A risk assessment method and system for a high-risk area of a batch but not supplied land

Abstract

The application discloses a risk assessment method and system for a high-risk area of land approval but non-supply, and belongs to the field of land resource management.The method is as follows: determining the plot classification results of a target area at each historical time point according to historical geospatial data of the target area; obtaining the supply-demand change trend of each plot type according to the plot classification results to calculate the demand intensity of each plot type at a current time point; taking the plots to be approved or approved but non-supplied in the target area at the current time point as first plots, and predicting the plot type evolution trend of the first plots according to the surrounding plot information of the first plots and the policy text data of the target area at each historical time point; and evaluating the risk of approval but non-supply of the target area according to the plot type evolution trend of each first plot and the demand intensity of each plot type at the current time point. The application can improve the accuracy of identifying the high-risk area of approval but non-supply.

Description

Technical Field

[0001] This application relates to the field of land resource management, and in particular to a risk assessment method and system for areas with a high incidence of approved but unsupplied land. Background Technology

[0002] As a core support area for urban development and economic growth, land resource management involves a crucial step in the process of rationally allocating approved land resources and curbing the increase of inefficient land use, such as approved but not supplied land and idle land.

[0003] Existing land management methods, on the one hand, rely excessively on a "one-size-fits-all" approach of administrative directives or analyze land using only lagging statistical methods such as annual land change surveys, making it difficult to capture the real-time impact of dynamic variables such as fluctuations in land market supply and demand and adjustments in industrial policies. On the other hand, they lack an effective tracking mechanism for the two-way feedback between the implementation of land supply plans and changes in market demand, resulting in the assessment of supply and demand matching remaining at the "post-event verification" stage. This fails to identify early signs of resource allocation imbalances, ultimately exacerbating the cumulative outbreak of risks associated with approved but unsupplied land. As the above analysis shows, existing methods often rely too heavily on single policy controls or post-event statistical analysis, lacking real-time perception and forward-looking judgment of regional dynamic changes, leading to significant errors in the final judgment of areas with approved but unsupplied land.

[0004] Therefore, how to build a dynamic risk assessment mechanism based on the formulation of land supply plans and changes in actual demand, and accurately identify areas where there may be a high incidence of approved but unsupplied land in the future, has become a key issue that urgently needs to be addressed. Summary of the Invention

[0005] This application provides a risk assessment method and system for areas with a high incidence of approved but unsupplied land, which can solve the problem of low accuracy in identifying such areas in the prior art.

[0006] One embodiment of this application provides a risk assessment method for areas with a high incidence of approved but unsupplied land, including:

[0007] Collect geospatial data of the target area at several historical time points, and determine the land parcel classification results of the target area at the corresponding historical time points based on the geospatial data;

[0008] Based on the land parcel classification results at each of the historical time points, the supply and demand change trends of each land parcel type are obtained, and the demand intensity of each land parcel type at the current time point is calculated based on the supply and demand change trends.

[0009] The land parcels within the target area at the current time point that are pending approval or approved but not yet supplied are taken as the first land parcels. Based on the geospatial data of each historical time point and the land parcel classification results, spatial analysis is performed on each first land parcel to obtain information on the surrounding land parcels of each first land parcel at each historical time point.

[0010] Collect policy text data of the target area at each of the historical time points, and predict the land type evolution trend of the first land parcel through time series analysis based on the policy text data of each of the historical time points and the surrounding land parcel information;

[0011] The risk of approved but not supplied land in the target area is assessed based on the land type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time.

[0012] Compared with existing technologies, the above embodiments have the following beneficial effects: By collecting geospatial data through remote sensing technology and analyzing historical land parcel classification data and supply and demand trends based on geospatial data, the demand intensity of different types of land parcels can be inferred; furthermore, through time series modeling analysis, combined with the evolution trend of surrounding land parcels in historical time and policy text data at corresponding time points, the land parcel type evolution trend of the first land parcel can be inferred from the change patterns of neighboring land parcels, thereby more accurately determining the type of land supply that should be converted in the future; finally, by combining the demand forecasts of each type of land parcel and the future land supply type of each first land parcel, the supply and demand balance in the target area can be assessed. When the supply and demand in the target area is unbalanced, it indicates that there is a higher risk of approved but not supplied land in the target area, thereby improving the spatial correlation and dynamic prediction capability of the risk assessment of approved but not supplied land.

[0013] Further, determining the land parcel classification result of the target area at the corresponding historical time point based on the geospatial data includes:

[0014] The boundaries of each land parcel are extracted from the geospatial data using an edge detection algorithm, and the boundaries are corrected based on the geographic information data of each land parcel.

[0015] Based on the boundary, remote sensing images of the corresponding land parcels are cropped from the geospatial data, and several preset remote sensing indices are calculated based on the band combinations in each remote sensing image.

[0016] The remote sensing indices are input into the pre-trained support vectors to obtain the land parcel type of the corresponding land parcel.

[0017] Compared with existing technologies, the above embodiments have the following beneficial effects: First, the geospatial data is subjected to boundary extraction and correction to ensure the accuracy of the spatial location and outline information of each plot, avoiding classification errors caused by blurred boundaries. Subsequently, multiple preset remote sensing indices (such as NDVI, NDBI, etc.) are extracted from the remote sensing images, and an index system reflecting the land use characteristics is constructed by combining bands. This system is then input into a trained support vector machine model for classification and recognition, thereby achieving rapid and large-scale automatic recognition based on image data. This effectively improves the efficiency of spatiotemporal data processing and the accuracy of plot classification, providing a solid foundation for subsequent analysis.

[0018] Furthermore, based on the land parcel classification results at each of the historical time points, the supply and demand trends for each land parcel type are obtained, and the demand intensity for each land parcel type at the current time point is calculated based on the supply and demand trends.

