Land planning based area measurement system and method

Abstract

The application relates to a land planning area measurement system and method, which comprises the following steps: acquiring multi-source data of a land planning area by a collection module, and storing the data in a storage module; introducing the acquired multi-source data of the land planning area into a data processing module for pretreatment, and extracting forest land characteristics and a region boundary; generating a dynamic change graph of real-time monitoring of the forest land area, analyzing change driving factors; predicting a forest land area change trend; generating a measurement result, and comparing the measurement result with a change setting range threshold value to perform early warning. The application can perform real-time dynamic monitoring on land types such as forest land and farmland through time sequence remote sensing image data, generate a change trend graph, analyze a model, and predict a change trend of the land area, which provides a dynamic change reference for land planners, helps to predict future land use requirements, ecological environment changes and the like, and provides data support for scientific planning and reasonable utilization of land resources.

Description

Technical Field

[0001] This invention belongs to the field of area measurement technology, specifically an area measurement system and method based on land planning. Background Technology

[0002] With increasing emphasis on land resource management, the scientific and precise nature of land planning and resource utilization has become increasingly important; land area measurement, as a key link in land planning, is directly related to the rational allocation and utilization efficiency of land resources.

[0003] In monitoring forest land change trends, existing technical solutions generally lack real-time capability; most traditional methods rely on static remote sensing image data for analysis, which cannot quickly capture dynamic changes in forest land; this lag affects the response speed of land managers to forest land changes, causing potential ecological damage and resource waste, and the factors of soil change cannot be analyzed, lacking effective quantitative prediction models for soil loss, thus failing to provide sufficient support for forest land protection and restoration.

[0004] In view of this, an area measurement system and method based on land planning is proposed. Summary of the Invention

[0005] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0006] Given the following technical problems in existing technologies: in monitoring forest land change trends, existing technical solutions generally lack real-time capability; most traditional methods rely on static remote sensing image data for analysis, which cannot quickly capture dynamic changes in forest land; this lag affects the response speed of land managers to forest land changes, causing potential ecological damage and resource waste, and the factors of soil change cannot be analyzed, lacking effective quantitative prediction models for soil loss, thus failing to provide sufficient support for forest land protection and restoration.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an area measurement method based on land planning, comprising the following steps;

[0008] S1. Acquire multi-source data of the land planning area through the acquisition module and store this data in the storage module;

[0009] S2. Import the acquired multi-source land planning area data into the data processing module for preprocessing, and extract forest land characteristics and regional boundaries;

[0010] S3. Generate dynamic change graphs of forest area in real time and analyze the driving factors of change;

[0011] S4. Predict the trend of forest area change;

[0012] S5. Generate measurement results and compare them with the threshold value set for the change range to issue an early warning.

[0013] As a preferred technical solution for an area measurement method based on land planning, step S1 includes the following specific steps:

[0014] S11. Acquire images and collect topographic data of the forest area using drones;

[0015] S12. Deploy ground-based meteorological station equipment in the target area and acquire meteorological data, including real-time precipitation, temperature, wind speed and humidity data;

[0016] S13. Obtain slope distribution data through aerial photography terminal;

[0017] S14. Store the acquired topographic data, meteorological data, and slope distribution data of the forest land into the first storage component.

[0018] As a preferred technical solution for an area measurement method based on land planning, the data preprocessing in S2 includes the following specific steps:

[0019] S21. Obtain points with obvious geometric features from the images, obtain matching image feature point sets from historical image data, calculate the Euclidean distance between the feature points of the current images and the feature points of the historical images, and calculate the cosine similarity between the image feature points and the feature points of the reference map.

[0020] S22. Classify the land surface types of the preprocessed remote sensing images; generate a predicted label map from the classification results.

[0021] S23. Perform error compensation on the acquired meteorological data, topographic data, and surface type data, and calculate the error correction factor.

[0022] As a preferred technical solution for an area measurement method based on land planning, the area boundary processing in S2 includes the following specific steps:

[0023] S24. Use conditional random fields for boundary correction and optimize boundary accuracy by minimizing the following energy function.

