Land space planning method and system applying data analysis
By screening multi-dimensional landmark points and dividing boundaries using the CA model, the problem of large boundary errors in national land space planning is solved, and more accurate and reasonable national land space planning is achieved to adapt to dynamic changes.
Patent Information
- Application Number
- CN202510783611.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-19
- Publication Date
- 2025-09-05
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The boundary errors of China's existing land space planning are large, and its accuracy and rationality are low, making it difficult to adapt to the needs of dynamic changes.
By acquiring multi-source geographic location data, multi-dimensional landmark screening and alignment are performed, the data is split into multiple cells, the core elements of the cells are defined, a CA model is established, the external overall boundary and the internal connection boundary are divided, and multi-angle analysis is performed.
It improves the accuracy and rationality of national land space planning, meets the needs of dynamic changes in boundaries, and provides data support for future planning.
Smart Images
Figure CN120596587A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of land data analysis, and in particular to a land space planning method and system using data analysis. Background Art
[0002] In the field of national land space planning, with the deepening advancement of new urbanization, ecological civilization construction, and regional coordinated development strategies, traditional empirical planning methods are no longer able to adapt to the complex demands of spatial governance. Currently, national land space faces multiple challenges, including tightening resource constraints, increasing ecological security risks, and unbalanced urban and rural development. Scientific and refined planning methods are urgently needed. The rapid development of data analysis technology has provided a new approach to addressing this problem. By integrating multi-source heterogeneous data (such as remote sensing imagery, geographic information, socioeconomic statistics, and IoT sensor data), combined with big data mining, machine learning, and spatial econometric models, it is possible to accurately identify resource and environmental carrying capacity, assess ecological service functions, simulate urban expansion patterns, and optimize the layout of functional areas.
[0003] In the existing technology, the fixed overall outer and internal boundaries of the national land space are determined solely by relying on experience, which cannot meet the dynamic changes of the national land space, resulting in large boundary errors and low accuracy and rationality of national land space planning.
[0004] Therefore, how to improve the accuracy and adaptability of boundaries is a technical problem that needs to be solved. Summary of the Invention
[0005] The purpose of the present invention is to solve the problem that the boundary error is large and the accuracy and rationality of national land space planning are low in the existing technology, and a national land space planning method using data analysis is proposed, which includes: Obtain multi-source geographic location data for the territorial space area to be analyzed, perform multi-dimensional landmark point screening on the territorial space area to be analyzed, obtain a landmark point set, and align the multi-source geographic location data for the territorial space area to be analyzed through the landmark point set; Split the national spatial area to be analyzed into multiple cells, define the core elements of the cells, and establish a CA model; The CA model is used to divide the external overall boundary and internal connection boundary of the national spatial area to be analyzed; Conduct multi-angle analysis of national land space planning based on the external overall boundary and internal connection boundary.
[0006] In some embodiments of the present application, before performing multi-dimensional landmark point screening on the land space area to be analyzed, the method further includes pre-processing the multi-source geographic location data, specifically, Convert each source geographic location data in the multi-source geographic location data into a standard coordinate system to achieve coordinate system one; Determine the original resolution of each source geolocation data in the multi-source geolocation data, calculate the minimum effective resolution, perform initial registration and superposition on the geolocation data with different original resolutions to obtain the registration error, calculate the target resolution based on the registration error and the minimum effective resolution, and unify the resolution of the multi-source geolocation data according to the target resolution; Identify the attributes of different original regions in the national land space area to be analyzed. The attributes of the original regions include regional function type, terrain complexity information, land feature density information, and monitoring scale information. Based on the regional function type, terrain complexity information, land feature density information, and monitoring scale information, determine the resolution requirement for each original region. The resolution requirement of each original area is matched with the target resolution to identify the multi-scale original areas that require multi-scale resolution in all original areas. The multi-scale original areas are divided into multiple accuracy levels, each accuracy level corresponds to a resolution, and a multi-scale resolution pyramid is constructed to achieve the unification and adaptation of the resolution of multi-source geographic location data.
