Sample point optimization method and device for sparse soil sampling area and electronic equipment

Abstract

The invention provides a sampling point optimization method and device for a soil sampling sparse area and electronic equipment. The method comprises the following steps: identifying sparse layering units and non-sparse layering units in a plurality of layering units; taking each sparse layering unit as a layering unit to be optimized; obtaining an environment similarity between the to-be-optimized layering unit and the non-sparse layering unit; calculating a first influence degree of the geographical environment characteristics of the to-be-optimized layering unit on the soil attributes in the soil sampling area, and calculating a second influence degree of the geographical environment characteristics of the non-sparse layering unit on the soil attributes in the soil sampling area; and according to the environment similarity and the influence degree difference value, selecting a target layering unit from the plurality of non-sparse layering units, and taking a sample point in the target layering unit as a virtual sample point of the to-be-optimized layering unit. By means of the method, the representativeness of the sample points in the sparse sampling area in the soil attribute investigation process is improved, and a real-time and efficient soil attribute high-precision drawing is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of soil property investigation, and in particular to a sampling point optimization method, device and electronic equipment for a sparsely sampled soil area. Background Art

[0002] In the process of obtaining high-precision mapping of soil properties, it is often necessary to make statistical inferences based on limited sample points, and the distribution characteristics of the sample points directly determine the mapping accuracy. In actual soil survey sampling, based on considerations such as convenience or preference, it is often impossible to ensure that the sampling points are evenly covered in the survey area, resulting in relatively concentrated sample points in some areas and relatively sparse sample points in some areas. The mapping accuracy of survey areas with dense sample points is usually relatively high, while the mapping accuracy of survey areas with sparse sample points is low, which in turn affects the accurate estimation of the overall soil condition in the region. In order to improve the accuracy of digital soil mapping, it is necessary to optimize the sample point design for sparse sampling areas. Summary of the invention

[0003] The present invention provides a method, device and electronic equipment for optimizing sample points in a sparsely sampled area of ​​soil, which improves the representativeness of sample points in a sparsely sampled area during a soil property survey, so as to obtain real-time, efficient and high-precision mapping of soil properties.

[0004] The present invention provides a method for optimizing sampling points in a sparsely sampled area of ​​soil, comprising the following steps: According to one or more geographical environmental characteristics, a stratification standard is constructed; and according to the stratification standard, the soil sampling area is stratified to obtain a plurality of stratification units; Identify sparse hierarchical units and non-sparse hierarchical units among the plurality of hierarchical units; and use each sparse hierarchical unit as a hierarchical unit to be optimized; Obtaining the environmental similarity between the stratified unit to be optimized and the non-sparse stratified unit; and calculating the first influence of the geographical environmental characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculating the second influence of the geographical environmental characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; Obtaining, according to the first influence and the second influence, an influence difference value between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit; According to the environmental similarity and the influence difference value, a target hierarchical unit is selected from the plurality of non-sparse hierarchical units, and the sample points in the target hierarchical unit are used as virtual sample points of the hierarchical unit to be optimized.

[0005] According to the sampling point optimization method for a sparse soil sampling area provided by the present invention, the identifying of sparse stratification units and non-sparse stratification units in a plurality of stratification units specifically includes: According to the number of sample points and unit area of ​​each stratified unit, the sample point density of each stratified unit is obtained; According to the sample point density of each hierarchical unit, sparse hierarchical units and non-sparse hierarchical units in the plurality of hierarchical units are identified.

[0006] According to the sampling point optimization method for a sparsely sampled soil area provided by the present invention, the step of obtaining the environmental similarity between the to-be-optimized stratification unit and the non-sparse stratification unit specifically includes: Obtaining the feature similarity of each geographical environment feature between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit; The environment similarity is obtained according to the similarities of each feature.

[0007] According to the sampling point optimization method for a sparsely sampled soil area provided by the present invention, the geographical environment feature includes a category feature; the step of obtaining the feature similarity of each geographical environment feature between the stratified unit to be optimized and the non-sparse stratified unit specifically includes: If the geographical environment feature is a categorical feature, the feature similarity of the geographical environment feature is obtained by judging whether the categorical feature of the to-be-optimized hierarchical unit is the same as the categorical feature of the non-sparse hierarchical unit.

