Land resource asset servicing time sequence simulation method and system

Abstract

The invention discloses a land resource asset servicing time sequence simulation method, which comprises the following steps: acquiring construction map spot data of a target area in historical years, and performing spatial rasterization processing to obtain a grid map layer in a map spot state in multiple years; calculating a current land resource asset servicing resistance comprehensive value of each grid layer based on a preset servicing resistance evaluation system; constructing a space-time probability prediction model, and performing parameter fitting by using map spot data for construction in historical years; calculating the prediction probability of each grid layer in the target year based on the fitted space-time probability prediction model; the servicing resistance comprehensive value and the prediction probability of each grid layer are synthesized, and a servicing implementation potential value of each grid layer is calculated; and based on the servicing implementation potential value, generating a suggested scheme for guiding a land resource asset servicing implementation time sequence. According to the method, the limitation of traditional static evaluation is overcome, continuous simulation of a servicing time sequence is realized, and a decision basis is provided for medium-and-long-term land servicing planning.

Description

Technical Field

[0001] This invention relates to the field of land spatial planning technology, specifically to a method and system for simulating the time sequence of land resource asset preparation. Background Technology

[0002] With the continuous advancement of urbanization and industrialization, the rational allocation and efficient utilization of land resources have become core issues for regional sustainable development. In land resource management and urban renewal practices, how to scientifically and orderly promote land resource asset consolidation, especially the redevelopment and functional optimization of existing construction land, is a significant challenge. Traditional land consolidation decisions often rely on empirical judgment or static evaluation, lacking dynamic simulation and quantitative prediction of the spatiotemporal evolution of land resources, leading to frequent problems such as unreasonable consolidation timing and resource misallocation.

[0003] Current land resource assessment technologies often focus on suitability or potential analysis at a single point in time, such as static scoring based on dimensions like ownership clarity, plot function, or land quality. However, these methods often overlook the temporal and spatial correlations and continuity of land use changes, such as the spillover effects of development on the target plot and the dynamic impact of policies and market conditions at different times on the land consolidation process. Therefore, existing methods struggle to simulate the future consolidation sequence of land resource assets and cannot provide scientific and precise decision support for medium- and long-term land consolidation planning.

[0004] Furthermore, since land consolidation involves multiple obstacles such as ownership integration, functional adjustment, and quality improvement, the existing evaluation system is often one-dimensional or fails to integrate systematically, resulting in an incomplete assessment of consolidation obstacles and affecting the accuracy of subsequent consolidation potential calculations. Summary of the Invention

[0005] To overcome the above-mentioned technical defects, the present invention provides a method and system for simulating the time sequence of land resource asset preparation.

[0006] To solve the above problems, the present invention is implemented according to the following technical solution:

[0007] In a first aspect, the present invention provides a method for simulating the time series of land resource asset consolidation, comprising: acquiring historical construction land use map patch data of a target area and performing spatial rasterization processing to obtain raster layers of land use map patch states for multiple years; calculating the current comprehensive value of land resource asset consolidation resistance for each raster layer based on a preset consolidation resistance evaluation system, wherein the consolidation resistance evaluation system includes three dimensions: ownership, function, and quality; constructing a spatiotemporal probability prediction model, wherein the spatiotemporal probability prediction model uses time variables and variables representing spatial adjacency influence as independent variables, and the predicted probability of the raster layer transforming into a preset land use type in the target year as the dependent variable, and performs parameter fitting using the construction land use map patch data of the historical years; calculating the predicted probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model; calculating its consolidation implementation potential value by combining the comprehensive value of consolidation resistance and the predicted probability of each raster layer; and generating a suggested scheme to guide the implementation time series of land resource asset consolidation based on the consolidation implementation potential value.

[0008] In conjunction with the first aspect, the present invention provides a first specific implementation of the first aspect. Specifically, the step of acquiring historical construction land cover data of a target area and spatially rasterizing it to obtain a raster layer of land cover status for multiple years includes the following steps: acquiring construction land cover vector data of the target area in multiple consecutive historical years; dividing the target area into several regular raster units according to a preset size to construct a raster net covering the target area; performing spatial overlay analysis on the construction land cover vector data of each historical year with the raster net, and calculating the proportion of the construction land cover area within each raster unit to the total area of ​​the raster unit for each raster unit; using the proportion of each raster unit in each historical year as its land use status attribute value, and generating raster layers by year, with each raster layer recording the status values ​​of all raster units in that year, forming a time-series construction land cover raster dataset.

[0009] In conjunction with the first aspect, the present invention provides a second specific implementation of the first aspect. Specifically, the step of calculating the comprehensive value of the current land resource asset preparation resistance for each raster layer based on a preset preparation resistance evaluation system includes the following steps: determining the dimensions included in the preparation resistance evaluation system and the evaluation indicators under each dimension; collecting spatial data related to the evaluation indicators and standardizing or normalizing the spatial data; converting the processed spatial data to the same geospatial reference system as the raster layer and calculating the values ​​of each evaluation indicator within each raster layer; performing weighted calculations on the evaluation indicator values ​​of different dimensions within each raster layer based on predetermined weights to obtain the comprehensive value of the preparation resistance for that raster layer; and spatially rasterizing the comprehensive value of the preparation resistance to form a preparation spatial resistance raster map covering the target area.

[0010] In conjunction with the first aspect, this invention provides a third specific implementation of the first aspect. Specifically, the construction of the spatiotemporal probability prediction model, which uses time variables and variables representing spatial adjacency influences as independent variables, and the predicted probability of a raster layer transforming into a preset land use type in a target year as the dependent variable, and uses construction land cover patch data from historical years for parameter fitting, specifically includes the following steps: based on the construction land cover raster dataset from historical years, extracting the construction land cover attribute value of each raster layer in each year; binarizing the construction land cover attribute value into a land use status identifier according to a preset threshold, wherein if the construction land proportion of the raster layer is greater than or equal to 50%, it is marked. If the land use status is not specified, it is marked as construction land. Based on preset neighborhood analysis rules, the spatial adjacency influence variable for each raster layer in each year is calculated. This spatial adjacency influence variable is the average value of the construction land cover attribute of the raster within its surrounding neighborhood. Using the time variable and the spatial adjacency influence variable as independent variables, and the land use status identifier as the dependent variable, a spatiotemporal probability prediction model is constructed using logistic regression. The spatiotemporal probability prediction model is then fitted with parameters using the historical construction land cover raster dataset to obtain the model regression coefficients. The fitted spatiotemporal probability model is then used to predict the probability that each raster layer will be converted to construction land in a future target year.

