Mangrove forest monitoring sample plot sampling method, device, computer equipment and storage medium

Abstract

The present application relates to the technical field of mangrove ecological analysis, and particularly relates to a mangrove monitoring sample plot sampling method and device and computer equipment, ecological index calculation is performed on each mangrove candidate patch of each time phase, a multi-index feature system is constructed, hierarchical cluster analysis is introduced, sample plot objective layering and automatic grouping of the mangrove patches of multiple time phases are realized, subjectivity in the sample plot selection process is significantly reduced, and the accuracy, stability and efficiency of the mangrove monitoring sample plot sampling are improved.

Description

Technical Field

[0001] This invention relates to the field of mangrove ecological analysis technology, and in particular to a mangrove monitoring plot sampling method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Mangrove ecological surveys are a crucial foundation for coastal ecological protection and management, and the rationality of sample plot selection directly affects the accuracy and representativeness of ecological assessment results. Current sample plot layouts largely rely on human experience, typically based on administrative divisions or typical areas, lacking unified and objective quantitative standards. This easily leads to uneven spatial distribution and makes it difficult to comprehensively reflect ecological differences at the regional scale.

[0003] Remote sensing technology provides crucial data support for monitoring the distribution and changes of mangroves, but its application in sample plot placement decisions remains limited, and a systematic sample plot selection method tailored to ecological survey needs has yet to be established. With the survey scope continuously expanding, traditional experience-based sampling methods struggle to balance differences in ecological types, spatial heterogeneity, and long-term monitoring requirements. Summary of the Invention

[0004] Based on this, the purpose of this invention is to provide a method, apparatus, computer equipment, and storage medium for sampling mangrove monitoring plots. This method calculates ecological indicators for each candidate mangrove patch at different time phases, constructs a multi-indicator feature system, and introduces hierarchical clustering analysis to achieve objective stratification and automatic grouping of mangrove patches at multiple time phases. This significantly reduces the subjectivity in the plot selection process and improves the accuracy, stability, and efficiency of mangrove monitoring plot sampling.

[0005] In a first aspect, embodiments of this application provide a sampling method for mangrove monitoring plots, comprising the following steps:

[0006] Obtain multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological correlation data; Based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, mangrove candidate patches are constructed to obtain several mangrove candidate patches for each temporal phase. Based on the mangrove ecological association data, ecological indicators are calculated for each mangrove candidate patch in each time phase, and ecological feature vectors for each mangrove candidate patch in each time phase are constructed. Hierarchical clustering and ecological category stratification are performed based on the ecological feature vectors of each mangrove candidate patch in the same time phase to obtain a set of mangrove patches of several ecological categories in each time phase, wherein the set of mangrove patches includes several mangrove candidate patches of the corresponding ecological category. The number of sample plots is calculated based on the mangrove patch sets of each ecological category in each time phase, and the number of sample plots of each ecological category in each time phase is obtained. Based on the mangrove patch sets of each ecological category in the same time phase and the corresponding number of sample plots of each ecological category, sample plots within each category are screened to obtain several mangrove target patches of each ecological category in each time phase, which are used as the sampling results of mangrove monitoring sample plots.

[0007] Secondly, embodiments of this application provide a mangrove monitoring plot sampling device, comprising: The data acquisition module is used to acquire multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological association data; The patch construction module is used to construct mangrove candidate patches based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, and obtain several mangrove candidate patches for each temporal phase. The index calculation module is used to calculate the ecological index of each mangrove candidate patch in each time phase based on the mangrove ecological association data, and to construct the ecological feature vector of each mangrove candidate patch in each time phase. The category identification module is used to perform hierarchical clustering and ecological category stratification based on the ecological feature vectors of each mangrove candidate patch in the same time phase, to obtain a set of mangrove patches of several ecological categories in each time phase, wherein the set of mangrove patches includes several mangrove candidate patches of the corresponding ecological category. The sample plot selection module is used to calculate the number of sample plots based on the mangrove patch sets of each ecological category in each time phase, and obtain the number of sample plots of each ecological category in each time phase; and to select sample plots within each category based on the mangrove patch sets of each ecological category in the same time phase and the corresponding number of sample plots in each ecological category, so as to obtain several mangrove target patches of each ecological category in each time phase, which are used as the sampling results of mangrove monitoring sample plots.

[0008] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, it implements the steps of the mangrove monitoring plot sampling method as described in the first aspect.

[0009] Fourthly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the steps of the mangrove monitoring plot sampling method as described in the first aspect.