[0008] According to the sampling point optimization method for a sparsely sampled area of ​​soil provided by the present invention, the geographical environment feature includes a numerical feature; the step of obtaining the feature similarity of each geographical environment feature between the stratified unit to be optimized and the non-sparse stratified unit specifically includes: If the geographical environment feature is a numerical feature, obtaining a first probability density distribution curve of the numerical feature of the to-be-optimized hierarchical unit and a second probability density distribution curve of the numerical feature of the non-sparse hierarchical unit; Obtaining a first curve coverage area of ​​the to-be-optimized hierarchical unit under the numerical characteristics through the first probability density distribution curve; Obtaining a second curve coverage area of ​​the non-sparse hierarchical unit under the numerical feature through the second probability density distribution curve; Obtaining a curve intersection coverage area through the first probability density distribution curve and the second probability density distribution curve; The feature similarity of the geographical environment feature is obtained according to the first curve coverage area, the second curve coverage area and the curve intersection coverage area.

[0009] According to the sampling point optimization method for a sparsely sampled soil area provided by the present invention, a target stratification unit is selected from a plurality of non-sparse stratification units according to the environmental similarity and the influence difference value, specifically comprising: Calculating the ratio between the environmental similarity and the influence difference value to obtain the ratio corresponding to each of the non-sparse hierarchical units; wherein the environmental similarity is proportional to the ratio, and the influence difference value is inversely proportional to the ratio; Sorting the ratios corresponding to each of the non-sparse hierarchical units from large to small, and determining the first-ranked non-sparse hierarchical unit as the target hierarchical unit; The environmental similarity between the to-be-optimized hierarchical unit and the target hierarchical unit is greater than an environmental similarity threshold.

[0010] The present invention also provides a sampling point optimization device for a sparsely sampled soil area, comprising the following parts: A regional stratification module is used to construct a stratification standard according to one or more geographical environmental characteristics; and stratify the soil sampling area according to the stratification standard to obtain a plurality of stratification units; A region identification module is used to identify sparse hierarchical units and non-sparse hierarchical units among the multiple hierarchical units; each sparse hierarchical unit is used as a hierarchical unit to be optimized; A similarity acquisition module, used to acquire the environmental similarity between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit; An influence degree acquisition module is used to calculate the first influence degree of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculate the second influence degree of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; according to the first influence degree and the second influence degree, obtain the influence degree difference value between the stratified unit to be optimized and the non-sparse stratified unit; The sample point optimization module is used to select a target hierarchical unit from the plurality of non-sparse hierarchical units according to the environmental similarity and the influence difference value, and use the sample points in the target hierarchical unit as virtual sample points of the hierarchical unit to be optimized.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the sampling point optimization method for a sparse soil sampling area as described in any one of the above is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the sampling point optimization method for a sparsely sampled area of ​​soil sampling as described in any one of the above.

[0013] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described sampling point optimization methods for sparsely sampled areas of soil.

[0014] The method, device and electronic device for optimizing sample points in a sparse soil sampling area provided by the present invention obtain the environmental similarity between the sparse stratification units and the non-sparse stratification units; and the difference in the influence of the geographical environmental characteristics of the sparse stratification units and the non-sparse stratification units on the soil properties in the soil sampling area; while ensuring that the environmental similarity is high and the difference in the influence is small, a target stratification unit is selected from multiple non-sparse stratification units, and the sample points in the target stratification unit are used as virtual sample points of the stratification unit to be optimized, thereby improving the representativeness of the sample points in the sparse sampling area during the soil property investigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is one of the flow diagrams of the sampling point optimization method for sparse soil sampling areas provided by the present invention.

[0017] Figure 2 It is a schematic diagram of the principle of the sampling point optimization method for sparse soil sampling areas provided by the present invention.

[0018] Figure 3 This is the second flow chart of the sampling point optimization method for sparse soil sampling areas provided by the present invention.

[0019] Figure 4 It is a structural schematic diagram of a sampling point optimization device for a sparsely sampled soil area provided by the present invention.