[0019] Based on the boundaries and types of each plot at each historical time point, the total area of ​​different plot types at each historical time point is calculated to obtain time series data of plot type area.

[0020] Based on the time series data of the land parcel area for each land parcel type, calculate the land parcel area growth rate corresponding to each land parcel type;

[0021] Based on the land area and the land area growth rate of each land parcel type at the current time point, the growth area corresponding to each land parcel type is calculated, and the growth area is used as the demand intensity.

[0022] Compared with existing technologies, the above embodiments have the following beneficial effects: by accurately recording the area changes of different land parcel types in historical periods, the supply and demand intensity of different types of land parcels can be inferred. For land parcel types with higher demand, the corresponding land parcel area will grow rapidly. Therefore, based on the land parcel area growth rate and the current area, the future growth space of different types of land parcels can be estimated, resulting in a more timely and forward-looking demand intensity. This can more objectively reflect the actual demand intensity of different land parcel types in urban expansion or functional transformation, thereby providing a more scientific data basis for screening high-risk areas.

[0023] Further, the step of performing spatial analysis on each first land parcel based on the geospatial data of each historical time point and the land parcel classification results to obtain information on surrounding land parcels of each first land parcel at each historical time point includes:

[0024] Based on the geospatial data, identify several second plots adjacent to the first plot at each of the historical time points;

[0025] Based on the land parcel classification results, determine the land parcel type of each second land parcel at each of the historical time points;

[0026] The land parcel type and land parcel area of ​​the second land parcel are used as the surrounding land parcel information of the first land parcel at the corresponding historical time point.

[0027] Compared with existing technologies, the above embodiments have the following beneficial effects: By extracting and analyzing the spatial characteristics of surrounding plots of the first plot at different times, the spatial dimension of risk assessment and the ability to perceive neighborhood evolution are enhanced. This method not only identifies the static attributes of the first plot itself, but also mines the temporal spatial data of historical plot evolution to reveal the role evolution trend of the first plot in its spatial environment, thereby capturing the most suitable plot type for the first plot to form in the future. Finally, by integrating neighborhood information, it achieves the tracing of regional risk causes and the forward-looking prediction of future trends.

[0028] Furthermore, the step of predicting the land parcel type evolution trend of the first land parcel through time-series analysis based on the policy text data at each of the historical time points and the surrounding land parcel information includes:

[0029] The policy text data and surrounding land parcel information at each of the historical time points are input into a pre-trained time series classification model to obtain the probability distribution of the first land parcel being transformed into each of the land parcel types at the current time point; the probability distribution includes: the probability value of the first land parcel being transformed into each of the land parcel types.

[0030] Compared to existing technologies, the above embodiments have the following advantages: By introducing a time series classification model to incorporate policy text data and surrounding land parcel evolution data into the model, a probabilistic prediction of the land parcel type evolution trend of the first parcel is achieved. This not only preserves the causal logic of the impact of policy dynamics on land use but also integrates the spatial evolution patterns of surrounding land parcel development, giving the model strong real-world driving force and generalization ability. Furthermore, by outputting the probability distribution of the first parcel's future transformation into various types of land parcels, the probability of its transformation into the actual land supply type is calculated, thereby assessing the possibility of approval without supply, improving the accuracy and interpretability of the risk assessment process.

[0031] Furthermore, assessing the risk of approved but not yet supplied land in the target area based on the land parcel type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time includes:

[0032] Based on the probability distribution, determine the type of the first land parcel with the highest probability value corresponding to each of the first land parcels;

[0033] Based on the planned use of each first plot and the corresponding first plot type, second plots that can be initially supplied are selected from all the first plots;

[0034] Based on the corresponding first land parcel type for each second land parcel, determine the supply intensity of each land parcel type at the current time point;

[0035] Assess the risk of approved but not supplied land in the target area based on the supply intensity and demand intensity of each land parcel type at the current point in time.

[0036] Compared with existing technologies, the above embodiments have the following beneficial effects: by predicting the future demand of different types of land parcels, and further combining the current first land parcels into the actual land supply type at the current time, supply and demand can be matched from both the supply and demand sides, and the risk of approval but not supply in the current target area can be accurately assessed.

[0037] Another embodiment of this application provides a risk assessment system for areas with a high incidence of approved but unsupplied land, characterized in that it includes: a land parcel classification module, a supply and demand calculation module, a spatial analysis module, a first land parcel evolution prediction module, and an approved but unsupplied land risk identification module;

[0038] The land parcel classification module is used to collect geospatial data of the target area at several historical time points, and determine the land parcel classification result of the target area at the corresponding historical time points based on the geospatial data.

[0039] The supply and demand calculation module is used to obtain the supply and demand change trend of each type of land parcel based on the land parcel classification results at each of the historical time points, and to calculate the demand intensity of each type of land parcel at the current time point based on the supply and demand change trend.

[0040] The spatial analysis module is used to take the land parcels that are pending approval or approved but not supplied in the target area at the current time point as the first land parcels, and perform spatial analysis on each of the first land parcels based on the geospatial data of each of the historical time points and the land parcel classification results to obtain the surrounding land parcel information of each of the first land parcels at each of the historical time points.

[0041] The first land parcel evolution prediction module is used to collect policy text data at each of the historical time points within the target area, and predict the land parcel type evolution trend of the first land parcel through time series analysis based on the policy text data at each of the historical time points and the surrounding land parcel information.

[0042] The approved but not supplied risk identification module is used to assess the approved but not supplied risk of the target area based on the land type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time.