[0011] In conjunction with the first aspect, the present invention provides a fourth specific implementation of the first aspect. Specifically, the step of calculating the predicted probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model includes the following steps: determining the target prediction year and the corresponding time variable; calculating the spatial adjacency influence variable corresponding to each raster layer in the most recent year based on the construction land coverage raster dataset of the most recent historical year; substituting the time variable and the spatial adjacency influence variable corresponding to each raster layer into the fitted spatiotemporal probability prediction model; calculating the predicted probability value of each raster layer transforming into construction land in the target year according to the model formula; and assigning the predicted probability value back to the corresponding raster layer to form a predicted construction land probability raster map covering the target area.

[0012] In conjunction with the first aspect, the present invention provides a fifth specific implementation of the first aspect, specifically, the spatiotemporal probability prediction model adopts a logistic regression model, in the form of: ;in, raster layer The predicted probability of land use for construction in the target year. The time variable is the target year. raster layer Spatial adjacency influences variables. These are the model parameters obtained by fitting construction map patch data from historical years.

[0013] In conjunction with the first aspect, the present invention provides a sixth specific implementation of the first aspect. Specifically, the step of calculating the preparation and implementation potential value of each of the grid layers by combining the comprehensive value of the preparation resistance and the predicted probability includes the following steps: spatially aligning the predicted construction land probability grid map with the preparation spatial resistance grid map; obtaining the preparation and implementation potential value for each grid layer according to a preset potential calculation formula; normalizing or standardizing the preparation and implementation potential values ​​of all grid layers so that the potential values ​​fall within a uniform comparable range; and assigning the processed preparation and implementation potential value back to the corresponding grid layer to form a preparation and implementation potential grid map covering the target area.

[0014] In conjunction with the first aspect, the present invention provides a seventh specific embodiment of the first aspect, wherein the potential calculation formula is as follows: ;in, raster layer The original potential value for preparation and implementation; raster layer The predicted probability of land use for construction; raster layer The overall value of the running resistance.

[0015] In conjunction with the first aspect, the present invention provides an eighth specific implementation of the first aspect. Specifically, the step of generating a suggested scheme for guiding the implementation sequence of land resource asset consolidation based on the consolidation implementation potential value includes the following steps: dividing the raster layer into several consolidation priority levels according to the magnitude of the consolidation implementation potential value; performing spatial clustering and boundary optimization on the raster layer according to the consolidation priority level, combined with the spatial proximity principle and planning constraints, to form several suggested consolidation areas; determining the consolidation implementation sequence order based on the average or comprehensive consolidation implementation potential value of each suggested consolidation area; and generating a suggested scheme for the consolidation implementation sequence that includes the phased and zoned consolidation scope, suggested implementation time, and priority, and outputting it as a visualization map or structured report.

[0016] Secondly, the present invention also provides a land resource asset consolidation time series simulation system, including: a data acquisition and processing module, used to acquire historical construction map patch data of the target area for different years, and to perform spatial rasterization processing on it to obtain a raster layer of construction map patch status for multiple years;

[0017] The land preparation resistance calculation module is used to calculate the comprehensive value of the current land resource asset preparation resistance for each grid layer based on a preset land preparation resistance evaluation system. The land preparation resistance evaluation system includes three dimensions: ownership, function, and quality.

[0018] The model building and fitting module is used to build a spatiotemporal probability prediction model. The spatiotemporal probability prediction model uses time variables and variables representing spatial adjacency influence as independent variables, the predicted probability of a raster layer changing to a preset land use type in the target year as the dependent variable, and uses the construction map patch data of the historical years for parameter fitting.

[0019] The prediction probability calculation module is used to calculate the prediction probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model.

[0020] The maintenance potential calculation module is used to calculate the maintenance implementation potential value of each grid layer by combining the overall maintenance resistance value and the predicted probability.

[0021] The scheme generation module is used to generate a suggested scheme to guide the timing of land resource asset preparation and implementation based on the preparedness implementation potential value.

[0022] Compared with the prior art, the beneficial effects of the present invention are:

[0023] By constructing a spatiotemporal probability prediction model that incorporates both temporal and spatial adjacency variables into the prediction framework, the probability of land resource asset utilization type transformation in different target years can be dynamically simulated. This method overcomes the limitations of traditional static evaluation, achieving continuous simulation of land consolidation timelines and providing quantitative decision-making basis for medium- and long-term land consolidation planning. By pre-setting a consolidation resistance evaluation system covering ownership, function, and quality, the consolidation resistance of each raster layer can be comprehensively and systematically quantified. This multi-dimensional integrated assessment avoids the one-sidedness of single-indicator evaluation and more realistically reflects the multiple constraints faced by land consolidation in actual implementation. By combining the comprehensive consolidation resistance value and spatiotemporal prediction probability of each raster layer, its consolidation implementation potential value is calculated. This method not only considers the inherent limitations of the land parcels but also incorporates their development probability within the regional spatiotemporal context, thereby identifying high-potential consolidation areas and their temporal characteristics. The guidance scheme based on the generated consolidation implementation potential value can clarify the consolidation priorities and implementation paths for different regions and time stages. This method combines historical construction map patch data, multi-dimensional evaluation data, and spatiotemporal prediction models to achieve a systematic transformation from raw geographic information data to knowledge support for land development decisions. Through spatial rasterization processing and model calculation, intuitive spatialized suggestion schemes are generated, enhancing the auxiliary decision-making value of land resource big data in national land spatial planning and governance. Attached Figure Description

[0024] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings, wherein:

[0025] Figure 1 This is a flowchart of a land resource asset consolidation time-series simulation method according to the present invention.

