High-cold region land utilization change driving factor identification method
By constructing a structural equation model in an alpine cold zone, analyzing the land use amplitude data and driving factor amplitude data, identifying the core driving factors of land use change in an alpine cold zone, solving the problem that traditional methods are difficult to analyze the complex relationship between land use changes in an alpine cold zone.
Patent Information
- Application Number
- CN202510117104.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-24
- Publication Date
- 2025-05-27
AI Technical Summary
Due to the influence of severe climate and high-altitude environment in high-altitude areas, land use methods are significantly different from those in other regions. It is difficult for traditional single factor analysis methods to comprehensively analyze the complex relationship between land use changes.
By obtaining at least two phases of land use data and driver factor data in the high-altitude zone, the land use variation data and driver factor variation data are calculated, and the land use change driver factor identification model is input in the high-altitude zone. The influence indicators of different driver factors on land use changes are determined based on the structural equation model.
It is able to conduct a comprehensive analysis of land use drivers based on special environmental conditions in high-altitude areas, and identify the core drivers of land use changes in high-altitude areas, solving the problem that traditional methods are difficult to analyze the complex relationship between multiple causes and one effect.
Smart Images
Figure CN120046328A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of geographic big data modeling, and particularly relates to a method for identifying driving factors of land use change in alpine regions. Background Art
[0002] Driving factors of land use change refer to various factors that cause land type conversion, including direct factors and indirect factors. These driving factors interact with each other and jointly affect land use change. At present, in the research methods of land use change driving forces, more emphasis is placed on the analysis of single factors. Taking the land use change category value as the dependent variable and a single driving force factor as the independent variable, the relationship of land use change is reflected by the regression equation coefficient value. This method is simple, practical, and has strong scalability.
[0003] However, due to the influence of the cold climate and high altitude environment in alpine regions, the growth of vegetation is restricted, land resources are scarce, and soil fertility is low. These special environmental conditions have a profound impact on land use, making the land use patterns in alpine regions significantly different from those in other regions. The complex one-to-many causal relationship between numerous natural geography, social economy, and climate change factors and land use change in alpine regions makes it difficult to comprehensively analyze using traditional single-factor analysis methods.
[0004] Therefore, there is an urgent need for a method for identifying driving factors of land use change in alpine regions. Summary of the Invention
[0005] In view of this, the present application provides a method for identifying driving factors of land use change in alpine regions, which can identify the driving factors of land use change in alpine regions. The technical solution is as follows.
[0006] In a first aspect, a method for identifying driving factors of land use change in alpine regions according to the present invention includes:
[0007] Obtain land use change amplitude data and driving factor change amplitude data; the land use change amplitude data is used to characterize the change situation of land use data in the target alpine region; the driving factor change amplitude data is used to characterize the change situation of driving factor data in the target alpine region;
[0008] Input the land use change amplitude data and the driving factor change amplitude data into the driving factor identification model of land use change in alpine regions to obtain the influence index of different driving factors on land use change in the target alpine region;
[0009] According to the influence index of different driving factors on land use change, determine the target driving factors of land use change in the target alpine region; the identification model of driving factors for land use change in the alpine region is constructed based on the structural equation model by determining measurement variables and latent variables according to land use change amplitude data and driving factor change amplitude data.
[0010] In an alternative embodiment, the obtaining of land use change amplitude data and driving factor change amplitude data includes:
[0011] Obtain at least two periods of land use data of the target alpine region and driving factor data related to land use change;
[0012] Obtain land use change amplitude data according to the difference between at least two periods of land use data, and obtain driving factor change amplitude data according to the difference between at least two periods of driving factor data.
[0013] In an alternative embodiment, before the step of obtaining land use change amplitude data according to the difference between at least two periods of land use data and obtaining driving factor change amplitude data according to the difference between at least two periods of driving factor data, it further includes:
[0014] Resample the land use data to make the resolution of the land use data and the driving factor data unified.
[0015] In an alternative embodiment, the obtaining of the influence index of different driving factors on land use change in the target alpine region includes:
[0016] According to the output result of the identification model of driving factors for land use change in the alpine region, obtain the path coefficient and the loading coefficient; the path coefficient is used to indicate the causal relationship between the latent variable and the driving factor, and the loading coefficient is used to indicate the causal relationship between the measurement variable and the latent variable;
[0017] According to the path coefficient and the loading coefficient, determine the influence index of different driving factors on land use change in the target alpine region.
[0018] In an alternative embodiment, the method further includes:
[0019] Conduct a goodness-of-fit analysis on the identification model of driving factors for land use change in the alpine region through the land use change amplitude data and the driving factor change amplitude data to obtain a fitting result;
[0020] According to the fitting result, adjust the parameters of the identification model of driving factors for land use change in the alpine region.
[0021] A method for identifying driving factors for land use change in the alpine region provided by the present invention has the following advantages.