[0007] In some embodiments of the present application, multi-dimensional landmark point screening is performed on the land space area to be analyzed, including: determining a first gridding degree for each original region according to a target resolution or a resolution of a multi-precision level; obtaining an average amount of data collected and a data analysis capability for each original region, and determining a second gridding degree for each original region according to the average amount of data collected and the data analysis capability; A third gridding degree is set based on the first gridding degree and the second gridding degree of the original area, and the original area is gridded by the third gridding degree to obtain a plurality of grid cells, which are used to describe the entire land space area to be analyzed; Multiple candidate landmarks are identified in each grid cell, and the multi-dimensional evaluation content of each candidate landmark is analyzed. The multi-dimensional evaluation content includes the evaluation content of three properties: significance, consistency, and stability. The screening indicators are defined by comprehensively evaluating the evaluation content of these three properties; The candidate landmark points under each grid unit are screened by using the screening indicators, and the screened results are used as landmark points.
[0008] In some embodiments of the present application, the multi-source geographic location data of the land space area to be analyzed are aligned by using a set of landmark points, including: The number of landmarks, the uniformity of landmark distribution, and the density of landmarks under each grid unit are counted. The corresponding registration model type for each grid unit is selected based on the number of landmarks, the uniformity of landmark distribution, and the density of landmarks. The registration model parameters are then optimized to achieve registration alignment between multi-source geographic location data.
[0009] In some embodiments of the present application, the national space area to be analyzed is split into multiple cells, including: Each grid unit is regarded as a cell, and the state attributes of the cell are set. The state attributes are land use type or other basic information.
[0010] In some embodiments of the present application, the core elements of a cell are defined, including: The core elements include neighborhood structure and state transition rules, which are jointly reflected by neighborhood type and neighborhood radius; Determine the neighborhood type of each cell, establish a diffusion model for each grid cell, describe the spatial diffusion effect of the grid cell through the diffusion model, analyze the spatial autocorrelation between grid cells, adjust the spatial diffusion effect according to the spatial autocorrelation, and thus determine the neighborhood radius; The driving factors of the grid cells are collected, including neighborhood status, macro indicators and random disturbance terms. The state transition rules are set according to the neighborhood status, macro indicators and random disturbance terms.
[0011] In some embodiments of the present application, the CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed, including: For the entire national space area to be analyzed, the CA model is run and the cellular state is iteratively updated until the spatial pattern tends to be stable. The outer contour boundary of the grid cells in the stable state is identified through edge detection algorithm or spatial cluster analysis, which serves as the external overall boundary of the national space area to be analyzed.
[0012] In some embodiments of the present application, the CA model is used to divide the external overall boundary and the internal connection boundary of the national land space area to be analyzed, and further includes: Aiming at the connection between the unit grids under the national land space area to be analyzed, the connection cost between different grid units is calculated through minimum cost path analysis and network flow model, and the connection rules are constructed. The connection rules are introduced into the CA model, and the CA model is run to extract the boundaries of the unit grids inside the national land space area to be analyzed as the internal connection boundaries.
[0013] Correspondingly, this application also provides a national land space planning system using data analysis, including: The first module is used to obtain multi-source geographic location data of the territorial space area to be analyzed, perform multi-dimensional landmark point screening on the territorial space area to be analyzed, obtain a landmark point set, and align the multi-source geographic location data of the territorial space area to be analyzed through the landmark point set; The second module is used to split the national spatial area to be analyzed into multiple cells, define the core elements of the cells, and establish a CA model; The third module is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed through the CA model; The fourth module is used to conduct multi-angle analysis of national land space planning based on the external overall boundary and internal connection boundary.
[0014] The present invention has the following beneficial effects: 1. Perform multi-dimensional landmark screening on the national territory to be analyzed. This screening considers multiple dimensions based on spatial distribution to ensure the common rationality of landmarks across multi-source data. This also provides the accuracy of registration of multi-source geographic location data, providing a reliable foundation for subsequent boundary determination. Define the core elements of the cell and establish a CA model. This model's core elements are defined based on multiple characteristics of the national territory to improve the model's adaptability.