[0026] Figure 2 This is a block diagram of an electronic device used to implement embodiments of the present invention;

[0027] In the picture:

[0028] 100 - Electronic device, 101 - Computing unit, 102 - ROM, 103 - RAM, 104 - Bus, 105 - I / O interface, 106 - Input unit, 107 - Output unit, 108 - Storage unit, 109 - Communication unit. Detailed Implementation

[0029] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0030] like Figure 1 As shown, this invention provides a method and system for simulating the time series of land resource asset consolidation.

[0031] Example 1

[0032] like Figure 1 As shown, a land resource asset consolidation time-series simulation method includes: acquiring historical construction land use map patch data of a target area and performing spatial rasterization processing to obtain raster layers of land use map patch states for multiple years; calculating the current comprehensive land resource asset consolidation resistance value of each raster layer based on a preset consolidation resistance evaluation system, wherein the consolidation resistance evaluation system includes three dimensions: ownership, function, and quality; constructing a spatiotemporal probability prediction model, wherein the spatiotemporal probability prediction model uses time variables and variables representing spatial adjacency influence as independent variables, and the predicted probability of the raster layer transforming into a preset land use type in the target year as the dependent variable, and performs parameter fitting using the historical construction land use map patch data; calculating the predicted probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model; calculating its consolidation implementation potential value by combining the comprehensive consolidation resistance value and the predicted probability of each raster layer; and generating a suggested scheme to guide the implementation time sequence of land resource asset consolidation based on the consolidation implementation potential value.

[0033] Specifically, this invention overcomes the limitations of previous methods that relied solely on a single factor (such as spatial suitability) by constructing a multi-dimensional evaluation system for land consolidation resistance, encompassing ownership, function, and quality. This method comprehensively quantifies the difficulty and cost of land consolidation from multiple core dimensions, including the intrinsic attributes (quality), socio-economic attributes (ownership), and planning attributes (function) of land resources, making the assessment of land resource asset consolidation potential more closely aligned with actual management needs. By constructing a spatiotemporal probability prediction model, it combines temporal evolution trends with spatial adjacency effects. This not only predicts the future land use change probability of a single raster layer but also overcomes the shortcomings of traditional static evaluations or models that only consider time trends, making the prediction results more dynamic and spatially logical, thus providing a scientific basis for medium- and long-term land consolidation planning.

[0034] This invention innovatively combines the comprehensive value of land consolidation resistance, reflecting the "current difficulty," with the predicted probability, reflecting the "future trend," to calculate the land consolidation implementation potential value. This indicator considers both current development constraints and possible future development directions, effectively identifying priority areas with "relatively low resistance and a high probability of transformation." The resulting land consolidation recommendations clearly define the spatial implementation sequence and timing, significantly improving the efficiency of land resource asset revitalization and redevelopment, and providing intuitive technical support for scientific decision-making by government and management departments. By spatially rasterizing the map data, complex land management issues are transformed into computable spatial unit analysis. The entire method's input, calculation, and output all have clear spatial attributes, allowing the analysis process and results to be intuitively visualized on maps, greatly enhancing the intuitiveness of the solution and facilitating understanding and application across different departments and decision-making levels.

[0035] In a preferred embodiment, S100: acquire historical construction map patch data of the target area for different years, and perform spatial rasterization processing to obtain a raster layer of map patch status for multiple years.

[0036] Specifically, this is achieved by collecting historical annual land survey results or 30-meter resolution global land cover data (such as...). This involves obtaining construction map patch data for the target area for each of the past 10 consecutive years (e.g., 2015–2024). The acquired vector data is then formatted and topologically checked. The software organizes data by year, saving each entry as a vector polygon file in the format "Year_Construction Land Patch.shp". The construction land patches from the most recent year are used as current land resource asset data. The target area is divided into a regular spatial grid. A 200m × 200m raster net is used to fully cover the study area, generating a uniquely numbered raster unit layer. The construction land patch data for each of the past 10 years is spatially overlaid with the raster net. For each raster unit (corresponding to one grid cell), the proportion of construction land area within that unit to the total area of ​​the unit is calculated and denoted as the M value (ranging from 0 to 1). This value represents the construction and development intensity of that spatial unit in that year. The calculated M values ​​for each grid cell for each year are used as attribute fields and integrated into the attribute table of the raster layer. Each row in the attribute table represents an independent raster unit, and each column records the proportion of construction land in that unit in different years, thus forming a structured data table with a spatiotemporal sequence. Finally, based on this attribute table, the M values ​​for each year can be exported as independent raster layers. Each raster layer represents the construction land coverage status for a year, thus obtaining a time series raster dataset.

[0037] In a preferred embodiment, the step of acquiring historical construction map patch data of the target area for different years and performing spatial rasterization processing on it to obtain a raster layer showing the construction map patch status for multiple years specifically includes the following steps:

[0038] S101: Obtain construction map patch vector data of the target area in multiple consecutive historical years;

[0039] Specifically, by collecting land use survey data or 30-meter resolution global land cover data for the target area over the past 10 consecutive years (e.g., 2015 to 2024), vector surface data of construction land patches for each year are obtained. These data are then formatted, coordinate-calibrated, and topologically processed to form a vector dataset named "Year_Construction Land Patch". Data from the year most recent to the present will be used as the baseline for current construction land.

[0040] S102: Divide the target area into several regular grid units according to a preset size, and construct a grid fishing net covering the target area;

[0041] Specifically, using a fixed size of 200 meters × 200 meters, the target area is divided into regular grids, each grid is assigned a unique number, and a raster fishing net layer covering the entire research area is generated.

[0042] S103: Perform spatial overlay analysis between the construction map patch vector data of each historical year and the grid fishing net, and calculate the proportion of the construction map patch area in each grid cell to the total area of ​​the grid cell for each grid cell.

[0043] Specifically, the vector data of construction land patches for each year are spatially overlaid with the raster network for analysis. For each raster cell, the proportion of the construction land patch area within that cell to the total area of ​​the raster cell is calculated, defined as the construction land proportion (M value), which characterizes the construction and development intensity of that raster cell in the corresponding year.

[0044] S104: The proportion of each raster cell in each historical year is used as its land use status attribute value, and raster layers are generated according to the year. Each raster layer records the status value of all raster cells in that year, forming a time series construction land cover raster dataset.