[0024] As a preferred technical solution for an area measurement method based on land planning, the dynamic change of forest area in S3 includes the following specific steps:

[0025] S31. By comparing remote sensing image data at different time points, the change in forest area is detected, and the output formula is ΔA = A. new -A old Where ΔA represents the change in forest area, A new A represents the forest area measured at the new time. old This indicates the area of ​​forest land as measured at a previous time.

[0026] S32. Using a deep learning model, feature extraction and change prediction are performed on the image data to generate a change map, where each pixel value represents the magnitude of the change. The output formula is y. i =classify(x i for i∈[1,N], where x i For the i-th pixel, y i This is the label for the change in that pixel.

[0027] As a preferred technical solution for area measurement based on land planning, the change-driving factor analysis in S3 includes the following specific steps:

[0028] S33. By analyzing the relationship between historical meteorological data and forest land changes, forest land changes can be predicted. Let R(t) represent the meteorological driving factor at a certain time t. Then the output formula for the relationship between forest land area change ΔA and meteorological factor R(t) is ΔA(t)=β1R(t)+β2·ΔA(t-1)+∈, where ΔA(t) is the forest land area change at time t, R(t) is the meteorological factor at time t; β1 is the coefficient of the meteorological factor, representing the degree of influence of the meteorological factor on forest land changes; β2 is the autoregressive coefficient, representing the influence of the previous forest land change on the current change; ∈ is the error term, representing unpredictable factors.

[0029] S34. Analyze the impact of topography and soil factors on forest land change. Let S represent soil moisture and G represent slope. The relationship between forest land area change and these factors can be described by the following model: ΔA(t)=γ1S(t)+γ2G(t)+γ3R(t)+δ, where S(t) is the soil moisture at time t; G(t) is the slope at time t; γ1, γ2, and γ3 are the coefficients of the corresponding factors, representing the degree of influence of these factors on forest land change; and δ is the error term.

[0030] S35. Using land use data and combining changes in remote sensing images, establish a model of the impact of human activities on forest land change; let U(t) represent the amount of land use change at time t, and the impact model of forest land area change can be described as ΔA(t)=θ1U(t)+θ2·R(t)+θ3·G(t)+ζ, where U(t) is the amount of land use change at time t; θ1, θ2, θ3 are coefficients, representing the impact of these factors on forest land change; ζ is the error term.

[0031] As a preferred technical solution for an area measurement method based on land planning, step S4 includes the following specific steps:

[0032] S41. Construct a multivariate ARIMA model with exogenous variables, incorporating meteorological, soil, and topographic exogenous factors. t =c+φ1Y t-1 +…+φ p Y t-p +θ1∈ t-1 +…+θ q ∈ t-q +X t β+∈ t , where Y t Let be the forest area at time t, and c be a constant term, φ1, φ2, ..., φ p The autoregressive coefficients represent the influence of forest area at past p time points on the current forest area, θ1, θ2, ..., θ q X is the moving average coefficient, representing the impact of the error term over the past q time steps on the current forest area. t This is an exogenous variable matrix containing meteorological, topographical, and human activity factors. β represents the coefficients of the exogenous variables, indicating the degree of influence of each exogenous variable on forest area change. t The error term represents random disturbances;

[0033] S42. After training the above model, use the model to predict the forest area; suppose we want to predict the forest area at the next m time points. The following prediction formula is obtained. in Let |t+k| be the predicted forest area at time t+k, where |t+k| is the exogenous variable at time t+k, composed of meteorological and topographic data, ∈ t+k The error term is set as white noise.

[0034] As a preferred technical solution for an area measurement method based on land planning, step S5 includes the following specific steps:

[0035] S51. When the measured area is less than the set threshold, a warning is issued to provide feedback for subsequent treatment; otherwise, no warning is issued when the measured area is not less than the set threshold.