[0022] The method for identifying driving factors of land use change in alpine regions provided by the present invention is used to identify the driving factors of land use change in alpine regions and identify the core driving factors of land use change in alpine regions. First, for the target alpine region to be identified, at least two-phase land use data of the target alpine region and driving factor data related to land use change are obtained. Based on the obtained at least two-phase data, land use change amplitude data and driving factor change amplitude data can be obtained. The change amplitude data can be confirmed by calculating the difference between the two-phase data. The obtained land use change amplitude data and driving factor change amplitude data are input into the constructed model for identifying driving factors of land use change in alpine regions, and influence indexes of different driving factors on land use change in the target alpine region are obtained from the output of the model. The influence indexes include direct influence, indirect influence, and overall influence. According to this influence index, it can be determined which driving factors have a greater impact on land use change in the target alpine region, so as to confirm the target driving factors, that is, the core driving factors. The model for identifying driving factors of land use change in alpine regions is constructed based on the structural equation model. The latent variables and measurement variables of the structural equation model are determined according to the land use change amplitude data and driving factor change amplitude data, which involve land use change indexes, natural geography indexes, social economy indexes, and climate change indexes. Based on the latent variables and measurement variables, the model for identifying driving factors of land use change in alpine regions is constructed according to the structural equation model. This model can reflect the causal relationship between the latent variables and measurement variables, so as to obtain the influence indexes of different driving factors on land use change in the target alpine region. According to this influence index, the core driving factors can be screened out from these driving factors. Compared with the traditional research method of land use change driving force that focuses on the analysis of a single factor, the method for identifying driving factors of land use change in alpine regions provided by the present invention can comprehensively analyze the driving factors of land use by analyzing the complex relationship of multiple causes and one effect between natural geography, social economy, and climate change and land use change, and can obtain the core driving factors of land use change in alpine regions according to the special environmental conditions in alpine regions.
[0023] In a second aspect, the present invention provides a device for identifying driving factors of land use change in alpine regions, and the device includes:
[0024] An acquisition module, configured to acquire land use change amplitude data and driving factor change amplitude data; the land use change amplitude data is used to characterize the change of land use data in the target alpine region; the driving factor change amplitude data is used to characterize the change of driving factor data in the target alpine region;
[0025] An influence confirmation module, configured to input the land use change amplitude data and driving factor change amplitude data into the model for identifying driving factors of land use change in alpine regions, and obtain influence indexes of different driving factors on land use change in the target alpine region;
[0026] A target driving factor determination module, configured to determine the target driving factors for land use change in the target alpine region according to the influence indexes of different driving factors on land use change; the driving factor identification model for land use change in the alpine region is constructed based on a structural equation model by determining measurement variables and latent variables according to land use change amplitude data and driving factor change amplitude data.
[0027] In an optional implementation manner, the obtaining module is specifically configured to:
[0028] Obtain at least two-phase land use data of the target alpine region and driving factor data related to land use change;
[0029] Obtain land use change amplitude data according to the difference between at least two-phase land use data, and obtain driving factor change amplitude data according to the difference between at least two-phase driving factor data.
[0030] In an optional implementation manner, the obtaining module is further configured to:
[0031] Resample the land use data to make the resolution of the land use data and the driving factor data unified.
[0032] In an optional implementation manner, the influence confirmation module is specifically configured to:
[0033] Obtain a path coefficient and a loading coefficient according to the output result of the driving factor identification model for land use change in the alpine region; the path coefficient is used to indicate the causal relationship between the latent variable and the driving factor, and the loading coefficient is used to indicate the causal relationship between the measurement variable and the latent variable;
[0034] Determine the influence indexes of different driving factors on land use change in the target alpine region according to the path coefficient and the loading coefficient.
[0035] In an optional implementation manner, the device further includes:
[0036] An adjustment module, configured to perform goodness-of-fit analysis on the driving factor identification model for land use change in the alpine region through the land use change amplitude data and the driving factor change amplitude data to obtain a fitting result; and adjust the parameters of the driving factor identification model for land use change in the alpine region according to the fitting result.
[0037] In a third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method for identifying driving factors for land use change in the alpine region according to the first aspect or any corresponding implementation manner thereof.
[0038] Fourthly, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to make a computer execute the method for identifying driving factors of land use change in alpine regions according to the first aspect or any corresponding embodiment thereof above.
[0039] Fifthly, the present invention provides a computer program product, including computer instructions, and the computer instructions are used to make a computer execute the method for identifying driving factors of land use change in alpine regions according to the first aspect or any corresponding embodiment thereof above. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0041] Figure 1 It is a schematic flowchart of a method for identifying driving factors of land use change in alpine regions shown according to an exemplary embodiment.
[0042] Figure 2 It is a schematic flowchart of a method for identifying driving factors of land use change in alpine regions based on ArcGIS software and AMOS software shown according to an exemplary embodiment.
[0043] Figure 3 It is a schematic diagram of an initial conceptual model of natural geography, social economy, climate change and land use change in Basin A shown according to an exemplary embodiment.
