An intelligent monitoring method, system and device for forest and grass ecological environment

Abstract

The present invention relates to the technical field of forest and grass ecological environment monitoring, and specifically relates to an intelligent monitoring method, system and device for forest and grass ecological environment. The method obtains various ecological index data of a specified monitoring plot in the forest and grass ecological environment within a preset historical time period; obtains ecological index correlation pairs according to the distribution of any two ecological index data over time; obtains the standard range of each ecological index in the ecological index correlation pairs according to the ecological index data corresponding to the ecological index correlation pairs; and determines whether the current plot is a boundary plot according to the distribution of the ecological index data corresponding to the ecological index correlation pairs in the current plot within the corresponding standard range. By analyzing the distribution of the ecological index data in the current plot within the corresponding standard range, the present invention can quickly determine whether the current plot is a boundary plot, improve the efficiency of boundary plot determination, and effectively reduce resource waste.

Description

Technical Field

[0001] The present invention relates to the technical field of forest and grass ecological environment monitoring, and specifically relates to an intelligent monitoring method, system and device for forest and grass ecological environment. Background Art

[0002] Existing monitoring methods for forest and grass ecological environment usually lay professional monitoring equipment in selected sample plots to monitor various ecological indicators of the sample plots in real time, and then evaluate the current situation of forest and grass resources in real time. However, due to external factors such as human activity interference, the selected standard sample plots may evolve into transitional zones between ecosystems such as forests and grasslands, that is, boundary sample plots. As the "ongoing" recorder of ecological processes, the ecological parameters of boundary sample plots fluctuate frequently, resulting in the inability to accurately evaluate the current situation of forest and grass resources. Therefore, boundary sample plots are usually not suitable as standard sample plots for monitoring and evaluating forest and grass ecological environment. In existing methods, a large amount of data analysis is required to evaluate boundary sample plots, which is inefficient and causes a large amount of resource waste. Summary of the Invention

[0003] In order to solve the technical problem of low evaluation efficiency of boundary sample plots, the purpose of the present invention is to provide an intelligent monitoring method, system and device for forest and grass ecological environment. The specific technical solutions adopted are as follows:

[0004] In a first aspect, an embodiment of the present invention provides an intelligent monitoring method for forest and grass ecological environment. The method includes the following steps:

[0005] Obtain various ecological index data of a designated monitoring sample plot in the forest and grass ecological environment within a preset historical time period;

[0006] Obtain ecological index correlation pairs according to the distribution of any two ecological index data over time within a preset historical time period;

[0007] Obtain the standard range of each ecological index in each ecological index correlation pair according to the ecological index data within the preset historical time period corresponding to each ecological index correlation pair;

[0008] Judge whether the current sample plot is a boundary sample plot according to the distribution of the ecological index data corresponding to each ecological index correlation pair in the current sample plot of the forest and grass ecological environment within the corresponding standard range.

[0009] Further, the method for obtaining the ecological index correlation pairs is as follows:

[0010] Obtain the correlation degree of any two ecological index data according to the distribution of any two ecological index data over time within a preset historical time period;

[0011] When the degree of association is greater than the preset degree-of-association threshold, the ecological indicators corresponding to the two types of ecological indicator data are taken as an ecological indicator association pair.

[0012] Further, the method for obtaining the degree of association is as follows:

[0013] Divide the preset historical time period into local time periods of a preset duration, and sequentially construct a sample set from the first preset number of local time periods in chronological order;

[0014] For any sample set and any type of ecological indicator data, cluster the ecological indicator data of this type in each local time period of the sample set through a hierarchical clustering algorithm to obtain the reference clustering clusters of the ecological indicator data of this type in each local time period of the sample set;

[0015] Obtain the range of the ecological indicator data in each reference clustering cluster as the reference range corresponding to the reference clustering cluster;

[0016] Based on the range of the ecological indicator data within the preset historical time period, divide the ecological indicator data into a second preset number of interval segments, and obtain the interval points corresponding to each interval segment;

[0017] For any interval point, obtain the number of all reference clustering clusters whose reference range contains this interval point as the distribution frequency of this interval point corresponding to this type of ecological indicator data in the sample set;

[0018] According to the difference between the distribution frequency and the distribution frequency of this interval point corresponding to this type of ecological indicator data in the preset neighborhood sample set of the sample set, obtain the reference fluctuation degree of this interval point corresponding to this type of ecological indicator data in the sample set;

[0019] Take the average value of the reference fluctuation degrees of all interval points corresponding to this type of ecological indicator data in the sample set as the overall fluctuation degree of this type of ecological indicator data in the sample set;

[0020] According to the difference in the overall fluctuation degrees of any two types of ecological indicator data in each sample set, obtain the degree of association between the two types of ecological indicator data.

[0021] Further, the method for obtaining the reference fluctuation degree is as follows:

[0022] Obtain the difference between the distribution frequency of this interval point corresponding to this type of ecological indicator data in the sample set and the distribution frequency of this interval point corresponding to this type of ecological indicator data in each preset neighborhood sample set of the sample set as the first difference;

[0023] Take the average value of the first differences as the reference fluctuation degree of this interval point corresponding to this type of ecological indicator data in the sample set.

