standardized data into GIS software. Using intersection analysis tools (e.g., buffer analysis, overlay analysis), determine the spatial relationship between each functional node and the land use. Identify whether a functional node is within a certain distance of a land use area or whether it spatially overlaps with a land use area. Use a graph database or graph data structure to store and represent the association between land use areas and functional nodes. Treat land use areas and functional nodes as nodes in the graph, and their associations as edges. Add attribute information to each edge and node. For edges, add association types (e.g., proximity, containment) and association strengths (e.g., distance, association frequency). For nodes, add their own attribute data. Use visualization tools to display the association graph.

[0047] Step S42: Conduct in-depth analysis of the generated correlation map to uncover the correlation patterns between land use and functional nodes. For example, analyze which functional nodes are more closely associated with different types of land use, as well as the distribution of correlation strength. Statistically count the number and proportion of various correlation relationships, understand the degree of manifestation of different location factors (service location, transportation location, and environmental location) in the correlation relationships, clarify the TOD planning objectives, and identify the key focus areas and expected effects of service location, transportation location, and environmental location in this planning. Select cases similar to the current planning scenario from the historical optimization case library, analyze the weight allocation of service location, transportation location, and environmental location factors in these cases, and the results achieved. Combining the analysis results of the correlation map, the TOD planning objectives, and the experience of historical cases, preliminarily determine the weight parameters of service location, transportation location, and environmental location factors.

[0048] Step S43: Based on the characteristics of the data (such as data scale, data type, data distribution, etc.) and evaluation requirements, select a machine learning model. Common models include neural networks, decision trees, support vector machines, etc. Preprocess the weight parameters and related training data, including data cleaning, removing noisy data and outliers, and data standardization to unify data of different scales to the same scale range, thereby improving the training effect of the model. Divide the preprocessed data into training and test sets. Use the training set to train the machine learning model. By continuously adjusting the model parameters, the model can learn the relationship between various influencing factors and location value. Use the test set to evaluate the trained model. Optimize the model based on the evaluation results, and adjust the weight allocation to improve the model's accuracy and generalization ability. After multiple training and optimizations, determine the final machine learning model parameters and construct a multi-dimensional location value evaluation model. This model can automatically adjust the weight ratio of each influencing factor in service location, transportation location, and environmental location based on various input data.

[0049] Step S44: Based on the multi-dimensional location value assessment model, construct a hierarchical structure model. Set the target layer as the location value assessment of various land uses, the criteria layer as accessibility, transportation convenience, and environmental suitability, and the scheme layer as specific land uses. Determine the importance judgment matrix of each criterion layer indicator relative to the target layer. Perform pairwise comparisons of the relative importance of accessibility, transportation convenience, and environmental suitability to construct a judgment matrix. Determine the normalization of each column of the matrix by... Summing the normalized matrix row by row, through , to obtain the feature vector, through The largest eigenvalue is obtained, where, and It is a row index. It is a column index. These are the number of criteria layer indicators, and the normalized matrix elements. These are the normalized matrix elements. It is the first The temporary weights (unnormalized) of the i-th indicator are determined by placing them in the normalized matrix. The sum of all elements in the row is obtained. No. The final weights of each indicator (after normalization). It is the sum of the temporary weights of all indicators. It is to determine the largest eigenvalue of the matrix. It is a judgment matrix With weight vector The product of the first product One element, It is the first The weighted correlation ratio of each indicator to its own weight is used to normalize the feature vector and obtain the weight vector of each criterion layer indicator relative to the target layer. Relevant data of various land uses are input into the multi-dimensional location value assessment model to obtain the scores of each land use in terms of accessibility, transportation convenience and environmental adaptability. Based on the weight vector obtained by the analytic hierarchy process, the accessibility, transportation convenience and environmental adaptability scores of each land use are weighted and summed to obtain the dynamic quantitative scoring results of various land uses.