[0020] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the descriptions used in this way can be interchanged where appropriate, so that the embodiments can be implemented in a sequence other than that illustrated or described in the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of the steps that appear in the present application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between units can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0023] At present, the feature-based sample optimization design methods mainly include stratified sampling method and Latin hypercube method. The stratified method performs random sampling based on feature stratification, while the Latin hypercube method optimizes the sample points to make them as evenly distributed as possible in each feature stratification. These methods can ensure the representativeness of the sample points for the stratified characteristics to a certain extent, but this post-encryption sampling method is time-consuming and labor-intensive, and the lag in obtaining sample point information makes it defective in real-time high-precision statistical inference of soil properties. Virtual sample points can provide a way to support real-time high-precision mapping of soil properties.

[0024] The virtual sample point design method is mainly based on synthesizing existing sample points into virtual sample points in a certain way. The synthesis process mainly performs weighted averaging on spatial distance or attribute distance, and the correlation and importance between features are relatively insufficiently considered, resulting in the inability of virtual sample points to be fully distributed in certain important feature layers, so that the key information of important features cannot be fully represented by the sample points.

[0025] The present invention aims to improve the accuracy of soil property mapping evaluation in sparse sample point survey areas (hereinafter referred to as soil sampling areas), and proposes a sample point optimization method for sparse soil sampling areas to achieve low-cost and efficient acquisition of sample point optimization with high feature representativeness.

[0026] Combine the following Figure 1-Figure 5 The specific contents of the present invention are described.

[0027] Figure 1 It is a flow chart of a method for optimizing sampling points in a sparsely sampled area of ​​soil provided by the present invention, including steps S101-S105.

[0028] Step S101, constructing a stratification standard according to one or more geographical environmental characteristics; and stratifying the soil sampling area according to the stratification standard to obtain a plurality of stratification units.

[0029] In the embodiment of the present invention, different combinations of geographical environmental features form different stratification standards. Under the corresponding stratification standards, corresponding multiple stratification units are obtained for the soil sampling area. When the soil sampling area is stratified according to a single geographical environmental feature, the geographical environmental feature is a one-dimensional stratification standard; when the study area is stratified according to a combination of two geographical environmental features, the geographical environmental feature combination is a two-dimensional stratification standard; and so on. The soil sampling areas are stratified by the combination of these characteristics. This combination of geographical environmental characteristics is called Dimensional hierarchical standards, such as Figure 2 As shown, based on different dimensions, we can determine Class stratification standards.

[0030] Step S102, identifying sparse hierarchical units and non-sparse hierarchical units among a plurality of hierarchical units; and taking each sparse hierarchical unit as a hierarchical unit to be optimized.

[0031] Specifically, based on the existing sample points in the soil sampling area, the sparseness of the sample point distribution in the soil sampling area is evaluated, and the sparse stratification units and non-sparse stratification units in multiple stratification units are identified. To this end, it is necessary to calculate the sample point density of each stratification unit under each stratification standard.

[0032] In a possible implementation manner, in step S102, identifying sparse hierarchical units and non-sparse hierarchical units among a plurality of hierarchical units specifically includes: According to the number of sample points and the unit area of ​​each stratification unit, the sample point density of each stratification unit is obtained; according to the sample point density of each stratification unit, the sparse stratification units and the non-sparse stratification units in the multiple stratification units are identified.

[0033] Specifically, the sample density of each stratification unit under each stratification standard is as follows: in, It means in The first The sample density of each stratified unit ( ), For the The number of all stratification units under the stratification standard, It means in The first The number of sample points in a stratified unit, No. The first The area of ​​the stratified unit.

[0034] Furthermore, in order to optimize the sample points of the sparse hierarchical units, a relative sample point density threshold is determined, and the hierarchical units involved in the area below the threshold are used as sparse hierarchical units.

[0035] First, calculate the sample density threshold. The calculation formula is as follows: in, is the sampling point density of the soil sampling area, is the total number of sampling points in the soil sampling area, is the total area of ​​the soil sampling area.

[0036] Secondly, based on the sample density threshold The sample point density of the stratification units under the stratification standard is graded, and the stratification units with sample point density higher than the threshold are regarded as sparse stratification units. In this case, no sample point optimization is required; otherwise, they are regarded as non-sparse stratification units.

[0037] Step S103, obtaining the environmental similarity between the stratified unit to be optimized and the non-sparse stratified unit; and calculating the first influence of the geographical environmental characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculating the second influence of the geographical environmental characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area.

