A forest quality precise promotion quality evaluation plot extraction method and system

Abstract

The application discloses a kind of forest quality precision promotion quality evaluation plot extraction method and system, belong to forestry information technology field, including obtaining forest quality precision promotion plot basic database, basic database includes spatial position information, administrative division information and forest quality precision promotion attribute information;Set extraction precondition, precondition includes extraction proportion parameter, administrative division constraint condition and maximum distance threshold value between plot;Based on maximum distance threshold value, administrative division is taken as clustering unit, the plot in basic database is carried out spatial clustering analysis, the plot with spatial distance not more than maximum distance threshold value is clustered to the same candidate plot set, generates several candidate plot sets;In each candidate plot set, administrative division is taken as hierarchical variable, according to extraction proportion parameter, hierarchical random sampling is independently executed, and quality evaluation plot extraction result is generated.The application realizes the randomness and fairness of plot extraction, eliminates artificial subjective intervention factor.

Description

Technical Field

[0001] This invention belongs to the field of forestry information technology, specifically relating to a method and system for extracting quality evaluation patches for precise improvement of forest quality in forestry, used to automatically extract quality evaluation patches from annual self-inspection patches for precise improvement of forest quality according to the requirements of forestry management departments. Background Technology

[0002] Forest quality improvement assessment is an important means for forestry management departments to evaluate the effectiveness of annual afforestation and forest management work. According to current forestry management regulations, provincial forestry authorities are required to select a certain proportion of forest quality improvement maps from the annual self-reports submitted by grassroots units and organize field verification personnel to conduct on-site verification and quality assessment.

[0003] Currently, the extraction of quality assessment patches for precise improvement of forest quality mainly faces the following technical problems: First, the manual sampling method is subject to significant human subjective interference, making it difficult to guarantee the randomness and fairness of the sampling results and affecting the objectivity of the quality evaluation conclusions.

[0004] Second, taking Guangdong Province as an example, the number of forest quality improvement maps reported annually through self-inspection is approximately 40,000. If the sampling rate is 12.5%, then about 5,000 maps need to be sampled. Manual sampling would require 2 to 3 staff members working continuously for 5 to 7 days to complete, which is a heavy task with low efficiency.

[0005] Third, although the traditional computer random sampling method can achieve randomness, the sampling results are too discrete in spatial distribution, and the distance between the sampled patches is far. This results in long distances, heavy workload, and a field verification cycle of 2 to 3 months for field verification personnel, which seriously affects work efficiency.

[0006] Therefore, there is an urgent need for an automated method and system for extracting forest quality assessment patches that can take into account randomness, fairness, and spatial aggregation. Summary of the Invention

[0007] This invention addresses the aforementioned problems and overcomes the shortcomings of existing technologies by providing a method and system for extracting forest quality assessment patches for precise improvement in forestry. It solves the problems of existing methods for extracting forest quality assessment patches, such as significant human intervention, low work efficiency, and spatially dispersed extraction results leading to long field verification distances.

[0008] To achieve the above objectives, the present invention adopts the following technical solution.

[0009] In a first aspect, the present invention provides a method for extracting forest quality assessment patches for precise improvement of forest quality, comprising the following steps; Step S1: Obtain the basic database of forest quality improvement maps reported in the annual self-inspection. The basic database includes the spatial location information, administrative division information and forest quality improvement attribute information of each map. Step S2: Set the preconditions for extraction, including extraction ratio parameters, administrative division constraints, and maximum distance threshold between map patches; Step S3: Based on the maximum distance threshold, using administrative divisions as clustering units, perform spatial clustering analysis on the map patches in the basic database, clustering map patches whose spatial distance does not exceed the maximum distance threshold into the same candidate map patch set, generating several candidate map patch sets; Step S4: In each of the candidate map patch sets, stratified random sampling is performed independently according to the extraction ratio parameter, with administrative division as the stratification variable, to generate quality evaluation map patch extraction results; Step S5: Summarize and output the extraction results to generate a list of quality evaluation patches.

[0010] Furthermore, the preconditions for extraction in step S2 also include: a minimum extraction quantity threshold and a maximum extraction quantity upper limit set according to the administrative division level.

[0011] Furthermore, the spatial clustering analysis in step S3 employs a density-based spatial clustering algorithm or a distance-threshold-based hierarchical clustering algorithm, and performs clustering operations according to county-level administrative divisions.

[0012] Furthermore, the maximum distance threshold is reasonably set in combination with the road network density and terrain conditions of the field verification area to balance the spatial randomness of the extracted map patches with the accessibility of the field verification.

[0013] Furthermore, in step S4, the stratified random sampling uses prefecture-level or county-level administrative divisions as stratification variables, and performs random sampling independently within each stratum, so that the sampling ratio of each stratum is consistent with the sampling ratio parameter.