[0050] In a preferred embodiment of the present invention, a development intensity assessment model is constructed to calculate the initial average plot ratio for various land uses, including: S51: Real-time integration of location value assessment with current floor area ratio data; and generation of initial average floor area ratio for various land uses by weighted calculation of comprehensive scores for service location, transportation location and environmental location.

[0051] In this embodiment of the invention, location value assessment and current floor area ratio data are integrated in real time. A benchmark development intensity level is generated by calculating a comprehensive score through weighted average. This fully considers the location conditions and existing development foundation of the land, avoiding the one-sidedness of relying solely on current data or theoretical location value. This makes the benchmark level more in line with actual development needs. With the help of a preset intensity correction rule library and historical case library, the deviation between the benchmark level and the current floor area ratio is dynamically calibrated. This not only follows the normative requirements of planning management but also draws on the successful experience of similar projects, effectively reducing subjective judgment bias and improving the adaptability of development intensity parameters to actual planning scenarios. By combining the benchmark level and correction coefficient through iterative calculation, the initial development intensity parameters are derived, achieving an organic unity between theoretical assessment and practical feedback. This ensures that the parameters are both in line with location value orientation and have practical feasibility, thus improving the scientific nature of land development intensity planning.

[0052] In a specific embodiment of the present invention, the specific steps include: Step S51: Based on the quantitative evaluation results, integrate the location value assessment with the current plot ratio data to establish a unified data table or database, link the two together, and ensure that the location value score and the current plot ratio data of each plot of land can accurately correspond. Determine appropriate weights for service location, transportation location and environmental location respectively. Based on the determined weights, perform a weighted summation of the quantitative scores of service location, transportation location and environmental location to obtain the comprehensive score of each plot of land. The calculation formula is: the comprehensive score equals the service location score multiplied by the service location weight plus the transportation location score multiplied by the transportation location weight multiplied by the environmental location score multiplied by the environmental location weight.

[0053] Step S52: Compare the benchmark development intensity level with the current floor area ratio data. Calculate the deviation by dividing the deviation by the current floor area ratio (the floor area ratio corresponding to the benchmark development intensity level minus the current floor area ratio). Search the preset intensity correction rule library for a correction rule that matches the current deviation. The intensity correction rule library contains correction strategies and methods for different deviation scenarios. The rules are formulated based on urban planning experience and relevant regulations, referencing a historical case library. Combining the rule matching results and the analysis of historical cases, various factors are comprehensively considered to generate a correction coefficient for the initial development intensity parameter. The correction coefficient can be adjusted according to the magnitude and direction of the deviation. For example, if the benchmark development intensity level is higher than the current floor area ratio and the deviation is large, the correction coefficient may be greater than 1; conversely, if the deviation is small, the correction coefficient may be close to 1.

[0054] Step S53: Based on the correction coefficient of the initial development intensity parameter, multiply the basic development intensity parameter corresponding to the benchmark development intensity level with the correction coefficient. Check the resulting development intensity parameter to determine whether it meets the relevant requirements of urban planning and the actual situation. If it does not meet the requirements, the correction coefficient needs to be readjusted and iterative calculation is performed again until the obtained development intensity parameter is reasonable. After multiple iterative calculations, the development intensity parameter that meets the requirements is finally determined and used as the initial development intensity parameter.

[0055] In a preferred embodiment of the present invention, step S6 may include: S61: Based on the initial development intensity parameters and the requirements of high-density development, functional integration and transportation accessibility in the TOD planning principles, a set of multi-dimensional objective functions is formed, including the function of maximizing economic benefits, the function of maximizing rail transit passenger volume, the function of optimizing the living environment and the function of land equilibrium. S62: Based on a multi-dimensional set of objective functions, the algorithm parameters are dynamically configured using a multi-objective genetic algorithm framework, based on the initial development intensity parameters and the set of objective functions. S63: Based on the algorithm parameters, the initial parameters are iteratively optimized in multiple rounds using the parallel computing capabilities of the distributed computing cluster to generate a multi-objective balanced Pareto optimal solution set.