[0038] In a possible implementation, in step S103, the environmental similarity between the hierarchical unit to be optimized and the non-sparse hierarchical unit is obtained, specifically including: obtaining the feature similarity of each geographical environmental feature between the hierarchical unit to be optimized and the non-sparse hierarchical unit; and obtaining the environmental similarity based on each feature similarity.

[0039] Specifically, in order to achieve the optimization of virtual sample points of sparse stratified units, it is necessary to select sample points of non-sparse stratified units with similar geographical environment elements as the candidate sample point set. Therefore, in order to extract non-sparse stratified units with similar geographical environments for reference, it is also necessary to evaluate the degree of direct environmental similarity of stratified units. The more consistent the geographical environment characteristics between stratified units, the more similar the environments of the two stratified units are.

[0040] In one possible implementation, the geographical environment features include categorical features; obtaining the feature similarity of each geographical environment feature between the stratified unit to be optimized and the non-sparse stratified unit, specifically including: if the geographical environment feature is a categorical feature, obtaining the feature similarity of the geographical environment feature by judging whether the categorical features of the stratified unit to be optimized and the categorical features of the non-sparse stratified unit are the same.

[0041] In the embodiment of the present invention, the categorical features include discrete features such as soil type, etc. In the embodiment of the present invention, the specific types of the discrete features are not specifically limited.

[0042] For example, if the geographical environment feature is a categorical feature, the stratification features of the two stratification units are consistent, that is, the two units are similar in the stratification feature; otherwise, they are different. and non-sparse hierarchical units For two stratified units, they are The hierarchical features under the categorical features are and , the characteristic similarity of the geographical environment characteristics between the two is calculated as follows: In a possible implementation, the geographical environment feature includes a numerical feature; obtaining the feature similarity of each geographical environment feature between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit specifically includes: steps S301-S305.

[0043] Step S301: If the geographical environment feature is a numerical feature, obtain a first probability density distribution curve of the numerical feature of the hierarchical unit to be optimized and a second probability density distribution curve of the numerical feature of the non-sparse hierarchical unit.

[0044] Step S302, obtaining the first curve coverage area of ​​the to-be-optimized hierarchical unit under the numerical feature through the first probability density distribution curve; obtaining the second curve coverage area of ​​the non-sparse hierarchical unit under the numerical feature through the second probability density distribution curve; obtaining the intersection coverage area of ​​the curves through the first probability density distribution curve and the second probability density distribution curve; Step S303, obtaining the feature similarity of the geographical environment feature according to the first curve coverage area, the second curve coverage area and the curve intersection coverage area.

[0045] Next, steps S301 to S305 are described in detail.

[0046] If the geographical environment characteristics are numerical characteristics, the geographical environment characteristics within the layered unit have a certain numerical range. The more consistent the value range and distribution of two stratified units under the corresponding geographical environment characteristics, the more similar they are in this characteristic; otherwise, they are less similar. The numerical probability density distribution function within the layer under the numerical features is calculated, and the feature similarity between the probability density function curves of the two is calculated as shown in the calculation formula: in, Respectively and The coverage area of ​​the probability density distribution curve of two stratified units under a numerical variable, is the area under the intersection of two probability density distribution curves. The probability density distribution function (PDF) of each numerical variable in each hierarchical unit is estimated based on the kernel density method (KDE). The core calculation formula of this method is: in is the window interval when calculating the probability density, is the kernel function, are independently distributed object sample points.

[0047] Through the above feature similarity The calculation formula is based on the first curve covering area , the second curve covers the area And the intersection coverage area of ​​the curve , get the feature similarity of geographical environment features .

[0048] In a possible implementation, in step S103, calculating the first influence of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculating the second influence of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area, specifically includes: For the stratified unit to be optimized, its geographical environment characteristics cannot be completely consistent with those of the non-sparse stratified unit. The influence of various geographical environment characteristics on soil properties varies. Even under the same geographical environment characteristics, different distribution characteristics have different effects on the distribution of soil properties.