[0024] Further, the method for obtaining the degree of association is as follows:

[0025] For any two ecological index data, the difference in the overall fluctuation degree of these two ecological index data in each sample set is obtained, and all are used as the second difference.

[0026] The result of negatively correlating and normalizing the variance of the second difference is used as the degree of association between these two ecological index data.

[0027] Further, the method for obtaining the standard range is as follows:

[0028] For any ecological index association pair, map the two ecological index data corresponding to this ecological index association pair within a preset historical time period to a two-dimensional space coordinate system; wherein, the abscissa and ordinate of the two-dimensional space coordinate system correspond to the two ecological index data corresponding to this ecological index association pair.

[0029] According to the distances between the corresponding coordinate points in the two-dimensional space coordinate system, cluster the coordinate points in the two-dimensional space coordinate system through a hierarchical clustering algorithm to obtain analysis clusters.

[0030] The range of each ecological index data in each analysis cluster is used as the standard range of each ecological index in this ecological index association pair; wherein, one analysis cluster includes the ranges of two ecological index data and the ranges of the two ecological index data in one analysis cluster are kept corresponding.

[0031] Further, the method for obtaining the boundary sample plot is as follows:

[0032] According to the distribution of the ecological index data corresponding to each ecological index association pair in the current sample plot of the forest and grass ecological environment within the corresponding standard range, obtain the degree of chaos of the current sample plot.

[0033] When the degree of chaos is greater than a preset chaos degree threshold, it is determined that the current sample plot is a boundary sample plot.

[0034] When the degree of chaos is less than or equal to the preset chaos degree threshold, it is determined that the current sample plot is not a boundary sample plot.

[0035] Further, the method for obtaining the degree of chaos is as follows:

[0036] For any ecological index association pair, when the two ecological index data corresponding to this ecological index association pair in the current sample plot are within the standard ranges of the two ecological indexes in this ecological index association pair, mark the chaos index of this ecological index association pair as 0.

[0037] When the data of the two ecological indicators corresponding to the ecological indicator association pair in the current sample plot are not within the standard ranges of the two ecological indicators in the ecological indicator association pair, mark the confusion indicator of the ecological indicator association pair as 1;

[0038] Take the sum of the confusion indicators of all ecological indicator association pairs in the current sample plot as the degree of confusion of the current sample plot.

[0039] In a second aspect, another embodiment of the present invention provides an intelligent monitoring system for forest and grass ecological environment, which includes:

[0040] A data acquisition module for acquiring various ecological indicator data of a specified monitoring sample plot of the forest and grass ecological environment within a preset historical time period;

[0041] An ecological indicator association pair acquisition module for acquiring ecological indicator association pairs according to the distribution of any two ecological indicator data over time within a preset historical time period;

[0042] A standard range acquisition module for acquiring the standard ranges of each ecological indicator in each ecological indicator association pair according to the ecological indicator data within the preset historical time period corresponding to each ecological indicator association pair;

[0043] A boundary sample plot judgment module for judging whether the current sample plot is a boundary sample plot according to the distribution of the ecological indicator data corresponding to each ecological indicator association pair in the current sample plot of the forest and grass ecological environment within the corresponding standard ranges.

[0044] In a third aspect, another embodiment of the present invention provides an intelligent monitoring device for forest and grass ecological environment, which includes: a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods are implemented.

[0045] The present invention has the following beneficial effects:

[0046] First, according to the distribution of any two ecological index data over time within a preset historical time period, the present invention obtains ecological index correlation pairs, accurately determines the ecological indices with correlations, avoids the interference of ecological indices with weak correlations on the analysis of boundary plots in the subsequent process, and at the same time excludes the analysis of ecological indices with weak correlations, improving the efficiency of judging whether the current plot is reasonable; in order to accurately and efficiently analyze whether the current plot is a boundary plot in the subsequent process, further based on the ecological index data within the preset historical time period corresponding to each ecological index correlation pair, the standard range of each ecological index in each ecological index correlation pair is obtained, accurately reflecting the standard range corresponding to each ecological index in each ecological index correlation pair in the standard plot; further, according to the distribution of the ecological index data corresponding to each ecological index correlation pair in the current plot of the forest and grass ecological environment within the corresponding standard range, it is accurately judged whether the current plot is a boundary plot, effectively improving the efficiency of judging whether the current plot is a boundary plot, and at the same time avoiding obtaining and analyzing more data for the current plot, effectively reducing a large amount of resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 It is a schematic flowchart of an intelligent monitoring method for forest and grass ecological environment provided by an embodiment of the present invention;

[0049] Figure 2 It is a flowchart of a method for obtaining ecological index correlation pairs provided by an embodiment of the present invention;

[0050] Figure 3 It is a flowchart of a method for obtaining boundary plots provided by an embodiment of the present invention;

[0051] Figure 4 It is a structural diagram of an intelligent monitoring system for forest and grass ecological environment provided by an embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of an intelligent monitoring device for forest and grass ecological environment provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manner, structure, characteristics and effects of a method, system and device for intelligent monitoring of the forest and grass ecological environment according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0055] The following specifically describes the specific solutions of a method, system and device for intelligent monitoring of the forest and grass ecological environment provided by the present invention in combination with the accompanying drawings.