[0056] In this embodiment of the invention, multi-dimensional objective functions such as economic benefits, rail transit passenger volume, and living environment are generated based on the TOD planning principle. This ensures that the optimization of development intensity takes into account the diverse needs of urban development, avoids imbalances caused by a single objective, and reflects the core requirements of high-density development, functional integration, and transportation accessibility under the TOD model. The dynamic definition of objective priority and weight allocation logic enables the planning to flexibly adjust its focus according to actual needs, enhancing the adaptability of the scheme to different urban functional positioning and development stages. A multi-objective genetic algorithm framework is introduced, utilizing its global search capability and Pareto optimal solution characteristics to efficiently explore the optimal combination of development intensity parameters under complex constraints, avoiding getting trapped in local optima and improving the scientificity and rationality of the planning scheme. With the help of the parallel computing capability of the distributed computing cluster, the time cost of multiple rounds of iterative optimization is significantly shortened, enabling efficient processing of large-scale data and complex models, and ensuring that the generated Pareto optimal solution set has both multi-objective balance and practical feasibility.

[0057] In a specific embodiment of the present invention, the specific steps include: S61: Using initial development intensity parameters (such as plot ratio, building density, functional zoning ratio, etc.) as core variables, and combining them with TOD planning principles, key indicators related to high-density development, functional diversification, and transportation accessibility are identified, such as population density, rail station coverage radius, and green space ratio. The economic benefit maximization function is: ， ,in, To measure the total land appreciation value in the station area. This refers to the total area of ​​residential land within the station area. The average plot ratio for residential land in the station area. The price increase per square meter of residential land building area This refers to the total land area designated for commercial and service industries within the station area. This refers to the average plot ratio of commercial and service land in the station area. Adding value to the price per square meter of commercial land building area. Within the station area i Average land price for this type of land use This represents the average land price for various land uses within the station area. For land use type indexing, the objective function for maximizing rail transit passenger volume is: ,in, To measure passenger traffic volume in the station area, For residential land transportation rate, For commercial and service industry land use, traffic utilization rate The optimal objective function for the traffic utilization rate of public management and public service land and the living environment is: , To measure the quality of the living environment in the station area, Given the total service area of ​​the station area, integrate the above functions into an objective function vector. This forms a set of multi-dimensional optimization objective functions, among which the formula for the land equilibrium function is: ; in, The objective function for land use balance is denoted as , which aims to minimize this value (i.e., minimize the total deviation of the proportion of various land uses); ... i This represents the total area of ​​land for the i-th type of land use (unit: m). 2 ), consistent with the previous definitions of parameters such as SR and SB (e.g., S1=SR is the total area of ​​residential land); This represents the average plot ratio of the i-th type of land use, consistent with the definitions of parameters such as FR and FB mentioned above (e.g., F1=FR is the average plot ratio of residential land). This represents the planned target building area percentage for land use type i (a preset value, set according to TOD functional requirements, such as residential land β). R =0.4 represents a target percentage of 40%.

[0058] S62: Based on a multi-dimensional objective function set, receive the initial development intensity parameters preset by the user or system, extract key constraints such as urban master planning indicators, ecological protection red lines, and rail station capacity limits, and set objective priorities according to the planning objectives. For example, if it is the urban core area, set... The highest priority is given to newly built residential areas. It has the highest priority and automatically assigns weights based on the real-time input planning goals through the human-computer interaction interface.

[0059] S63: Based on the priority and weight allocation logic of each objective, a non-dominated sorting genetic algorithm is adopted to adapt to the needs of multi-objective optimization. Upper and lower limits for the development intensity parameter are set according to planning specifications and current conditions. The population size is set according to the land use quantity and parameter complexity. Parameters corresponding to high-priority objectives use a higher crossover probability to accelerate the propagation of excellent solutions, while parameters for low-priority objectives use a lower mutation probability to maintain solution stability. Combined with weight allocation, the overall fitness is defined. , and The normalized extremum of the objective function. The land use type index is used to obtain the dynamic configuration algorithm parameters.