[0010] In this application embodiment, a mangrove monitoring plot sampling method, device, computer equipment and storage medium are provided. Ecological indicators are calculated for each mangrove candidate patch in each time phase, a multi-indicator feature system is constructed and hierarchical cluster analysis is introduced to realize objective stratification and automatic grouping of mangrove patches in multiple time phases. This significantly reduces the subjectivity in the plot selection process and improves the accuracy, stability and efficiency of mangrove monitoring plot sampling.

[0011] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0012] Figure 1 A schematic flowchart illustrating a mangrove monitoring plot sampling method provided in one embodiment of this application; Figure 2 This is a flowchart illustrating step S2 of a mangrove monitoring plot sampling method provided in one embodiment of this application. Figure 3 This is a flowchart illustrating step S3 of a mangrove monitoring plot sampling method provided in one embodiment of this application. Figure 4 This is a flowchart illustrating step S4 of a mangrove monitoring plot sampling method provided in one embodiment of this application. Figure 5 This is a flowchart illustrating step S5 of a mangrove monitoring plot sampling method provided in one embodiment of this application. Figure 6 This is a flowchart illustrating step S51 of a mangrove monitoring plot sampling method provided in one embodiment of this application; Figure 7 This is a schematic diagram of the mangrove monitoring plot sampling device provided in one embodiment of this application; Figure 8 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation

[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0014] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0015] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0016] Please see Figure 1 , Figure 1 The following is a flowchart illustrating a mangrove monitoring plot sampling method provided in one embodiment of this application. The method includes the following steps: S1: Obtain multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological association data.

[0017] The main body executing the mangrove monitoring plot sampling method is the sampling equipment (hereinafter referred to as the sampling equipment) of the mangrove monitoring plot sampling method. In an optional embodiment, the sampling equipment can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0018] In this embodiment, the sampling device obtains multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological association data. The mangrove ecological association data includes mangrove distribution vector data, topographic and tidal flat elevation data, flood frequency statistics, meteorological and environmental data (such as annual average temperature and annual precipitation), and spatial distribution data of human activities (such as roads, settlements, shoreline development intensity, and nature reserve boundaries).

[0019] In an optional embodiment, the sampling device performs unified preprocessing on the multi-temporal satellite remote sensing image data, including atmospheric correction, geometric correction, cloud and cloud shadow removal, as well as image resampling and spatial cropping, to improve the accuracy of feature extraction.

[0020] S2: Based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, construct mangrove candidate patches to obtain several mangrove candidate patches for each temporal phase.

[0021] In this embodiment, the sampling device constructs mangrove candidate patches based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, and obtains several mangrove candidate patches for each temporal phase.

[0022] Please see Figure 2 , Figure 2 The flowchart of step S2 in the mangrove monitoring plot sampling method provided in one embodiment of this application includes steps S21 to S23, as follows: S21: Based on the mangrove ecological association data, feature extraction is performed on all pixels of the satellite remote sensing images of each time phase in the multi-temporal satellite remote sensing image data to obtain the feature extraction dataset of each time phase.

[0023] In this embodiment, the sampling device extracts features from all pixels of satellite remote sensing images of each time phase in the multi-temporal satellite remote sensing image data based on the mangrove ecological association data, and obtains feature extraction datasets for each time phase. The multi-dimensional feature datasets include feature extraction data of each pixel, and the feature extraction data includes multispectral bands and terrain features.

[0024] S22: Input the multi-temporal satellite remote sensing image data and the multi-dimensional feature datasets of each temporal phase into the pre-trained mangrove distribution mask generation model to generate mangrove distribution masks and obtain mangrove distribution mask data for each temporal phase.

[0025] The pre-trained mangrove distribution mask generation model adopts a random forest model. In this embodiment, the sampling device inputs the multi-temporal satellite remote sensing image data and the multi-dimensional feature datasets of each temporal phase into the pre-trained mangrove distribution mask generation model to generate mangrove distribution masks and obtain mangrove distribution mask data for each temporal phase.

[0026] S23: Based on the mangrove distribution mask data of each time phase, perform vectorization and connected component analysis to obtain several mangrove candidate patches for each time phase.

[0027] In this embodiment, the sampling device performs vectorization and connected component analysis on the mangrove distribution mask data of each time phase to obtain several mangrove candidate patches of each time phase.

[0028] Specifically, the sampling device performs post-processing on the mangrove distribution mask data for each time phase, including morphological denoising, hole filling, boundary smoothing, and removal of isolated misclassified patches. The sampling device vectorizes the mangrove distribution mask data of the post-processed monkeys for each time phase and performs connected component analysis to obtain several candidate mangrove patches for each time phase. The sampling device then processes each candidate mangrove patch, deleting small patches with an area less than 100 m², repairing boundary self-intersections and gaps, and extracting center point and boundary information.

[0029] S3: Based on the mangrove ecological association data, calculate the ecological indicators for each mangrove candidate patch in each time phase, and construct the ecological feature vector of each mangrove candidate patch in each time phase.