[0056] Embodiment 1:

[0057] The specific implementation scenario of this embodiment is as follows: In the existing method, sample plots are selected in forests and grasslands to obtain various ecological index data, and then the current situation of forest and grass resources is evaluated in real time. In order to accurately evaluate forest and grass resources, reasonable selection of samples is required to avoid the ecological environment of the selected sample plots being chaotic due to external factors, that is, the boundary sample plots between ecological systems such as forests and grasslands, and thus the situation of forest and grass resources cannot be accurately reflected. Therefore, accurate selection of samples is needed. In the existing method, when analyzing the chaos of the ecological environment of the selected sample plots, various ecological index data are obtained for observation for a period of time, resulting in a waste of a large amount of resources and low efficiency, and it is impossible to efficiently judge whether the selected sample plot is a boundary sample plot. In order to efficiently analyze whether the current sample plot is a boundary sample plot, in this embodiment, first, various ecological index data of the designated monitoring sample plot of the forest and grass ecological environment within a preset historical time period are analyzed to obtain ecological index correlation pairs that are related to each other, and further, the standard range of each ecological index in each ecological index correlation pair is obtained. Then, it is analyzed whether the ecological index data corresponding to each ecological index correlation pair in the current sample plot is within the standard range of the corresponding ecological index, indirectly reflecting the deviation of the ecological environment in the current sample plot, so as to efficiently judge whether the current sample plot is a boundary sample plot, avoiding obtaining more data for the current sample plot, and effectively avoiding waste of resources on the premise of ensuring accuracy.

[0058] The present invention proposes a method for intelligent monitoring of the forest and grass ecological environment. Please refer to Figure 1 , which shows a schematic flowchart of a method for intelligent monitoring of the forest and grass ecological environment provided by an embodiment of the present invention. The method includes the following steps:

[0059] Step S1: Obtain various ecological index data of a specified monitoring plot of the forest and grass ecological environment within a preset historical time period.

[0060] Specifically, in order to efficiently analyze whether the selected plot of the forest and grass ecological environment is reasonable, this embodiment needs to first obtain various ecological index data of a specified monitoring plot of the forest and grass ecological environment within a preset historical time period, so as to prepare for obtaining the standard range corresponding to each ecological index data, and thus facilitate accurately analyzing whether the currently selected plot of the forest and grass ecological environment is reasonable. Among them, this embodiment sets the preset historical time period to 5 years and the time interval between two adjacent moments of data collection to 1 hour. The implementer can set the size of the preset historical time period and the time interval between two adjacent moments of data collection according to the actual situation, and no limitation is made here. It should be noted that there are multiple specified monitoring plots, which are the standard plots corresponding to the forest and the grass, and there is no interference from external uncertain factors. This embodiment sets the number of specified monitoring plots to 100, among which, 50 specified monitoring plots are the standard plots of the forest, and 50 specified monitoring plots are the standard plots of the grass. The implementer can set the number of specified monitoring plots and the number of standard plots of the forest and the grass in the specified monitoring plots according to the actual situation, and no limitation is made here.

[0061] Among them, in this embodiment, an environmental mapping instrument is used to obtain environmental-related index data such as temperature index data, light intensity index data, and wind speed index data of each specified monitoring plot at each moment; a multi-spectral camera carried by a drone is used to obtain vegetation-related index data such as vegetation coverage index data and species richness index data of each specified monitoring plot at each moment; a soil system is used to obtain soil-related index data such as pH index data and organic carbon content index data of each specified monitoring plot at each moment; therefore, the ecological index data includes temperature index data, light intensity index data, wind speed index data, vegetation coverage index data, species richness index data, pH index data, organic carbon content index data, etc.

[0062] Step S2: Obtain ecological index association pairs according to the distribution of any two ecological index data over time within a preset historical time period.

[0063] It is known that there is a certain corresponding relationship among different types of ecological index data in the standard sample plots under normal circumstances. For example, when the index data of the organic carbon content in the standard sample plot is large, the index data of the vegetation coverage is also relatively large; while for the boundary sample plot, the relationship among different types of ecological index data will be significantly different from the relationship shown in the standard sample plot. For example, when the index data of the organic carbon content in the boundary sample plot is small, the index data of the vegetation coverage may also be relatively large. Therefore, in this embodiment, a standard range comparison table corresponding to different types of ecological indexes in the standard sample plot can be constructed, and it can be analyzed whether the ecological index data in the current sample plot exists in the relationship mode corresponding to the standard range comparison table, so as to efficiently judge whether the current sample plot belongs to the boundary sample plot.

[0064] In actual situations, not all types of ecological indexes are correlated. For example, the size of the biomass index data depends on the volume and density of plants, while the vegetation height index data only reflects the vertical growth of plants, and there is no obvious correlation between the biomass index and the vegetation height index. In the process of constructing the standard range comparison table corresponding to the ecological indexes, if irrelevant ecological indexes are included, it will introduce noise and then interfere with the judgment of the correlation of the ecological index data corresponding to a single ecological environment, resulting in errors when analyzing the chaos degree of the sample plot. Therefore, before constructing the standard range comparison table, it is first necessary to determine the pairs of ecological indexes that are correlated, and exclude the ecological indexes that are irrelevant to each other, so as to improve the accuracy of calculating the chaos degree of the sample plot, and then increase the correctness of judging the boundary sample plot.