[0043] Further, the land parcel classification module includes: an edge detection unit, a remote sensing index calculation unit, and a classification unit; the land parcel classification module is used to determine the land parcel classification result of the target area at the corresponding historical time point based on the geospatial data, including:

[0044] The edge detection unit is used to extract the boundaries of each land parcel from the geospatial data using an edge detection algorithm, and to correct the corresponding boundaries based on the geographic information data of each land parcel.

[0045] The remote sensing index calculation unit is used to cut the remote sensing image of the corresponding plot from the geospatial data according to the boundary, and to calculate a number of preset remote sensing indices according to the band combination in each remote sensing image.

[0046] The classification unit is used to input the several remote sensing indices into the pre-trained support vector to obtain the land parcel type of the corresponding land parcel.

[0047] Furthermore, the supply and demand calculation module includes: a time-series data statistics unit, a time-series data analysis unit, and a supply and demand calculation unit; the supply and demand calculation module is used to obtain the supply and demand change trend of each land parcel type based on the land parcel classification results at each of the historical time points, and to calculate the demand intensity of each land parcel type at the current time point based on the supply and demand change trend.

[0048] The time-series data statistics unit is used to calculate the total area of ​​different land parcel types at each historical time point based on the boundaries and land parcel types of each land parcel at each historical time point, and obtain time-series data of land parcel type area.

[0049] The time-series data analysis unit is used to calculate the land area growth rate corresponding to each land parcel type based on the time-series data of the land parcel area.

[0050] The supply and demand calculation unit is used to calculate the growth area corresponding to each of the land parcel types based on the land parcel area and the land parcel area growth rate at the current time point, and to use the growth area as the demand intensity.

[0051] Further, the spatial analysis module includes: a second land parcel acquisition unit, a second land parcel type confirmation unit, and a surrounding land parcel information acquisition unit; the spatial analysis module is used to perform spatial analysis on each first land parcel based on the geospatial data of each of the historical time points and the land parcel classification results, to obtain surrounding land parcel information of each first land parcel at each of the historical time points, including:

[0052] The second land parcel acquisition unit is used to determine, based on the geospatial data, a number of second land parcels adjacent to the first land parcel at each of the historical time points;

[0053] The second land parcel type confirmation unit is used to determine the land parcel type of each second land parcel at each of the historical time points based on the land parcel classification results;

[0054] The surrounding land information acquisition unit is used to use the land type and land area of ​​the second land plot as the surrounding land information of the first land plot at the corresponding historical time point. Attached Figure Description

[0055] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1 This is a flowchart illustrating a risk assessment method for areas with a high incidence of approved but unsupplied land, as provided in some embodiments of this application.

[0057] Figure 2 This is a schematic diagram of the structure of a risk assessment system for areas with a high incidence of approved but unsupplied land, provided in some embodiments of this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0060] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0061] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0062] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0063] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0064] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0065] Existing land management methods, on the one hand, rely excessively on a "one-size-fits-all" approach of administrative directives or analyze land using only lagging statistical methods such as annual land change surveys, making it difficult to capture the real-time impact of dynamic variables such as fluctuations in land market supply and demand and adjustments in industrial policies. On the other hand, they lack an effective tracking mechanism for the two-way feedback between the implementation of land supply plans and changes in market demand, resulting in the assessment of supply and demand matching remaining at the "post-event verification" stage. This fails to identify early signs of resource allocation imbalances, ultimately exacerbating the cumulative outbreak of the risk of land being approved but not supplied. As the above analysis shows, existing methods often rely too heavily on single policy controls or post-event statistical analysis, lacking real-time perception and forward-looking judgment of regional dynamic changes, leading to significant errors in the final identification of areas with approved but unsupplied land.

[0066] Please refer to Figure 1 To address the low accuracy in identifying areas with a high incidence of approved but unsupplied land in existing technologies, this application provides a risk assessment method for areas with a high incidence of approved but unsupplied land, comprising steps S101 to S105, specifically:

[0067] S101: Collect geospatial data of the target area at several historical time points, and determine the land parcel classification results of the target area at the corresponding historical time points based on the geospatial data.

[0068] Furthermore, in some embodiments of this application, the geospatial data includes: remote sensing images of the target area, wherein the remote sensing images include remote sensing images taken by drones and satellite images, and the remote sensing images are multispectral remote sensing images.

[0069] Preferably, in some embodiments of this application, before determining the land parcel classification result of the target area corresponding to the historical time point based on the geospatial data, the method further includes:

[0070] Geometric correction is performed on satellite imagery and UAV remote sensing images to calibrate coordinate deviations in the images and unify them into a preset coordinate system, thereby obtaining corrected geospatial data.

[0071] For the corrected geospatial data, contrast enhancement technology is applied to optimize the texture visibility in the geospatial data. Brightness and contrast parameters are adjusted using preset thresholds to determine the enhanced geospatial data.

[0072] Furthermore, in some embodiments of this application, determining the land parcel classification result of the target area at the corresponding historical time point based on the geospatial data includes:

[0073] The boundaries of each land parcel are extracted from the geospatial data using an edge detection algorithm, and the boundaries are corrected based on the geographic information data of each land parcel.

[0074] Based on the boundary, remote sensing images of the corresponding land parcels are cropped from the geospatial data, and several preset remote sensing indices are calculated based on the band combinations in each remote sensing image.

[0075] The remote sensing indices are input into the pre-trained support vectors to obtain the land parcel type of the corresponding land parcel.

[0076] Preferably, in some embodiments of this application, the step of extracting the boundaries of various land parcels from the geospatial data using an edge detection algorithm, and correcting the corresponding boundaries based on the geographic information data of each land parcel, includes:

[0077] By using the Canny edge detection algorithm to process images in geospatial data, edge lines with obvious color changes in the images are extracted.