[0014] Furthermore, the summary output in step S5 includes: generating a detailed list of the extracted map features, a statistical table of the number of extracted features by administrative division, and a spatial distribution map of the extracted map features.

[0015] Furthermore, the method for extracting forest quality assessment patches for precise improvement can be triggered by a single click, automatically completing the entire process from basic data reading, rule matching, random extraction to result aggregation.

[0016] Secondly, the present invention also provides a forest quality precision improvement quality evaluation patch extraction system for executing the forest quality precision improvement quality evaluation patch extraction method, including a data acquisition module, a precondition setting module, an aggregation extraction engine module, and a result output module. The data acquisition module is used to acquire the basic database of forest quality precision improvement patches reported annually through self-inspection; The aforementioned precondition setting module is used to set extraction ratio parameters, administrative division constraints, and maximum distance threshold between map patches; The aggregation extraction engine module is used to perform spatial clustering analysis on the map patches in the basic database using administrative divisions as clustering units, clustering map patches whose spatial distance does not exceed the maximum distance threshold into the same candidate map patch set, generating several candidate map patch sets, and performing stratified random sampling in each candidate map patch set using administrative divisions as stratification variables; The result output module is used to summarize the extraction results and generate a list of quality evaluation patches.

[0017] Furthermore, the aggregation extraction engine module includes: Spatial clustering unit is used to perform spatial clustering of map patches according to county-level administrative divisions, and to group map patches whose spatial distance does not exceed the preset maximum distance threshold into the same candidate set; The random sampling unit is used to perform stratified random sampling in each candidate set; The rule management unit is used to store and manage aggregation extraction rules, distance threshold parameters, and sampling algorithm parameters, and supports dynamic configuration and version management of rules.

[0018] Furthermore, the forest quality precision improvement quality evaluation patch extraction system also includes a visualization module for displaying the spatial distribution map of the extracted patches and the extraction statistics.

[0019] Beneficial effects of this invention: (1) This invention achieves randomness and fairness in the extraction of map patches by combining aggregate extraction rules with stratified random sampling algorithm, and eliminates human subjective intervention factors.

[0020] (2) This invention uses spatial clustering constraints to make the patches in the extraction results relatively clustered in space, which effectively shortens the on-site verification route for field verification personnel and significantly improves the efficiency of field verification.

[0021] (3) The present invention sets the maximum distance threshold in combination with the road network density and terrain conditions of the field verification area, so that the sampling results can adapt to the actual situation of different geographical areas, ensuring spatial clustering while taking into account the randomness of sampling.

[0022] (4) This invention reduces the extraction time from several days in the traditional manual method to minutes through one-click automated processing, which greatly improves work efficiency.

[0023] (5) The present invention ensures that the sampling results are evenly distributed in each administrative region by means of a stratified random sampling strategy, thereby improving the representativeness of the quality evaluation. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the overall process of a method for extracting forest quality evaluation patches for precise improvement according to the present invention.

[0026] Figure 2 This is a schematic diagram of the module structure of a forest quality assessment patch extraction system for precise improvement of forest quality according to the present invention.

[0027] Figure 3 This is a schematic diagram of the internal structure of the aggregation extraction engine module of the present invention.

[0028] Figure 4 This is a schematic diagram comparing the spatial distribution of extraction results in an embodiment of the present invention.

[0029] The diagram is labeled as follows: 101 is the data acquisition module, 102 is the precondition setting module, 103 is the aggregation extraction engine module, 104 is the result output module, 105 is the visualization display module; 1031 is the spatial clustering unit, 1032 is the random sampling unit, and 1033 is the rule management unit. Detailed Implementation

[0030] To make the technical problems solved, the technical solutions, and the beneficial effects of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0031] like Figure 1 As shown in the figure, the method for extracting forest quality assessment patches for precise improvement provided by an embodiment of the present invention includes the following steps; Step S1: Obtain the basic database of forest quality improvement maps reported in the annual self-inspection.

[0032] After completing the annual self-assessment of forest quality improvement, provincial forestry management departments compile the forest quality improvement map data reported by various grassroots units to form a basic database. This basic database includes the spatial location information (longitude and latitude coordinates or vector boundary data) of each map patch, administrative division information (province, city, county, and township levels), and forest quality improvement attribute information (afforestation year, afforestation type, afforestation area, etc.). Taking Guangdong Province as an example, the number of forest quality improvement map patches reported in the annual self-assessment is approximately 40,000.

[0033] Step S2: Set the preconditions for extraction.

[0034] System administrators set extraction prerequisites through the user interface, which mainly include: (1) Sampling ratio parameters: set according to the sampling ratio requirements for different project types of quality evaluation as stipulated by the forestry management department.