[0060] S64: Initial parameters and objective function are distributed to distributed nodes. Each node independently processes the evaluation and evolution of individuals in the population. A master-slave architecture is adopted, with the master node responsible for population management and optimal solution integration, and slave nodes calculating individual fitness in parallel. High-fitness individuals are retained through tournament selection. Simulated binary crossover is used for continuous variables, and single-point crossover is used for discrete variables. Uniform mutation is added to variables to maintain population diversity. After each iteration, the population is non-dominated and sorted. Calculate the distance to congestion. Index of the objective function The total number of objective functions, No. y The individual in the first m Crowding distance component on each objective function It is an index of an individual in the population, retains Pareto front solutions, and outputs a set of Pareto optimal solutions after a preset number of iterations. It contains multiple non-dominant optimal solutions, and each solution corresponds to a set of balanced development intensity parameters.

[0061] In a preferred embodiment of the present invention, step S7 may include: S71: Compare and analyze parameters such as the recommended range of floor area ratio and land use ratio in the optimized solution set with the development intensity indicators in the current control detailed plan in real time, automatically generate a difference map before and after optimization, and mark the quantitative differences of key indicators. S72: Based on the quantitative differences of key indicators and combined with the requirements of regional development planning, the optimization solution set is subjected to secondary constraint verification through the rule engine to eliminate solution set schemes that conflict with the higher-level plan. S73: Based on the development intensity parameters, index comparison results, and constraint verification report of the preferred scheme, the plot ratio index is obtained.

[0062] In this embodiment of the invention, the optimized parameters are compared with the existing control plan indicators in real time to generate a difference map, enabling planners to intuitively grasp the specific adjustment direction and quantitative basis of development intensity optimization. This enhances the transparency and interpretability of the planning scheme. By using a rule engine to eliminate schemes that conflict with higher-level plans, the optimization results are ensured to meet the overall requirements of regional development, effectively avoiding planning conflicts. Based on functional positioning, the target weights are dynamically adjusted and multi-dimensional quantitative scoring is performed. This respects the development priorities of different regions and selects the most suitable scheme through scientific sorting, achieving a deep integration of technical rationality and policy objectives. Complex data is integrated into a visualized decision-making report, providing decision-makers with intuitive and clear reference basis, and significantly improving the efficiency of planning decisions. Overall, this process, through a closed loop of comparative analysis, conflict verification, dynamic adaptation, and visualization, ensures that the development intensity optimization scheme has both multi-objective balance at the technical level and meets policy constraints and regional development needs, providing scientific and reliable decision support for the refined allocation of land resources under the TOD model.

[0063] In a specific embodiment of the present invention, the specific steps include: S71: Extract parameters such as recommended floor area ratio range and land use ratio from the optimized solution set. These parameters are development intensity-related data obtained after multi-objective optimization in the previous steps. Collect development intensity indicators from the current control detailed plan. These indicators are the existing planning standards. For each parameter in the optimized solution set, compare it one by one with the corresponding indicators in the current control plan. Use data visualization tools to present the differences before and after optimization in the form of charts (such as bar charts, line charts, etc.). Mark the quantitative differences of key indicators on the chart, such as the increase or decrease of floor area ratio and the percentage change of land use ratio, to obtain the quantitative differences of key indicators.

[0064] S72: Through regional development planning, identify the various requirements and constraints on development intensity, such as building height restrictions and green space ratio requirements for specific areas. Based on the requirements of regional development planning, configure the rules of the rule engine. The rule engine can be a program module based on preset logic, used to automatically verify the optimized solution set. Input the optimized solution set into the rule engine, check each scheme according to the configured rules, and identify the solution set schemes that conflict with the higher-level plan. For example, if the green space ratio of a certain scheme is lower than the regional planning requirements, the scheme is judged as a conflicting scheme. The solution set schemes that conflict with the higher-level plan identified during the verification process are removed from the optimized solution set.