[0078] The broken edges are connected by morphological closing operations, and false edges are filtered out to obtain the first boundary of each plot.

[0079] Extract road grids (i.e., geographic information data) from existing maps, and determine the second boundary of each plot based on the plots divided by the road grids;

[0080] The first boundary and the second boundary are superimposed and compared using a spatial alignment algorithm (such as affine transformation). For the first boundary whose deviation exceeds a preset value, the position is corrected based on the second boundary.

[0081] The above-mentioned method for obtaining land parcel boundaries can improve the accuracy and spatial matching of land parcel boundary extraction, providing a reliable data foundation for subsequent land use analysis and planning decisions.

[0082] Preferably, in some embodiments of this application, the step of cropping the remote sensing image of the corresponding plot from the geospatial data according to the boundary, and calculating a number of preset remote sensing indices based on the band combinations in each remote sensing image, includes: based on the first boundary of each plot extracted and corrected in the previous step, using an image cropping function to crop the image region of each plot from the multispectral remote sensing image to obtain the remote sensing image corresponding to each plot; then, for the remote sensing image of each plot, selecting red light, near-infrared and other bands, calculating remote sensing indices such as the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Built-up Index (NDBI), and the Soil Adjusted Vegetation Index (SAVI), as input data for subsequent plot feature analysis. By extracting key remote sensing features reflecting the plot's vegetation cover, building intensity, and surface conditions, it is helpful to achieve precise analysis of plot use identification and change monitoring.

[0083] Preferably, in some embodiments of this application, the step of inputting the plurality of remote sensing indices into a pre-trained support vector to obtain the land parcel type includes: wherein the support vector machine is trained and obtained by: collecting a batch of remote sensing image data with known land parcel types, calculating the NDVI, NDBI, SAVI, and other remote sensing indices for each land parcel as training features, and using the corresponding land parcel type as a label; using the scikit-learn library in Python to call the SVC function to train these features and labels, and finally obtaining a support vector machine model that can be used for land parcel type prediction; inputting the NDVI, NDBI, and SAVI, and other remote sensing indices calculated for each land parcel as feature vectors into a pre-trained support vector machine (SVM) classification model using existing land parcel type labeled data; the model outputs that the land parcel belongs to a preset land parcel type label such as "residential land," "industrial land," or "cultivated land," thereby achieving automatic land parcel classification. By constructing a support vector machine classification model, an effective mapping between remote sensing indices and land parcel types is achieved, providing a high-accuracy classification tool for subsequent automatic land parcel identification.

[0084] As can be seen from the above embodiments, this application first extracts and corrects the boundaries of geospatial data to ensure the accuracy of the spatial location and outline information of each plot, avoiding classification errors caused by blurred boundaries. Subsequently, multiple preset remote sensing indices (such as NDVI, NDBI, etc.) are extracted from the remote sensing images, and an index system reflecting the land use characteristics is constructed by combining bands. This system is then input into a trained support vector machine model for classification and recognition, thereby achieving rapid and large-scale automatic recognition based on image data. This effectively improves the efficiency of spatiotemporal data processing and the accuracy of plot classification, providing a solid foundation for subsequent analysis.

[0085] S102: Based on the land parcel classification results at each of the historical time points, obtain the supply and demand change trend of each land parcel type, and calculate the demand intensity of each land parcel type at the current time point based on the supply and demand change trend.

[0086] Furthermore, in some embodiments of this application, the step of obtaining the supply and demand trend of each land parcel type based on the land parcel classification results at each of the historical time points, and calculating the demand intensity of each land parcel type at the current time point based on the supply and demand trend:

[0087] Based on the boundaries and types of each plot at each historical time point, the total area of ​​different plot types at each historical time point is calculated to obtain time series data of plot type area.

[0088] Based on the time series data of the land parcel area for each land parcel type, calculate the land parcel area growth rate corresponding to each land parcel type;

[0089] Based on the land area and the land area growth rate of each land parcel type at the current time point, the growth area corresponding to each land parcel type is calculated, and the growth area is used as the demand intensity.

[0090] Preferably, in some embodiments of this application, the step of calculating the total area of ​​different land parcel types at each historical time point based on the boundaries and land parcel types of each land parcel at each historical time point, and obtaining time-series data of land parcel type area, includes: the land parcel types include: cultivated land, residential land, industrial land, commercial land, public service facility land, and vacant land, etc.; determining the land parcel area of ​​each land parcel based on the first boundary of each land parcel at each historical time point, and accumulating the land parcel areas corresponding to the same land parcel type at the same time point to obtain the total land parcel area of ​​each land parcel type at different time points, and sorting them according to the chronological order to generate time-series data of land parcel type area.

[0091] Preferably, in some embodiments of this application, the step of calculating the land area growth rate corresponding to each land parcel type based on the land parcel type area time series data includes: using the total land parcel area of ​​each land parcel type at each historical time point in the land parcel type area time series data, using a linear regression method to fit the area change trend over time, and the regression slope is used as the average area growth rate of the land parcel type, thereby reflecting the area change trend of each land parcel type more smoothly and accurately.

[0092] Preferably, in some embodiments of this application, the step of calculating the growth area corresponding to each of the land parcel types based on the land parcel area and the land parcel area growth rate at the current time point, and using the growth area as the demand intensity, includes: obtaining the total land parcel area of ​​each land parcel type at the last historical time point, and multiplying the total land parcel area by the corresponding land parcel area growth rate to obtain the total land parcel area corresponding to each land parcel type at the current time point; using the total land parcel area corresponding to each land parcel type at the current time point as the demand intensity corresponding to each land parcel type to assess the future demand scale of land supply.