[0045] Specifically, the percentage of construction land area (M value) calculated for each raster cell in each year is used as an attribute field and added to the attribute table of the raster fishnet layer to form a structured spatiotemporal dataset. Each row in the attribute table corresponds to a raster cell, and each column corresponds to the percentage of construction land area in different years. Based on this attribute table, using the "feature to raster" function or similar tools in GIS software, the raster fishnet vector layer is converted into an independent raster layer, with the percentage field for each year used as the value field. Each exported raster layer represents the construction land coverage status of a specific year, and its cell value is the M value for that year. By arranging the exported raster layers for all years chronologically, a spatiotemporal raster dataset containing construction land coverage information for multiple consecutive years is finally formed.

[0046] S200: Based on a preset land consolidation resistance evaluation system, calculate the comprehensive value of the current land resource asset consolidation resistance for each of the grid layers. The land consolidation resistance evaluation system includes three dimensions: ownership, function, and quality.

[0047] Specifically, based on my country's practical experience in land resource asset consolidation, the core constraints faced in the consolidation process are summarized into three dimensions: ownership, function, and quality, and a corresponding evaluation index system is established:

[0048] Obstacles to ownership ( ): This reflects the difficulty of ownership integration and adjustment, including the cost of acquiring ownership / use rights, the clarity of ownership, the complexity of historical issues, the cost of space replacement, and the cost of property reconstruction.

[0049] Functional resistance ( : Reflects the constraints of land use control and planning compliance, including the degree of conflict with the "three lines" (permanent basic farmland, ecological protection red line, and urban development boundary), and whether it is located in the core area of ​​a nature reserve, etc.

[0050] Mass resistance ( ): Reflects the inputs required to improve land resource use conditions, including the need for supporting infrastructure construction, ecological environment restoration costs, and the difficulty of building renovation or demolition.

[0051] The weights of each dimension of the indicators are determined using the entropy weight method, the mean square error method, or the Delphi method, and a comprehensive evaluation model for the running resistance is constructed.

[0052] ;in, Indicates the first The overall value of the maintenance resistance of each raster layer. For the first The weight of each indicator For this raster layer at the 1st Standardized values ​​of the indicators The total number of indicators, satisfying .

[0053] Basic data for each indicator was obtained through surveys and data collection. Various secondary indicators were quantified and standardized, and spatialized to the same spatial resolution as the raster layer (e.g., 200m × 200m) to ensure each raster has the values ​​for each indicator. Weighted overlay analysis was performed at the raster level, and the comprehensive preparation resistance value R for each raster layer was calculated based on the evaluation model. Based on the distribution of R values, they were divided into four levels—high resistance, medium resistance, relatively low resistance, and low resistance—using either the natural breakpoint method or the expert threshold method, generating a "single map of spatial resistance for land resource assets." Higher preparation resistance indicates lower feasibility for preparation of that raster layer under current conditions.

[0054] In a preferred embodiment, the calculation of the comprehensive value of the current land resource asset preparation resistance for each of the grid layers based on a preset preparation resistance evaluation system specifically includes the following steps:

[0055] Determine the dimensions included in the aforementioned preparation resistance evaluation system and the evaluation indicators under each dimension;

[0056] Specifically, based on the core constraints faced by land resource asset consolidation work, an evaluation system is constructed that includes three dimensions: ownership, function, and quality. Several specific evaluation indicators are established under each dimension:

[0057] Ownership dimensions include, but are not limited to, clarity of ownership, cost of acquiring and storing usage rights, difficulty of ownership swap, and complexity of historical issues.

[0058] Functional dimensions include the degree of spatial conflict with the "three lines" (permanent basic farmland, ecological protection red line, and urban development boundary), whether it is located in the core area or buffer zone of nature reserve, and compliance with planned use.

[0059] Quality dimensions include terrain slope, infrastructure support level, ecological environment status, and difficulty of renovating or demolishing existing buildings and structures.

[0060] Collect spatial data related to the evaluation indicators, and standardize or normalize the spatial data.

[0061] Specifically, spatial data corresponding to each evaluation indicator is obtained through multiple sources, including land surveys, planning results, remote sensing imagery, and field research. The raw data is cleaned, formatted, and calibrated. Methods such as range standardization, Z-score standardization, or membership functions are used to normalize the values ​​of each indicator to a unified dimension (e.g., the 0-1 range) to eliminate the influence of dimensional differences.

[0062] The processed spatial data is converted to the same geospatial reference system as the raster layer, and the values ​​of each evaluation index in each raster layer are calculated.

[0063] Specifically, the standardized spatial data of each indicator is converted to the same geographic coordinate system and spatial resolution as the raster layer. Through spatial overlay and zonal statistics, the average or representative value of each evaluation indicator in each raster layer is calculated and recorded in the raster attribute table to form a multi-indicator raster layer.

[0064] Based on predetermined weights, the evaluation index values ​​of different dimensions within each grid layer are weighted and calculated to obtain the comprehensive value of the preparation resistance of that grid layer.

[0065] Specifically, the weights of each dimension and indicator are determined using the entropy weight method, the analytic hierarchy process (AHP), or the Delphi method. Based on these weights, the indicator values ​​within each raster layer are linearly weighted and summed to calculate the comprehensive running resistance value of that unit. The calculation formula is as follows: ;in, Indicates the first The overall value of the maintenance resistance of each raster layer. For the first The weight of each indicator Let j be the standardized value of the raster layer on the j-th metric. This represents the total number of indicators.

[0066] The overall value of the vehicle's resistance is spatially rasterized to form a vehicle spatial resistance raster map covering the target area.

[0067] Specifically, the calculated combined resistance values ​​of each grid layer are spatially reconstructed to generate a continuous spatial resistance surface. Based on the natural breakpoints, quantiles, or preset thresholds of the resistance values, they can be divided into four resistance levels: high, medium, low, and low, and visualized as a "single map of spatial resistance for maintenance," which can be used to intuitively identify the distribution of maintenance difficulty and priority areas.

[0068] S300: Construct a spatiotemporal probability prediction model, wherein the spatiotemporal probability prediction model uses time variables and variables representing spatial adjacency influence as independent variables, the predicted probability of a raster layer transforming into a preset land use type in the target year as the dependent variable, and uses the construction map patch data of the historical years for parameter fitting.