[0044] Figure 4 It is a schematic diagram of the relationship path of natural geography, social economy, climate change and land use change in Basin A shown according to an exemplary embodiment.
[0045] Figure 5 It is a schematic structural diagram of a device for identifying driving factors of land use change in alpine regions provided by an embodiment of the present application.
[0046] Figure 6 It is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.
[0048] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or a representation of a correlation relationship. For example, A indicates B, which can mean that A directly indicates B. For example, B can be obtained through A; it can also mean that A indirectly indicates B. For example, A indicates C, and B can be obtained through C; it can also mean that there is a correlation relationship between A and B.
[0049] In the description of the embodiments of this application, the term "corresponding" can represent a direct or indirect corresponding relationship between two parties, can also represent a correlation relationship between two parties, or can be a relationship such as indication and being indicated, configuration and being configured, etc.
[0050] In the embodiments of this application, "predefined" can be implemented by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in a device (for example, including a terminal device and a network device). This application does not limit its specific implementation method.
[0051] Due to the influence of the severe cold climate and high altitude environment in alpine regions, the growth of vegetation is restricted, land resources are scarce, and soil fertility is low. These special environmental conditions have a profound impact on land use, making the land use patterns in alpine regions significantly different from those in other regions. To effectively solve the land use problems in alpine regions and achieve sustainable development, it is necessary to conduct an in-depth analysis of the driving factors of land use change. Driving factors refer to various factors that cause land type conversion, including direct factors and indirect factors. These driving factors interact with each other and jointly affect the land use change in alpine regions.
[0052] However, in the current research methods for the driving forces of land use change in alpine regions, more attention is paid to the analysis of single factors. Taking the land use change category value as the dependent variable and a single driving force factor as the independent variable, the relationship of land use change is reflected through the regression equation coefficient value. This method is simple, practical, and has strong scalability. In the complex human-land relationship in alpine regions, the complex relationship of multiple causes and one effect between numerous natural geography, social economy, and climate change factors and land use change is difficult to express by traditional empirical statistical methods.
[0053] Therefore, to address the deficiencies of traditional methods, an embodiment of the present invention provides a method for identifying driving factors of land use change in alpine regions. By analyzing the complex many-causes-one-effect relationship between natural geography, socioeconomic factors, and climate change and land use change, it is possible to comprehensively analyze the driving factors of land use for the special environmental conditions in alpine regions and obtain the core driving factors of land use change in alpine regions.
[0054] The method flow of a method for identifying driving factors of land use change in alpine regions provided by this embodiment is as Figure 1 shown and includes the following steps.
[0055] S101. Obtain land use change amplitude data and driving factor change amplitude data.
[0056] Specifically, the land use change amplitude data is obtained based on the change situation of the land use data in the target alpine region, and the driving factor change amplitude data is obtained based on the change situation of the driving factor data in the target alpine region. That is, it is necessary to obtain the land use data and driving factor data of the target alpine region to be identified and at least two periods of data.
[0057] S102. Input the land use change amplitude data and the driving factor change amplitude data into the driving factor identification model of land use change in alpine regions to obtain the influence indicators of different driving factors on land use change in the target alpine region.
[0058] Specifically, input the obtained land use change amplitude data and driving factor change amplitude data into the constructed driving factor identification model of land use change in alpine regions to obtain the influence indicators of different driving factors on land use change in the target alpine region. Specifically, obtain the different influences of different driving factors on land use change in the target alpine region, including direct influence, indirect influence, and overall influence. Based on these influences, the influence degree of each driving factor on land use change in the target alpine region can be determined.
[0059] S103. Determine the target driving factors of land use change in the target alpine region according to the influence indicators of different driving factors on land use change.
[0060] Specifically, according to the influence degree of each of the above driving factors on land use change in the target alpine region, determine the driving factors with a greater influence on land use change in the alpine region to obtain the target driving factors, that is, the core driving factors.
[0061] The identification model of driving factors for land use change in alpine regions in the above steps is constructed based on the structural equation model by determining measurement variables and latent variables according to land use change amplitude data and driving factor change amplitude data. According to the constructed model, the causal relationship between measurement variables and latent variables can be determined, so as to obtain the influence degree of different driving factors on land use change in the target alpine region.
[0062] Optionally, the obtaining of land use change amplitude data and driving factor change amplitude data specifically includes: obtaining at least two-phase land use data of the target alpine region and driving factor data related to land use change; obtaining land use change amplitude data according to the difference between at least two-phase land use data, and obtaining driving factor change amplitude data according to the difference between at least two-phase driving factor data. In addition, before calculating the difference, it is necessary to resample the land use data to make the resolution of the land use data and the driving factor data unified.