[0036] A land planning-based area measurement system includes a data acquisition module, a data processing module, an image generation module, a data analysis module, a change prediction module, a comparison and early warning module, and a control module. The data acquisition module is used to collect various characteristics of forest land. The data processing module is used to denoise the collected data. The image generation module is used to compare the collected data with historical data to demonstrate the change process. The data analysis module is used to calculate the results of the change data. The change prediction module is used to predict the change trend of forest land area. The comparison and early warning module is used to compare the data change results.

[0037] As a preferred technical solution for an area measurement system based on land planning, the control module is used to control the operation of the data acquisition module, data processing module, image generation module, data analysis module, change prediction module, and comparison and early warning module.

[0038] The beneficial effects of this invention are:

[0039] This invention enables real-time dynamic monitoring of land types such as forest land and farmland using time-series remote sensing image data, generates trend maps of changes, and analyzes models to predict the trend of land area changes. This provides land planners with a reference for dynamic changes, helps predict future land use needs and changes in the ecological environment, and provides data support for the scientific planning and rational use of land resources.

[0040] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0042] Figure 1 This is a flowchart illustrating an area measurement method based on land planning according to the present invention.

[0043] Figure 2 This is a schematic diagram of the framework of an area measurement system based on land planning according to the present invention. Detailed Implementation

[0044] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0045] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0047] Secondly, the present invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not according to the usual scale. Furthermore, the schematic diagrams are merely examples and should not limit the scope of protection of the present invention. In addition, actual fabrication should include three-dimensional spatial dimensions of length, width, and depth.

[0048] Example 1

[0049] Reference Figure 1 This is the first embodiment of the present invention, which provides an area measurement method based on land planning, including the following steps;

[0050] S1. Acquire multi-source data of the land planning area through the acquisition module and store this data in the storage module. Acquire images through drones and collect topographic data of forest land for terrain modeling and vegetation height calculation.

[0051] Furthermore, ground-based meteorological station equipment is deployed in the target area to acquire meteorological data, including real-time precipitation, temperature, wind speed, and humidity data; slope distribution data is acquired through aerial photography terminals; and the acquired forest terrain data, meteorological data, and slope distribution data are stored in the first storage component.

[0052] By acquiring remote sensing imagery, meteorological data, topographic data, and historical land use data, we can gain a comprehensive understanding of the current state of the land, its climate, and topographic features, providing strong data support for subsequent area measurement and trend analysis. Acquiring high-resolution remote sensing imagery and detailed meteorological and topographic data helps reduce errors in measurement and ensures the accuracy and detail of the data.

[0053] S2. Import the acquired multi-source land planning area data into the data processing module for preprocessing, and extract forest land characteristics and regional boundaries;

[0054] Furthermore, points with distinct geometric features are extracted from the image to obtain the image feature point set {P1, P2, ..., P...}. m Each point has a descriptor vector D. i Obtain matching image feature point sets {Q1, Q2, ..., Q} from historical image data. n Each point has a descriptor vector D. j And calculate the feature points P of the captured image. i and historical image feature points Q j The Euclidean distance is calculated using the following formula: Where D i，k and D j，k These are the descriptor vectors D i and D j The k-th component is calculated, and the image feature point P is calculated. i and reference map feature points Q j The cosine similarity is calculated using the formula: S cosine The value range is [-1, 1]. The closer it is to 1, the more similar the directions of the two vectors are. And for P... i Choose its two nearest neighbors Q j and Q k Calculate the Euclidean distance between the two. If the ratio R > Threshold, then Q is considered... j With P i The match is unreliable and should be discarded.

[0055] The preprocessed remote sensing image is used for land surface type classification; each pixel is classified into water body, vegetation, bare land, and building category; the classification results generate a predicted label map, where each pixel represents the corresponding land surface type, and the output formula is y. i =classify(x i for i∈[1,N], x i It is the i-th pixel in the remote sensing image, y i These are the corresponding surface type labels; label categories include water bodies, vegetation, bare land, and buildings;

[0056] Error compensation is applied to the acquired meteorological, topographic, and surface type data. The error correction factor is calculated, and the output formula is as follows: ΔA represents the corrected area, ω i It is a weighting factor, representing the weight of this region, ΔA iIt is the error compensation amount for each region; weight ω i The measurement accuracy is dynamically adjusted according to the characteristics of the region (such as slope, vegetation density, etc.) to ensure consistency in measurement accuracy across different regions.