[0069] Specifically, the dependent variable ( Whether a raster layer is converted to a preset land use type (such as construction land) in the target year can be represented by a binary variable (0 / 1) or directly modeled as a conversion probability (a continuous value between 0 and 1).

[0070] Independent variables include:

[0071] Time variables: such as year sequence, time trend items, or time variables related to the implementation of policies and plans.

[0072] Spatial adjacency variables: variables that reflect spatial autocorrelation and neighborhood influence, such as the proportion of developed land within a certain range around the raster layer (e.g., 3×3, 5×5 windows) in historical years, and the Euclidean distance to the nearest developed land.

[0073] Using a historical (e.g., the past 10 years) construction land raster dataset, the training and validation sets are divided chronologically. The spatial adjacency influence variables, temporal variables, and corresponding land use status (whether converted to construction land) of each raster layer in each year are input into the model for parameter estimation or model training.

[0074] The classification accuracy and predictive stability of the model were evaluated using methods such as confusion matrix, ROC curve, Kappa coefficient, and temporal cross-validation. Based on the results, variable selection, model parameters, and spatial weight structure were optimized to ensure the model has reliable spatiotemporal extrapolation capabilities. Using the fitted spatiotemporal probability prediction model, the probability of each raster layer transforming into construction land was calculated by inputting the time variable corresponding to the target year and the current spatial adjacency influence variable. This generated a land use transformation probability raster map covering the target area, providing a quantitative basis for subsequent development potential identification and spatial optimization.

[0075] In a preferred embodiment, the construction of the spatiotemporal probability prediction model, which uses time variables and variables representing spatial adjacency influences as independent variables, and the predicted probability of a raster layer transforming into a preset land use type in a target year as the dependent variable, and uses construction map patch data from the historical years for parameter fitting, specifically includes the following steps:

[0076] Based on the historical construction land cover raster dataset, the construction land cover attribute value of each raster layer in each year is extracted; the construction land cover attribute value is binarized into a land use status identifier according to a preset threshold. If the construction land proportion of the raster layer is greater than or equal to 50%, it is marked as construction land status; otherwise, it is marked as non-construction land status.

[0077] Specifically, based on the historical construction land cover raster dataset, the proportion of construction land (M value) of each raster layer in each year is binarized according to a preset threshold. The threshold is set to 50%, that is: if the M value of a raster layer in a specific year is ≥ 50%, it is marked as "construction land status" and the corresponding code is Y=1; if the M value is < 50%, it is marked as "non-construction land status" and the corresponding code is Y=0, thus forming the land use status identifier (dependent variable Y) for each year.

[0078] Based on the preset neighborhood analysis rules, the spatial adjacency influence variable corresponding to each raster layer in each year is calculated. The spatial adjacency influence variable is the average value of the construction land coverage attribute value of the raster in the surrounding neighborhood of the raster layer.

[0079] Specifically, for each raster layer, the spatial adjacency influence variable (S) is calculated for each year. Using a preset neighborhood analysis rule (such as a 3×3 or 5×5 moving window), the average construction land ratio (M value) of all rasters within the neighborhood of the unit is calculated to obtain the average construction land coverage of the unit in that year, which is used to characterize the spatial diffusion or agglomeration effect.

[0080] Using time variables and spatial adjacency influence variables as independent variables, and land use status identifiers as dependent variables, a spatiotemporal probability prediction model is constructed using logistic regression.

[0081] Specifically, time variables (such as year number T, e.g., 2015 is set as 1, 2016 as 2, ...) and spatial adjacency influence variables ( Using land use status identifier (Y) as the dependent variable and taking Y as the independent variable, a binary logistic regression model is established, in the following form: ;in, raster layer The predicted probability of land use for construction in the target year, where T is the time variable for the target year. raster layer Spatial adjacency influences variables.

[0082] These are the model parameters obtained by fitting construction map patch data from historical years.

[0083] The spatiotemporal probability prediction model is fitted with parameters using the historical land use cover raster dataset to obtain the model regression coefficients;

[0084] Specifically, using historical (e.g., 10 consecutive years) construction land cover raster datasets, the corresponding data for all raster layers in each year are ( The training samples were used to fit the coefficients of the logistic regression model using the maximum likelihood estimation method, and the results were obtained. .

[0085] The fitted spatiotemporal probability pre-model is used to predict the probability that each raster layer will be converted into construction land in the future target year.

[0086] Specifically, the fitted model is used to predict the target year (e.g., 2030). For each raster layer, the corresponding time variable is input. (Predicted year number) and its spatial adjacency influence variables in the current year (or the most recent year). Calculate the predicted probability that this unit will be converted into construction land in the target year: ; For the first The predicted probability of a raster layer being designated as construction land in the target year. For the target year sequence number raster layer Spatial adjacency affects variables. This applies to each raster layer.

[0087] and Substitute into the model and calculate the corresponding probability value. Based on this, a raster map of the probability of construction land expansion in the entire target area is generated to identify spatial units that may undergo future land use changes.

[0088] S400: Based on the fitted spatiotemporal probability prediction model, calculate the predicted probability of each raster layer in the target year.

[0089] Specifically, select the target year to be predicted (e.g., 2030). For each raster layer, obtain its spatial adjacency influence variables (e.g., the mean of the built-up land coverage rate within the neighborhood) for the current or most recent year, and set the time variable in the model to the corresponding target year's index. Based on the fitted logistic regression model: ; For the first The predicted probability of a raster layer being designated as construction land in the target year. For the target year sequence number This is the spatial adjacency influence variable for the raster layer. These are the fitted regression coefficients. For each raster layer... and Substitute into the model and calculate the corresponding probability value. The predicted probability values ​​of each raster layer are reorganized into spatial raster data to generate a construction land expansion probability raster map covering the entire target area. This layer continuously reflects the likelihood of different spatial units being converted into construction land in the future target year. Based on the distribution characteristics of the predicted probabilities, probability levels (such as high probability, medium probability, and low probability) can be further divided, and hotspot areas and spatial patterns of future construction land expansion can be identified.