[0049] In order to ensure that the virtual sample points provided by the non-sparse feature stratification unit are representative of the geographical environment characteristics of the stratification unit to be optimized. It is necessary to measure the influence of different distribution characteristics under the same geographical environment characteristics for the non-sparse feature stratification unit. And select the unit with the smallest difference in influence with the distribution characteristics of the stratification unit to be optimized as the target stratification unit. This process needs to first measure the importance of different environmental characteristics to the soil survey and monitoring attributes, and secondly measure the importance of each distribution characteristic to the soil monitoring attribute under a certain geographical environment characteristic. Finally, combined with the importance of environmental characteristics to the soil survey and monitoring attributes, and the importance of each distribution characteristic to the soil monitoring attribute under the geographical environment characteristics, comprehensively evaluate the difference in influence between the stratification unit to be optimized and the non-sparse stratification unit. For the relevant content of the difference in influence, please refer to the specific content of step S104.

[0050] For example, the influence of the geographical environment characteristics of any stratification unit (non-sparse stratification unit or non-sparse stratification unit) on the soil properties in the soil sampling area is determined by the following method: Value and Based on the calculation of the geographic detector The value reflects the contribution of each geographical environment feature to the distribution of the target soil survey and monitoring attributes. The larger the value, the greater the contribution of geographical environment characteristics to soil target properties. The second step is to use the risk area detection function of the geographical detector to detect the soil target properties. The statistic tests the importance of each distribution feature relative to the target soil property under the geographical environment characteristics. The larger the value, the more important the distribution feature is to the soil properties.

[0051] It should be noted that in the embodiment of the present invention, the specific calculation process of the contribution of each geographical environment feature to the distribution of the target soil survey and monitoring attribute is not specifically limited, and the importance of each distribution feature under the geographical environment feature relative to the target soil attribute is not specifically limited, so as to meet the above Value and The value is defined as follows.

[0052] In a possible implementation, the influence of the geographical environment characteristics of the stratified unit on the soil properties in the soil sampling area is , determined by the following formula: in, is the q value of the sth geographical environment feature, is the distribution characteristic corresponding to the sth geographical environment characteristic in the stratified unit The t-value of .

[0053] In the embodiment of the present invention, the relationship between the geographical environment feature and its corresponding distribution feature is given as an example. If the geographical environment feature is soil dryness, its corresponding distribution feature may include: dry, moist, wet, etc. In a stratified unit, for the geographical environment feature of soil dryness, its distribution feature may include: dry, moist, wet or one or more. In different stratified units, the geographical environment feature is the same, but the distribution feature may be different.

[0054] Step S104: Obtaining the influence difference value between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit according to the first influence and the second influence.

[0055] Based on the above, for Two hierarchical units, evaluate the hierarchical unit to be optimized With non-sparse hierarchical units The difference in influence between them is: .

[0056] Step S105 : selecting a target hierarchical unit from a plurality of non-sparse hierarchical units according to the environmental similarity and the influence difference value, and using the sample points in the target hierarchical unit as virtual sample points of the hierarchical unit to be optimized.

[0057] In a possible implementation manner, in step S105, selecting a target hierarchical unit from a plurality of non-sparse hierarchical units according to the environmental similarity and the influence difference value specifically includes: Calculate the ratio between the environmental similarity and the influence difference value to obtain the ratio corresponding to each non-sparse hierarchical unit; wherein the environmental similarity is proportional to the ratio, and the influence difference value is inversely proportional to the ratio; sort the ratio corresponding to each non-sparse hierarchical unit from large to small, and determine the non-sparse hierarchical unit with the first ranking as the target hierarchical unit; wherein the environmental similarity between the hierarchical unit to be optimized and the target hierarchical unit is greater than the environmental similarity threshold.

[0058] In an embodiment of the present invention, the target hierarchical unit is determined based on the principle of "maximum environmental similarity and minimum impact difference value". Since only the ratio of environmental similarity to impact difference value is considered to select the target hierarchical unit, a non-sparse hierarchical unit with too small environmental similarity may be determined as the target hierarchical unit. Therefore, when sorting the ratio corresponding to each non-sparse hierarchical unit from large to small, it is necessary to pre-set the environmental similarity threshold, and only the non-sparse hierarchical units with environmental similarity greater than the environmental similarity threshold can be used for the subsequent sorting process of the ratio of environmental similarity to impact difference value. In the embodiment of the present invention, the selection of the environmental similarity threshold is not specifically limited.