[0035] (2) Administrative division constraints: Set minimum extraction thresholds for different project types at each level of administrative division and minimum extraction area threshold to ensure that each administrative division unit has a sufficient and reasonable number of extraction patches.

[0036] (3) Maximum distance threshold: Set the maximum spatial distance between map patches that field inspectors can accept.

[0037] Step S3: Perform spatial clustering analysis based on aggregation extraction rules.

[0038] The aggregation extraction engine processes the polygons in the base database according to the following rules: First, using county-level administrative divisions as the basic clustering unit, within the county-level administrative boundaries, map features whose spatial distance does not exceed a preset maximum distance threshold are clustered into the same candidate set. The clustering algorithm can employ density-based spatial clustering methods (such as the DBSCAN algorithm) or distance-threshold-based hierarchical clustering methods.

[0039] Secondly, if the number of map features in a candidate set is insufficient to meet the minimum extraction requirements for the administrative division, the distance threshold should be appropriately relaxed for supplementary clustering, or the candidate set should be merged with adjacent candidate sets.

[0040] This step generates several candidate patch sets that satisfy spatial aggregation constraints, with the patches in each candidate set being relatively concentrated in space.

[0041] Step S4: Perform stratified random sampling.

[0042] In the generated candidate map patch set, a stratified random sampling algorithm is used for the final map patch extraction. Specifically, the administrative division is used as the stratification variable, and within each stratum, random sampling is performed independently from the candidate map patch set corresponding to that stratum according to a preset extraction ratio.

[0043] Step S5: Summarize and output the extraction results.

[0044] The system automatically summarizes the extraction results and generates the following output: (1) A detailed list of the extracted map patches, including map patch number, administrative division affiliation, spatial coordinates, forest quality precision improvement attributes, etc.; (2) Statistical table of sampling quantities by administrative division; (3) Spatial distribution map of the extracted patches.

[0045] The above steps S1 to S5 are triggered by the one-click extraction function provided by the system and do not require manual intervention.

[0046] Spatial distribution analysis was performed on the extraction results. (Refer to...) Figure 4 As shown, Figure 4 The left side (a) shows the spatial distribution of map patches obtained using the traditional pure random sampling method. Figure 4 The right side (b) shows the spatial distribution of the map patches extracted using the method of this invention. Figure 4 The comparison clearly shows that: traditional pure random sampling methods result in highly discrete spatial distribution of map features, with large average straight-line distances between adjacent features, and some exceeding 10 kilometers in distance. This necessitates long-distance travel between different areas for field inspectors, leading to low inspection efficiency. In contrast, the map features extracted using the method of this invention exhibit a clear clustered spatial distribution. The maximum distance between features within the same candidate set does not exceed a preset distance threshold of 0.5 kilometers (the specific value is determined by actual settings). The features are relatively concentrated within the same geographical area, allowing field inspectors to complete on-site verification of multiple features in a single trip, significantly reducing travel time. Furthermore, because stratified random sampling is used in step S4, the map features within each candidate set still maintain a certain degree of spatial randomness, preventing the sampling results from being overly concentrated in a local area and ensuring the objectivity and representativeness of the quality evaluation results.

[0047] In addition, this embodiment provides a forest quality assessment patch extraction system for precise improvement of forest quality in forestry, referring to... Figure 2 The module structure shown includes: The data acquisition module 101 is used to obtain the basic database of forest quality precision improvement patches reported annually from the forestry management database or data interface, and to perform data verification and format standardization processing.

[0048] The precondition setting module 102 provides a graphical parameter configuration interface for setting preconditions such as extraction ratio parameters, administrative division constraints, and maximum distance thresholds.

[0049] The aggregation extraction engine module 103 is the core processing module of this system, used to perform spatial clustering analysis and stratified random sampling algorithms.

[0050] The result output module 104 is used to generate a detailed list, statistical report and spatial distribution map of the extracted patches.

[0051] The visualization module 105 is used to display the spatial distribution of the extracted patches on the map, and supports interactive operations such as zooming, panning, and clicking to view patch details.

[0052] Specifically, refer to Figure 3 The aggregation extraction engine module 103 further includes: Spatial clustering unit 1031 performs spatial clustering of map features according to administrative divisions, and classifies map features whose spatial distance does not exceed the preset maximum distance threshold into the same candidate set.

[0053] Random sampling unit 1032 performs stratified random sampling in each candidate set, using administrative division as the stratification variable to ensure the uniformity of the sampling.

[0054] The rule management unit 1033 is used to store and manage aggregation extraction rules, distance threshold parameters, and sampling algorithm parameters, and supports dynamic configuration and version management of rules.

