Tree age determination method and device for arid and semi-arid region protection forest

Abstract

The invention discloses a tree age determination method and device for a protection forest in an arid and semi-arid region, and relates to the technical field of remote sensing monitoring, and the method comprises the steps: randomly sampling a plurality of trees from the protection forest in the arid and semi-arid region as reference trees; determining a tree age prediction model based on the tree ages, the vegetation indexes and the actually measured growth parameter groups of the plurality of reference trees; acquiring latitude and longitude and an actually measured growth parameter group of the tree to be estimated; based on the longitude and latitude of the to-be-estimated tree, extracting the vegetation index of the to-be-estimated tree from the vegetation index data of the arid and semi-arid region protection forest; and inputting the vegetation index of the to-be-estimated tree and the actually measured growth parameter group of the to-be-estimated tree into the tree age prediction model to obtain a tree age prediction value of the to-be-estimated tree. According to the method, the tree age prediction model is constructed, so that the tree age estimation efficiency and precision of the arid and semi-arid region protection forest are improved.

Description

Technical Field

[0001] The present application relates to the field of remote sensing monitoring technology, and in particular to a method and device for determining the tree age of shelterbelts in arid and semi-arid areas. Background Art

[0002] Windbreaks and sand-fixing forests in arid and semi-arid regions, such as the Northwest Desert and the Loess Plateau, are perennially subject to shifting sand and wind erosion. Rapidly estimating shelterbelt age information not only helps assess stand health but also provides a scientific basis for optimizing shelterbelt management. Current research on shelterbelts, at the macro level, focuses primarily on the role of remote sensing and GIS in shelterbelt monitoring and optimizing shelterbelt grid layout. At the micro level, research focuses primarily on tree species selection and growth characteristics, with less attention paid to identifying individual characteristics, particularly age estimation. Tree height is a key factor in determining tree age and a crucial indicator for identifying shelterbelt characteristics. Traditional methods for measuring tree age include tree ring analysis and growth cone sampling. These methods primarily rely on analyzing the number of growth rings in tree cross-sections and using growth cones to extract cylindrical samples from trees. Determining age by counting the number of growth rings is not only harmful to the tree, but also complex and technically demanding, making them unsuitable for living trees. With the development of remote sensing technology and statistics, the former has the characteristics of non-destructiveness, wide coverage, and convenient data acquisition, while the latter can integrate multiple influencing factors and improve analysis accuracy.

[0003] Currently, tree age estimation methods focus on three main areas: first, using high-resolution remote sensing imagery to identify tree canopy characteristics through image processing techniques and combine them with growth models to estimate tree age; second, using LiDAR to obtain three-dimensional structural information about trees and combine it with growth models to estimate tree age; and third, combining traditional measurement methods with remote sensing technology to conduct comprehensive analysis of multi-source data to improve the accuracy of tree age measurement. Specific applications of remote sensing technology and statistical methods for estimating tree age information are as follows. LiDAR can obtain information such as tree height, canopy structure, and leaf area index, and can be combined with growth models to estimate tree age. While LiDAR offers advantages such as high accuracy and the ability to directly obtain three-dimensional structural information, it also suffers from high data acquisition costs, limited coverage, and complex data processing. SAR (Radio Frequency Assisted Ranging) uses polarization information and interferometry to analyze tree height changes and indirectly estimate tree age. Its advantage is its ability to penetrate cloud cover, making it suitable for tropical and cloudy regions. However, data processing is complex, making it difficult to directly infer tree age. Random forests (RF) and support vector machines (SVM) can combine remote sensing data with ground-based measurements to develop tree age prediction models using machine learning. These methods are suitable for high-dimensional data, can handle nonlinear relationships, and improve estimation accuracy. However, they require a large amount of training data, are computationally complex, and have difficulty accounting for variable influences. Bayesian regression, on the other hand, can incorporate prior knowledge into tree age estimation, improving uncertainty analysis capabilities. It is suitable for small sample data and can provide an estimated uncertainty range. However, its disadvantages are computational complexity and reliance on a reasonable prior distribution. In summary, existing remote sensing and statistical methods each have their advantages in forest age estimation. Remote sensing provides large-scale, non-destructive monitoring capabilities, while statistical methods can quantify variable influences and improve model interpretability. However, both methods face challenges in model practicality and are limited by data processing difficulties. Therefore, large-scale application of these methods for tree age estimation in arid and semi-arid regions is challenging, and their widespread application in the protection and monitoring of windbreak forests is limited. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for determining the age of shelterbelts in arid and semi-arid areas, which can improve the efficiency and accuracy of tree age estimation of shelterbelts in arid and semi-arid areas.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for determining the age of shelterbelts in arid and semi-arid areas, comprising:

[0007] Obtain remote sensing images of shelterbelts in arid and semi-arid areas;

[0008] Extracting vegetation index data of shelterbelts in arid and semi-arid areas based on the remote sensing images;

[0009] Several trees were randomly sampled from shelterbelts in arid and semi-arid areas as benchmark trees;

[0010] Obtaining the ages and measured growth parameter sets of multiple benchmark trees;

[0011] Extract the vegetation index of each benchmark tree from the vegetation index data of shelterbelts in arid and semi-arid areas based on the latitude and longitude of each benchmark tree;

[0012] Constructing a regression equation with the vegetation index and the measured growth parameter group as independent variables and tree age as a dependent variable;

[0013] The tree age prediction model was obtained by fitting the coefficients of the regression equation using the tree age, vegetation index and measured growth parameter groups of multiple benchmark trees;

[0014] Any tree in the shelterbelt of arid and semi-arid areas is taken as the tree to be estimated;

[0015] Obtain the latitude and longitude of the trees to be estimated and a group of measured growth parameters;

[0016] Extracting the vegetation index of the trees to be estimated from the vegetation index data of shelterbelts in arid and semi-arid areas based on the latitude and longitude of the trees to be estimated;

[0017] The vegetation index of the tree to be estimated and the measured growth parameter group of the tree to be estimated are input into the tree age prediction model to obtain the predicted value of the tree age to be estimated.

[0018] Optionally, the spatial resolution of the remote sensing image is 100 meters.

[0019] Optionally, extracting vegetation index data of shelterbelts in arid and semi-arid areas based on the remote sensing image includes:

[0020] Preprocessing the remote sensing image to obtain a preprocessed remote sensing image; the preprocessing includes radiometric calibration and atmospheric correction;

[0021] Extracting initial vegetation index data of shelterbelts in arid and semi-arid areas based on the remote sensing images;

[0022] The initial vegetation index data were normalized to obtain the vegetation index data of shelterbelts in arid and semi-arid areas.

[0023] Optionally, the preprocessing tool is: ENVI Classic5.3;

[0024] The tool for extracting the initial vegetation index data of shelterbelts in arid and semi-arid areas is: Variables to Bands Painings in ENVI Classic5.3.

[0025] Optionally, the measured growth parameter group includes: tree height, diameter at breast height, crown width and crown height.

[0026] Optionally, the tree age prediction model is:

[0027] y=1.272+0.179×x1+1.402×x2+0.254×x3+0.133×x4+0.057×x5;

[0028] Among them, y is the tree age, x1 is the crown height, x2 is the vegetation index, x3 is the crown width, x4 is the tree height, and x5 is the breast height diameter.

[0029] Optionally, the latitude and longitude of the benchmark trees and the trees to be estimated are obtained by importing remote sensing images into ArcGIS 10.6.

[0030] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for determining the tree age of protective forests in arid and semi-arid areas.

[0031] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for determining the tree age of protective forests in arid and semi-arid areas.

[0032] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above-mentioned method for determining the tree age of protective forests in arid and semi-arid areas.