[0059] By calculating the ratio of the environmental similarity to the influence difference value, the ratio corresponding to each non-sparse hierarchical unit is sorted from large to small, and the non-sparse hierarchical unit with the first ranking is determined as the target hierarchical unit.

[0060] Finally, the sample points in the target hierarchical unit are used as virtual sample points of the hierarchical unit to be encrypted. The sample points in the target hierarchical unit can be all or part of the virtual sample points of the hierarchical unit to be encrypted, which is not specifically limited in the embodiment of the present invention.

[0061] The present invention can achieve the following beneficial effects by adopting the above method: The environmental similarity between the sparse stratification units and the non-sparse stratification units is obtained; as well as the difference in the influence of the geographical environmental characteristics of the sparse stratification units and the non-sparse stratification units on the soil properties in the soil sampling area; while ensuring that the environmental similarity is high and the difference in influence is small, the target stratification unit is selected from multiple non-sparse stratification units, and the sample points in the target stratification unit are used as virtual sample points of the stratification unit to be optimized, thereby improving the representativeness of the sample points in the sparse sampling area during the soil property survey.

[0062] The sampling point optimization device for a sparsely sampled area of ​​soil provided by the present invention is described below. The sampling point optimization device for a sparsely sampled area of ​​soil described below and the sampling point optimization device for a sparsely sampled area of ​​soil described above can be referred to each other.

[0063] Figure 4 A schematic diagram of the structure of a sampling point optimization device for a sparsely sampled soil area provided by the present invention includes the following parts: The regional stratification module 410 is used to construct a stratification standard according to one or more geographical environmental characteristics; and stratify the soil sampling area according to the stratification standard to obtain a plurality of stratification units.

[0064] The region identification module 420 is used to identify sparse hierarchical units and non-sparse hierarchical units among the multiple hierarchical units; and to use each sparse hierarchical unit as a hierarchical unit to be optimized.

[0065] The similarity acquisition module 430 is used to acquire the environmental similarity between the hierarchical unit to be optimized and the non-sparse hierarchical unit.

[0066] The influence acquisition module 440 is used to calculate the first influence of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculate the second influence of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; based on the first influence and the second influence, the influence difference value between the stratified unit to be optimized and the non-sparse stratified unit is obtained.

[0067] The sample point optimization module 450 is used to select a target hierarchical unit from a plurality of non-sparse hierarchical units according to the environmental similarity and influence difference values, and use the sample points in the target hierarchical unit as virtual sample points of the hierarchical unit to be optimized.

[0068] In a possible implementation, the region identification module 420 is specifically configured to: According to the number of sample points and unit area of ​​each stratified unit, the sample point density of each stratified unit is obtained; According to the sample point density of each hierarchical unit, sparse hierarchical units and non-sparse hierarchical units in the plurality of hierarchical units are identified.

[0069] In a possible implementation, the similarity acquisition module 430 is specifically configured to: Obtaining the feature similarity of each geographical environment feature between the stratification unit to be optimized and the non-sparse stratification unit; According to the similarity of each feature, the environmental similarity is obtained.

[0070] In a possible implementation, the geographical environment feature includes a category feature; the similarity acquisition module 430 is specifically used to: If the geographical environment feature is a categorical feature, the feature similarity of the geographical environment feature is obtained by judging whether the categorical feature of the stratification unit to be optimized is the same as the categorical feature of the non-sparse stratification unit.

[0071] In a possible implementation, the geographical environment feature includes a numerical feature; the similarity acquisition module 430 is specifically used to: If the geographical environment feature is a numerical feature, obtaining a first probability density distribution curve of the numerical feature of the hierarchical unit to be optimized and a second probability density distribution curve of the numerical feature of the non-sparse hierarchical unit; Obtaining the first curve coverage area of ​​the to-be-optimized hierarchical unit under the numerical characteristics through the first probability density distribution curve; Through the second probability density distribution curve, the second curve coverage area of ​​the non-sparse hierarchical unit under the numerical feature is obtained; Obtaining the intersection coverage area of ​​the curves through the first probability density distribution curve and the second probability density distribution curve; The feature similarity of the geographical environment feature is obtained according to the first curve coverage area, the second curve coverage area and the curve intersection coverage area.