[0093] As can be seen from the above embodiments, this application infers the supply and demand intensity of different types of land parcels by accurately recording the area changes of different land parcel types in historical periods. For land parcel types with higher demand, the corresponding land parcel area will grow rapidly. Therefore, based on the land parcel area growth rate and the current area, the future growth space of different types of land parcels can be estimated, resulting in a more timely and forward-looking demand intensity. This can more objectively reflect the actual demand intensity of different land parcel types in urban expansion or functional transformation, thereby providing a more scientific data basis for screening high-risk areas.

[0094] S103: Take the land parcels in the target area at the current time point that are pending approval or approved but not supplied as the first land parcels, and perform spatial analysis on each of the first land parcels based on the geospatial data of each of the historical time points and the land parcel classification results to obtain the surrounding land parcel information of each of the first land parcels at each of the historical time points.

[0095] Further, the step of performing spatial analysis on each first land parcel based on the geospatial data of each historical time point and the land parcel classification results to obtain information on surrounding land parcels of each first land parcel at each historical time point includes:

[0096] Based on the geospatial data, identify several second plots adjacent to the first plot at each of the historical time points;

[0097] Based on the land parcel classification results, determine the land parcel type of each second land parcel at each of the historical time points;

[0098] The land parcel type and land parcel area of ​​the second land parcel are used as the surrounding land parcel information of the first land parcel at the corresponding historical time point.

[0099] Preferably, in some embodiments of this application, the step of performing spatial analysis on each first plot based on the geospatial data of each historical time point and the plot classification results to obtain the surrounding plot information of each first plot at each historical time point specifically involves: designating each plot adjacent to the first plot as a second plot, determining several second plots surrounding each first plot at each historical time point, determining the plot area of ​​each second plot based on the boundaries of each second plot, determining the plot type of each second plot from the plot classification results, and combining the plot type and plot area of ​​each second plot corresponding to each first plot into surrounding plot information.

[0100] As can be seen from the above embodiments, this application enhances the spatial dimension of risk assessment and the ability to perceive neighborhood evolution by extracting and analyzing the spatial characteristics of surrounding plots of the first plot at different times. This method not only identifies the static attributes of the first plot itself, but also mines the temporal spatial data of historical plot evolution to reveal the role evolution trend of the first plot in its spatial environment, thereby capturing the most suitable plot type for the first plot to form in the future. Finally, by integrating neighborhood information, it achieves the tracing of regional risk causes and the forward-looking prediction of future trends.

[0101] S104: Collect policy text data at each of the historical time points within the target area; based on the policy text data at each of the historical time points and the surrounding land parcel information, predict the land parcel type evolution trend of the first land parcel through time series analysis.

[0102] Furthermore, in some embodiments of this application, the step of predicting the land parcel type evolution trend of the first land parcel through time-series analysis based on the policy text data at each of the historical time points and the surrounding land parcel information includes:

[0103] The policy text data and surrounding land parcel information at each of the historical time points are input into a pre-trained time series classification model to obtain the probability distribution of the first land parcel being transformed into each of the land parcel types at the current time point; the probability distribution includes: the probability value of the first land parcel being transformed into each of the land parcel types.

[0104] Preferably, in some embodiments of this application, the step of inputting the policy text data and surrounding land parcel information at each of the historical time points into a pre-trained time series classification model to obtain the probability distribution of the first land parcel being converted into each of the land parcel types at the current time point includes: wherein the time series classification model adopts a long short-term memory network model, which includes an input layer, two layers of long short-term memory network units, a dropout layer, a fully connected layer, and a softmax output layer; performing one-hot encoding on the land parcel types in the surrounding land parcel information, normalizing the land parcel area, concatenating the corresponding features of the two to obtain a multi-dimensional feature vector, while ensuring that the feature vector is concatenated in the time order of the data, thereby obtaining the time series input; inputting the time series through the input layer, and sequentially passing through two layers of long short-term memory network units, a dropout layer, a fully connected layer, and a softmax output layer to obtain the first probability of the first land parcel being converted into each land parcel type.

[0105] As can be seen from the above embodiments, this application incorporates policy text data and surrounding land parcel evolution data into a time series classification model, enabling probabilistic prediction of the land parcel type evolution trend of the first parcel. This not only preserves the causal logic of policy dynamics' impact on land use but also integrates the spatial evolution patterns of surrounding land parcels, giving the model strong real-world driving force and generalization ability. Furthermore, by outputting the probability distribution of the first parcel's future transformation into various land parcel types, the probability of its transformation into the actual land supply type is calculated, thereby assessing the likelihood of approval without supply, improving the accuracy and interpretability of the risk assessment process.

[0106] S105: Assess the risk of approved but not supplied land in the target area based on the land type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time.

[0107] Furthermore, in some embodiments of this application, assessing the risk of approved but not supplied land in the target area based on the land parcel type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time includes:

[0108] Based on the probability distribution, determine the type of the first land parcel with the highest probability value corresponding to each of the first land parcels;

[0109] Based on the planned use of each first plot and the corresponding first plot type, second plots that can be initially supplied are selected from all the first plots;

[0110] Based on the corresponding first land parcel type for each second land parcel, determine the supply intensity of each land parcel type at the current time point;

[0111] Assess the risk of approved but not supplied land in the target area based on the supply intensity and demand intensity of each land parcel type at the current point in time.

[0112] Preferably, in some embodiments of this application, determining the supply intensity of each land parcel type at the current time point according to the corresponding first land parcel type of each first land parcel includes: determining the supply area corresponding to different types of land parcels according to the corresponding first land parcel type of each first land parcel. For example, if the first land parcel type of first land parcel A is residential land and the land parcel area of ​​first land parcel A is 20, and the first land parcel type of first land parcel B is also residential land and the land parcel area of ​​first land parcel B is 12, then the supply area of ​​the residential land parcel type is the total area of ​​all first land parcels with the first land parcel type of residential land.