[0015] 2. The CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed. The CA model is run for the two boundaries separately, and connection rules are introduced to improve the reliability and accuracy of the determination of the two boundaries. Based on the external overall boundary and the internal connection boundary, a multi-angle analysis of the national land space planning is carried out, which improves the accuracy and rationality of the national land space planning, meets the dynamic change needs of the boundary, provides data support for the future of national land space planning, and facilitates the formulation of future development tasks of national land space planning. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A flowchart of a land space planning method using data analysis proposed by the present invention; Figure 2 This is a structural diagram of a national land space planning system using data analysis proposed by the present invention. DETAILED DESCRIPTION
[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.
[0018] Reference Figure 1 , a land space planning method using data analysis, comprising the following steps: Step S101, obtain multi-source geographic location data of the national land space area to be analyzed, perform multi-dimensional landmark point screening on the national land space area to be analyzed, obtain a landmark point set, and use the landmark point set to align the multi-source geographic location data of the national land space area to be analyzed.
[0019] In this embodiment, multi-source geographic location data such as remote sensing images, geographic information, and socioeconomic statistics are divided into external overall boundaries and internal connection boundaries through data alignment (achieved by relying on common landmarks with higher reliability in multi-source geographic location data) and cellular automaton (CA) model simulation, providing a scientific basis for regional development and protection.
[0020] In some embodiments of the present application, before performing multi-dimensional landmark point screening on the land space area to be analyzed, the method further includes pre-processing the multi-source geographic location data, specifically, Convert each source geographic location data in the multi-source geographic location data into a standard coordinate system to achieve coordinate system one; Determine the original resolution of each source geolocation data in the multi-source geolocation data, calculate the minimum effective resolution, perform initial registration and superposition on the geolocation data with different original resolutions to obtain the registration error, calculate the target resolution based on the registration error and the minimum effective resolution, and unify the resolution of the multi-source geolocation data according to the target resolution; Identify the attributes of different original regions in the national land space area to be analyzed. The attributes of the original regions include regional function type, terrain complexity information, land feature density information, and monitoring scale information. Based on the regional function type, terrain complexity information, land feature density information, and monitoring scale information, determine the resolution requirement for each original region. The resolution requirement of each original area is matched with the target resolution to identify the multi-scale original areas that require multi-scale resolution in all original areas. The multi-scale original areas are divided into multiple accuracy levels, each accuracy level corresponds to a resolution, and a multi-scale resolution pyramid is constructed to achieve the unification and adaptation of the resolution of multi-source geographic location data.
[0021] In this embodiment, before screening the landmark points of multi-source geographic location data, in order to ensure the consistency and accuracy between the geographic location data from different sources, it is necessary to unify the coordinates and adapt the resolution of the geographic location data from different sources. Convert remote sensing images (such as Landsat data, WGS84 coordinate system), terrain data (such as DEM, UTM coordinate system), etc. into a unified coordinate system (such as CGCS2000). The minimum effective resolution refers to the coarsest resolution in the multi-source data under the premise of meeting the resolution requirements. It determines the minimum spatial detail expression capability after data fusion. The registration error refers to the positional deviation generated by different data sources in the spatial alignment process (direct superposition of unprocessed multi-source geographic location data), usually in pixels or meters. It reflects the accuracy requirements of data fusion. The product of the minimum effective resolution and the registration error is used as the spatial error to calculate the target resolution according to the spatial error requirements.
[0022] In this embodiment, the unified target resolution does not meet the resolution requirements or data analysis requirements of all regions, so a multi-scale resolution pyramid is established for regions that do not meet the resolution requirements. The resolution requirements are determined based on the regional functional type (such as city, farmland, ecological protection area), terrain complexity (such as slope >15° is complex), and land feature density (such as building density >30% is high density). Multi-scale original area: refers to the area in the same data source that requires different resolutions due to spatial heterogeneity (such as urban / rural, terrain undulations). Accuracy level: The resolution level is divided according to application requirements (such as disaster monitoring, urban planning), and each level corresponds to a specific resolution. Pyramid structure: Each level is an independent grid, which is linked by resampling. Resampling method: High → Medium: Bilinear interpolation (smooth transition). Medium → Low: Aggregation (such as mean, maximum value).