[0033] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0034] The present application provides a method and device for determining the age of shelterbelts in arid and semi-arid areas, which matches tree age, tree measured data and normalized vegetation index (NDVI) data according to the latitude and longitude of the sample points; establishes a regression equation based on the matching results; obtains a remote sensing image containing the measured data of trees in shelterbelts in arid and semi-arid areas and normalized vegetation index (NDVI) data; calculates the normalized vegetation index (NDVI) data from the remote sensing image; and calculates the tree age based on the regression equation, the measured data of trees and the normalized vegetation index (NDVI) data calculated from the remote sensing image. The present invention explores a new way to estimate the age of shelterbelts in arid and semi-arid areas, namely, using the measured data of trees and the normalized vegetation index (NDVI) to establish a linear regression relationship with the tree age to estimate the age information of shelterbelts. The present invention combines geographical and statistical technical methods to provide a method for quickly estimating the age of shelterbelts in arid and semi-arid areas, which can help researchers and managers understand the growth status and health level of vegetation. Through the analysis of remote sensing data, efficient and accurate vegetation monitoring can be achieved, providing a scientific basis for ecological protection and resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 This is a flow chart of a method for determining the tree age of a shelterbelt in an arid or semi-arid area in one embodiment of the present application;

[0037] Figure 2 This is a schematic diagram of a method for determining the tree age of a shelterbelt in an arid or semi-arid area in one embodiment of the present application;

[0038] Figure 3 This is a schematic diagram of remote sensing image preprocessing in one embodiment of the present application;

[0039] Figure 4 Schematic diagram of false color images of green, red, and near-infrared bands in one embodiment of the present application;

[0040] Figure 5 This is a schematic diagram of calculating NDVI in one embodiment of the present application;

[0041] Figure 6 A schematic diagram of loading coordinate points with longitude and latitude in one embodiment of the present application;

[0042] Figure 7Schematic diagram of extracting pixel values in NDVI images according to coordinate points in one embodiment of the present application;

[0043] Figure 8 The frequency and standardized residual histogram of the regression model in one embodiment of the present application;

[0044] Figure 9 This is a normal PP plot of the standardized residuals of the regression model in one embodiment of the present application;

[0045] Figure 10 This is a scatter plot of the standardized residuals and predicted values of the regression model in one embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0048] In an exemplary embodiment, Figure 1 As shown, a method for determining the tree age of a shelterbelt in arid and semi-arid areas is provided, comprising:

[0049] Step 101: Obtain a remote sensing image of a shelterbelt in an arid or semi-arid area. The spatial resolution of the remote sensing image is 100 meters.

[0050] Step 102: Extracting vegetation index data for shelterbelts in arid and semi-arid areas based on remote sensing images. Extracting vegetation index data for shelterbelts in arid and semi-arid areas based on remote sensing images includes: preprocessing the remote sensing images to obtain preprocessed remote sensing images. The preprocessing includes radiometric calibration and atmospheric correction. Extracting initial vegetation index data for shelterbelts in arid and semi-arid areas based on the remote sensing images. Normalizing the initial vegetation index data to obtain vegetation index data for shelterbelts in arid and semi-arid areas. The preprocessing tool is: ENVI Classic 5.3. The tool for extracting initial vegetation index data for shelterbelts in arid and semi-arid areas is: Variables to Bands Painings in ENVI Classic 5.3.

[0051] Step 103: Randomly sample multiple trees from the shelterbelt in the arid and semi-arid areas as benchmark trees.

[0052] Step 104: Obtain the tree ages and measured growth parameter groups of multiple benchmark trees. The measured growth parameter groups include: tree height, diameter at breast height, crown width, and crown height.

[0053] Step 105: extracting the vegetation index of each benchmark tree from the vegetation index data of the shelterbelt in arid and semi-arid areas based on the latitude and longitude of each benchmark tree.