[0113] Preferably, in some embodiments of this application, assessing the risk of unsupplied land in the target area based on the supply intensity and demand intensity of each land parcel type at the current time includes: assuming the current demand intensity for each land parcel type is (residential land: 42, commercial land: 11, industrial land: 21, public service facility land: 4), and the supply intensity for each land parcel type is (residential land: 30, commercial land: 9, industrial land: 12, public service facility land: 3). It can be seen that in the above example, each item in the supply intensity is less than the corresponding item in the demand intensity, indicating that there is no risk of unsupplied land in the target area. If multiple items in the supply intensity are greater than their corresponding items in the demand intensity, then there is a risk of unsupplied land in the target area.

[0114] As can be seen from the above embodiments, this application predicts the future demand for different types of land parcels and further combines the current first land parcels with the actual land supply type at the current time point, thereby matching supply and demand from both the supply and demand sides and accurately assessing the risk of approval but not supply in the current target area.

[0115] In summary, the risk assessment method for areas with a high incidence of approved but unsupplied land provided in this application has the following advantages compared to existing technologies: It collects geospatial data using remote sensing technology and analyzes historical land parcel classification data and supply-demand trends based on the geospatial data to infer the current demand intensity for different types of land parcels; further, through time-series modeling analysis, combined with the historical evolution trends of surrounding land parcels and corresponding policy text data, it infers the land parcel type evolution trend of the first land parcel from the change patterns of neighboring land parcels, thereby more accurately determining the type of land supply that should be converted in the future; finally, by combining the demand forecasts for each type of land parcel and the future land supply type of each first land parcel, it assesses the supply-demand balance within the target area. When the supply and demand are unbalanced within the target area, it indicates a higher risk of approved but unsupplied land, thus improving the spatial correlation and dynamic prediction capabilities of the risk assessment of approved but unsupplied land.

[0116] like Figure 2 As shown, based on the above-mentioned method embodiments, an embodiment of this application provides a risk assessment system for areas with a high incidence of approved but unsupplied land, including: a land parcel classification module 201, a supply and demand calculation module 202, a spatial analysis module 203, a first land parcel evolution prediction module 204, and an approved but unsupplied land risk identification module 205.

[0117] Further, in some embodiments of this application, the land parcel classification module 201 is used to collect geospatial data of the target area at several historical time points, and determine the land parcel classification result of the target area at the corresponding historical time points based on the geospatial data; the supply and demand calculation module 202 is used to obtain the supply and demand change trend of each land parcel type based on the land parcel classification result at each historical time point, and calculate the demand intensity of each land parcel type at the current time point based on the supply and demand change trend; the spatial analysis module 203 is used to take the land parcels pending approval or approved but not yet supplied in the target area at the current time point as the first land parcel, and calculate the demand intensity of each land parcel type at the current time point based on the geospatial data at each historical time point. Based on the land parcel classification results, spatial analysis is performed on each first land parcel to obtain information on surrounding land parcels at each historical time point; the first land parcel evolution prediction module 204 is used to collect policy text data of the target area at each historical time point, and predict the land parcel type evolution trend of the first land parcel through time series analysis based on the policy text data of each historical time point and the surrounding land parcel information; the approved but not supplied risk identification module 205 is used to assess the approved but not supplied risk of the target area based on the land parcel type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time point.

[0118] Further, in some embodiments of this application, the land parcel classification module 201 includes: an edge detection unit, a remote sensing index calculation unit, and a classification unit; the land parcel classification module 201 is used to determine the land parcel classification result of the target area at the corresponding historical time point based on the geospatial data, including: the edge detection unit is used to extract the boundaries of each land parcel from the geospatial data through an edge detection algorithm, and correct the corresponding boundaries based on the geographic information data of each land parcel; the remote sensing index calculation unit is used to crop the remote sensing image of the corresponding land parcel from the geospatial data according to the boundary, and calculate a number of preset remote sensing indices based on the band combination in each remote sensing image; the classification unit is used to input the number of remote sensing indices into the pre-trained support vector to obtain the land parcel type of the corresponding land parcel.

[0119] Further, in some embodiments of this application, the supply and demand calculation module 202 includes: a time-series data statistics unit, a time-series data analysis unit, and a supply and demand calculation unit; the supply and demand calculation module 202 is used to obtain the supply and demand change trend of each type of land parcel based on the land parcel classification results at each of the historical time points, and to calculate the demand intensity of each type of land parcel at the current time point based on the supply and demand change trend; the time-series data statistics unit is used to calculate the total area of ​​different types of land parcels at each historical time point based on the boundaries and land parcel types of each land parcel at each historical time point, and to obtain time-series data of land parcel type area; the time-series data analysis unit is used to calculate the land parcel area growth rate corresponding to each type of land parcel based on the land parcel area time-series data of land parcel type area; the supply and demand calculation unit is used to calculate the growth area corresponding to each type of land parcel based on the land parcel area and the land parcel area growth rate corresponding to each type of land parcel at the current time point, and to use the growth area as the demand intensity.

[0120] Further, in some embodiments of this application, the spatial analysis module 203 includes: a second land parcel acquisition unit, a second land parcel type confirmation unit, and a surrounding land parcel information acquisition unit; the spatial analysis module 203 is used to perform spatial analysis on each first land parcel based on the geospatial data and land parcel classification results at each of the historical time points to obtain surrounding land parcel information for each first land parcel at each of the historical time points, including: the second land parcel acquisition unit is used to determine a number of second land parcels adjacent to the first land parcel at each of the historical time points based on the geospatial data; the second land parcel type confirmation unit is used to determine the land parcel type of each second land parcel at each of the historical time points based on the land parcel classification results; the surrounding land parcel information acquisition unit is used to use the land parcel type and land parcel area of ​​the second land parcel as the surrounding land parcel information of the first land parcel at the corresponding historical time point.