[0023] In some embodiments of the present application, multi-dimensional landmark point screening is performed on the land space area to be analyzed, including: determining a first gridding degree for each original region according to a target resolution or a resolution of a multi-precision level; obtaining an average amount of data collected and a data analysis capability for each original region, and determining a second gridding degree for each original region according to the average amount of data collected and the data analysis capability; A third gridding degree is set based on the first gridding degree and the second gridding degree of the original area, and the original area is gridded by the third gridding degree to obtain a plurality of grid cells, which are used to describe the entire land space area to be analyzed; Multiple candidate landmarks are identified in each grid cell, and the multi-dimensional evaluation content of each candidate landmark is analyzed. The multi-dimensional evaluation content includes the evaluation content of three properties: significance, consistency, and stability. The screening indicators are defined by comprehensively evaluating the evaluation content of these three properties; The candidate landmark points under each grid unit are screened by using the screening indicators, and the screened results are used as landmark points.
[0024] In this embodiment, the basic granularity of the grid is determined based on the target resolution or the resolution of the multi-precision level. In a single-resolution scenario, the grid size equals the target resolution (e.g., 30m×30m). In a multi-precision scenario, each precision level corresponds to a separate grid (e.g., 15m×15m for high-precision, 30m×30m for medium-precision). For example, if the target resolution is 30m, the first gridding level is a uniform 30m×30m grid. Average data acquisition volume (D): The number of data points acquired per unit area (e.g., 100 points per square kilometer). Data analysis capacity (C): The amount of data that can be processed per unit time (e.g., 1TB per day). Grid size is positively correlated with D (finer grids in data-dense areas) and negatively correlated with C (coarser grids for weaker computing power). Grid size = m / D*C. The average of the two gridding levels is taken. The gridding level can be reflected by parameters such as grid size and grid density.
[0025] In this example, saliency measures whether a point represents a key feature (e.g., a sudden elevation change or a land use change). Consistency measures whether a point's performance is consistent across different data sources (e.g., the positional deviation of the same feature in a DEM and an optical image is less than 1 pixel). Stability measures whether a point exhibits minimal variation over time (e.g., a long-standing building corner). These three dimensions are then quantified to determine the screening criteria.
[0026] ; in, For the The screening index of the grid unit, 3 represents the quantitative parameters of the evaluation content of the three properties of significance, consistency and stability, and the three quantitative parameters are normalized. For the three dimensions The combined weight of the dimensions, For the The grid unit under The quantization parameter size of each dimension, for The maximum value in for The minimum value in For the The first constant corresponding to the grid cells, express The average value of the correction of the sum of the three dimensions is between 0.891 and 1.234. The first constant is used to balance the size of the correction function. The evaluation content of the three properties of significance, consistency and stability is comprehensively used to define the screening index for the screening of landmark points.
[0027] In some embodiments of the present application, the multi-source geographic location data of the land space area to be analyzed are aligned by using a set of landmark points, including: The number of landmarks, the uniformity of landmark distribution, and the density of landmarks under each grid unit are counted. The corresponding registration model type for each grid unit is selected based on the number of landmarks, the uniformity of landmark distribution, and the density of landmarks. The registration model parameters are then optimized to achieve registration alignment between multi-source geographic location data.