[0054] Step 106: constructing a regression equation with the vegetation index and the measured growth parameter group as independent variables and tree age as the dependent variable;

[0055] Step 107: Using the tree ages, vegetation indices, and measured growth parameter groups of multiple benchmark trees, the coefficients of the regression equation are fitted to obtain a tree age prediction model. The tree age prediction model is:

[0056] y=1.272+0.179×x1+1.402×x2+0.254×x3+0.133×x4+0.057×x5.

[0057] Among them, y is the tree age, x1 is the crown height, x2 is the vegetation index, x3 is the crown width, x4 is the tree height, and x5 is the breast height diameter.

[0058] Step 108: Obtain any tree in the shelterbelt in the arid or semi-arid area as the tree to be estimated.

[0059] Step 109: Obtain the latitude and longitude of the trees to be estimated and the measured growth parameter set. The latitude and longitude of the benchmark trees and the trees to be estimated are obtained by importing remote sensing images into ArcGIS 10.6.

[0060] Step 1010: extracting the vegetation index of the tree to be estimated from the vegetation index data of the shelterbelt in arid and semi-arid areas based on the latitude and longitude of the tree to be estimated.

[0061] Step 1011: Input the vegetation index of the tree to be estimated and the measured growth parameter group of the tree to be estimated into the tree age prediction model to obtain the predicted value of the tree age to be estimated.

[0062] Shelterbelts in arid and semi-arid areas have unique vegetation characteristics, and existing technologies are not yet able to meet the needs of quickly estimating tree age information for shelterbelts in such areas. This invention combines geographical and statistical techniques to provide a method for quickly estimating tree age for shelterbelts in arid and semi-arid areas, which can help researchers and managers understand the growth status and health level of vegetation. Through the analysis of remote sensing data, efficient and accurate vegetation monitoring can be achieved, providing a scientific basis for ecological protection and resource management. Figure 2 , methods for determining the tree age of shelterbelts in arid and semi-arid areas include:

[0063] Step 1) Obtain the measured data of the shelterbelt trees in the arid and semi-arid areas and the remote sensing image of the Normalized Difference Vegetation Index (NDVI); the remote sensing image is a high-resolution remote sensing image, and the appropriate band is selected. Figure 3 and Figure 4 Import the downloaded remote sensing image into ENVI Classic 5.3 to perform radiometric calibration and atmospheric correction. Image atmospheric correction uses the "Radiometric Correction" function in the "Image Analysis" tool and select the corresponding image for correction.

[0064] Step 2) extracting the net normalized difference vegetation index (NDVI) data of the shelterbelt in the arid and semi-arid areas from the remote sensing image; Figure 5 Extracting the normalized vegetation index (NDVI) data from the obtained data specifically includes using the Variables to Bands Painings tool in ENVIClassic5.3 and the formula NDVI=(b4-b3) / (b4+b3), where b3 is the red band and b4 is the near-red band, to obtain the normalized vegetation index (NDVI) data of the image.

[0065] like Figure 6 The processed image was imported into ArcGIS 10.6, and the latitude and longitude coordinates of the measured trees were loaded and projected. The projected coordinate system was GCS_WGS_1984.

[0066] Step 3) Match the tree age and tree measured data and the Normalized Difference Vegetation Index (NDVI) data by the latitude and longitude of the sample points; establish the regression equation based on the matching results, y = a0 + a1 × x1 + a2 × x2 + ... + a n ×x n

[0067] Among them, y is the dependent variable of tree age, x i (i=1,2,...,n) are related independent variables, including measured data and normalized difference vegetation index (NDVI), a i (i=1,2,...,n) is the fitting coefficient;

[0068] Step 4) Calculate the tree age based on the obtained regression equation, the measured tree data, and the Normalized Difference Vegetation Index (NDVI) data extracted from the remote sensing image.