[0063] Optionally, in the above step S102, obtaining the influence index specifically includes: obtaining the path coefficient and the loading coefficient according to the output result of the identification model of driving factors for land use change in alpine regions; the path coefficient is used to indicate the causal relationship between the latent variable and the driving factor, and the loading coefficient is used to indicate the causal relationship between the measurement variable and the latent variable; according to the path coefficient and the loading coefficient, determine the influence index of different driving factors on land use change in the target alpine region. In addition, the goodness-of-fit analysis of the identification model of driving factors for land use change in alpine regions can be carried out through land use change amplitude data and driving factor change amplitude data to obtain the goodness-of-fit result; according to the goodness-of-fit result, adjust the parameters of the identification model of driving factors for land use change in alpine regions.
[0064] The method for identifying driving factors for land use change in alpine regions provided in the above embodiments can be implemented based on ArcGIS software and AMOS software. Therefore, in this embodiment, a method for identifying driving factors for land use change in alpine regions based on ArcGIS software and AMOS software is provided, and the specific process is as Figure 2 shown, including the following steps.
[0065] S201. Obtain at least two-phase land use data of the alpine region and driving factor data affecting land use change.
[0066] First, it is necessary to clarify that the target area is an alpine region with high altitude, perennial low temperature, and perennial non-thawing soil frozen layer, and collect at least two-phase land use distribution data of different years in the alpine region. The driving factor data includes three levels: natural geography, social economy, and climate change, and at least 3 measurement indicators are selected at each level; it should be noted that according to the regional characteristics of the alpine region, the natural geography level should include measurement indicators representing the characteristics of frozen soil, and the social economy level should include measurement indicators representing the characteristics of pastoral development.
[0067] It should be noted that land use data and driving factor data usually exist in the form of raster data.
[0068] S202. Resample the land use distribution data according to the land use patterns in the alpine region, and combine the driving factor data to obtain the land use change amplitude data and the driving factor change amplitude spatial data set at a unified resolution.
[0069] In the above steps, when resampling the land use distribution data, according to the differences in land use patterns in the alpine region, the land use types should be divided into ten categories: cultivated land, grassland, forest land, shrub land, wetland, water area, tundra, construction land, bare land, glacier and permanent snow, and the category codes are set as numbers 1-10 in sequence; use "Raster to polygon" in ArcGIS software to vectorize the two-phase land use raster data. The "Raster to Polygon" tool is a commonly used geoprocessing tool for converting raster data into vector data (Polygon).
[0070] The driving factor change amplitude spatial data set at the same resolution is calculated in ArcGIS software. Among them: if the driving factor data source is in the spatial raster data format, it is necessary to resample the selected data to unify the data resolution; if the driving factor data is meteorological station or central point data, it is necessary to perform spatial interpolation on the selected central point (or station) data to obtain the spatial distribution data of each driving factor and unify the data resolution.
[0071] Based on the "Raster calculator" in ArcGIS software, calculate the change amplitude on the corresponding grid cells of the spatial distribution data of different periods of each driving factor, keep the data resolution unified, and output the row and column numbers of the grid cells with the help of programming language, and output the change amplitude of each driving factor in the corresponding grid cells; among them, the pixel value less than 0 represents the decrease of the driving factor during the research period; the pixel value greater than 0 represents the increase of the driving factor during the research period; the pixel value equal to 0 represents that the driving factor remains unchanged during the research period. It is used to perform various mathematical operations, logical operations, statistical analyses and function operations based on raster data. The "Raster calculator" tool allows users to process raster data by writing expressions for raster operations and spatial analysis.
[0072] S203. Based on the principle of structural equation model, construct an identification model for the driving factors of land use change in the alpine region.
[0073] In the above steps, the structural equation model is a hypothetical model based on empirical theory to construct causal relationships. After verifying the rationality of the model, the causal relationship between the dependent variable and the independent variable is quantified. This model can not only handle the situation where one variable corresponds to multiple dependent variables simultaneously, but also precisely analyze the logical relationships among them. By analyzing the goodness of fit between the model and the data and then adjusting the model, the direct and indirect effects between different indicators can be analyzed. The structural equation model consists of two parts, the structural model and the measurement model. The structural model establishes the causal relationship between latent variables that cannot be directly observed and is used to describe the structural relationship between latent variables. The measurement model is a model that describes the relationship between latent variables and measured variables.
[0074] For the identification model of driving factors for land use change in alpine regions, first, according to the principle of the structural equation model, the latent variables and measured variables of the model are determined. The selected driving factors include three aspects: natural geography, social economy, and climate change. Therefore, natural geography, social economy, climate change, and land use change are the latent variables of the identification model of driving factors for land use change in alpine regions. The measured variables are at least three measurement indicators for each of the three aspects of natural geography, social economy, and climate change, and the measured variable of land use change is the area change amplitude of ten land use types.
[0075] The identification model of driving factors for land use change in alpine regions needs to first propose an initial conceptual model of the impact of natural geography, social economy, and climate change on land use change and construct it using AMOS software.
[0076] S204. Input the land use change amplitude data and the driving factor change amplitude spatial data set into the identification model of driving factors for land use change in alpine regions for simulation and verify the model.
