Intelligent analysis method and system based on cloud computing land resource information data

Abstract

The invention relates to the field of data processing, in particular to an intelligent analysis method and system based on cloud computing land resource information data, and the method comprises the steps: carrying out the regional division of a land, obtaining a plurality of regions, and constructing a data set of each region; the data set comprises three soil data including soil nutrients, pH value and vegetation coverage rate; acquiring a local Moran index of each piece of soil data in each region, calculating a spatial heterogeneity index of each region, and taking a reciprocal of a product of the local Moran index of the soil data and the spatial heterogeneity index as a correlation anomaly degree of the corresponding soil data; and marking the region where the correlation abnormal degree of the soil data is greater than a preset abnormal threshold value as an abnormal region, and making a treatment measure for the abnormal region. According to the method, the local Moran index, the spatial heterogeneity index and the correlation anomaly degree of the soil data are calculated and analyzed, so that the abnormal region can be accurately identified, and targeted treatment measures can be formulated.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more specifically, to an intelligent analysis method and system for land resource information data based on cloud computing. Background Art

[0002] As an important component of the earth's land surface, soil is not only the material basis for agricultural and urban development, but also a key factor in maintaining ecological balance and promoting sustainable development. Through in-depth soil data analysis, we can fully understand key indicators such as soil nutrient status, pH, organic matter content, etc. These indicators are of great significance for guiding agricultural production, optimizing land use methods, and protecting the ecological environment.

[0003] Prior art, such as a patent application document with publication number CN118735714A, discloses a soil improvement data analysis method and system. The soil improvement data analysis method includes: regularly or continuously sampling soil moisture and salt at a sample site, recording the soil data, and based on the data, studying the soil moisture content and salt content, establishing a database, analyzing the spatiotemporal distribution and variation characteristics before and after improvement, and drawing a spatial distribution map. In combination with changes in groundwater depth, the soil improvement situation is analyzed, adaptation information is obtained, and based on the analysis results, abnormal soil is managed and the improvement plan is optimized.

[0004] The above soil improvement data analysis method evaluates the effect of soil improvement by analyzing and visualizing the spatial distribution of soil data, and adjusts the management strategy accordingly. However, it does not take into account the differences in soil properties at different spatial locations, which leads to significant differences in soil property values ​​in some areas from those in the surrounding areas during analysis. These outliers may not be true outliers, making the soil property analysis results inaccurate. Summary of the invention

[0005] In order to solve the above-mentioned technical problem of inaccurate soil property analysis results, the present invention provides solutions in the following aspects.

[0006] In a first aspect, an intelligent analysis method for land resource information data based on cloud computing includes: Divide the land into regions to obtain multiple regions, and construct a data set for each region; the data set includes three soil data items: soil nutrients, pH, and vegetation coverage; Obtaining the local Moran's index of each soil data item in each region, and calculating the spatial heterogeneity index of each region, and taking the inverse of the product of the local Moran's index of the soil data and the spatial heterogeneity index as the correlation abnormality degree of the corresponding soil data; Mark the area where the correlation anomaly degree of soil data is greater than the preset anomaly threshold as an abnormal area, and formulate treatment measures for the abnormal area; The spatial heterogeneity index satisfies the relationship: ; In the formula, For the The spatial heterogeneity index of a region, is the number of items of soil data collected, For all regions The weight of the soil data, For the In the region Neighborhood difference of soil data, For the The mean of the neighborhood differences of all soil data items in a region.

[0007] The present invention analyzes the spatial distribution characteristics of soil data, calculates the corresponding local Moran index and spatial heterogeneity index, and comprehensively considers the similarity of soil properties in adjacent areas and the spatial differences of soil properties, which helps to more accurately understand the spatial distribution law of soil properties, thereby improving the accuracy of the analysis results.