[0090] In a preferred embodiment, calculating the predicted probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model specifically includes the following steps:

[0091] Determine the target forecast year and the corresponding time variables;

[0092] Specifically, a target year for predicting the conversion of construction land is set, such as 2030. The target year is then converted into the time-dependent variable values ​​required by the model. For example, taking the starting year 2015 as the base (T=1) for consecutive year numbers, then 2030 corresponds to... .

[0093] Based on the construction land cover raster dataset of the most recent historical year, calculate the spatial adjacency influence variable of each raster layer in the most recent year;

[0094] Specifically, based on the construction land cover raster dataset of the most recent historical year (e.g., the base year 2024), for each raster layer, using a preset neighborhood analysis window (e.g., a 3×3 window), the average proportion of construction land in each raster within its surrounding neighborhood is calculated to obtain the spatial adjacency influence variable of that raster layer in the most recent year. .

[0095] Substitute the time variable and the spatial adjacency influence variable corresponding to each raster layer into the fitted spatiotemporal probability prediction model;

[0096] Specifically, the year sequence number corresponding to each raster layer. Spatial adjacency influence variables

[0097] Substitute the values ​​into the fitted spatiotemporal probability prediction model. The model adopts the following logistic regression form: ; For the first Predicted probabilities for each raster layer

[0098] For the target year sequence number This is the spatial adjacency influence variable for the raster layer. These are the fitted regression coefficients.

[0099] The predicted probability value of each raster layer being converted into construction land in the target year is calculated based on the model formula;

[0100] Specifically, the probability value of each raster layer being converted into construction land in the target year is calculated one by one according to the model formula. , The value ranges from 0 to 1. The higher the value, the greater the likelihood that the raster layer will be converted into construction land in the target year.

[0101] The predicted probability values ​​are assigned back to the corresponding raster layer to form a predicted construction land probability raster map covering the target area.

[0102] Specifically, the predicted probability values ​​for each raster layer are calculated. The data are reassigned to the corresponding grid cells to form a spatially continuous raster map of predicted construction land probability. This result visually demonstrates the potential spatial distribution of future construction land expansion, can be used to identify high-probability transformation areas, and provides a basis for decision-making in land resource asset consolidation and spatial planning.

[0103] In a preferred embodiment, the spatiotemporal probability prediction model adopts a logistic regression model, in the form of: ;in, raster layer The predicted probability of whether the land is designated for construction in the target year. The time variable is the target year. Let i be the spatial adjacency influence variable for raster layer i. These are the model parameters obtained by fitting construction map patch data from historical years.

[0104] S500: Calculate the maintenance implementation potential value of each grid layer by combining the overall maintenance resistance value and the predicted probability.

[0105] In a preferred embodiment, the step of calculating the refurbishment implementation potential value by combining the overall refurbishment resistance value and the predicted probability of each of the grid layers specifically includes the following steps:

[0106] Spatially align the predicted construction land probability raster map with the prepared space resistance raster map;

[0107] Specifically, the predicted construction land probability raster map and the preparation space resistance raster map are unified to the same geographic coordinate system and spatial resolution to ensure that the two layers are fully aligned in terms of the number of grids, row and column numbers, and spatial extent.

[0108] For each raster layer, the preparation implementation potential value is obtained according to a preset potential calculation formula;

[0109] Specifically, for each raster layer, its original potential value is calculated using a preset potential calculation formula:

[0110] ;in, raster layer The original potential value for preparation and implementation; This represents the predicted probability of land use for construction in this unit.

[0111] This is the combined value of the unit's running resistance. To prevent the denominator from being zero, when... When this happens, it can be set to a very small positive value (e.g., Alternatively, the potential value of this type of unit can be defined separately.

[0112] The preparation implementation potential values ​​of all raster layers are normalized or standardized so that the preparation implementation potential values ​​fall within a comparable range.

[0113] Specifically, the original potential values ​​for all raster layers. Normalization or standardization should be performed to ensure the values ​​fall within a uniform numerical range (i.e., a comparable range) (e.g., 0-1) to enhance spatial comparability. One of the following methods can be used:

[0114] Range normalization: ;

[0115] Z-score standardization: ;in, The mean, The standard deviation is denoted as .

[0116] The processed preparation and implementation potential values ​​are assigned back to the corresponding raster layer to form a preparation and implementation potential raster map covering the target area.

[0117] Specifically, the standardized potential value The corresponding raster layer is assigned back to generate a raster map of the land consolidation implementation potential covering the entire target area. A higher potential value indicates a higher overall feasibility for implementation considering future construction possibilities and current consolidation constraints. Based on actual analysis needs, continuous potential values ​​are divided into several levels (e.g., high, medium, and low levels, or five levels) using the natural breakpoint method, quantile method, or equal interval method, and corresponding thematic maps are generated to provide intuitive spatial decision support for land consolidation prioritization and spatial optimization.

[0118] In a preferred embodiment, the preset potential calculation formula is: Where C is the potential value for preparation implementation, P is the predicted probability, and R is the comprehensive value of preparation resistance.

[0119] S600: Based on the preparedness implementation potential value, generate a suggested plan to guide the timing of land resource asset preparedness implementation.

[0120] In a preferred embodiment, generating a suggested plan to guide the timing of land resource asset consolidation based on the consolidation implementation potential value specifically includes the following steps:

[0121] Based on the magnitude of the refurbishment implementation potential value, the raster layer is divided into several refurbishment priority levels;

[0122] Specifically, based on the distribution of the potential values ​​for maintenance implementation, the raster layer is divided into three or more levels of maintenance priorities: high, medium, and low, using methods such as the natural breakpoint method, the equal interval method, or the quantile method. High priority corresponds to areas with higher potential values, representing areas where overall maintenance conditions are relatively mature.

[0123] Based on the aforementioned maintenance priority level, combined with the spatial proximity principle and planning constraints, the grid layer is spatially clustered and its boundaries are optimized to form several suggested maintenance areas.

[0124] Specifically, based on priority raster layers, adjacent raster layers with the same or similar priorities are merged using spatial clustering methods (such as connectivity-based regional grouping and cluster analysis). Simultaneously, existing spatial control boundaries such as the overall land use plan, ecological protection red lines, and permanent basic farmland are overlaid, and the clustering results are trimmed and optimized to form several spatially continuous proposed development zones that comply with planning constraints.