[0030] In this embodiment, the sampling device calculates ecological indicators for each mangrove candidate patch at each time phase based on the mangrove ecological association data, and constructs an ecological feature vector for each mangrove candidate patch at each time phase. The ecological feature vector includes several indicators, including habitat status indicators, patch structure indicators, area dynamic change indicators, and environmental status indicators.

[0031] Please see Figure 3 , Figure 3 The flowchart of step S3 in the mangrove monitoring plot sampling method provided in one embodiment of this application includes steps S31 to S34, as follows: S31: Based on the spectral data in the mangrove ecological association data and the preset average normalized vegetation index (ANOVA) calculation algorithm, the ANOVA is calculated for each mangrove candidate patch in each time phase to obtain the ANOVA for each mangrove candidate patch in each time phase, which is used as the habitat status indicator.

[0032] In this embodiment, the sampling device calculates the average normalized vegetation index (ANOVA) for each mangrove candidate patch at each time phase based on the spectral data in the mangrove ecological association data and a preset ANOVA calculation algorithm. This ANOVA is used as the habitat status indicator. The spectral data includes the near-infrared reflectance and red reflectance of each pixel in each mangrove candidate patch. The ANOVA calculation algorithm is as follows:

[0033] In the formula, For the first i The average normalized vegetation index of the candidate mangrove patches For the first i The number of pixels in each mangrove candidate patch. For the first i The first mangrove candidate patch j Near-infrared reflectance per pixel, For the first i The first mangrove candidate patch j Red light band reflectance of each pixel; S32: Based on the area data in the mangrove ecological association data and the preset patch structure index calculation algorithm, the patch structure index of each mangrove candidate patch in each time phase is calculated to obtain the patch structure index of each mangrove candidate patch in each time phase.

[0034] In this embodiment, the sampling device calculates the patch structure index for each candidate mangrove patch at each time phase based on the area data in the mangrove ecological association data and a preset patch structure index calculation algorithm, thereby obtaining the patch structure index for each candidate mangrove patch at each time phase. The patch structure index includes a shape index and a boundary density. The patch structure index calculation algorithm is as follows:

[0035]

[0036] In the formula, For the first i Shape index of mangrove candidate patches For the first i Area data for candidate mangrove patches, For the first i One of the candidate mangrove patches, For the first i Boundary density of candidate mangrove patches.

[0037] S33: Based on the area data in the mangrove ecological association data and the preset area dynamic change index calculation algorithm, calculate the area dynamic change index of each mangrove candidate patch in each time phase to obtain the area dynamic change index of each mangrove candidate patch in each time phase.

[0038] In this embodiment, the sampling device calculates the area dynamic change index for each mangrove candidate patch at each time phase based on the area data in the mangrove ecological association data and a preset area dynamic change index calculation algorithm, thereby obtaining the area dynamic change index for each mangrove candidate patch at each time phase. The area dynamic change index calculation algorithm is as follows:

[0039] In the formula, For the first iDynamic indicators of the area change of individual mangrove candidate patches The time interval between phases, For phase The i The patch area of ​​each mangrove candidate patch, For phase The i Boundary density of candidate mangrove patches.

[0040] S34: Obtain environmental status indicators for each mangrove candidate patch at each time phase; combine the habitat status indicators, patch structure indicators, area dynamic change indicators, and environmental status indicators of each mangrove candidate patch at the same time phase to construct the ecological feature vector of each mangrove candidate patch at each time phase.

[0041] In this embodiment, the sampling device obtains environmental status indicators for each mangrove candidate patch at each time phase, wherein the environmental status indicators include patch tidal flat elevation, flooding frequency, and distance from the sea.

[0042] The sampling device splices together the habitat status indicators, patch structure indicators, area dynamic change indicators, and environmental status indicators of each mangrove candidate patch in the same time phase to construct the ecological feature vector of each mangrove candidate patch in each time phase.

[0043] S4: Perform hierarchical clustering and ecological category stratification based on the ecological feature vectors of each mangrove candidate patch in the same time phase to obtain a set of mangrove patches of several ecological categories in each time phase.

[0044] In this embodiment, the sampling device performs hierarchical clustering and ecological category stratification based on the ecological feature vectors of each mangrove candidate patch in the same time phase to obtain a set of mangrove patches of several ecological categories in each time phase, wherein the set of mangrove patches includes several mangrove candidate patches of the corresponding ecological category.

[0045] Please see Figure 4 , Figure 4 The flowchart of step S4 in the mangrove monitoring plot sampling method provided in one embodiment of this application includes steps S41 to S44, as follows: S41: Standardize the ecological feature vectors of each mangrove candidate patch to obtain the standardized ecological feature vectors of each mangrove candidate patch.