[0028] In this embodiment, the number of marker points (Count): the total number of marker points after screening in each grid unit. Uniformity of distribution (Uniformity): the spatial dispersion of marker points in the grid (such as measured by the coefficient of variation CV of the nearest neighbor distance). Density (Density): the number of marker points per unit area (such as points / km²). The types of registration models include rigid transformation, affine transformation, projection transformation, and non-rigid transformation. For example, for rigid transformation, the applicable conditions are: the number of marker points ≥ 5, uniformity > 0.7, and density > 10 points / km² (applicable to small-scale areas with no terrain undulations). For affine transformation, the applicable conditions are: the number of marker points ≥ 8, uniformity > 0.6, and density > 15 points / km² (applicable to medium-scale areas with slight terrain changes). For projection transformation, the applicable conditions are: the number of marker points ≥ 12, uniformity > 0.5, and density > 20 points / km² (applicable to large-scale areas with complex terrain). Non-rigid transformations are applicable when the number of landmarks is ≥ 20, uniformity is > 0.4, and density is > 30 points / km² (e.g., TPS and B-spline, suitable for areas with local deformation). Registration model parameters are optimized to minimize registration error: transformation parameters are iteratively adjusted to minimize the root mean square error (RMSE) between landmark pairs. Perform iterative optimization and initialize transformation parameters. Calculate the current RMSE. If the RMSE exceeds a threshold (e.g., 1 pixel), adjust parameters (e.g., add control points or adjust transformation complexity) and repeat until convergence.
[0029] Step S102: split the national land space area to be analyzed into multiple cells, define the core elements of the cells, and establish a CA model.
[0030] In this example, the divided grid units are used as individual cells to form discretized analysis units, with each grid unit (e.g., 40m×40m) being considered a cell. The cell state is initialized to the land use type (e.g., construction land, cultivated land, forest land, water area).
[0031] In some embodiments of the present application, the national space area to be analyzed is split into multiple cells, including: Each grid unit is regarded as a cell, and the state attributes of the cell are set. The state attributes are land use type or other basic information.
[0032] In this embodiment, other basic information includes land cover type, elevation, slope, and other information. Land cover type refers to the actual land cover within a cell (e.g., vegetation, bare land, buildings). Examples include evergreen broadleaf forests, concrete pavement, and water bodies. Elevation refers to the cell center or average elevation (derived from DEM data) of 50.3 m. Slope refers to the average slope within a cell (calculated from the DEM) of 8.5°.
[0033] In some embodiments of the present application, the core elements of a cell are defined, including: The core elements include neighborhood structure and state transition rules, which are jointly reflected by neighborhood type and neighborhood radius; Determine the neighborhood type of each cell, establish a diffusion model for each grid cell, describe the spatial diffusion effect of the grid cell through the diffusion model, analyze the spatial autocorrelation between grid cells, adjust the spatial diffusion effect according to the spatial autocorrelation, and thus determine the neighborhood radius; The driving factors of the grid cells are collected, including neighborhood status, macro indicators and random disturbance terms. The state transition rules are set according to the neighborhood status, macro indicators and random disturbance terms.
[0034] In this embodiment, the neighborhood type is the direction of the neighborhood. Von Neumann neighborhood: only includes four directions: up, down, left, and right. Moore neighborhood: includes 8 surrounding directions, four directions: up, down, left, and right + diagonal (extended Von Neumann). Neighborhood radius: the physical range of the neighborhood (such as 50m, 100m), which is dynamically adjusted through spatial autocorrelation analysis. The diffusion model is used to simulate the conductivity or fluidity of the grid unit, that is, the region, to obtain the function of the diffusion model. The spatial autocorrelation between the grid units is analyzed, and the global Moran's index (Global Moran's I) is calculated to evaluate the overall spatial autocorrelation. The local Moran's index (Local Moran's I) is calculated to identify hot / cold spot areas and obtain the spatial autocorrelation intensity. The adjustment coefficient is determined based on the spatial autocorrelation intensity. The spatial diffusion effect is adjusted by multiplying the adjustment coefficient by the function of the diffusion model to determine the neighborhood radius.
[0035] In this embodiment, the state transition rules include the transition between different grid cell types, neighborhood state, the state set of neighborhood cells (such as the proportion of construction land in the neighborhood), macro indicators, external factors affecting the overall situation (such as GDP and policy intensity), random disturbance terms, and unpredictable emergencies (such as the probability of natural disasters). For example, land use type conversion (such as cultivated land to construction land): Neighborhood impact: If the proportion of construction land area in the neighborhood is greater than 60%, the conversion probability is increased by 30%.