[0057] Conditional Random Fields (CRFs) are used for boundary refinement. CRFs can optimize classification results by analyzing the dependencies between pixels, reducing classification errors and refining boundaries. Let the pixels in the image be {x1, x2, ..., x...}. N}, with labels {y1, y2, ..., y N The boundary accuracy is optimized by minimizing the following energy function, and the output formula is: Where θ i (y i φ is the energy of a single pixel, representing the difference between the pixel's initial classification and its actual label. ij (y i y j ) is pixels x i With her neighbor x j The interaction term between pixels represents the similarity between pixels; by minimizing this energy function, the boundary region can be optimized, the boundary between different land surface types can be refined, and the area measurement can be made more accurate.

[0058] It can effectively eliminate image distortion and noise, ensuring high-quality data; this is crucial for classification accuracy and error correction in subsequent analysis. By classifying land surface types, it can achieve high-precision identification of different land surface types such as water bodies, vegetation, bare land, and buildings, avoiding errors caused by manual classification. Through refined boundary correction methods, it ensures the accuracy of classification results, especially in complex terrain and diverse land surface types, which helps improve the identification accuracy of ground data. Through error compensation, it can automatically identify and correct systematic errors in the measurement process, especially in complex terrain (such as mountains and hills) or obstructed areas (such as forests and buildings), effectively improving the accuracy of measurement results.

[0059] S3. Generate dynamic change graphs of forest area in real time and analyze the driving factors of change;

[0060] Furthermore, by comparing remote sensing image data at different time points, the change in forest area is detected, and the output formula is ΔA = A new -A old Where ΔA represents the change in forest area, A new A represents the forest area measured at the new time. old This indicates the area of ​​forest land as measured at a previous time.

[0061] A deep learning model is used to extract features and predict changes in image data, generating a change map where each pixel value represents the magnitude of the change. The output formula is y. i =classify(x i for i∈[1,N], where x i For the i-th pixel, y i This is the label for the change in that pixel (0 indicates no change, 1 indicates change);

[0062] By analyzing the relationship between historical meteorological data and forest land change, a meteorological factor model is established to predict forest land change. Let R(t) represent the meteorological driving factor (such as precipitation) at a certain time t. Then, the output formula for the relationship between forest land area change ΔA and meteorological factor·R(t) is ΔA(t)=β1R(t)+β2·ΔA(t-1)+∈, where ΔA(t) is the forest land area change at time t, R(t) is the meteorological factor (such as precipitation, temperature, etc.) at time t; β1 is the coefficient of the meteorological factor, representing the degree of influence of the meteorological factor on forest land change; β2 is the autoregressive coefficient, representing the influence of the previous forest land change on the current change; ∈ is the error term, representing unforeseen factors (such as human activities).

[0063] To analyze the impact of topography and soil factors on forest land change, let S represent soil moisture and G represent slope. The relationship between forest land area change and these factors can be described by the following model: ΔA(t)=γ1S(t)+γ2G(t)+γ3R(t)+δ, where S(t) is the soil moisture at time t; G(t) is the slope at time t; γ1, γ2, and γ3 are the coefficients of the corresponding factors, representing the degree of influence of these factors on forest land change; and δ is the error term.

[0064] Using land use data and combining changes in remote sensing imagery, a model of the impact of human activities on forest land change is established. Let U(t) represent the land use change at time t. The impact model of forest land area change can be described as ΔA(t) = θ1U(t) + θ2·R(t) + θ3·G(t) + ζ, where U(t) is the land use change at time t (e.g., newly added building areas, agricultural areas, etc.); θ1, θ2, and θ3 are coefficients representing the impact of these factors on forest land change; and ζ is the error term.