[0065] Among them, to judge whether two ecological indexes are correlated, it is necessary to combine the data characteristics of specific ecological processes. If there is no direct driving relationship between ecological index A and ecological index B in ecological functions, then when the data of ecological index A has a distribution pattern, the data of ecological index B always shows a random distribution without rules; if ecological index A and ecological index B are correlated, then when the data of ecological index A is always distributed within a certain fixed range, the data of ecological index B also satisfies a certain regular interval range distribution; furthermore, in this embodiment, according to the distribution of any two ecological index data over time in a preset historical time period, the ecological index correlation pairs are obtained, and the correlated ecological indexes are accurately determined, which is beneficial to accurately constructing the standard range comparison table corresponding to the ecological indexes subsequently.

[0066] Preferably, in a realizable manner of this embodiment, for the method of obtaining the ecological index correlation pairs, please refer to Figure 2 , which shows a flowchart of a method for obtaining the ecological index correlation pairs provided in this embodiment. The method includes the following steps:

[0067] Step S201: Obtain the correlation degree of any two ecological index data according to the distribution of any two ecological index data over time in a preset historical time period.

[0068] The distributions of two associated ecological indicators in a standard plot must have a stable trend. For example, for the carbon content indicator and the vegetation coverage indicator in a forest ecological pattern, the distribution range of the carbon content indicator data in the standard plot of the forest is usually within , and the distribution range of the vegetation coverage indicator data is usually within ; for the carbon content indicator and the vegetation coverage indicator in a grassland ecological pattern, the distribution range of the carbon content indicator data in the standard plot of the grassland is usually within , and the distribution range of the vegetation coverage indicator data is usually within ; Therefore, the overall trends of the distribution intervals of the corresponding data of the carbon content indicator and the vegetation coverage indicator are consistent in time series, and the carbon content indicator and the vegetation coverage indicator are two associated ecological indicators. For two uncorrelated ecological indicators, the interval ranges of their corresponding data do not have a consistent trend in time series and are disordered. Therefore, in this embodiment, the correlation degree of any two ecological indicator data is obtained according to the distribution of any two ecological indicator data over time in a preset historical period. The greater the correlation degree, the more relevant the corresponding two ecological indicators are.

[0069] In a feasible implementation manner of this embodiment, the method for obtaining the correlation degree is as follows: In order to accurately analyze the distribution of various ecological indicator data in a preset historical period, this embodiment divides the preset historical period into local time periods of a preset duration, and sequentially constructs a sample set from the first preset number of local time periods in chronological order; this embodiment sets the preset duration to 1 week and the first preset number to 10. The implementer can set the size of the preset duration and the first preset number according to the actual situation, which is not limited here. It should be noted that if the remaining local time periods are less than 10, the remaining local time periods are still divided into a sample set. For any sample set and any kind of ecological indicator data, the ecological indicator data in each local time period in the sample set is clustered by the hierarchical clustering algorithm to obtain the reference clustering clusters of the ecological indicator data in each local time period in the sample set; among them, the hierarchical clustering algorithm is a well-known technology and will not be elaborated here;

[0070] In order to determine the distribution of the ecological indicator data, and then obtain the range of the ecological indicator data in each reference clustering cluster as the reference range of the corresponding reference clustering cluster; based on the range of the ecological indicator data in the preset historical period, the ecological indicator data is divided into a second preset number of interval segments, and the interval points corresponding to each interval segment are obtained; this embodiment sets the second preset number to 6. The implementer can set the size of the second preset number according to the actual situation, which is not limited here. For example, assume that the value range of the carbon content indicator in the preset historical period is , the divided interval segments are respectively , , , , and , and the interval points are 10, 20, 30, 40, 50, 60, and 70 respectively. For any interval point, obtain the number of all reference clustering clusters whose reference range contains this interval point, as the distribution times of this interval point corresponding to this ecological index data in this sample set; the larger the distribution times, the more frequently this ecological index data is distributed at this interval point in this sample set;

[0071] In order to analyze the stability of the distribution of this ecological index data at this interval point in this sample set, and then in this embodiment, according to the difference between the distribution times and the distribution times of this interval point corresponding to this ecological index data in the preset neighborhood sample set of this sample set, obtain the reference fluctuation degree of this interval point corresponding to this ecological index data in this sample set; wherein, in this embodiment, the preset neighborhood sample set of this sample set is set to 6 sample sets adjacent to this sample set. For example, if this sample set is the k-th sample set, then the preset neighborhood sample set of this sample set is the (k - 3)-th sample set, the (k - 2)-th sample set, the (k - 1)-th sample set, the (k + 1)-th sample set, the (k + 2)-th sample set, and the (k + 3)-th sample set. The implementer can set the number and position of the preset neighborhood sample set according to the actual situation, which is not limited here. It should be noted that if this sample set is a boundary sample set, only analyze the existing preset neighborhood sample sets of this sample set;