[0121] Furthermore, in some embodiments of this application, the first land parcel evolution prediction module 204 is used to predict the land parcel type evolution trend of the first land parcel through time series analysis based on the policy text data at each of the historical time points and the surrounding land parcel information, including:

[0122] The policy text data and surrounding land parcel information at each of the historical time points are input into a pre-trained time series classification model to obtain the probability distribution of the first land parcel being transformed into each of the land parcel types at the current time point; the probability distribution includes: the probability value of the first land parcel being transformed into each of the land parcel types.

[0123] Further, in some embodiments of this application, the approved but not supplied risk identification module 205 includes: a first land parcel type prediction unit, a second land parcel screening unit, a supply intensity prediction unit, and a supply-demand matching unit; the approved but not supplied risk identification module 205 is used to assess the approved but not supplied risk of the target area based on the land parcel type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time, including: the first land parcel type prediction unit is used to determine the first land parcel type with the highest probability value corresponding to each first land parcel based on the probability distribution; the second land parcel screening unit is used to screen out second land parcels that can be initially supplied from all the first land parcels based on the planned use of each first land parcel and the corresponding first land parcel type; the supply intensity prediction unit is used to determine the supply intensity of each land parcel type at the current time based on the corresponding first land parcel type of each second land parcel; the supply-demand matching unit is used to assess the approved but not supplied risk of the target area based on the supply intensity and demand intensity of each land parcel type at the current time.

[0124] It is understood that the above system embodiments correspond to the method embodiments of this application, and can implement the risk assessment method for areas with a high incidence of approved but unsupplied land provided by any of the above method embodiments of this application.

[0125] In summary, the risk assessment system for areas with a high incidence of approved but unsupplied land provided in this application has the following advantages compared to existing technologies: It collects geospatial data using remote sensing technology and analyzes historical land parcel classification data and supply-demand trends based on the geospatial data to infer the current demand intensity for different types of land parcels; further, through time-series modeling analysis, combined with the historical evolution trends of surrounding land parcels and corresponding policy text data, it infers the land parcel type evolution trend of the first land parcel from the change patterns of neighboring land parcels, thereby more accurately determining the type of land supply that should be converted in the future; finally, by combining the demand forecasts for each type of land parcel and the future land supply type of each first land parcel, it assesses the supply-demand balance within the target area. When the supply and demand are unbalanced within the target area, it indicates a higher risk of approved but unsupplied land, thus improving the spatial correlation and dynamic prediction capabilities of the risk assessment for approved but unsupplied land.

[0126] It should be noted that the system embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided in this application, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0127] Based on the above-described embodiments of the risk assessment method for high-incidence areas of approved but unsupplied land, another embodiment of this application provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the risk assessment method for high-incidence areas of approved but unsupplied land according to any embodiment of this application.

[0128] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more module units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0129] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0130] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0131] Based on the above-described method embodiments, another embodiment of this application provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the risk assessment method for high-incidence areas of approved but unsupplied land as described in any of the above-described method embodiments of this application.

[0132] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

Claims

1. A method for risk assessment of a high-risk area of a batch-unprovided land, characterized in that, include: Collect geospatial data of the target area at several historical time points, and determine the land parcel classification results of the target area at the corresponding historical time points based on the geospatial data; Based on the land parcel classification results at each of the historical time points, the supply and demand change trends of each land parcel type are obtained, and the demand intensity of each land parcel type at the current time point is calculated based on the supply and demand change trends. The land parcels within the target area at the current time point that are pending approval or approved but not yet supplied are taken as the first land parcels. Based on the geospatial data of each historical time point and the land parcel classification results, spatial analysis is performed on each first land parcel to obtain information on the surrounding land parcels of each first land parcel at each historical time point. Collect policy text data of the target area at each of the historical time points, and predict the land type evolution trend of the first land parcel through time series analysis based on the policy text data of each of the historical time points and the surrounding land parcel information; The risk of approved but not supplied land in the target area is assessed based on the land type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time.

2. The risk assessment method for areas with a high incidence of approved but unsupplied land as described in claim 1, characterized in that, The step of determining the land parcel classification result of the target area at the corresponding historical time point based on the geospatial data includes: The boundaries of each land parcel are extracted from the geospatial data using an edge detection algorithm, and the boundaries are corrected based on the geographic information data of each land parcel. Based on the boundary, remote sensing images of the corresponding land parcels are cropped from the geospatial data, and several preset remote sensing indices are calculated based on the band combinations in each remote sensing image. The remote sensing indices are input into the pre-trained support vectors to obtain the land parcel type of the corresponding land parcel.

3. The risk assessment method for areas with a high incidence of approved but unsupplied land as described in claim 2, characterized in that, The process involves obtaining the supply and demand trends for each land parcel type based on the land parcel classification results at each historical time point, and calculating the demand intensity for each land parcel type at the current time point based on these supply and demand trends. Based on the boundaries and types of each plot at each historical time point, the total area of ​​different plot types at each historical time point is calculated to obtain time series data of plot type area. Based on the time series data of the land parcel area for each land parcel type, calculate the land parcel area growth rate corresponding to each land parcel type; Based on the land area and the land area growth rate of each land parcel type at the current time point, the growth area corresponding to each land parcel type is calculated, and the growth area is used as the demand intensity.