[0072] In a possible implementation, the sample point optimization module 450 is specifically configured to: Calculate the ratio between the environmental similarity and the influence difference value to obtain the ratio corresponding to each non-sparse hierarchical unit; wherein the environmental similarity is proportional to the ratio, and the influence difference value is inversely proportional to the ratio; The ratios corresponding to each non-sparse hierarchical unit are sorted from large to small, and the non-sparse hierarchical unit with the first sorting is determined as the target hierarchical unit; The environmental similarity between the hierarchical unit to be optimized and the target hierarchical unit is greater than the environmental similarity threshold.

[0073] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a sampling point optimization method for a sparsely sampled area of ​​soil, the method comprising: According to one or more geographical environmental characteristics, a stratification standard is constructed; and according to the stratification standard, the soil sampling area is stratified to obtain a plurality of stratification units; Identify sparse hierarchical units and non-sparse hierarchical units among the plurality of hierarchical units; and use each sparse hierarchical unit as a hierarchical unit to be optimized; Obtaining the environmental similarity between the hierarchical unit to be optimized and the non-sparse hierarchical unit; Calculate the first influence of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculate the second influence of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; obtain the difference in influence between the stratified unit to be optimized and the non-sparse stratified unit according to the first influence and the second influence; According to the difference values ​​of environmental similarity and influence, a target hierarchical unit is selected from multiple non-sparse hierarchical units, and the sample points in the target hierarchical unit are used as virtual sample points of the hierarchical unit to be optimized.

[0074] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0075] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored in a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute a method for optimizing sampling points in a sparsely sampled area of ​​soil sampling provided by the above methods, the method comprising: According to one or more geographical environmental characteristics, a stratification standard is constructed; and according to the stratification standard, the soil sampling area is stratified to obtain a plurality of stratification units; Identify sparse hierarchical units and non-sparse hierarchical units among the plurality of hierarchical units; and use each sparse hierarchical unit as a hierarchical unit to be optimized; Obtaining the environmental similarity between the hierarchical unit to be optimized and the non-sparse hierarchical unit; Calculate the first influence of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculate the second influence of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; obtain the difference in influence between the stratified unit to be optimized and the non-sparse stratified unit according to the first influence and the second influence; According to the difference values ​​of environmental similarity and influence, a target hierarchical unit is selected from multiple non-sparse hierarchical units, and the sample points in the target hierarchical unit are used as virtual sample points of the hierarchical unit to be optimized.

[0076] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform a method for optimizing sampling points in a sparsely sampled area of ​​soil provided by the above methods, the method comprising: According to one or more geographical environmental characteristics, a stratification standard is constructed; and according to the stratification standard, the soil sampling area is stratified to obtain a plurality of stratification units; Identify sparse hierarchical units and non-sparse hierarchical units among the plurality of hierarchical units; and use each sparse hierarchical unit as a hierarchical unit to be optimized; Obtaining the environmental similarity between the hierarchical unit to be optimized and the non-sparse hierarchical unit; Calculate the first influence of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculate the second influence of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; obtain the difference in influence between the stratified unit to be optimized and the non-sparse stratified unit according to the first influence and the second influence; According to the difference values ​​of environmental similarity and influence, a target hierarchical unit is selected from multiple non-sparse hierarchical units, and the sample points in the target hierarchical unit are used as virtual sample points of the hierarchical unit to be optimized.

[0077] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0078] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing sampling points in a sparsely sampled area of ​​soil, characterized in that: include: Constructing stratification criteria based on one or more geographic environmental characteristics; and stratifying the soil sampling area according to the stratification standard to obtain a plurality of stratification units; Identifying sparse hierarchical units and non-sparse hierarchical units among a plurality of hierarchical units; Taking each sparse hierarchical unit as a hierarchical unit to be optimized; Obtaining the environmental similarity between the stratified unit to be optimized and the non-sparse stratified unit; and calculating the first influence of the geographical environmental characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculating the second influence of the geographical environmental characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; Obtaining, according to the first influence and the second influence, an influence difference value between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit; According to the environmental similarity and the influence difference value, a target hierarchical unit is selected from the plurality of non-sparse hierarchical units, and the sample points in the target hierarchical unit are used as virtual sample points of the hierarchical unit to be optimized.