[0036] Macro constraints: If GDP growth rate > 5%, conversion probability + 15%.
[0037] Random Perturbation: Introduces a 5% chance of randomly triggering a transformation.
[0038] The state transition rule uses the state transition probability to describe the possibility of transition. The formula is as follows: ; in, is the state transition probability, 、 、 are the weight coefficients of neighborhood influence, macro influence, and random disturbance, For cells The neighborhood cell set of For cells and neighboring cells The spatial weights between (usually decay with clustering), is an exponential function, if the neighborhood cell The state is the target state , then it is 1, otherwise it is 0, For macro indicators at all times The normalized value of is a random disturbance term.
[0039] Step S103: Use the CA model to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed.
[0040] In this embodiment, the ca model is run on the external overall boundary and the internal connection boundary respectively to simulate the dynamic change and evolution of the region.
[0041] In some embodiments of the present application, the CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed, including: For the entire national space area to be analyzed, the CA model is run and the cellular state is iteratively updated until the spatial pattern tends to be stable. The outer contour boundary of the grid cells in the stable state is identified through edge detection algorithm or spatial cluster analysis, which serves as the external overall boundary of the national space area to be analyzed.
[0042] In this example, the external boundary focuses on the overall scope of the region, while the internal boundary focuses on the functional connections between subregions. The two have different parameter settings, rule definitions, and simulation objectives in the CA model. The same CA model can coordinate the relationship between the two through layered simulation or multi-objective optimization to ensure logical consistency.
[0043] The cellular automation (CA) model is combined with spatial analysis technology to dynamically identify the external overall boundaries and internal connection boundaries of the national land space area. The specific steps are as follows: Run the CA model and iteratively update the cell state according to the state transition rules until the spatial pattern becomes stable (e.g., no significant change after 5 consecutive iterations).
[0044] For grid cells in a stable state, edge detection algorithms (such as Sobel and Canny) or spatial clustering analysis (such as DBSCAN and K-means) are applied to identify the outer contour boundaries.
[0045] The outer contour boundary is defined as the set of grid cells where the cell state undergoes a sudden change (e.g., from non-construction land to construction land) in a stable state.
[0046] The technologies involved are as follows: Edge detection algorithm: Sobel operator: detects boundaries by calculating the gradient magnitude.
[0047] Canny operator: combines Gaussian filtering, non-maximum suppression, and double threshold detection, suitable for data with high noise.
[0048] Spatial cluster analysis: DBSCAN: Based on density clustering, automatically identify the outer boundaries of high-density areas.
[0049] K-means: The number of clusters must be specified in advance and is suitable for areas with clear boundaries.
[0050] In some embodiments of the present application, the CA model is used to divide the external overall boundary and the internal connection boundary of the national land space area to be analyzed, and further includes: Aiming at the connection between the unit grids under the national land space area to be analyzed, the connection cost between different grid units is calculated through minimum cost path analysis and network flow model, and the connection rules are constructed. The connection rules are introduced into the CA model, and the CA model is run to extract the boundaries of the unit grids inside the national land space area to be analyzed as the internal connection boundaries.
[0051] In this example, based on least cost path (LCP) analysis and a network flow model, the connection costs (such as terrain resistance, economic costs, and ecological sensitivity) between different grid cells are calculated to construct a cost matrix. The cost matrix thresholds are established in the connection rules to complete the connection. The connection rules are then incorporated into the state transition rules, and the CA model is run to extract the boundaries: Run the CA model and update the cell state according to the connection rules.
[0052] Extract the boundaries of the internal mesh cells in the steady state (e.g., by region growing or connected component analysis).
[0053] The technologies involved are as follows: Minimum cost path analysis: Dijkstra algorithm: Calculates the shortest path from a single source, applicable to static cost matrices.
[0054] A* algorithm: Combined with heuristic functions to accelerate search, suitable for large-scale grids.