4. The risk assessment method for areas with a high incidence of approved but unsupplied land as described in claim 2, characterized in that, The step of performing spatial analysis on each first land parcel based on the geospatial data of each historical time point and the land parcel classification results to obtain information on surrounding land parcels of each first land parcel at each historical time point includes: Based on the geospatial data, identify several second plots adjacent to the first plot at each of the historical time points; Based on the land parcel classification results, determine the land parcel type of each second land parcel at each of the historical time points; The land parcel type and land parcel area of ​​the second land parcel are used as the surrounding land parcel information of the first land parcel at the corresponding historical time point.

5. A risk assessment method for areas with a high incidence of approved but unsupplied land, as described in claim 4, characterized in that... The step of predicting the land parcel type evolution trend of the first land parcel through time series analysis, based on the policy text data at each of the historical time points and the surrounding land parcel information, includes: The policy text data and surrounding land parcel information at each of the historical time points are input into a pre-trained time series classification model to obtain the probability distribution of the first land parcel being transformed into each of the land parcel types at the current time point; the probability distribution includes: the probability value of the first land parcel being transformed into each of the land parcel types.

6. The risk assessment method for areas with a high incidence of approved but unsupplied land as described in claim 5, characterized in that, The assessment of the approved but not yet supplied risk in the target area based on the land parcel type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time includes: Based on the probability distribution, determine the type of the first land parcel with the highest probability value corresponding to each of the first land parcels; Based on the planned use of each first plot and the corresponding first plot type, second plots that can be initially supplied are selected from all the first plots; Based on the corresponding first land parcel type for each second land parcel, determine the supply intensity of each land parcel type at the current time point; Assess the risk of approved but not supplied land in the target area based on the supply intensity and demand intensity of each land parcel type at the current point in time.

7. A risk assessment system for areas with a high incidence of approved but unsupplied land, characterized in that, include: The module includes a land parcel classification module, a supply and demand calculation module, a spatial analysis module, a first land parcel evolution prediction module, and a risk identification module for land parcels that have been approved but not yet supplied. The land parcel classification module is used to collect geospatial data of the target area at several historical time points, and determine the land parcel classification result of the target area at the corresponding historical time points based on the geospatial data. The supply and demand calculation module is used to obtain the supply and demand change trend of each type of land parcel based on the land parcel classification results at each of the historical time points, and to calculate the demand intensity of each type of land parcel at the current time point based on the supply and demand change trend. The spatial analysis module is used to take the land parcels that are pending approval or approved but not supplied in the target area at the current time point as the first land parcels, and perform spatial analysis on each of the first land parcels based on the geospatial data of each of the historical time points and the land parcel classification results to obtain the surrounding land parcel information of each of the first land parcels at each of the historical time points. The first land parcel evolution prediction module is used to collect policy text data at each of the historical time points within the target area, and predict the land parcel type evolution trend of the first land parcel through time series analysis based on the policy text data at each of the historical time points and the surrounding land parcel information. The approved but not supplied risk identification module is used to assess the approved but not supplied risk of the target area based on the land type evolution trend of each first land parcel, the planned use of each first land parcel, and the demand intensity of each land parcel type at the current time.

8. A risk assessment system for areas with a high incidence of approved but unsupplied land as described in claim 7, characterized in that, The land parcel classification module includes: an edge detection unit, a remote sensing index calculation unit, and a classification unit; the land parcel classification module is used to determine the land parcel classification result of the target area at the corresponding historical time point based on the geospatial data, including: The edge detection unit is used to extract the boundaries of each land parcel from the geospatial data using an edge detection algorithm, and to correct the corresponding boundaries based on the geographic information data of each land parcel. The remote sensing index calculation unit is used to cut the remote sensing image of the corresponding plot from the geospatial data according to the boundary, and to calculate a number of preset remote sensing indices according to the band combination in each remote sensing image. The classification unit is used to input the several remote sensing indices into the pre-trained support vector to obtain the land parcel type of the corresponding land parcel.

9. A risk assessment system for areas with a high incidence of approved but unsupplied land as described in claim 8, characterized in that, The supply and demand calculation module includes: a time-series data statistics unit, a time-series data analysis unit, and a supply and demand calculation unit; the supply and demand calculation module is used to obtain the supply and demand change trend of each land parcel type based on the land parcel classification results at each of the historical time points, and to calculate the demand intensity of each land parcel type at the current time point based on the supply and demand change trend. The time-series data statistics unit is used to calculate the total area of ​​different land parcel types at each historical time point based on the boundaries and land parcel types of each land parcel at each historical time point, and obtain time-series data of land parcel type area. The time-series data analysis unit is used to calculate the land area growth rate corresponding to each land parcel type based on the time-series data of the land parcel area. The supply and demand calculation unit is used to calculate the growth area corresponding to each of the land parcel types based on the land parcel area and the land parcel area growth rate at the current time point, and to use the growth area as the demand intensity.

10. A risk assessment system for areas with a high incidence of approved but unsupplied land, as described in claim 9, is characterized in that... The spatial analysis module includes: a second land parcel acquisition unit, a second land parcel type confirmation unit, and a surrounding land parcel information acquisition unit; the spatial analysis module is used to perform spatial analysis on each first land parcel based on the geospatial data of each historical time point and the land parcel classification results, to obtain surrounding land parcel information of each first land parcel at each historical time point, including: The second land parcel acquisition unit is used to determine, based on the geospatial data, a number of second land parcels adjacent to the first land parcel at each of the historical time points; The second land parcel type confirmation unit is used to determine the land parcel type of each second land parcel at each of the historical time points based on the land parcel classification results; The surrounding land information acquisition unit is used to use the land type and land area of ​​the second land plot as the surrounding land information of the first land plot at the corresponding historical time point.

Images