[0046] In this embodiment, the sampling device standardizes the ecological feature vectors of each mangrove candidate patch to obtain the standardized ecological feature vectors of each mangrove candidate patch, thereby eliminating the differences in the dimensions of different indicators.

[0047] S42: Based on the ecological feature vectors of each mangrove candidate patch after standardization and the preset distance calculation algorithm, perform distance calculation to construct a distance matrix of mangrove candidate patches; treat each mangrove candidate patch as an independent cluster, and iteratively merge the two closest mangrove candidate patches according to the distance matrix of mangrove candidate patches to obtain a set of mangrove candidate patches.

[0048] In this embodiment, the sampling device calculates distances based on the standardized ecological feature vectors of each mangrove candidate patch and a preset distance calculation algorithm to construct a mangrove candidate patch distance matrix. The mangrove candidate patch distance matrix includes the distances between each mangrove candidate patch. The distance calculation algorithm is as follows:

[0049] In the formula, For the first i One mangrove candidate patch and the first j The distance between candidate mangrove patches This represents the number of indicators in the ecological feature vector. For the first n The weight parameters of each indicator For the standardized processing of the first i In the ecological feature vector of the mangrove candidate patches, the first... n The value of each indicator, For the standardized processing of the first j In the ecological feature vector of the mangrove candidate patches, the first... n The value of each indicator.

[0050] The sampling device treats each of the mangrove candidate patches as an independent cluster, and iteratively merges the two closest mangrove candidate patches according to the distance matrix of the mangrove candidate patches to obtain a set of mangrove candidate patches, wherein the set of mangrove candidate patches includes several mangrove candidate patches.

[0051] S43: Using the set of mangrove candidate patches as the input set for the first iteration, and based on the several mangrove candidate patches in the input set and the preset intra-class sum of squares increment calculation algorithm, obtain the intra-class sum of squares increment of each mangrove candidate patch; based on the intra-class sum of squares increment of each mangrove candidate patch, merge the two mangrove candidate patches with the smallest sum of squares to obtain the output set of the current iteration.

[0052] In this embodiment, the sampling device uses the set of mangrove candidate patches as the input set for the first iteration. Based on several mangrove candidate patches in the input set and a preset algorithm for calculating the intra-class sum of squares increment, it obtains the intra-class sum of squares increment among the mangrove candidate patches. The two mangrove candidate patches with the smallest intra-class sum of squares increment are merged to obtain several mangrove candidate patch clusters, and the output set for the current iteration is constructed. The algorithm for calculating the intra-class sum of squares increment is as follows:

[0053] In the formula, For the increment of the sum of squares within the class, This is the first mangrove candidate patch to be merged. This is the second mangrove candidate patch to be merged. This represents the average feature vector of the first mangrove candidate patch to be merged within the merged mangrove candidate patch cluster. The average feature vector of the second mangrove candidate patch to be merged is within the merged mangrove candidate patch cluster.

[0054] S44: Use the output set of the current iteration as the input set of the next iteration, and repeat the merging of mangrove candidate patches to obtain the output set of the last iteration; use the contour coefficient maximization method to extract the partitioning results corresponding to several clusters with the same number as the optimal clustering number from the output set of the last iteration to obtain several sets of mangrove patches of the ecological category.

[0055] In this embodiment, the sampling device uses the output set of the current iteration as the input set of the next iteration, and repeats the merging of mangrove candidate patches until they are merged into a single cluster's clustering tree, thus obtaining the output set of the last iteration.

[0056] The sampling device uses the silhouette coefficient maximization method to extract the partitioning results corresponding to several clusters with the same number as the optimal clustering number from the output set of the last iteration, thereby obtaining a set of mangrove patches of several ecological categories.

[0057] Specifically, the sampling device obtains the overall average silhouette coefficient of each candidate cluster number based on a preset number of candidate cluster numbers, the output set of the last iteration, and a preset silhouette coefficient calculation algorithm. The candidate cluster number corresponding to the largest overall average silhouette coefficient is taken as the optimal cluster number. The silhouette coefficient calculation algorithm is as follows:

[0058] In the formula, The overall average profile coefficient. For the first i The profile coefficients of individual mangrove candidate patches The number of candidate mangrove patches, For the first i The average distance between a mangrove candidate patch and the nearest neighboring mangrove candidate patch cluster. For the first i The average distance between a mangrove candidate patch and other mangrove candidate patches within its cluster.

[0059] The sampling device extracts a number of clusters corresponding to the optimal cluster number from the output set of the last iteration, based on the optimal cluster number, to obtain a set of mangrove patches of several ecological categories. Finally, the ecological category of each mangrove patch is obtained, and ecological stratification is completed. This is used to guide the allocation of sample plots and ensure that mangrove patches of each ecological category are sampled reasonably according to area and intra-category heterogeneity.