[0055] Network flow model: Max-flow min-cut theorem: Identify key connection nodes and bottlenecks within a region.
[0056] Random walk model: simulates the movement of random particles in a grid and calculates the connection probability.
[0057] Step S104: Conduct a multi-angle analysis of the national land space planning based on the external overall boundary and the internal connection boundary.
[0058] In this example, the multi-angle analysis includes ecological protection, development intensity, functional layout, transportation network, and risk prevention and control. More accurate data analysis and prediction are carried out based on the external overall boundary and internal connection boundary.
[0059] Correspondingly, this application also provides a national land space planning system that applies data analysis, such as Figure 2 Shown, including, The first module is used to obtain multi-source geographic location data of the territorial space area to be analyzed, perform multi-dimensional landmark point screening on the territorial space area to be analyzed, obtain a landmark point set, and align the multi-source geographic location data of the territorial space area to be analyzed through the landmark point set; The second module is used to split the national spatial area to be analyzed into multiple cells, define the core elements of the cells, and establish a CA model; The third module is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed through the CA model; The fourth module is used to conduct multi-angle analysis of national land space planning based on the external overall boundary and internal connection boundary.
[0060] The present invention has the following beneficial effects: 1. Perform multi-dimensional landmark screening on the national territory to be analyzed. This screening considers multiple dimensions based on spatial distribution to ensure the common rationality of landmarks across multi-source data. This also provides the accuracy of registration of multi-source geographic location data, providing a reliable foundation for subsequent boundary determination. Define the core elements of the cell and establish a CA model. This model's core elements are defined based on multiple characteristics of the national territory to improve the model's adaptability.
[0061] 2. The CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed. The CA model is run for the two boundaries separately, and connection rules are introduced to improve the reliability and accuracy of the determination of the two boundaries. Based on the external overall boundary and the internal connection boundary, a multi-angle analysis of the national land space planning is carried out, which improves the accuracy and rationality of the national land space planning, meets the dynamic change needs of the boundary, provides data support for the future of national land space planning, and facilitates the formulation of future development tasks of national land space planning.
[0062] Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented via hardware or via software combined with a necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product. This software product can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash drive, or external hard drive) and includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various implementation scenarios of the present invention.
[0063] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.
[0064] Those skilled in the art will appreciate that the modules in the system of the implementation scenario can be distributed in the system of the implementation scenario according to the implementation scenario description, or can be modified accordingly and located in one or more systems different from the implementation scenario. The modules of the above implementation scenario can be combined into one module or further divided into multiple submodules.
[0065] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.
Claims
1. A land space planning method using data analysis, characterized in that: include, Obtain multi-source geographic location data for the territorial space area to be analyzed, perform multi-dimensional landmark point screening on the territorial space area to be analyzed, obtain a landmark point set, and align the multi-source geographic location data for the territorial space area to be analyzed through the landmark point set; Split the national spatial area to be analyzed into multiple cells, define the core elements of the cells, and establish a CA model; The CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed; Conduct multi-angle analysis of national land space planning based on the external overall boundary and internal connection boundary.
2. The land space planning method using data analysis according to claim 1, characterized in that: Before performing multi-dimensional landmark screening on the land space area to be analyzed, the method further includes pre-processing the multi-source geographic location data, specifically, Convert each source geographic location data in the multi-source geographic location data into a standard coordinate system to achieve coordinate system one; Determine the original resolution of each source geolocation data in the multi-source geolocation data, calculate the minimum effective resolution, perform initial registration and superposition on the geolocation data with different original resolutions to obtain the registration error, calculate the target resolution based on the registration error and the minimum effective resolution, and unify the resolution of the multi-source geolocation data according to the target resolution; Identify the attributes of different original regions in the national land space area to be analyzed. The attributes of the original regions include regional function type, terrain complexity information, land feature density information, and monitoring scale information. Based on the regional function type, terrain complexity information, land feature density information, and monitoring scale information, determine the resolution requirement for each original region. The resolution requirement of each original area is matched with the target resolution to identify the multi-scale original areas that require multi-scale resolution in all original areas. The multi-scale original areas are divided into multiple accuracy levels, each accuracy level corresponds to a resolution, and a multi-scale resolution pyramid is constructed to achieve the unification and adaptation of the resolution of multi-source geographic location data.