[0077] In the above steps, the land use change amplitude data and the driving factor change amplitude spatial data set are located on the grid cells in ArcGIS software. A grid cell refers to the smallest unit that forms a grid in raster data. In high-resolution spatial data analysis, the entire study area is divided into multiple grids of the same size, and each grid cell represents a certain geographical area and spatial range. Grid cells are the basic units for spatial data storage, analysis, and calculation.
[0078] The land use change amplitude data on the grid cells are the area change amplitude ratios of each land use type in at least two periods of land use data. The calculation method is as follows: Using the spatial distribution data of the driving factor change amplitude at a unified resolution as a template, construct a vector data of square grid with the resolution size as the side length in the study area; Use programming language to read the row and column numbers of the square grid vector data, and the row and column numbers should be consistent with the row and column numbers of the driving factor change amplitude on the grid cells; Number the square grid vector data according to the order of the row and column numbers; Based on the ArcGIS software, conduct an intersection analysis of the vectorized land use spatial data and the square grid vector data to obtain the distribution maps of each land use type in different periods for each grid cell; Calculate the area of each land use type for each grid cell, divide the obtained area by the area of the square grid to obtain the area ratio of each type for each grid cell, and at the same time ensure that the sum of the area ratios of each type on the same grid cell is 1; Calculate the area change amplitude ratios of each land use type at the grid cell scale for several periods; Among them, a pixel value less than 0 represents a decrease in the area of the land use type during the study period; a pixel value greater than 0 represents an increase in the area of the land use type during the study period; a pixel value equal to 0 represents that the area of the land use type remains unchanged during the study period.
[0079] The spatial data set of the driving factor change amplitude is the change amplitude of natural geography, social economy, and climate change measurement variables in the same period as the land use data; Read the area change amplitude ratio data of each land use type at the grid cell scale in the alpine region and the driving factor change amplitude data for each grid cell, and keep the two in one-to-one correspondence according to the row and column numbers of the grid cells; Run the driving factor identification model in the AMOS software, and check the simulation effect by examining the ratio of the path coefficient to the loading coefficient of the fitting model and the relevant fitting indexes.
[0080] S205. According to the model output results, clarify the main driving factors of land use change in the alpine region.
[0081] Specifically, the model output results of the above steps are simulation results, which are the simulation results when all fitting indexes in the driving factor identification model meet the fitting standards and the model fitting degree is good. The main driving factors of land use change in the alpine region should include the influencing ways and degrees of the three latent variables of natural geography, social economy, and climate change on land use change, including direct influence, indirect influence, and overall influence, as well as the contribution degrees of the measurement variables of the three latent variables respectively, and obtain the measurement variable with the largest contribution degree.
[0082] To better illustrate the driving factor identification method for land use change in the alpine region provided by the above embodiments, the following further illustrates the embodiments of the present invention with specific implementation cases.
[0083] This example takes Basin A as the example study area to clearly and completely describe the specific processes and technical solutions in the above embodiments. Basin A is 2057 km long and has a basin area of 24.05 km 2 , and the average altitude of Basin A is above 3000 m. It has a low temperature and little accumulated temperature, and is a typical alpine cold region.
[0084] The data used in the basin are the land use distribution data in 2000 and 2020. The natural geographical driving factors include elevation, slope, normalized difference vegetation index, and annual surface frozen soil duration; the slope data are calculated in the ArcGIS software based on the elevation data; the annual surface frozen soil duration represents the development characteristics of frozen soil. According to the ground temperature data of meteorological stations, the number of days when the ground temperature is lower than 0°C is statistically counted to represent the annual surface frozen soil duration; the social and economic driving factors include population, gross domestic product, animal husbandry output value, and soil and water conservation project construction area; the animal husbandry output value is selected to represent the development characteristics of animal husbandry in alpine cold regions; especially in recent years, the soil and water conservation projects for wind prevention and sand fixation in Basin A have also had a great impact on the land use pattern. Therefore, considering the actual situation, the soil and water conservation project construction area is taken as one of the driving factors; the climate change driving factors include precipitation, temperature, wind speed, and actual evapotranspiration.
[0085] According to the differences in land use patterns in alpine cold regions, the land use types are divided into ten categories: cultivated land, grassland, forest land, shrub land, wetland, water area, tundra, construction land, bare land, glacier, and permanent snow cover. The category codes are successively the numbers 1-10; this case focuses on analyzing the types of cultivated land, forest land, shrub land, grassland, and bare land. Use the "Raster topolygon" in the ArcGIS software to vectorize the land use raster data in 2000 and 2020.