[0060] S5: Calculate the number of sample plots based on the mangrove patch sets of each ecological category in each time phase to obtain the number of sample plots for each ecological category in each time phase; screen sample plots within each category based on the mangrove patch sets of each ecological category in the same time phase and the corresponding number of sample plots for each ecological category to obtain several target mangrove patches for each ecological category in each time phase, which are used as the sampling results of mangrove monitoring sample plots.

[0061] In this embodiment, the sampling device calculates the number of sample plots based on the mangrove patch sets of each ecological category in each time phase, thereby obtaining the number of sample plots for each ecological category in each time phase.

[0062] The sampling equipment screens mangrove patches within each ecological category based on the set of mangrove patches in the same time phase and the number of corresponding ecological category plots, and obtains several target mangrove patches in each ecological category in each time phase as the sampling results of mangrove monitoring plots.

[0063] Specifically, the sampling equipment selects several mangrove candidate patches from the mangrove patch set of each ecological category that have the smallest distance from the cluster center and meet the distance requirements between mangrove candidate patches. Patches in inaccessible areas or with excessively high implementation costs are eliminated, resulting in several target mangrove patches for each ecological category at each time phase, which are used as the sampling results for mangrove monitoring plots. Ecological indicators are calculated for each mangrove candidate patch at each time phase, a multi-indicator feature system is constructed, and hierarchical cluster analysis is introduced to achieve objective stratification and automatic grouping of mangrove patches at multiple time phases. This significantly reduces the subjectivity in the plot selection process and improves the accuracy, stability, and efficiency of mangrove monitoring plot sampling.

[0064] Please see Figure 5 , Figure 5The flowchart of step S5 in the mangrove monitoring plot sampling method provided in one embodiment of this application includes steps S51 to S53, as follows: S51: Obtain the plot weight parameters for each ecological category at each time phase, as well as the distance between each mangrove candidate patch at each time phase and the average feature vector of all mangrove candidate patches.

[0065] In this embodiment, the sampling device obtains the plot weight parameters of each ecological category in each time phase and the distance between each mangrove candidate patch in each time phase and the average feature vector of all mangrove candidate patches. The average feature vector of all mangrove candidate patches is obtained by averaging the ecological feature vectors of all mangrove candidate patches in the current time phase.

[0066] The plot weight parameters include area weight parameters and intra-class heterogeneity weights. The area weight parameter indicates the proportion of mangrove patches, and the intra-class heterogeneity weight parameter indicates the degree of ecological difference among patches within an ecological category. Please refer to [link / reference]. Figure 6 , Figure 6 The flowchart of step S51 in the mangrove monitoring plot sampling method provided in one embodiment of this application is as follows: S511: Based on the mangrove patch set of each ecological category in each time phase and the preset area weight calculation algorithm, obtain the area weight parameters of each ecological category in each time phase.

[0067] In this embodiment, the sampling device obtains the area weight parameters for each ecological category in each time phase based on the mangrove patch set for each time phase and a preset area weight calculation algorithm. The area weight calculation algorithm is as follows:

[0068] In the formula, For the first k Area weight parameters for each ecological category, For the first k A collection of mangrove patches belonging to various ecological categories. The first in the current ecological category of mangrove patch set i One mangrove candidate patch, This represents the number of candidate mangrove patches in the current ecological category set.

[0069] S512: Obtain the distance between each mangrove candidate patch in the mangrove patch set of each ecological category in each time phase and the average feature vector of the current ecological category; based on the number of mangrove candidate patches in the mangrove patch set of each ecological category in each time phase, the distance between each mangrove candidate patch and the average feature vector of the current ecological category, and the preset intra-class heterogeneity weight calculation algorithm, obtain the intra-class heterogeneity weight parameters of each ecological category in each time phase.

[0070] In this embodiment, the sampling device obtains the distance between each mangrove candidate patch in the mangrove patch set of each ecological category at each time phase and the average feature vector of the current ecological category.

[0071] The sampling device obtains the intra-class heterogeneity weight parameters for each ecological category at each time phase based on the number of mangrove candidate patches in the mangrove patch set for each ecological category at each time phase, the distance between each mangrove candidate patch and the average feature vector of the current ecological category, and a preset intra-class heterogeneity weight calculation algorithm. The intra-class heterogeneity weight calculation algorithm is as follows:

[0072] In the formula, For the first k Intra-class heterogeneity weight parameters for each ecological category, For each mangrove patch in the set of mangrove patches for each ecological category, compare each candidate mangrove patch with the current... k The distance between the average feature vectors of each ecological category For the current number k The average feature vector of each ecological category.