[0008] Preferably, the process of obtaining the neighborhood difference includes: Calculate the The mean of the Euclidean distances between the region and all other regions. The area whose Euclidean distance is less than the preset distance threshold is taken as the first The neighborhood of a region; Calculate the The first Soil data and In the region The mean of the numerical differences of the soil data is obtained In the region Neighborhood difference of soil data.

[0009] Neighborhood diversity reflects the The degree of difference between a region and its neighboring regions in soil data. This degree of difference can reveal the spatial distribution characteristics of soil data, including similarity, difference and change trend; when the degree of difference between the neighboring regions of a certain region is significantly larger or smaller, it may mean that there are abnormal soil properties in the region, which requires special attention and treatment.

[0010] Preferably, the process of obtaining the abnormal threshold is: The average value and standard deviation of the correlation anomaly degree of any soil data in all regions are calculated, and the sum of the average value and the standard deviation is used as the anomaly threshold.

[0011] The calculation of the anomaly threshold takes into account the mean and standard deviation of the correlation anomaly degree, which can reflect the distribution characteristics of soil data in all areas. The mean represents the overall level, while the standard deviation reflects the degree of dispersion of the data. The combination of the two makes the anomaly threshold more in line with the actual situation of the data.

[0012] Preferably, the entire area The weight of each soil data item satisfies the following relationship: ; In the formula, For all regions The weight of the soil data, For all regions Global Moran's index for soil data.

[0013] When analyzing soil data, the weight of each soil data will directly affect the accuracy and reliability of the analysis results. By setting reasonable weights, the analysis process can be optimized and the analysis results can be more in line with the actual situation. By setting weights using the above relationship, soil data with strong spatial autocorrelation can be given a greater weight in the analysis, thereby improving the accuracy of the analysis results.

[0014] Preferably, the process of obtaining the neighborhood difference includes: Calculate the The mean of the Euclidean distances of the region to all other regions. The area whose Euclidean distance is less than the preset distance threshold is taken as the first The neighborhood of a region; For each neighborhood area, The average Euclidean distance between the region and all regions and the The product of the reciprocal of the Euclidean distance between a region and the neighborhood region is taken as the distance weight of the neighborhood region; For each neighborhood area Soil data and In the region The numerical difference of each soil data item is multiplied by the corresponding distance weight and summed, and then divided by the number of neighboring areas to obtain the In the region Neighborhood difference of soil data.

[0015] Neighborhood difference is an important indicator to measure the difference between soil data in different regions. The numerical differences of soil data in different regions and the consideration of distance weights can reflect the spatial heterogeneity of soil data, which is an important basis for formulating targeted treatment measures.

[0016] Preferably, the entire area The weight of each soil data item satisfies the following relationship: ; In the formula, For all regions The weight of the soil data, For all regions The global Moran index of the soil data, is a constant.

[0017] Preferably, the abnormal degree of correlation also satisfies the relationship: ; In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region.

[0018] Preferably, the abnormal degree of correlation also satisfies the relationship: ; In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region, , All are weights.

[0019] In the second aspect, an intelligent analysis system for land resource information data based on cloud computing includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent analysis method for land resource information data based on cloud computing is implemented.

[0020] The beneficial effects of the present invention are: The present invention divides the analyzed land into regions, takes into account the spatial distribution characteristics of soil data, calculates the local Moran index and the spatial heterogeneity index, and calculates the degree of data correlation anomaly based on the local Moran index and the spatial heterogeneity index. This comprehensive analysis helps to more accurately understand the spatial distribution law of soil properties, thereby improving the accuracy of the analysis results; By further setting anomaly thresholds, areas with abnormal soil properties can be accurately identified. These areas are often areas with poor soil quality or potential problems and require special attention and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a method flow chart of steps S1 to S3 in the intelligent analysis method of land resource information data based on cloud computing in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] The embodiment of the present invention discloses an intelligent analysis method of land resource information data based on cloud computing, referring to Figure 1 , including steps S1 to S3, which are specifically as follows: S1: Divide the land into regions to obtain multiple regions, and construct a data set for each region; the data set includes three soil data items: soil nutrients, pH, and vegetation coverage.