[0072] The greater the reference fluctuation degree, the more unstable the distribution of this ecological index data at this interval point in this sample set. Among them, the method for obtaining the reference fluctuation degree is: obtain the absolute value of the difference between the distribution times of this interval point corresponding to this ecological index data in this sample set and the distribution times of this interval point corresponding to this ecological index data in each preset neighborhood sample set of this sample set, all as the first difference; the greater the first difference, the more unstable the distribution of this ecological index data at this interval point. In order to accurately reflect the distribution situation of this ecological index data at this interval point in this sample set, and then take the mean value of the first difference as the reference fluctuation degree of this interval point corresponding to this ecological index data in this sample set;

[0073] In order to overall reflect the distribution fluctuation situation of this ecological index data in this sample set, and then take the mean value of the reference fluctuation degrees of all interval points corresponding to this ecological index data in this sample set as the overall fluctuation degree of this ecological index data in this sample set;

[0074] Similarly, obtain the overall fluctuation degree of each ecological index data in each sample set. When the differences in the overall fluctuation degrees of any two ecological index data in each sample set are similar, it indicates that the overall distribution trends of the two ecological index data within the preset time period are more consistent, and the association between the two ecological index data is stronger; furthermore, in this embodiment, the association degree between any two ecological index data is obtained according to the differences in the overall fluctuation degrees of the two ecological index data in each sample set. Among them, the method for obtaining the association degree is as follows: for any two ecological index data, obtain the difference in the overall fluctuation degrees of the two ecological index data in each sample set as the second difference; take the result of the negative correlation and normalization of the variance of the second difference as the association degree between the two ecological index data. It should be noted that in the process of obtaining the second difference, the types of ecological indexes corresponding to the minuend and the subtrahend should always be kept consistent. For example, if the two ecological index data are the x-th ecological index data and the y-th ecological index data respectively, then when obtaining the corresponding second difference of the two ecological index data in each sample set, it must be uniformly the difference between the overall fluctuation degree of the x-th ecological index data and the overall fluctuation degree of the y-th ecological index data, or uniformly the difference between the overall fluctuation degree of the y-th ecological index data and the overall fluctuation degree of the x-th ecological index data, which is not limited here.

[0075] Among them, the calculation formula for the association degree is: ; in the formula, is the association degree between the x-th ecological index data and the y-th ecological index data; is the variance of the second difference corresponding to the x-th ecological index data and the y-th ecological index data; exp is the exponential function with the natural constant as the base.

[0076] Thus far, the association degree between any two ecological index data is obtained.

[0077] Step S202: When the association degree is greater than the preset association degree threshold, regard the ecological indexes corresponding to the corresponding two ecological index data as an ecological index association pair.

[0078] It is known that the greater the association degree, the greater the association between the ecological indexes corresponding to the corresponding two ecological index data. Furthermore, in this embodiment, the preset association degree threshold is set to 0.5, and the implementer can set the size of the preset association degree threshold according to the actual situation, which is not limited here. When the association degree is greater than the preset association degree threshold, regard the ecological indexes corresponding to the corresponding two ecological index data as an ecological index association pair.

[0079] Thus far, all ecological index association pairs in the forest and grass ecological environment are obtained.

[0080] Step S3: Based on the ecological index data within the corresponding preset historical time period for each ecological index association pair, obtain the standard range of each ecological index in each ecological index association pair.

[0081] Since the ecological index data within the preset historical time period are all ecological index data in standard plots, in order to determine the standard range of each ecological index corresponding to each ecological index association pair, in this embodiment, based on the ecological index data within the preset historical time period corresponding to each ecological index association pair, the standard range of each ecological index in each ecological index association pair is obtained.

[0082] Preferably, in a feasible implementation manner of this embodiment, the method for obtaining the standard range is as follows: For any ecological index association pair, map the two ecological index data corresponding to this ecological index association pair within the preset historical time period to a two-dimensional space coordinate system; wherein, the abscissa and ordinate of the two-dimensional space coordinate system correspond to the two ecological index data corresponding to this ecological index association pair; for example, if the two ecological index data corresponding to this ecological index association pair are ecological index A and ecological index B respectively, then the abscissa and ordinate of the two-dimensional space coordinate system are ecological index A data and ecological index B data respectively. It should be noted that if the abscissa of the two-dimensional space coordinate system is ecological index A data, then the ordinate of the two-dimensional space coordinate system is ecological index B data; if the abscissa of the two-dimensional space coordinate system is ecological index B data, then the ordinate of the two-dimensional space coordinate system is ecological index A data, which is not limited here.