[0073] S52: Based on the distance between each mangrove candidate patch in each time phase and the average feature vector of all mangrove candidate patches, and the preset total number of sample plots calculation algorithm, obtain the total number of sample plots in each time phase.

[0074] In this embodiment, the sampling device obtains the total number of sample plots for each time phase based on the distance between each mangrove candidate patch and the average feature vector of all mangrove candidate patches in each time phase, and a preset algorithm for calculating the total number of sample plots. The algorithm for calculating the total number of sample plots is as follows:

[0075] In the formula, This represents the total number of sample plots. This is an adjustment coefficient used to control the density of the sample plot. The number of candidate mangrove patches, For the first iThe distance between a candidate mangrove patch and the average feature vector of all candidate mangrove patches. This represents the average feature vector of all candidate mangrove patches. This represents the number of ecological categories.

[0076] S53: Based on the plot weight parameters of each ecological category in each time phase, the total number of plots in each time phase, and the preset plot quantity calculation algorithm, obtain the number of plots for each ecological category in each time phase.

[0077] In this embodiment, the sampling device obtains the number of sample plots for each ecological category in each time phase based on the sample plot weight parameters for each ecological category in each time phase, the total number of sample plots in each time phase, and a preset sample plot quantity calculation algorithm. The sample plot quantity calculation algorithm is as follows:

[0078] In the formula, For the first k Number of sample plots for each ecological category For the first k The plot weight parameters for each ecological category.

[0079] Please refer to Figure 7 , Figure 7 This is a schematic diagram of the structure of a mangrove monitoring plot sampling device provided in one embodiment of this application. The device can be implemented entirely or partially through software, hardware, or a combination of both. The device 7 includes: Data acquisition module 71 is used to acquire multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological association data; The patch construction module 72 is used to construct mangrove candidate patches based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, and obtain several mangrove candidate patches for each temporal phase. The index calculation module 73 is used to calculate the ecological index of each mangrove candidate patch in each time phase based on the mangrove ecological association data, and construct the ecological feature vector of each mangrove candidate patch in each time phase. The category identification module 74 is used to perform hierarchical clustering and ecological category stratification based on the ecological feature vectors of each mangrove candidate patch in the same time phase, to obtain a set of mangrove patches of several ecological categories in each time phase, wherein the set of mangrove patches includes several mangrove candidate patches of the corresponding ecological category. The sample plot screening module 75 is used to calculate the number of sample plots based on the mangrove patch set of each ecological category in each time phase, and obtain the number of sample plots of each ecological category in each time phase; and to screen sample plots within the same ecological category based on the mangrove patch set of each ecological category in the same time phase and the corresponding number of sample plots of the ecological category, and obtain several mangrove target patches of each ecological category in each time phase, which are used as the sampling results of mangrove monitoring sample plots.

[0080] In this embodiment, a data acquisition module obtains multi-temporal satellite remote sensing image data and mangrove ecological association data of the target mangrove area; a patch construction module constructs mangrove candidate patches based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, obtaining several mangrove candidate patches for each temporal phase; an index calculation module calculates ecological indicators for each mangrove candidate patch for each temporal phase based on the mangrove ecological association data, constructing ecological feature vectors for each mangrove candidate patch for each temporal phase; and a category recognition module identifies the ecological features of each mangrove candidate patch within the same temporal phase. Feature vectors are used for hierarchical clustering and ecological category stratification to obtain sets of mangrove patches for several ecological categories at each time phase. Each set of mangrove patches includes several candidate mangrove patches for the corresponding ecological category. A plot selection module calculates the number of plots for each ecological category at each time phase based on the sets of mangrove patches for each ecological category. Within-category plot selection is then performed based on the sets of mangrove patches for each ecological category at the same time phase and the corresponding number of plots for each ecological category, resulting in several target mangrove patches for each ecological category at each time phase, which serve as the sampling results for mangrove monitoring plots. Ecological indicators are calculated for each candidate mangrove patch at each time phase, constructing a multi-indicator feature system and introducing hierarchical clustering analysis. This achieves objective stratification and automatic grouping of mangrove patches across multiple time phases, significantly reducing subjectivity in the plot selection process and improving the accuracy, stability, and efficiency of mangrove monitoring plot sampling.

[0081] Please refer to Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. The computer device 8 includes: a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and executable on the processor 81. The computer device can store multiple instructions, which are adapted to be loaded and executed by the processor 81 as described above. Figures 1 to 6 The method steps of the illustrated embodiment, and the specific execution process, can be found in the illustration. Figures 1 to 6 The specific details of the illustrated embodiments will not be elaborated here.