[0069] The method for matching tree age with measured tree data and normalized vegetation index (NDVI) according to the latitude and longitude of the sampling points is as follows: locate the trees, the coordinate system must be consistent with the grid, use the GIS extraction tool to extract the NDVI value of the marked location, and export it as a CSV table. Measure the tree height, diameter at breast height, crown width and crown height of the shelterbelt in the arid and semi-arid areas, match the tree age with measured tree data and normalized vegetation index (NDVI) according to the latitude and longitude information of the sampling points, as shown in the following example: Figure 7 . Matching tree age and tree measured data and normalized difference vegetation index (NDVI) is carried out every year with a one-year cycle. In ArcGIS10.6, the latitude and longitude data of the sample points are imported and converted into point files in .shp format. Then, the ExtractValues to Points tool is used to extract the NDVI values to the corresponding sample point locations. The extracted results are exported as a text file and saved in Excel format. Subsequently, the Excel file is imported into IBM SPSS Statistics 27, and the regression equation is finally obtained through multiple linear regression analysis.

[0070] Through field surveys, field data was measured for trees in shelterbelts in arid and semi-arid regions. This data included tree height, diameter at breast height (DBH), crown width, crown height, and height below the first limb. Specifically, tree height, crown height, and height below the first limb were measured using a stadiometer and a tape measure, and the DBH of the trees in the shelterbelts in arid and semi-arid regions was measured using a caliper. Tree age data was provided by local forestry farms. Remote sensing images were downloaded and preprocessed. High-resolution remote sensing images were selected, and appropriate bands were selected. Data were downloaded from the Copernicus Open Access Hub (https: / / scihub.copernicus.eu / dhus / # / home) with a spatial resolution of 100 m. Preprocessing of the images involved importing them into ENVI Classic 5.3 for radiometric calibration and atmospheric correction (select Raster > Radiometric Correction > Radiance to Reflectance; Raster > Radiometric Correction > QUAC). Next, the normalized vegetation index (NDVI) data of the obtained image was extracted, specifically using the Variables to Bands Painings tool in ENVI Classic 5.3 and the formula NDVI = (b4-b3) / (b4+b3) to obtain the normalized vegetation index (NDVI) data of the image. The image was imported into ArcGIS 10.6, and the latitude and longitude coordinates of the measured trees were loaded and projected (the operation path was Data Management Tools—Projections and Transformations—Raster). The projection coordinate system was GCS_WGS_1984. According to the latitude and longitude of the sample points, the tree age and the measured tree data and the normalized vegetation index (NDVI) were matched. Specifically: Import the Excel spreadsheet containing the latitude and longitude of the sample points and the measured tree data into ArcGIS 10.6, select File—Add Data—Add XY Data, set the X Field to longitude and the Y Field to latitude, make sure to select the correct coordinate system GCS_WGS_1984, click OK, and the coordinate points will be added to the map as a layer. Next, use the Extract Values to Points tool (Spatial Analyst Tools—Extraction—Extract Values to Points) to extract the Normalized Difference Vegetation Index (NDVI) to the sample points, export it as a text file, and save it as an Excel file.The Excel file was imported into IBM SPSS Statistic 27. Multiple linear regression analysis was performed on the tree age data, the measured tree data, and the obtained Normalized Difference Vegetation Index (NDVI). The fitting equation was: y = 1.272 + 0.179 × x1 + 1.402 × x2 + 0.254 × x3 + 0.133 × x4 + 0.057 × x5. The fitting results are shown in Tables 1 to 5. The regression model had R = 0.908, R² = 0.825, adjusted R² = 0.819, and F = 138.320, with significance < 0.001. This indicates that the independent variables in this model have strong explanatory power for the dependent variable and can accurately estimate tree age. The variance inflation factors (VIFs) of this model were all less than 5, indicating that the model does not have multicollinearity. Standardized residual histograms ( ) are shown. Figure 8 ) and normal PP plot ( Figure 9 ) shows that this model meets the normality condition. Standardized residual scatter plot ( Figure 10 ) indicates that this model meets the homogeneity of variance condition.