[0086] Among the driving factors, the data sources of elevation, normalized difference vegetation index, population, and GDP are in raster format, and the two-phase data need to be resampled to unify the data resolution to 2 km; the animal husbandry output value and the soil and water conservation project construction area are the data of the central counties and cities in the study area, and the annual surface frozen soil duration, precipitation, temperature, wind speed, and actual evapotranspiration are the data of meteorological stations. The two-phase center point (or station) data need to be spatially interpolated to obtain the spatial distribution data of each driving factor, and the data resolution is unified to 2 km. Based on the "Raster calculator" in the ArcGIS software, calculate the amplitude change on the corresponding grid cells of the spatial distribution data of each driving factor in 2000 and 2020, and keep the data resolution at 2 km. With the help of the Python language, output the row and column numbers of the grid cells, and output the amplitude change of each driving factor in the corresponding grid cells. The amplitude change of each driving factor in Basin A is spatially distributed at a resolution of 2 km, and the output row and column numbers are 703 rows and 258 columns.
[0087] Taking natural geography, social economy, climate change, and land use change as the latent variables of the land use change driving factor identification model in Basin A, the measurement variables of natural geography are elevation, slope, normalized difference vegetation index, and annual surface frozen soil duration; the measurement variables of social economy are population, GDP, animal husbandry output value, and water and soil conservation project construction area; the measurement variables of climate change are precipitation, temperature, wind speed, and actual evapotranspiration; a land use change driving factor identification model for Basin A is constructed.
[0088] As Figure 3 shown, an initial conceptual model of natural geography, social economy, climate change, and land use change is constructed in AMOS software, where: terrain, soil, vegetation, etc. are not only the basic factors directly affecting land use change, but also can indirectly affect land use change by influencing the change of animal husbandry output value; therefore, Hypothesis H1a is proposed: natural geography has a direct impact on land use change; Hypothesis H1b: natural geography indirectly affects land use change by influencing social economy. Factors such as temperature and precipitation directly affect the growth characteristics of forest and grass, and the magnitude and direction of wind speed affect the frequency and intensity of wind erosion, sandstorms, etc., all of which will directly cause changes in land use patterns; in addition, it also indirectly affects land use by influencing the changes in underlying surface vegetation and frozen soil; therefore, Hypothesis H2a is proposed: climate change has a direct impact on land use change; Hypothesis H2b: climate change indirectly affects land use change by influencing natural geography. The development of the regional economic level and the rapid increase in population will increase the demand for social and economic land, and thus squeeze the ecological environment land, having a direct impact on the regional land use pattern; therefore, Hypothesis H3 is proposed: social economy directly affects land use change.
[0089] Taking the variable amplitude spatial distribution data of driving factors with a resolution of 2 km as a template, a square grid vector data of 2 km × 2 km in Basin A is constructed, and finally 61,235 grids in Basin A are obtained; the row and column numbers read by Python are consistent with the variable amplitude spatial data of each driving factor, and in the order of row and column numbers, the square grids are numbered from 1 to 61,235; based on ArcGIS software, an intersection analysis is carried out between the vectorized land use spatial data of 2000 and 2020 after resampling and the square grid vector data to obtain the distribution maps of each land use type on a grid-by-grid basis for the two periods of 2000 and 2020; the area variable amplitude ratio data of each land use type at the grid cell scale in Basin A from 2000 to 2020 are calculated;
[0090] The Python language can be used to read the area change ratio data of each land use type at the cell scale in Basin A and the change data of each driving factor on each grid cell, and keep the two in one-to-one correspondence according to the row and column numbers of the grid cells. Run the driving factor identification model in AMOS software, and evaluate the goodness of fit of the model by examining the ratio of the path coefficient to the loading coefficient of the fitting model and related fitting indices; the selected fitting indices include absolute fitting indices, incremental fitting indices and parsimonious fitting indices. The absolute fitting indices include the goodness of fit index and the root mean square of approximation error; the incremental fitting indices are the standardized fitting index, the incremental fitting index and the comparative fitting index; the parsimonious fitting index includes the parsimony adjusted index; the fitting index results of the driving factor identification model for land use change in Basin A are shown in Table 1. All fitting indices in the driving factor identification model for land use change in Basin A meet the fitting standards, and the goodness of fit of the model is good.
[0091] Table 1
[0092]
[0093] Figure 4 The path diagram of the driving factor relationship for land use change in Basin A is shown. The significance of each path coefficient has passed the 99% or 95% significance level. The influence effects of the three latent variables of natural geography, social economy and climate change on land use change in Basin A are shown in Table 2. The contribution degrees of the measurement indices to the latent variables in the driving factor identification model for land use change in Basin A are shown in Table 3. The overall influence effects of natural geography, social economy and climate change on cultivated land, grassland, forest land, shrub land and bare land in Basin A are shown in Table 4. The social economy in Basin A has the greatest impact on land use change, showing a negative impact; the impacts of natural geography and climate change on land use change are very small, showing a positive impact. In the land use change in Basin A, the positive contribution rate of grassland is the largest, the negative contribution rate of the annual surface frozen soil duration in natural geography is the largest, the positive contribution rate of evapotranspiration in climate change is the largest, and the positive contribution rate of the difference in animal husbandry in social economy is the largest. Natural geography and climate change have the greatest impact on the grassland type, both showing a positive impact, and the social economy has the greatest negative impact on the grassland type. Generally speaking, natural geography, climate change and social economy have the greatest impact on the grassland type, but the impact methods are different.