[0082] The processor 81 may include one or more processing cores. The processor 81 connects to various parts of the server using various interfaces and lines. It executes various functions and processes data of the mangrove monitoring sampling device 7 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 82, and by calling data from the memory 82. Optionally, the processor 81 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 81 may integrate one or a combination of several of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 81.

[0083] The memory 82 may include random access memory (RAM) or read-only memory. Optionally, the memory 82 may include a non-transitory computer-readable storage medium. The memory 82 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 82 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 82 may also be at least one storage device located remotely from the aforementioned processor 81.

[0084] This application embodiment also provides a storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figures 1 to 6 The method steps of the illustrated embodiment, and the specific execution process, can be found in the illustration. Figures 1 to 6 The specific details of the illustrated embodiments will not be elaborated here.

[0085] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0086] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the algorithm. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0088] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms.

[0092] This invention is not limited to the above-described embodiments. If any modifications or variations to this invention do not depart from the spirit and scope of this invention, and if such modifications and variations fall within the scope of the claims and equivalent technologies of this invention, then this invention also intends to include such modifications and variations.

Claims

1. A sampling method for mangrove monitoring plots, characterized in that, Includes the following steps: Obtain multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological correlation data; Based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, mangrove candidate patches are constructed to obtain several mangrove candidate patches for each temporal phase. Based on the mangrove ecological association data, ecological indicators are calculated for each mangrove candidate patch in each time phase, and ecological feature vectors for each mangrove candidate patch in each time phase are constructed. Hierarchical clustering and ecological category stratification are performed based on the ecological feature vectors of each mangrove candidate patch in the same time phase to obtain a set of mangrove patches of several ecological categories in each time phase, wherein the set of mangrove patches includes several mangrove candidate patches of the corresponding ecological category. The number of sample plots is calculated based on the mangrove patch sets of each ecological category in each time phase, and the number of sample plots of each ecological category in each time phase is obtained. Based on the mangrove patch sets of each ecological category in the same time phase and the corresponding number of sample plots of each ecological category, sample plots within each category are screened to obtain several mangrove target patches of each ecological category in each time phase, which are used as the sampling results of mangrove monitoring sample plots.

2. The mangrove monitoring plot sampling method according to claim 1, characterized in that, The step of constructing mangrove candidate patches based on the multi-temporal satellite remote sensing image data and mangrove ecological association data to obtain several mangrove candidate patches for each temporal phase includes the following steps: Based on the mangrove ecological association data, feature extraction is performed on all pixels of satellite remote sensing images of each time phase in the multi-temporal satellite remote sensing image data to obtain feature extraction datasets for each time phase, wherein the multi-dimensional feature datasets include feature extraction data of each pixel; The multi-temporal satellite remote sensing image data and the multi-dimensional feature datasets of each temporal phase are input into a pre-trained mangrove distribution mask generation model to generate mangrove distribution masks and obtain mangrove distribution mask data for each temporal phase. Vectorization and connected component analysis were performed on the mangrove distribution mask data of each time phase to obtain several mangrove candidate patches for each time phase.

3. The mangrove monitoring plot sampling method according to claim 2, characterized in that: The ecological feature vector includes several indicators, including habitat status indicators, patch structure indicators, area dynamic change indicators, and environmental status indicators. The step of calculating ecological indicators for each candidate mangrove patch at each time phase based on the mangrove ecological association data, and constructing an ecological feature vector for each candidate mangrove patch at each time phase, includes the following steps: Based on the spectral data in the mangrove ecological association data and the preset average normalized vegetation index (ANOVA) calculation algorithm, the ANOVA is calculated for each mangrove candidate patch in each time phase to obtain the ANOVA for each mangrove candidate patch in each time phase, which is used as the habitat status indicator. Based on the area data in the mangrove ecological association data and the preset patch structure index calculation algorithm, the patch structure index of each mangrove candidate patch in each time phase is calculated to obtain the patch structure index of each mangrove candidate patch in each time phase. Based on the area data in the mangrove ecological association data and the preset area dynamic change index calculation algorithm, the area dynamic change index of each mangrove candidate patch in each time phase is calculated to obtain the area dynamic change index of each mangrove candidate patch in each time phase. Environmental status indicators for each mangrove candidate patch at each time phase are obtained; habitat status indicators, patch structure indicators, area dynamic change indicators, and environmental status indicators of each mangrove candidate patch at the same time phase are spliced ​​together to construct ecological feature vectors for each mangrove candidate patch at each time phase.