[0071] Table 1 Summary of regression models

[0072]

[0073] Table 2 Regression model ANOVA table

[0074]

[0075] Table 3 Regression model coefficients

[0076]

[0077] Table 4 Correlation table of regression model coefficients

[0078]

[0079] Table 5 Residual statistics of regression model

[0080]

[0081] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for determining the age of a shelterbelt in an arid or semi-arid area is implemented.

[0082] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0083] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0084] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0085] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0086] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0087] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for determining the age of shelterbelts in arid and semi-arid areas, characterized in that: include: Obtain remote sensing images of shelterbelts in arid and semi-arid areas; Extracting vegetation index data of shelterbelts in arid and semi-arid areas based on the remote sensing images; Several trees were randomly sampled from shelterbelts in arid and semi-arid areas as benchmark trees; Obtaining the ages and measured growth parameter sets of multiple benchmark trees; Extract the vegetation index of each benchmark tree from the vegetation index data of shelterbelts in arid and semi-arid areas based on the latitude and longitude of each benchmark tree; Constructing a regression equation with the vegetation index and the measured growth parameter group as independent variables and tree age as a dependent variable; The tree age prediction model was obtained by fitting the coefficients of the regression equation using the tree age, vegetation index and measured growth parameter groups of multiple benchmark trees; Any tree in the shelterbelt of arid and semi-arid areas is taken as the tree to be estimated; Obtain the latitude and longitude of the trees to be estimated and a group of measured growth parameters; Extracting the vegetation index of the trees to be estimated from the vegetation index data of shelterbelts in arid and semi-arid areas based on the latitude and longitude of the trees to be estimated; The vegetation index of the tree to be estimated and the measured growth parameter group of the tree to be estimated are input into the tree age prediction model to obtain the predicted value of the tree age to be estimated.

2. The method for determining the tree age of a shelterbelt in arid and semi-arid areas according to claim 1, characterized in that: The spatial resolution of the remote sensing image is 100 meters.

3. The method for determining the tree age of a shelterbelt in arid and semi-arid areas according to claim 1, characterized in that: Extracting vegetation index data of shelterbelts in arid and semi-arid areas based on the remote sensing image, including: Preprocessing the remote sensing image to obtain a preprocessed remote sensing image; the preprocessing includes radiometric calibration and atmospheric correction; Extracting initial vegetation index data of shelterbelts in arid and semi-arid areas based on the remote sensing images; The initial vegetation index data were normalized to obtain the vegetation index data of shelterbelts in arid and semi-arid areas.

4. The method for determining the tree age of a shelterbelt in arid and semi-arid areas according to claim 3, characterized in that: The preprocessing tool is: ENVI Classic5.3; The tool for extracting the initial vegetation index data of shelterbelts in arid and semi-arid areas is: Variables to Bands Painings in ENVI Classic5.

3.

5. The method for determining the tree age of a shelterbelt in arid and semi-arid areas according to claim 1, characterized in that: The measured growth parameter group includes: tree height, diameter at breast height, crown width and crown height.

6. The method for determining the tree age of a shelterbelt in arid and semi-arid areas according to claim 1, characterized in that: The tree age prediction model is: y=1.272+0.179×x1+1.402×x2+0.254×x3+0.133×x4+0.057×x5; Among them, y is the tree age, x1 is the crown height, x2 is the vegetation index, x3 is the crown width, x4 is the tree height, and x5 is the breast height diameter.

7. The method for determining the tree age of a shelterbelt in arid and semi-arid areas according to claim 1, wherein: The latitude and longitude of the benchmark trees and the trees to be estimated were obtained by importing remote sensing images into ArcGIS 10.

6.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for determining the tree age of a shelterbelt in arid and semi-arid areas according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the tree age of a shelterbelt in arid and semi-arid areas according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining the tree age of a shelterbelt in arid and semi-arid areas according to any one of claims 1 to 7 is implemented.

Images