[0065] By displaying the trend of forest area change through dynamic graphs, heat maps and other methods, the change process is made more intuitive and easier to understand and communicate to decision-makers. Through the generation of analysis reports, the patterns of forest area change, error correction process, trend prediction results and other information can be comprehensively summarized, providing decision-makers with a complete and systematic data report.

[0066] S4. Predict the trend of forest area change;

[0067] Construct a multivariate ARIMA model with exogenous variables, incorporating meteorological, soil, and topographic exogenous factors. t =c+φ1Y t-1 +…+φ p Y t-p +θ1∈ t-1 +…+θ q ∈ t-q +X t β+∈ t , where Y t Let be the forest area at time t, and c be a constant term, φ1, φ2, ..., φ p The autoregressive coefficients represent the influence of forest area at past p time points on the current forest area, θ1, θ2, ..., θ q X is the moving average coefficient, representing the impact of the error term over the past q time steps on the current forest area. t This is an exogenous variable matrix, containing meteorological (e.g., precipitation, temperature), topographic (e.g., slope, altitude), and human activity factors. β represents the coefficients of the exogenous variables, indicating the degree of influence of each exogenous variable on forest area change. t The error term represents random disturbances;

[0068] After training the above model, it is used to predict the forest area; let's say we want to predict the forest area at the next m time points. The following prediction formula is obtained. in Let |t+k| be the predicted forest area at time t+k, where |t+k| is the exogenous variable at time t+k, composed of meteorological and topographic data, ∈ t+k The error term is set as white noise;

[0069] Forest land change prediction plays a vital role in land planning, ecological protection, and environmental management. By predicting forest land change trends, potential problems and opportunities can be identified in advance, providing decision-makers with data support and scientific basis, and helping to achieve sustainable forestry management and land use.

[0070] S5. Generate measurement results and compare them with the threshold value of the change range to issue an early warning;

[0071] When the measured area is less than the set threshold, a warning is issued to provide feedback for subsequent treatment; otherwise, no warning is issued when the measured area is not less than the set threshold.

[0072] Through the visualization and graphical analysis of the report, decision-makers can make land planning decisions more quickly and accurately, effectively promoting the optimal allocation of land resources.

[0073] Example 2

[0074] Reference Figure 2 The diagram illustrates a second embodiment of the present invention: an area measurement system based on land planning. This system includes a data acquisition module, a data processing module, an image generation module, a data analysis module, a change prediction module, a comparison and early warning module, and a control module. The data acquisition module collects various characteristics of forest land to ensure data accuracy. The data processing module denoises the collected data to ensure the accuracy of subsequent analysis results. The image generation module compares the collected data with historical data to demonstrate the change process, allowing decision-makers to intuitively understand the change status. The data analysis module calculates the results of the change data to identify the source of the change. The change prediction module predicts the trend of forest land area changes, which is of great significance for long-term land planning and ecological restoration. The comparison and early warning module compares the data change results to formulate policies for subsequent forest land protection, agricultural development, and ecological restoration. The control module controls the operation of the data acquisition module, data processing module, image generation module, data analysis module, change prediction module, and comparison and early warning module.