[0094] Table 2
[0095]
[0096] Table 3
[0097] Path Normalization coefficient Cultivated land ← Land use change -0.57 Grassland ← Land use change 0.89 Forest land ← Land use change -0.53 Bare land ← Land use change 0.75 Shrub land ← Land use change -0.19 Elevation ← Physical geography 0.16 Slope ← Physical geography 0.27 Normalized difference vegetation index ← Physical geography 0.45 Annual surface frozen soil duration ← Physical geography -0.67 Precipitation ← Climate change 0.65 Air temperature ← Climate change -0.44 Actual evapotranspiration ← Climate change 0.68 Wind speed ← Climate change -0.43 Population ← Socio - economy 0.17 Gross domestic product ← Socio - economy 0.46 Output value of animal husbandry ← Socio - economy 0.83 Construction area of soil and water conservation projects ← Socio - economy 0.54
[0098] Table 4
[0099]
[0100] In summary, the method for identifying driving factors of land use change in alpine regions provided by the embodiments of the present invention is used to identify the driving factors of land use change in alpine regions and identify the core driving factors of land use change in alpine regions. First, for the target alpine region to be identified, at least two-phase land use data and driving factor data related to land use change of the target alpine region are obtained. Based on the obtained at least two-phase data, land use change amplitude data and driving factor change amplitude data can be obtained, and the change amplitude data can be confirmed by calculating the difference between the two-phase data. The obtained land use change amplitude data and driving factor change amplitude data are input into the constructed identification model of driving factors of land use change in alpine regions, and influence indexes of different driving factors on land use change in the target alpine region output by the model are obtained. The influence indexes include direct influence, indirect influence and overall influence. According to this influence index, it can be determined which driving factors have a greater impact on land use change in the target alpine region, so as to confirm the target driving factors, that is, the core driving factors. The identification model of driving factors of land use change in alpine regions is constructed based on the structural equation model. The latent variables and measurement variables of the structural equation model are determined according to the land use change amplitude data and driving factor change amplitude data, which involve land use change indexes, natural geography indexes, social economy indexes and climate change indexes. According to the latent variables and measurement variables, the identification model of driving factors of land use change in alpine regions is constructed based on the structural equation model. This model can reflect the causal relationship between the latent variables and measurement variables, so as to obtain the influence indexes of different driving factors on land use change in the target alpine region. According to this influence index, the core driving factors can be screened out from these driving factors. Compared with the traditional research method of driving force of land use change that focuses on the analysis of a single factor, the method for identifying driving factors of land use change in alpine regions provided by the present invention can comprehensively analyze the driving factors of land use by analyzing the complex relationship of multiple causes and one effect between natural geography, social economy and climate change and land use change, and obtain the core driving factors of land use change in alpine regions according to the special environmental conditions in alpine regions.
[0101] In the embodiments of the present application, an apparatus for identifying driving factors of land use change in alpine regions is also provided. This apparatus is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.
[0102] The embodiments of the present application provide an apparatus for identifying driving factors of land use change in alpine regions. Figure 5It is a schematic structural diagram of a device for identifying driving factors of land use change in alpine regions provided by an embodiment of the present application. The device includes:
[0103] An acquisition module 501, configured to acquire land use change amplitude data and driving factor change amplitude data; the land use change amplitude data is used to characterize the change of land use data in the target alpine region; the driving factor change amplitude data is used to characterize the change of driving factor data in the target alpine region;
[0104] An influence confirmation module 502, configured to input the land use change amplitude data and the driving factor change amplitude data into a driving factor identification model for land use change in alpine regions to obtain influence indexes of different driving factors on land use change in the target alpine region;
[0105] A target driving factor determination module 503, configured to determine a target driving factor for land use change in the target alpine region according to the influence indexes of different driving factors on land use change; the driving factor identification model for land use change in alpine regions is constructed based on a structural equation model by determining measurement variables and latent variables according to land use change amplitude data and driving factor change amplitude data.
[0106] In an optional implementation manner, the acquisition module 501 is specifically configured to:
[0107] Acquire at least two periods of land use data in the target alpine region and driving factor data related to land use change;
[0108] Obtain land use change amplitude data according to the difference between at least two periods of land use data, and obtain driving factor change amplitude data according to the difference between at least two periods of driving factor data.
[0109] In an optional implementation manner, the acquisition module 501 is further configured to:
[0110] Resample the land use data to make the resolution of the land use data and the driving factor data unified.
[0111] In an optional implementation manner, the influence confirmation module 502 is specifically configured to:
[0112] Obtain a path coefficient and a loading coefficient according to the output result of the driving factor identification model for land use change in alpine regions; the path coefficient is used to indicate the causal relationship between the latent variable and the driving factor, and the loading coefficient is used to indicate the causal relationship between the measurement variable and the latent variable;
[0113] Determine influence indexes of different driving factors on land use change in the target alpine region according to the path coefficient and the loading coefficient.