[0065] S73: Integrate the development intensity parameters, indicator comparison results, and constraint verification reports of the preferred scheme, and present the integrated data in an intuitive and easy-to-understand way through professional visualization tools, such as creating charts and maps. Organize the visualization results into a visualization decision report, which is the plot ratio indicator.

[0066] like Figure 2 As shown, embodiments of the present invention also provide a multi-objective optimization system for urban rail transit station development intensity under the TOD (Transit-Oriented Development) model, including: The acquisition module is used to acquire planning data for the area where the target rail transit station is located, including land use, building area indicators and plot ratio data; based on the planning data, a circular research area is delineated with the rail transit station as the center and in accordance with the TOD planning standard; The assessment module is used to standardize various land use data within the study area to obtain standardized data, including land use classification, area statistics, and coding identification. Based on the standardized data, it analyzes the spatial relationship between various land uses and urban functional nodes, and conducts location value assessment to obtain quantitative evaluation results. Based on the quantitative evaluation results, it constructs a development intensity assessment model, calculates the initial average plot ratio of various land uses, and derives the initial development intensity parameters by combining the current data. The processing module is used to establish a development intensity optimization target system based on the TOD planning principle using initial development intensity parameters, and to iteratively optimize the initial development intensity parameters using a multi-objective genetic algorithm to output an optimized solution set. The optimized solution set is then compared and analyzed with the current planning indicators, and combined with the requirements of regional development planning to obtain the plot ratio index.

[0067] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0068] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0069] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A multi-objective optimization method for urban rail transit station development intensity under the TOD (Transit-Oriented Development) model, characterized in that, The method includes: S1: Obtain planning data for the area where the target rail transit station is located, including land use, building area indicators, and plot ratio data; S2: Based on the planning data, a circular research area is delineated with the rail transit station as the center, in accordance with the TOD planning standard; S3: Based on the study area, standardized data is obtained by standardizing various types of land use data within the area; S4: Based on the standardized data, analyze the spatial relationship between various land uses and urban functional nodes, and conduct location value assessment; S5: Based on the location value assessment, construct a development intensity assessment model, calculate the initial average plot ratio of various land uses, and derive the initial development intensity parameters in combination with the current data; S6: Establish a development intensity optimization target system based on the TOD planning principle, use a multi-objective genetic algorithm to iteratively optimize the initial development intensity parameters, and output the optimized solution set; S7: Compare and analyze the optimized solution set with the current planning indicators, and combine them with the requirements of regional development planning to obtain the plot ratio indicator.

2. The multi-objective optimization method for urban rail transit station development intensity under the TOD model according to claim 1, characterized in that, Based on planning data, a circular research area was delineated centered on the rail transit stations, in accordance with TOD planning standards, including: S21: Centered on rail transit stations, a circular research area covering the core impact range is automatically generated based on the correlation between pedestrian accessibility and spatial development intensity in TOD planning standards. S22: Based on the circular study area, dynamically match it with the land use properties and transportation network distribution in the planning data, eliminate redundant areas that are irrelevant to the development intensity, and obtain the study area range, radius parameters and boundary coordinates; S23: By standardizing the final defined study area range, radius parameters, and boundary coordinates, a standard defined circular study area is obtained.