2. The method for optimizing sampling points in a sparsely sampled area of ​​soil according to claim 1, characterized in that: The identifying of sparse hierarchical units and non-sparse hierarchical units among the plurality of hierarchical units specifically includes: According to the number of sample points and unit area of ​​each stratified unit, the sample point density of each stratified unit is obtained; According to the sample point density of each hierarchical unit, sparse hierarchical units and non-sparse hierarchical units in the plurality of hierarchical units are identified.

3. The method for optimizing sampling points in a sparsely sampled area of ​​soil according to claim 1, characterized in that: The obtaining of the environmental similarity between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit specifically includes: Obtaining the feature similarity of each geographical environment feature between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit; The environment similarity is obtained according to the similarities of each feature.

4. The method for optimizing sampling points in a sparsely sampled area of ​​soil according to claim 3, characterized in that: The geographical environment feature includes a category feature; the obtaining of the feature similarity of each geographical environment feature between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit specifically includes: If the geographical environment feature is a categorical feature, the feature similarity of the geographical environment feature is obtained by judging whether the categorical feature of the to-be-optimized hierarchical unit is the same as the categorical feature of the non-sparse hierarchical unit.

5. The method for optimizing sampling points in a sparsely sampled area of ​​soil according to claim 3, characterized in that: The geographical environment feature includes a numerical feature; the obtaining of the feature similarity of each geographical environment feature between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit specifically includes: If the geographical environment feature is a numerical feature, obtaining a first probability density distribution curve of the numerical feature of the to-be-optimized hierarchical unit and a second probability density distribution curve of the numerical feature of the non-sparse hierarchical unit; Obtaining a first curve coverage area of ​​the to-be-optimized hierarchical unit under the numerical characteristics through the first probability density distribution curve; Obtaining a second curve coverage area of ​​the non-sparse hierarchical unit under the numerical feature through the second probability density distribution curve; Obtaining a curve intersection coverage area through the first probability density distribution curve and the second probability density distribution curve; The feature similarity of the geographical environment feature is obtained according to the first curve coverage area, the second curve coverage area and the curve intersection coverage area.

6. The method for optimizing sampling points in a sparsely sampled area of ​​soil according to claim 1, characterized in that: Selecting a target hierarchical unit from the plurality of non-sparse hierarchical units according to the environmental similarity and the influence difference value specifically includes: Calculating the ratio between the environmental similarity and the influence difference value to obtain the ratio corresponding to each of the non-sparse hierarchical units; wherein the environmental similarity is proportional to the ratio, and the influence difference value is inversely proportional to the ratio; Sorting the ratios corresponding to each of the non-sparse hierarchical units from large to small, and determining the first-ranked non-sparse hierarchical unit as the target hierarchical unit; The environmental similarity between the to-be-optimized hierarchical unit and the target hierarchical unit is greater than an environmental similarity threshold.

7. A sampling point optimization device for sparse soil sampling areas, characterized in that: include: A regional stratification module is used to construct stratification standards based on one or more geographical environmental characteristics; and stratifying the soil sampling area according to the stratification standard to obtain a plurality of stratification units; A region identification module, used for identifying sparse hierarchical units and non-sparse hierarchical units among the plurality of hierarchical units; Taking each sparse hierarchical unit as a hierarchical unit to be optimized; A similarity acquisition module, used to acquire the environmental similarity between the to-be-optimized hierarchical unit and the non-sparse hierarchical unit; An influence degree acquisition module is used to calculate the first influence degree of the geographical environment characteristics of the stratified unit to be optimized on the soil properties in the soil sampling area, and calculate the second influence degree of the geographical environment characteristics of the non-sparse stratified unit on the soil properties in the soil sampling area; according to the first influence degree and the second influence degree, obtain the influence degree difference value between the stratified unit to be optimized and the non-sparse stratified unit; The sample point optimization module is used to select a target hierarchical unit from the plurality of non-sparse hierarchical units according to the environmental similarity and the influence difference value, and use the sample points in the target hierarchical unit as virtual sample points of the hierarchical unit to be optimized.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the sampling point optimization method for a sparsely sampled soil area according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the sampling point optimization method for a sparsely sampled soil area according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the sampling point optimization method for a sparsely sampled soil area according to any one of claims 1 to 6 is implemented.

Images