3. The land space planning method using data analysis according to claim 2, characterized in that: Perform multi-dimensional landmark screening on the land space area to be analyzed, including: determining a first gridding degree for each original region according to a target resolution or a resolution of a multi-precision level; obtaining an average amount of data collected and a data analysis capability for each original region, and determining a second gridding degree for each original region according to the average amount of data collected and the data analysis capability; A third gridding degree is set based on the first gridding degree and the second gridding degree of the original area, and the original area is gridded by the third gridding degree to obtain a plurality of grid cells, which are used to describe the entire land space area to be analyzed; Multiple candidate landmarks are identified in each grid cell, and the multi-dimensional evaluation content of each candidate landmark is analyzed. The multi-dimensional evaluation content includes the evaluation content of three properties: significance, consistency, and stability. The screening indicators are defined by comprehensively evaluating the evaluation content of these three properties; The candidate landmark points under each grid unit are screened by using the screening indicators, and the screened results are used as landmark points.
4. The land space planning method using data analysis according to claim 3 is characterized in that: The multi-source geographic location data of the land space area to be analyzed are aligned through the landmark point set, including: The number of landmarks, the uniformity of landmark distribution, and the density of landmarks under each grid unit are counted. The corresponding registration model type for each grid unit is selected based on the number of landmarks, the uniformity of landmark distribution, and the density of landmarks. The registration model parameters are then optimized to achieve registration alignment between multi-source geographic location data.
5. The land space planning method using data analysis according to claim 3 is characterized in that: The national spatial area to be analyzed is divided into multiple cells, including: Each grid unit is regarded as a cell, and the state attributes of the cell are set. The state attributes are land use type or other basic information.
6. The land space planning method using data analysis according to claim 5, characterized in that: The core elements that define a cell include: The core elements include neighborhood structure and state transition rules, which are jointly reflected by neighborhood type and neighborhood radius; Determine the neighborhood type of each cell, establish a diffusion model for each grid cell, describe the spatial diffusion effect of the grid cell through the diffusion model, analyze the spatial autocorrelation between grid cells, adjust the spatial diffusion effect according to the spatial autocorrelation, and thus determine the neighborhood radius; The driving factors of the grid cells are collected, including neighborhood status, macro indicators and random disturbance terms. The state transition rules are set according to the neighborhood status, macro indicators and random disturbance terms.
7. The land space planning method using data analysis according to claim 6, characterized in that: The CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed, including: For the entire national space area to be analyzed, the CA model is run and the cellular state is iteratively updated until the spatial pattern tends to be stable. The outer contour boundary of the grid cells in the stable state is identified through edge detection algorithm or spatial cluster analysis, which serves as the external overall boundary of the national space area to be analyzed.
8. The land space planning method using data analysis according to claim 6, characterized in that: The CA model is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed, including: Aiming at the connection between the unit grids under the national land space area to be analyzed, the connection cost between different grid units is calculated through minimum cost path analysis and network flow model, and the connection rules are constructed. The connection rules are introduced into the CA model, and the CA model is run to extract the boundaries of the unit grids inside the national land space area to be analyzed as the internal connection boundaries.
9. A land space planning system using data analysis, characterized in that: include, The first module is used to obtain multi-source geographic location data of the territorial space area to be analyzed, perform multi-dimensional landmark point screening on the territorial space area to be analyzed, obtain a landmark point set, and align the multi-source geographic location data of the territorial space area to be analyzed through the landmark point set; The second module is used to split the national spatial area to be analyzed into multiple cells, define the core elements of the cells, and establish a CA model; The third module is used to divide the external overall boundary and internal connection boundary of the national land space area to be analyzed through the CA model; The fourth module is used to conduct multi-angle analysis of national land space planning based on the external overall boundary and internal connection boundary.