[0083] According to the Euclidean distance between the corresponding coordinate points in the two-dimensional space coordinate system, cluster the coordinate points in the two-dimensional space coordinate system through the hierarchical clustering algorithm to obtain analysis clusters; the method for obtaining the Euclidean distance is a well-known technology and will not be elaborated here. Then, take the range of each ecological index data in each analysis cluster as the standard range of each ecological index in this ecological index association pair; wherein, an analysis cluster includes the ranges of two ecological index data and the ranges of the two ecological index data in an analysis cluster are kept corresponding. For example, assume that the two ecological index data corresponding to this ecological index association pair are carbon content index and vegetation coverage index. If two analysis clusters are finally obtained, among them, the standard range corresponding to the carbon content index data in one analysis cluster is and the standard range corresponding to the vegetation coverage index data is , then the standard range of one of the ecological index associations corresponding to this ecological index association pair is: 30 ≤ carbon content (g / kg) index data ≤ 50, 70 ≤ vegetation coverage (%) index data ≤ 90; the standard range corresponding to the carbon content index data in the other analysis cluster is and the standard range corresponding to the vegetation coverage index data is , the standard range corresponding to the other type of the ecological index association pair is: 10 ≤ carbon content (g / kg) index data ≤ 20, 50 ≤ vegetation coverage (%) index data ≤ 60.

[0084] Thus far, the standard ranges of each ecological index in each ecological index association pair are obtained.

[0085] Step S4: Determine whether the current plot is a boundary plot according to the distribution of the ecological index data corresponding to each ecological index association pair in the current plot of the forest and grass ecological environment within the corresponding standard range.

[0086] Specifically, when the ecological index data corresponding to an ecological index association pair in the current plot is within the corresponding standard range in the standard range comparison table, it indicates that the ecological index association pair in the current plot satisfies the typical characteristics of the ecosystem; when the ecological index data corresponding to the ecological index association pair in the current plot is not within the corresponding standard range in the standard range comparison table, it indicates that the relationship pattern between the ecological index association pairs in the current plot deviates from the typical characteristics of a single ecosystem, and the current plot is more likely to be a boundary plot. Furthermore, in this embodiment, it is determined whether the current plot is a boundary plot according to the distribution of the ecological index data corresponding to each ecological index association pair in the current plot of the forest and grass ecological environment within the corresponding standard range.

[0087] Preferably, in a feasible implementation manner of this embodiment, for the method of obtaining boundary plots, please refer to Figure 3 , which shows a flowchart of the method for obtaining a boundary plot provided in this embodiment. The method includes the following steps:

[0088] Step S301: Obtain the degree of chaos of the current plot according to the distribution of the ecological index data corresponding to each ecological index association pair in the current plot of the forest and grass ecological environment within the corresponding standard range.

[0089] When the ecological index data corresponding to the ecological index association pairs in the current plot is not distributed in the corresponding standard range more, it indicates that the ecological environment performance of the current plot is more complex. Furthermore, in this embodiment, the degree of chaos of the current plot is obtained according to the distribution of the ecological index data corresponding to each ecological index association pair in the current plot of the forest and grass ecological environment within the corresponding standard range. The greater the degree of chaos, the more likely the current sample is a boundary plot.

[0090] In an implementable manner of this embodiment, the method for obtaining the degree of chaos is as follows: For any ecological index association pair, when the data of the two ecological indexes corresponding to the ecological index association pair in the current sample plot are within the standard ranges of the two ecological indexes in the ecological index association pair, the chaos index of the ecological index association pair is marked as 0; when the data of the two ecological indexes corresponding to the ecological index association pair in the current sample plot are not within the standard ranges of the two ecological indexes in the ecological index association pair, the chaos index of the ecological index association pair is marked as 1; for example, if the two ecological indexes corresponding to the ecological index association pair are the carbon content index and the vegetation coverage index, and if the carbon content index data in the current sample plot is 40 and the vegetation coverage index is 80, then the chaos index of the ecological index association pair is marked as 0; if the carbon content index data in the current sample plot is 40 and the vegetation coverage index is 50, then the chaos index of the ecological index association pair is marked as 1. The sum of the chaos indexes of all the ecological index association pairs in the current sample plot is used as the degree of chaos of the current sample plot.

[0091] Step S302: Based on the degree of chaos, determine whether the current sample plot is a boundary sample plot.

[0092] It is known that the greater the degree of chaos, the more likely the current sample is a boundary sample plot. Furthermore, in this embodiment, the preset chaos degree threshold is set to 5. The implementer can set the size of the preset chaos degree threshold according to the actual situation, which is not limited here. When the degree of chaos is greater than the preset chaos degree threshold, it is determined that the current sample plot is a boundary sample plot; when the degree of chaos is less than or equal to the preset chaos degree threshold, it is determined that the current sample plot is not a boundary sample plot.

[0093] So far, it can be accurately and efficiently determined whether the current sample plot is a boundary sample plot, providing a topological optimization basis for the subsequent establishment of a regional forest and grass ecological intelligent monitoring network, ensuring that the selected sample plots meet the requirements of spatial representativeness and ecological integrity at the same time, and enabling efficient analysis of the forest and grass ecological environment.

[0094] In summary, this embodiment obtains various ecological index data of the designated monitoring sample plots of the forest and grass ecological environment within the preset historical time period; obtains ecological index association pairs according to the distribution of any two ecological index data over time; obtains the standard ranges of each ecological index in the ecological index association pair according to the ecological index data corresponding to the ecological index association pair; and determines whether the current sample plot is a boundary sample plot according to the distribution of the ecological index data corresponding to the ecological index association pair in the current sample plot within the corresponding standard ranges. By analyzing the distribution of the ecological index data in the current sample plot within the corresponding standard ranges, the present invention can quickly determine whether the current sample plot is a boundary sample plot, improving the efficiency of boundary sample plot determination and effectively reducing resource waste.