[0114] In an alternative embodiment, the apparatus further includes:
[0115] An adjustment module 504, configured to perform goodness-of-fit analysis on the driving factor identification model of land use change in alpine regions through land use amplitude data and driving factor amplitude data, and obtain a fitting result; and adjust the parameters of the driving factor identification model of land use change in alpine regions according to the fitting result.
[0116] The further function descriptions of the above-mentioned modules and units are the same as those in the corresponding embodiments above, and will not be elaborated here.
[0117] The apparatus for identifying driving factors of land use change in alpine regions in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0118] An embodiment of the present invention further provides a computer device having the above-mentioned Figure 5 apparatus for identifying driving factors of land use change in alpine regions.
[0119] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention. As shown in Figure 6 , the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common main board or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphic information in a graphical user interface on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as a server array, a set of blade servers, or a multi-processor device). Figure 6 Here, one processor 10 is taken as an example.
[0120] The processor 10 may be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device may be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.
[0121] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.
[0122] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating device and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely disposed relative to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.
[0123] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may also include a combination of the above types of memories.
[0124] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means. Figure 6 Taking the connection through the bus as an example.
[0125] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.
[0126] A part of the present invention can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, the method and / or technical solution according to the present invention can be called or provided. Those skilled in the art should be able to understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.
[0127] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for identifying driving factors of land use change in alpine regions, characterized in that: The method comprises: Acquire land use variation data and driving factor variation data; the land use variation data is used to characterize the change of land use data in the target alpine region; the driving factor variation data is used to characterize the change of driving factor data in the target alpine region; Input the land use variation data and driving factor variation data into the driving factor identification model of land use change in alpine regions to obtain the influence index of different driving factors on the land use change in the target alpine regions; According to the influence indicators of the different driving factors on land use change, the target driving factors of land use change in the target alpine area are determined; the driving factor identification model of land use change in the alpine area is constructed based on the structural equation model by determining the measured variables and potential variables according to the land use variation data and the driving factor variation data.
2. The method according to claim 1, characterized in that The obtaining of land use variation data and driving factor variation data includes: Obtain at least two periods of land use data and data on driving factors related to land use change in the target alpine region; The land use variation data are obtained according to the difference between at least two periods of land use data, and the driving factor variation data are obtained according to the difference between at least two periods of driving factor data.
3. The method according to claim 2, characterized in that Before the steps of obtaining land use variation data according to the difference between at least two periods of land use data and obtaining driving factor variation data according to the difference between at least two periods of driving factor data, the method further comprises: The land use data are resampled to make the resolution of land use data and driving factor data consistent.
4. The method according to claim 3, characterized in that The above indicators of the influence of different driving factors on the land use change in the target alpine region include: According to the output results of the identification model of driving factors of land use change in alpine regions, the path coefficient and the load coefficient are obtained; the path coefficient is used to indicate the causal relationship between the latent variable and the driving factor, and the load coefficient is used to indicate the causal relationship between the measured variable and the latent variable; According to the path coefficient and the load coefficient, the influence indicators of different driving factors on the land use change in the target alpine region are determined.
5. The method according to claim 4, characterized in that The method further comprises: Through the land use variation data and driving factor variation data, the fitting degree of the identification model of driving factors of land use change in alpine areas was analyzed and the fitting results were obtained. According to the fitting results, the parameters of the model for identifying driving factors of land use change in alpine regions are adjusted.
6. A device for identifying driving factors of land use change in alpine regions, characterized in that: The device comprises: An acquisition module is used to acquire land use variation data and driving factor variation data; the land use variation data is used to characterize the change of land use data in the target alpine region; the driving factor variation data is used to characterize the change of driving factor data in the target alpine region; An influence confirmation module is used to input the land use variation data and driving factor variation data into a high-cold area land use change driving factor identification model to obtain influence indicators of different driving factors on the land use change in the target high-cold area; The target driving factor determination module is used to determine the target driving factors of land use change in the target alpine area according to the influence indicators of the different driving factors on land use change; the driving factor identification model of land use change in the alpine area is determined by determining the measured variables and potential variables based on the land use variation data and the driving factor variation data, and is constructed based on the structural equation model.
7. The device according to claim 6, characterized in that The acquisition module is specifically used for: Obtain at least two periods of land use data and data on driving factors related to land use change in the target alpine region; The land use variation data are obtained according to the difference between at least two periods of land use data, and the driving factor variation data are obtained according to the difference between at least two periods of driving factor data.
8. The device according to claim 7, characterized in that The acquisition module is further used for: It is used to resample the land use data to make the resolution of land use data and driving factor data consistent.
9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for identifying driving factors of land use changes in high-cold areas according to any one of claims 1 to 5 by executing the computer instructions.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for identifying driving factors of land use change in alpine regions according to any one of claims 1 to 5.