[0055] Verification of Results: Taking the forest quality improvement assessment work in Guangdong Province in a certain year as an example, the basic database contained approximately 40,000 self-reported map patches, with an average extraction rate of 12.5%. Using the method of this invention for automated extraction, the entire process took approximately 3 minutes, extracting approximately 5,000 map patches. The extraction results showed a relatively concentrated spatial distribution within each city and county, with the average straight-line distance between adjacent extracted map patches controlled within a preset distance threshold (e.g., 0.5 kilometers, which can be set according to actual needs). Field inspectors conducted on-site verification based on the extraction results, shortening the overall verification cycle from the traditional 2-3 months to approximately 1 month, improving verification efficiency by over 60%, thus demonstrating the effectiveness and practicality of the method of this invention.

[0056] It is understood that the above specific description of the present invention is only for illustrating the present invention and is not limited to the technical solutions described in the embodiments of the present invention. Those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention to achieve the same technical effect; as long as the use needs are met, they are all within the protection scope of the present invention.

Claims

1. A method for extracting forest quality assessment patches for precise improvement, characterized in that, Includes the following steps: Step S1: Obtain the basic database of forest quality improvement maps reported in the annual self-inspection. The basic database includes the spatial location information, administrative division information and forest quality improvement attribute information of each map. Step S2: Set the preconditions for extraction, including extraction ratio parameters, administrative division constraints, and maximum distance threshold between map patches; Step S3: Based on the maximum distance threshold, using administrative divisions as clustering units, perform spatial clustering analysis on the map patches in the basic database, clustering map patches whose spatial distance does not exceed the maximum distance threshold into the same candidate map patch set, generating several candidate map patch sets; Step S4: In each of the candidate map patch sets, stratified random sampling is performed independently according to the extraction ratio parameter, with administrative division as the stratification variable, to generate quality evaluation map patch extraction results; Step S5: Summarize and output the extraction results to generate a list of quality evaluation patches.

2. The method for extracting forest quality assessment patches for precise improvement according to claim 1, characterized in that, The preconditions for extraction in step S2 also include: a minimum extraction quantity threshold and a maximum extraction quantity upper limit set according to the administrative division level.

3. The method for extracting forest quality assessment patches for precise improvement according to claim 1, characterized in that, The spatial clustering analysis in step S3 uses a density-based spatial clustering algorithm or a distance-threshold-based hierarchical clustering algorithm, and performs clustering operations according to county-level administrative divisions.

4. The method for extracting forest quality assessment patches for precise improvement according to claim 1, characterized in that, The maximum distance threshold is set reasonably in combination with the road network density and terrain conditions of the field verification area to balance the spatial randomness of the extracted map patches and the accessibility of the field verification.

5. The method for extracting forest quality assessment patches for precise improvement according to claim 1, characterized in that, The stratified random sampling described in step S4 uses prefecture-level or county-level administrative divisions as stratification variables, and performs random sampling independently within each stratum, so that the sampling ratio of each stratum is consistent with the sampling ratio parameter.

6. The method for extracting forest quality assessment patches for precise improvement according to claim 1, characterized in that, The summary output in step S5 includes: generating a detailed list of the extracted map features, a statistical table of the number of extracted features by administrative division, and a spatial distribution map of the extracted map features.

7. A method for extracting forest quality assessment patches for precise improvement according to any one of claims 1 to 6, characterized in that, The method for extracting forest quality assessment patches for precise improvement can be triggered by a single click and automatically completes the entire process from basic data reading, rule matching, random extraction to result summarization.

8. A system for extracting forest quality assessment patches for precise improvement, characterized in that, A method for extracting forest quality assessment patches for precise improvement according to any one of claims 1 to 7, comprising: The data acquisition module is used to acquire the basic database of forest quality precision improvement patches reported annually through self-inspection; The precondition setting module is used to set the extraction ratio parameters, administrative division constraints, and the maximum distance threshold between map patches; The aggregation extraction engine module is used to perform spatial clustering analysis on the map patches in the basic database using administrative divisions as clustering units, clustering map patches whose spatial distance does not exceed the maximum distance threshold into the same candidate map patch set, generating several candidate map patch sets, and performing stratified random sampling in each candidate map patch set using administrative divisions as stratification variables. The results output module is used to summarize the extraction results and generate a list of quality evaluation patches.

9. A forest quality precision improvement quality evaluation patch extraction system according to claim 8, characterized in that, The aggregation extraction engine module includes: Spatial clustering unit is used to perform spatial clustering of map patches according to county-level administrative divisions, and to group map patches whose spatial distance does not exceed the preset maximum distance threshold into the same candidate set; The random sampling unit is used to perform stratified random sampling in each candidate set; The rule management unit is used to store and manage aggregation extraction rules, distance threshold parameters, and sampling algorithm parameters.

10. A forest quality precision improvement quality evaluation patch extraction system according to claim 8, characterized in that, It also includes a visualization module, which displays the spatial distribution map of the extracted patches and the extraction statistics.

Images