[0095] Example 2:

[0096] The present invention also provides an intelligent monitoring system for forest and grass ecological environment. Please refer to Figure 4 , which shows the structure diagram of an intelligent monitoring system for forest and grass ecological environment provided by an embodiment of the present invention. The system includes: a data acquisition module 10, an ecological index correlation pair acquisition module 20, a standard range acquisition module 30, and a boundary sample plot judgment module 40.

[0097] The data acquisition module 10 is used to acquire various ecological index data of a specified monitoring sample plot in the forest and grass ecological environment within a preset historical time period.

[0098] The ecological index correlation pair acquisition module 20 is used to acquire ecological index correlation pairs according to the distribution of any two ecological index data over time within a preset historical time period.

[0099] The standard range acquisition module 30 is used to acquire the standard range of each ecological index in each ecological index correlation pair according to the ecological index data within the preset historical time period corresponding to each ecological index correlation pair.

[0100] The boundary sample plot judgment module 40 is used to judge whether the current sample plot is a boundary sample plot according to the distribution of the ecological index data corresponding to each ecological index correlation pair in the current sample plot of the forest and grass ecological environment within the corresponding standard range.

[0101] It should be noted that: for the system provided in the above embodiment, only the above division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, an intelligent monitoring system for forest and grass ecological environment provided in the above embodiment and an embodiment of an intelligent monitoring method for forest and grass ecological environment belong to the same concept. The specific implementation process can be seen in the method embodiment and will not be elaborated here.

[0102] Embodiment 3:

[0103] The present invention also provides an intelligent monitoring device for forest and grass ecological environment. Please refer to Figure 5 , the device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. Wherein, when the processor 402 executes the computer program 403, the device can execute any one of the intelligent monitoring methods for forest and grass ecological environment introduced above.

[0104] In addition, the present invention also provides an intelligent monitoring device for the forest and grass ecological environment. The device includes a memory and a processor. Among them, the memory stores executable program codes, and the processor is used to call and execute the executable program codes to execute an intelligent monitoring method for the forest and grass ecological environment provided by the embodiments of the present application. The device may specifically be a chip, a component or a module. The chip may include a connected processor and a memory. Among them, the memory is used to store instructions. When the processor calls and executes the instructions, the chip may execute an intelligent monitoring method for the forest and grass ecological environment provided by the above embodiments.

[0105] Embodiment 4:

[0106] The present invention also provides a computer-readable storage medium. Computer program codes are stored in the computer-readable storage medium. When the computer program codes run on a computer, the computer is enabled to execute the above-related method steps to implement an intelligent monitoring method for the forest and grass ecological environment provided by the above embodiments.

[0107] Embodiment 5:

[0108] The present invention also provides a computer program product. When the computer program product runs on a computer, the computer is enabled to execute the above-related steps to implement an intelligent monitoring method for the forest and grass ecological environment provided by the above embodiments.

[0109] Among them, the device, the computer-readable storage medium, the computer program product or the chip provided by the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be elaborated here.

[0110] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent monitoring method for the forest and grass ecological environment, characterized in that, The method includes the following steps: Obtain various ecological index data of a designated monitoring plot of the forest and grass ecological environment within a preset historical time period; Obtain ecological index correlation pairs according to the distribution of any two ecological index data over time within the preset historical time period; Obtain the standard range of each ecological index in each ecological index correlation pair according to the ecological index data within the preset historical time period corresponding to each ecological index correlation pair; Judge whether the current plot is a boundary plot according to the distribution of the ecological index data corresponding to each ecological index correlation pair in the current plot of the forest and grass ecological environment within the corresponding standard range; The method for obtaining the standard range is as follows: For any ecological index correlation pair, map the two ecological index data corresponding to the ecological index correlation pair within the preset historical time period to a two-dimensional space coordinate system; wherein, the abscissa and ordinate of the two-dimensional space coordinate system correspond to the two ecological index data corresponding to the ecological index correlation pair; According to the distances between the corresponding coordinate points in the two-dimensional space coordinate system, cluster the coordinate points in the two-dimensional space coordinate system through a hierarchical clustering algorithm to obtain analysis clustering clusters; Take the ranges of each ecological index data in each analysis clustering cluster as the standard ranges of each ecological index in the ecological index correlation pair; wherein, each analysis clustering cluster includes the ranges of two ecological index data and the ranges of the two ecological index data in one analysis clustering cluster are kept corresponding.

2. The intelligent monitoring method for forest and grass ecological environment according to claim 1, characterized in that The method for obtaining the ecological index correlation pairs is as follows: Obtain the correlation degree of any two ecological index data according to the distribution of any two ecological index data over time within the preset historical time period; When the correlation degree is greater than the preset correlation degree threshold, take the ecological indexes corresponding to the corresponding two ecological index data as an ecological index correlation pair.