4. The mangrove monitoring plot sampling method according to claim 3, characterized in that, The step of performing hierarchical clustering and ecological category stratification based on the ecological feature vectors of various mangrove candidate patches in the same time phase to obtain a set of mangrove patches of several ecological categories in each time phase includes the following steps: The ecological feature vectors of each mangrove candidate patch are standardized to obtain the standardized ecological feature vectors of each mangrove candidate patch. Based on the standardized ecological feature vectors of each mangrove candidate patch and a preset distance calculation algorithm, distance calculation is performed to construct a mangrove candidate patch distance matrix. Each mangrove candidate patch is treated as an independent cluster, and the two closest mangrove candidate patches are iteratively merged according to the mangrove candidate patch distance matrix to obtain a mangrove candidate patch set. The mangrove candidate patch set includes several mangrove candidate patches, and the mangrove candidate patch distance matrix includes the distances between each mangrove candidate patch. The set of mangrove candidate patches is used as the input set for the first iteration. Based on several mangrove candidate patches in the input set and a preset algorithm for calculating the intra-class sum of squares increment, the intra-class sum of squares increment among each mangrove candidate patch is obtained. The two mangrove candidate patches with the smallest intra-class sum of squares increment are merged to obtain the output set for the current iteration. The output set of the current iteration is used as the input set for the next iteration. The merging of mangrove candidate patches is repeated to obtain the output set of the last iteration. The contour coefficient maximization method is used to extract the partitioning results corresponding to several clusters with the same number as the optimal clustering number from the output set of the last iteration to obtain several sets of mangrove patches of the ecological category.

5. The mangrove monitoring plot sampling method according to claim 4, characterized in that, The step of calculating the number of sample plots for each ecological category of mangrove forests based on the mangrove patch sets of each time phase to obtain the number of sample plots for each ecological category of each time phase includes the following steps: The sample plot weight parameters for each ecological category at each time phase and the distance between each mangrove candidate patch at each time phase and the average feature vector of all mangrove candidate patches are obtained, wherein the average feature vector of all mangrove candidate patches is obtained by averaging the ecological feature vectors of all mangrove candidate patches at the current time phase. The total number of sample plots for each time phase is obtained based on the distance between each mangrove candidate patch and the average feature vector of all mangrove candidate patches in each time phase, as well as the preset total number of sample plots calculation algorithm. The number of sample plots for each ecological category in each time phase is obtained based on the sample plot weight parameters for each ecological category in each time phase, the total number of sample plots in each time phase, and the preset sample plot number calculation algorithm.

6. The mangrove monitoring plot sampling method according to claim 5, characterized in that: The plot weight parameters include area weight parameters and intra-class heterogeneity weights. The area weight parameters are used to indicate the proportion of mangrove patches, and the intra-class heterogeneity weight parameters are used to indicate the degree of ecological difference among patches within an ecological category. The process of obtaining the plot weight parameters for each ecological category at each time phase includes the following steps: Based on the mangrove patch sets of each ecological category in each time phase and the preset area weight calculation algorithm, the area weight parameters of each ecological category in each time phase are obtained. Obtain the distance between each mangrove candidate patch in the mangrove patch set of each ecological category in each time phase and the average feature vector of the current ecological category; based on the number of mangrove candidate patches in the mangrove patch set of each ecological category in each time phase, the distance between each mangrove candidate patch and the average feature vector of the current ecological category, and the preset intra-class heterogeneity weight calculation algorithm, obtain the intra-class heterogeneity weight parameters for each ecological category in each time phase.

7. A sampling device for mangrove monitoring plots, characterized in that, include: The data acquisition module is used to acquire multi-temporal satellite remote sensing image data of the target mangrove area and mangrove ecological association data; The patch construction module is used to construct mangrove candidate patches based on the multi-temporal satellite remote sensing image data and mangrove ecological association data, and obtain several mangrove candidate patches for each temporal phase. The index calculation module is used to calculate the ecological index of each mangrove candidate patch in each time phase based on the mangrove ecological association data, and to construct the ecological feature vector of each mangrove candidate patch in each time phase. The category identification module is used to perform hierarchical clustering and ecological category stratification based on the ecological feature vectors of each mangrove candidate patch in the same time phase, to obtain a set of mangrove patches of several ecological categories in each time phase, wherein the set of mangrove patches includes several mangrove candidate patches of the corresponding ecological category. The sample plot selection module is used to calculate the number of sample plots based on the mangrove patch sets of each ecological category in each time phase, and obtain the number of sample plots of each ecological category in each time phase; and to select sample plots within each category based on the mangrove patch sets of each ecological category in the same time phase and the corresponding number of sample plots in each ecological category, so as to obtain several mangrove target patches of each ecological category in each time phase, which are used as the sampling results of mangrove monitoring sample plots.

8. A computer device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor; the computer program, when executed by the processor, implements the steps of the mangrove monitoring plot sampling method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the mangrove monitoring plot sampling method as described in any one of claims 1 to 6.

Images