[0125] Based on the average or comprehensive maintenance implementation potential value of each of the proposed maintenance areas, determine the timing sequence of their maintenance implementation;

[0126] Specifically, for each recommended remediation zone k, the average remediation implementation potential (or area-weighted composite value) of all raster layers within it is calculated as the overall potential score for that zone. ;in, To suggest an overall potential score (area-weighted composite value) for the development zone k. For the area Inner The potential value for preparation implementation of each raster layer; For the area Inner The area of ​​each raster layer. Typically, with a uniform raster size, It is a constant; This represents the total area of ​​region k. This indicator, by using an area-weighted average of the potential values ​​of all raster layers within the region, more scientifically reflects the overall spatial development value of the region. According to... Sort the areas from highest to lowest. The higher the grade of the area, the better its overall preparation conditions, and the earlier it should be implemented.

[0127] Based on the aforementioned preparation and implementation sequence, a suggested plan for the preparation and implementation sequence is generated, which includes the phased and zoned preparation scope, recommended implementation time and priority, and output as a visual diagram or a structured report.

[0128] Specifically, by integrating the above spatial and temporal arrangements, a structured implementation plan for the preparation and preparation is formed, including:

[0129] The suggested spatial scope, area, and priority of each preparation zone;

[0130] Recommended implementation timelines (e.g., near-term, medium-term, long-term) based on overall potential scores;

[0131] Suggested implementation paths and spatial guidelines for preparation work at different stages;

[0132] Key constraints and policy recommendations based on potential composition (resistance and probability).

[0133] The plan will be output as a visual layout map, a timeline map, and a supporting structured report, providing a basis for decision-making regarding the spatial deployment and phased implementation of land resource asset preparation work.

[0134] Example 2

[0135] A land resource asset consolidation time-series simulation system includes: a data acquisition and processing module for acquiring historical construction land use map patch data of a target area for different years and performing spatial rasterization processing to obtain raster layers showing the status of land use map patches in multiple years; a consolidation resistance calculation module for calculating the current comprehensive value of land resource asset consolidation resistance for each raster layer based on a preset consolidation resistance evaluation system, wherein the consolidation resistance evaluation system includes three dimensions: ownership, function, and quality; and a model construction and fitting module for constructing a spatiotemporal probability prediction model, wherein the spatiotemporal probability prediction model uses time variables and characterization... The spatial adjacency influence variable is the independent variable, and the predicted probability of a raster layer transforming into a preset land use type in the target year is the dependent variable. Parameters are fitted using construction map patch data from the historical years. The prediction probability calculation module is used to calculate the predicted probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model. The land consolidation potential calculation module is used to calculate the land consolidation implementation potential value of each raster layer by combining the comprehensive value of land consolidation resistance and the predicted probability. The scheme generation module is used to generate an implementation scheme to guide land resource asset consolidation based on the land consolidation implementation potential value.

[0136] Example 3

[0137] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0138] Figure 2 A schematic block diagram of an example electronic device 100 that can be used to implement embodiments of the present invention is shown. Electronic device 100 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 100 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their links and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0139] like Figure 2 As shown, the electronic device 100 includes a computing unit 101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 102 or a computer program loaded from a storage unit 108 into a random access memory (RAM) 103. The RAM 103 may also store various programs and data required for the operation of the device 100. The computing unit 101, ROM 102, and RAM 103 are interconnected via a bus 104. An input / output (I / O) interface 105 is also linked to the bus 104.

[0140] Multiple components in electronic device 100 are linked to I / O interface 105, including: input unit 106, such as keyboard, mouse, etc.; output unit 107, such as various types of displays, speakers, etc.; storage unit 108, such as disk, optical disk, etc.; and communication unit 109, such as network card, modem, wireless transceiver, etc. Communication unit 109 allows electronic device 100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0141] The computing unit 101 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 101 performs the various methods and processes described above, such as a land resource asset consolidation time-series simulation method. For example, in some embodiments, a land resource asset consolidation time-series simulation method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 108. In some embodiments, part or all of the computer program can be loaded and / or installed on device 100 via ROM 102 and / or communication unit 109. When the computer program is loaded into RAM 103 and executed by the computing unit 101, one or more steps of the land resource asset consolidation time-series simulation method described above can be performed. Alternatively, in other embodiments, computing unit 101 may be configured in any other suitable manner (e.g., by means of firmware) to perform a land resource asset consolidation time-series simulation method.

[0142] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical links based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0146] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0147] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0149] For other structures of the land resource asset consolidation time-series simulation method and system described in this embodiment, please refer to the prior art.

[0150] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Therefore, any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for simulating the time series of land resource asset consolidation, characterized in that, include: The historical construction map patch data of the target area is obtained and spatially rasterized to obtain raster layers of map patch status for multiple years. Based on a preset land consolidation resistance evaluation system, the comprehensive value of the current land resource asset consolidation resistance for each of the grid layers is calculated. The land consolidation resistance evaluation system includes three dimensions: ownership, function, and quality. A spatiotemporal probability prediction model is constructed, wherein the spatiotemporal probability prediction model uses time variables and variables representing spatial adjacency influence as independent variables, and the predicted probability of a raster layer transforming into a preset land use type in a target year as the dependent variable, and uses construction map patch data from the historical years for parameter fitting. Based on the fitted spatiotemporal probability prediction model, the predicted probability of each raster layer in the target year is calculated; By combining the overall maintenance resistance value and the predicted probability of each grid layer, its maintenance implementation potential value is calculated; Based on the aforementioned potential value for land preparation and implementation, a suggested plan is generated to guide the timing of land resource asset preparation and implementation.

2. The land resource asset consolidation time-series simulation method according to claim 1, characterized in that, The process of acquiring historical construction map patch data for the target area and performing spatial rasterization to obtain raster layers showing the construction patch status for multiple years includes the following steps: Obtain construction map patch vector data of the target area in multiple consecutive historical years; The target area is divided into several regular grid units according to a preset size, and a grid fishing net covering the target area is constructed. The vector data of construction map patches from each historical year are spatially overlaid with the grid fishing net. For each grid cell, the proportion of the area of ​​the construction map patch in that grid cell to the total area of ​​that grid cell is calculated. The proportion of each raster cell in each historical year is used as its land use status attribute value, and raster layers are generated separately for each year. Each raster layer records the status value of all raster cells in that year, forming a time series construction land cover raster dataset.