3. The multi-objective optimization method for urban rail transit station development intensity under the TOD model according to claim 2, characterized in that, Based on the standardized data, the spatial relationship between various land uses and urban functional nodes is analyzed to conduct location value assessment, including: S41: Based on the standardized data, automatically obtain the geographic coordinates and attribute data of urban functional nodes, and spatially match them with the standardized land use data to generate a correlation map between land use and functional nodes. S42: Based on the correlation map, combined with the TOD planning objectives and the historical optimization case library, dynamically allocate the weight parameters of service location, transportation location and environmental location factors; S43: Based on the weight parameters, the weight allocation is dynamically optimized through a machine learning model to adjust the weight ratio of each influencing factor in service location, transportation location and environmental location, thereby constructing a multi-dimensional location value assessment model. S44: Based on the multi-dimensional location value assessment model, conduct location value assessments on the accessibility, transportation convenience, and environmental suitability of various types of land use.

4. The multi-objective optimization method for urban rail transit station development intensity under the TOD model according to claim 3, characterized in that, Construct a development intensity assessment model to calculate the initial average plot ratio for various land uses, including: S51: Real-time integration of location value assessment with current floor area ratio data; and generation of initial average floor area ratio for various land uses by weighted calculation of comprehensive scores for service location, transportation location and environmental location.

5. The multi-objective optimization method for urban rail transit station development intensity under the TOD model according to claim 4, characterized in that, Based on the TOD planning principles, a development intensity optimization objective system is established. A multi-objective genetic algorithm is used to iteratively optimize the initial development intensity parameters, outputting an optimized solution set, including: S61: Based on the initial development intensity parameters and the requirements of high-density development, functional integration and transportation accessibility in the TOD planning principles, a set of multi-dimensional objective functions is formed, including the function of maximizing economic benefits, the function of maximizing rail transit passenger volume, the function of optimizing the living environment and the function of land equilibrium. S62: Based on a multi-dimensional set of objective functions, the algorithm parameters are dynamically configured using a multi-objective genetic algorithm framework, based on the initial development intensity parameters and the set of objective functions. S63: Based on the algorithm parameters, the initial parameters are iteratively optimized in multiple rounds using the parallel computing capabilities of the distributed computing cluster to generate a multi-objective balanced Pareto optimal solution set.

6. The multi-objective optimization method for urban rail transit station development intensity under the TOD model according to claim 5, characterized in that, S7: By comparing and analyzing the optimized solution set with current planning indicators, and combining it with regional development planning requirements, the plot ratio indicators are obtained, including: S71: Compare and analyze parameters such as the recommended range of floor area ratio and land use ratio in the optimized solution set with the development intensity indicators in the current control detailed plan in real time, automatically generate a difference map before and after optimization, and mark the quantitative differences of key indicators. S72: Based on the quantitative differences of key indicators and combined with the requirements of regional development planning, the optimization solution set is subjected to secondary constraint verification through the rule engine to eliminate solution set schemes that conflict with the higher-level plan. S73: Based on the development intensity parameters, index comparison results, and constraint verification report of the preferred scheme, the plot ratio index is obtained.

7. A multi-objective optimization system for urban rail transit station development intensity under the TOD (Transit-Oriented Development) model, wherein the system implements the method as described in any one of claims 1 to 6, characterized in that, include: The acquisition module is used to acquire planning data for the area where the target rail transit station is located, including land use, building area indicators, and plot ratio data. Based on the planning data, a circular research area was delineated with the rail transit station as the center, in accordance with the TOD planning standards. The assessment module is used to standardize various land use data within the study area to obtain standardized data, including land use classification, area statistics, and coding identification. Based on the standardized data, it analyzes the spatial relationship between various land uses and urban functional nodes, and conducts location value assessment to obtain quantitative evaluation results. Based on the quantitative evaluation results, it constructs a development intensity assessment model, calculates the initial average plot ratio of various land uses, and derives the initial development intensity parameters by combining the current data. The processing module is used to establish a development intensity optimization target system based on the TOD planning principle using the initial development intensity parameters, and to iteratively optimize the initial development intensity parameters using a multi-objective genetic algorithm, outputting an optimized solution set. By comparing and analyzing the optimized solution set with the current planning indicators and combining it with the requirements of regional development planning, the plot ratio indicator is obtained.

8. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images