[0075] It should be understood that numerous specific implementation decisions can be made during the development of any actual implementation method, and in any engineering or design project. Such development efforts may be complex and time-consuming, but for those of ordinary skill in the art who benefit from this disclosure, the development effort will be a routine work of design, manufacturing, and production without requiring much experimentation.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An area measurement method based on land planning, characterized in that: Includes the following steps; S1. Acquire multi-source data of the land planning area through the acquisition module and store this data in the storage module; S2. Import the acquired multi-source land planning area data into the data processing module for preprocessing, and extract forest land characteristics and regional boundaries; S3. Generate dynamic change graphs of forest area in real time and analyze the driving factors of change; S4. Predict the trend of forest area change; S41. Construct a multivariate ARIMA model with exogenous variables, incorporating meteorological, soil, and topographic exogenous factors. ,in For a moment The area of ​​forest land, For constant terms, The autoregressive coefficient represents the past... The impact of forest area at a given moment on the current forest area. The moving average coefficient represents the past... The impact of the error term at each moment on the current forest area. This is an exogenous variable matrix, containing meteorological, topographical, and human activity factors. The coefficients of the exogenous variables represent the degree of influence of each exogenous variable on the change in forest area. The error term represents random disturbances; S42. After training a multivariate ARIMA model, use the multivariate ARIMA model to predict forest area; suppose we want to predict the future... Forest area at any given moment The following prediction formula is obtained. ,in For a moment The predicted forest area, For a moment The exogenous variables consist of meteorological and topographic data. The error term is set as white noise. S5. Generate measurement results and compare them with the threshold value of the change range to issue an early warning; S51. When the measured area is less than the set threshold, a warning is issued to provide feedback for subsequent treatment; otherwise, no warning is issued when the measured area is not less than the set threshold.

2. The area measurement method based on land planning according to claim 1, characterized in that: S1 includes the following specific steps: S11. Acquire images and collect topographic data of the forest area using drones; S12. Deploy ground-based meteorological station equipment in the target area and acquire meteorological data, including real-time precipitation, temperature, wind speed and humidity data; S13. Obtain slope distribution data through aerial photography terminal; S14. Store the acquired topographic data, meteorological data, and slope distribution data of the forest land into the first storage component.

3. The area measurement method based on land planning according to claim 2, characterized in that: The data preprocessing in S2 includes the following specific steps: S21. Obtain points with obvious geometric features from the images, obtain matching image feature point sets from historical image data, calculate the Euclidean distance between the feature points of the current images and the feature points of the historical images, and calculate the cosine similarity between the image feature points and the feature points of the reference map. S22. Classify the land surface types of the preprocessed remote sensing images; generate a predicted label map from the classification results. S23. Perform error compensation on the acquired meteorological data, topographic data, and surface type data, and calculate the error correction factor.

4. The area measurement method based on land planning according to claim 3, characterized in that: The region boundary processing in S2 includes the following specific steps: S24. Use conditional random fields for boundary correction and optimize boundary accuracy by minimizing the following energy function.

5. The area measurement method based on land planning according to claim 4, characterized in that: The dynamic changes in forest area in S3 include the following specific steps: S31. By comparing remote sensing image data at different time points, the change in forest area is detected, and the output formula is: ,in Indicates changes in forest area, This indicates the forest area measured at the new time. This indicates the area of ​​forest land as measured at a previous time. S32. Feature extraction and change prediction are performed on image data using a deep learning model to generate a change map, where each pixel value represents the magnitude of the change. The output formula is: ,in For the first 1 pixel This is the label for the change in that pixel.

6. The area measurement method based on land planning according to claim 5, characterized in that: The change-driving factor analysis in S3 includes the following specific steps: S33. By analyzing the relationship between historical meteorological data and forest land changes, forest land changes can be predicted. Indicates a certain moment Meteorological driving factors, then forest area changes and meteorological factors The relational output formula is ,in For a moment Changes in forest area, For a moment Meteorological factors; The coefficient represents the degree of influence of meteorological factors on forest land changes; The autoregressive coefficient represents the impact of the previous forest land change on the current change; This is the error term, representing unforeseen factors; S34. Analyze the impact of topography and soil factors on forest land change, and set... Indicates soil moisture. The relationship between slope, forest area changes, and these factors can be described by the following model. in For a moment Soil moisture; For a moment The slope; The coefficients of the corresponding factors represent the degree of influence of these factors on forest land change; This is the error term; S35. Using land use data and combining changes in remote sensing imagery, establish a model of the impact of human activities on forest land change; Indicates time The impact model of land use change and forest area change can be described as follows: ,in For a moment Land use change; The coefficients represent the impact of these factors on forest land change; This is the error term.

Images