3. The land resource asset consolidation time-series simulation method according to claim 1, characterized in that, The calculation of the comprehensive value of the current land resource asset preparation resistance based on the preset preparation resistance evaluation system specifically includes the following steps: Determine the dimensions included in the aforementioned preparation resistance evaluation system and the evaluation indicators under each dimension; Collect spatial data related to the evaluation indicators, and standardize or normalize the spatial data. The processed spatial data is converted to the same geospatial reference system as the raster layer, and the values ​​of each evaluation index in each raster layer are calculated. Based on predetermined weights, the evaluation index values ​​of different dimensions within each grid layer are weighted and calculated to obtain the comprehensive value of the preparation resistance of that grid layer. The overall value of the vehicle's resistance is spatially rasterized to form a vehicle spatial resistance raster map covering the target area.

4. The land resource asset consolidation time-series simulation method according to claim 1, characterized in that, The construction of the spatiotemporal probability prediction model, which uses time variables and variables representing spatial adjacency influences as independent variables, and the predicted probability of a raster layer transforming into a preset land use type in a target year as the dependent variable, and uses construction map patch data from the historical years for parameter fitting, specifically includes the following steps: Based on the historical land cover raster dataset, extract the land cover attribute values ​​for each raster layer in each year; The construction land coverage attribute value is binarized into a land use status identifier according to a preset threshold. If the construction land ratio of the raster layer is greater than or equal to 50%, it is marked as construction land status; otherwise, it is marked as non-construction land status. Based on the preset neighborhood analysis rules, the spatial adjacency influence variable corresponding to each raster layer in each year is calculated. The spatial adjacency influence variable is the average value of the construction land coverage attribute value of the raster in the surrounding neighborhood of the raster layer. Using time variables and spatial adjacency influence variables as independent variables, and land use status identifiers as dependent variables, a spatiotemporal probability prediction model is constructed using logistic regression. The spatiotemporal probability prediction model is fitted with parameters using the historical land use cover raster dataset to obtain the model regression coefficients; The fitted spatiotemporal probability pre-model is used to predict the probability that each raster layer will be converted into construction land in the future target year.

5. The land resource asset consolidation time-series simulation method according to claim 1, characterized in that, The calculation of the predicted probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model specifically includes the following steps: Determine the target forecast year and the corresponding time variables; Based on the construction land cover raster dataset of the most recent historical year, calculate the spatial adjacency influence variable of each raster layer in the most recent year; Substitute the time variable and the spatial adjacency influence variable corresponding to each raster layer into the fitted spatiotemporal probability prediction model; The predicted probability value of each raster layer being converted into construction land in the target year is calculated based on the model formula; The predicted probability values ​​are assigned back to the corresponding raster layer to form a predicted construction land probability raster map covering the target area.

6. The land resource asset consolidation time-series simulation method according to claim 5, characterized in that, The spatiotemporal probability prediction model adopts a logistic regression model, in the form of: ; in, raster layer The predicted probability of whether the land is designated for construction in the target year. The time variable is the target year. raster layer Spatial adjacency influences variables. These are the model parameters obtained by fitting construction map patch data from historical years.

7. The land resource asset consolidation time-series simulation method according to claim 1, characterized in that, The calculation of the maintenance implementation potential value by combining the overall maintenance resistance value and the predicted probability of each grid layer specifically includes the following steps: Spatially align the predicted construction land probability raster map with the prepared space resistance raster map; For each raster layer, the preparation implementation potential value is obtained according to a preset potential calculation formula; The preparation implementation potential values ​​of all raster layers are normalized or standardized so that the preparation implementation potential values ​​fall within a comparable range. The processed preparation and implementation potential values ​​are assigned back to the corresponding raster layer to form a preparation and implementation potential raster map covering the target area.

8. The land resource asset consolidation time-series simulation method according to claim 7, characterized in that, The formula for calculating the potential is: ;in, raster layer The original potential value for preparation and implementation; raster layer The predicted probability of land use for construction; This represents the overall resistance value for the preparation of raster layer i.

9. The land resource asset consolidation time-series simulation method according to claim 1, characterized in that, The step of generating a suggested plan to guide the timing of land resource asset consolidation based on the consolidation potential value specifically includes the following steps: Based on the magnitude of the refurbishment implementation potential value, the raster layer is divided into several refurbishment priority levels; Based on the aforementioned maintenance priority level, combined with the spatial proximity principle and planning constraints, the grid layer is spatially clustered and its boundaries are optimized to form several suggested maintenance areas. Based on the average or comprehensive maintenance implementation potential value of the suggested maintenance area, determine the maintenance implementation sequence; Based on the aforementioned preparation and implementation sequence, a suggested plan for the preparation and implementation sequence is generated, which includes the phased and zoned preparation scope, recommended implementation time and priority, and output as a visual diagram or a structured report.

10. A land resource asset consolidation time-series simulation system, characterized in that, include: The data acquisition and processing module is used to acquire historical construction map patch data of the target area and perform spatial rasterization processing to obtain raster layers of map patch status for multiple years. The land preparation resistance calculation module is used to calculate the comprehensive value of the current land resource asset preparation resistance for each grid layer using a preset land preparation resistance evaluation system. The land preparation resistance evaluation system includes three dimensions: ownership, function, and quality. The model building and fitting module is used to build a spatiotemporal probability prediction model. The spatiotemporal probability prediction model uses time variables and variables representing spatial adjacency influence as independent variables, the predicted probability of a raster layer changing to a preset land use type in the target year as the dependent variable, and uses the construction map patch data of the historical years for parameter fitting. The prediction probability calculation module is used to calculate the prediction probability of each raster layer in the target year based on the fitted spatiotemporal probability prediction model. The maintenance potential calculation module is used to calculate the maintenance implementation potential value of each grid layer by combining the overall maintenance resistance value and the predicted probability. The scheme generation module is used to generate a suggested scheme to guide the timing of land resource asset preparation and implementation based on the preparedness implementation potential value.

Images