3. The intelligent monitoring method for forest and grass ecological environment according to claim 2, characterized in that, The method for obtaining the correlation degree is as follows: Divide the preset historical time period into local time periods of a preset duration, and sequentially construct a sample set from the first preset number of local time periods in chronological order; For any sample set and any ecological index data, cluster the ecological index data in each local time period in the sample set through a hierarchical clustering algorithm to obtain the reference clustering clusters of the ecological index data in each local time period in the sample set; Obtain the range of the ecological index data in each reference clustering cluster as the reference range of the corresponding reference clustering cluster; Based on the range of the ecological index data within the preset historical time period, divide the ecological index data into a second preset number of interval segments, and obtain the interval points corresponding to each interval segment; For any interval point, obtain the number of all reference clustering clusters whose reference range contains the interval point as the distribution times of the interval point corresponding to the ecological index data in the sample set; Obtain the reference fluctuation degree of the interval point corresponding to the ecological index data in the sample set according to the difference between the distribution times and the distribution times of the interval point corresponding to the ecological index data in the preset neighborhood sample set of the sample set; The mean of the reference fluctuation degrees of all interval points corresponding to this type of ecological index data in this sample set is used as the overall fluctuation degree of this type of ecological index data in this sample set; According to the differences in the overall fluctuation degrees of any two types of ecological index data in each sample set, the correlation degree between these two types of ecological index data is obtained.

4. The intelligent monitoring method for the forest and grass ecological environment according to claim 3, wherein, The method for obtaining the reference fluctuation degree is as follows: Obtain the differences between the distribution times of this interval point corresponding to this type of ecological index data in this sample set and the distribution times of this interval point corresponding to this type of ecological index data in each preset neighborhood sample set of this sample set, and all of them are used as the first differences; The mean of the first differences is used as the reference fluctuation degree of this interval point corresponding to this type of ecological index data in this sample set.

5. The intelligent monitoring method for forest and grass ecological environment according to claim 3, characterized in that The method for obtaining the correlation degree is as follows: For any two types of ecological index data, obtain the differences in the overall fluctuation degrees of these two types of ecological index data in each sample set, and all of them are used as the second differences; The result of negative correlation and normalization of the variance of the second differences is used as the correlation degree between these two types of ecological index data.

6. The intelligent monitoring method for forest and grass ecological environment according to claim 1, characterized in that, The method for obtaining the boundary sample plot is as follows: According to the distribution of the ecological index data corresponding to each ecological index association pair in the current sample plot of the forest and grass ecological environment within the corresponding standard range, obtain the confusion degree of the current sample plot; When the confusion degree is greater than the preset confusion degree threshold, it is determined that the current sample plot is a boundary sample plot; When the confusion degree is less than or equal to the preset confusion degree threshold, it is determined that the current sample plot is not a boundary sample plot.

7. The intelligent monitoring method for forest and grass ecological environment according to claim 6, characterized in that, The method for obtaining the confusion degree is as follows: For any ecological index association pair, when the two types of ecological index data corresponding to this ecological index association pair in the current sample plot are within the standard ranges of the two ecological indexes in this ecological index association pair, mark the confusion index of this ecological index association pair as 0; When the two types of ecological index data corresponding to this ecological index association pair in the current sample plot are not within the standard ranges of the two ecological indexes in this ecological index association pair, mark the confusion index of this ecological index association pair as 1; The sum result of the confusion indexes of all ecological index association pairs of the current sample plot is used as the confusion degree of the current sample plot.

8. An intelligent monitoring system for forest and grass ecological environment, characterized in that, The system includes: A data acquisition module for acquiring various ecological index data of a specified monitoring sample plot of the forest and grass ecological environment within a preset historical time period; An ecological index association pair acquisition module for acquiring ecological index association pairs according to the distribution of any two types of ecological index data over time within a preset historical time period; A standard range acquisition module for acquiring the standard range of each ecological index in each ecological index association pair according to the ecological index data corresponding to each ecological index association pair within a preset historical time period; A boundary sample plot determination module for determining whether the current sample plot is a boundary sample plot according to the distribution of the ecological index data corresponding to each ecological index association pair in the current sample plot of the forest and grass ecological environment within the corresponding standard range; The method for obtaining the standard range is as follows: For any ecological index association pair, map the two ecological index data corresponding to the ecological index association pair within a preset historical time period to a two-dimensional space coordinate system; wherein, the abscissa and ordinate of the two-dimensional space coordinate system correspond to the two ecological index data corresponding to the ecological index association pair. According to the distances between the corresponding coordinate points in the two-dimensional space coordinate system, cluster the coordinate points in the two-dimensional space coordinate system through a hierarchical clustering algorithm to obtain analysis clusters. Use the ranges of each ecological index data in each analysis cluster as the standard ranges of each ecological index in the ecological index association pair; wherein, each analysis cluster includes the ranges of two ecological index data and the ranges of the two ecological index data in one analysis cluster remain corresponding.

9. An intelligent monitoring device for the forest and grass ecological environment, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for intelligent monitoring of forest and grass ecological environment according to any one of claims 1-7 above.

Images