[0024] Based on the influencing factors of land use (such as output capacity, vegetation coverage, artificial coverage, etc.), empirical division is carried out, and the areas with similar differences in land influencing factor data are divided into the same area to reduce data fluctuations and errors. Then the total number of land area divisions is recorded as .

[0025] Collect data for each area and determine the data items that need to be collected, including but not limited to land production capacity, vegetation coverage, artificial coverage, soil nutrient content, pH, altitude, slope, etc. The number of items of collected data is recorded as follows: (Example collection of three soil data items: soil nutrients, pH and vegetation coverage, namely Among them, vegetation coverage, artificial coverage and output capacity can be counted through field surveys, satellite remote sensing, etc., soil nutrient content and pH can be sampled and averaged in each area, and soil analysis can be performed using professional instruments. Altitude and slope can be measured using mobile meteorological equipment (such as GPS, altimeter, incline meter, etc.).

[0026] Further, the first The soil data value is recorded as ,in Indicates the area number (1≤ ≤ ), Indicates the data item number (1≤ ≤ ).

[0027] S2: Obtain the local Moran's index of each soil data item in each region, and calculate the spatial heterogeneity index of each region, and use the inverse of the product of the local Moran's index of the soil data and the spatial heterogeneity index as the correlation anomaly degree of the corresponding soil data.

[0028] In an embodiment of the present invention, the Moran index is used to analyze land attributes to identify which areas have significant spatial aggregation or dispersion. However, due to spatial heterogeneity caused by natural or human factors, the local Moran index of some areas may show abnormalities. The "abnormal" here does not mean that the data is wrong or problematic, but reflects the uniqueness of these areas in spatial distribution. If these "abnormal" areas caused by normal spatial heterogeneity and areas where there may be real problems (such as data errors, abnormal events, etc.) are not distinguished, normal spatial heterogeneity areas may be mistakenly identified as abnormal areas. Such misidentification will affect the technicians' accurate judgment of land resource information data, and thus lead to inappropriate decisions or analysis conclusions.

[0029] First, obtain the centroid corresponding to the outline of each region, and calculate the distance between any two regions based on the Euclidean distance between the centroids of each region. Based on the Euclidean distance, calculate the distance weight between each pair of regions, that is, the reciprocal of the Euclidean distance, expressed as ,in, For the Region and The distance weight of the region, For the Region and Then, all distance weights of the regions are sorted into a spatial weight matrix W. The global and local Moran indexes are calculated using the spatial weight matrix W and the data values ​​of all regions. For example, the distance weights of all regions are sorted into a spatial weight matrix W. The global Moran index of the soil data is denoted by , will In the region The local Moran index of the soil data is denoted by .

[0030] It should be noted that the Moran index is a prior art, and the specific steps for obtaining it will not be described in detail.

[0031] Secondly, for each region, the difference between it and all neighboring regions in each data is calculated.

[0032] Specifically, calculate the The mean of the Euclidean distances between the region and all other regions. The Euclidean distance of the first region is less than the preset distance threshold (in the embodiment of the present invention, the The region with the mean of the Euclidean distances between the region and all other regions as the distance threshold) is taken as the first The neighborhood area of ​​the area; calculate the The first Soil data and In the region The mean of the numerical differences of the soil data is obtained In the region Neighborhood difference of soil data.

[0033] For example, In the region The neighborhood difference of the soil data satisfies the relationship:

[0034] In the formula, For the In the region Neighborhood difference of soil data, For the The total number of neighboring regions of a region, For the The neighborhood area Item soil data value, For the In the region Item soil data value.

[0035] When The relationship between a region and its neighboring regions When the difference of soil data increases, It also increases, which means that the spatial autocorrelation of this soil data is weakened and the spatial variability is enhanced.

[0036] Furthermore, considering the close distance between the area and the The soil properties and environmental conditions of the two regions are more similar, and a distance weight is introduced to make the closer regions more important to the first region. The impact on the region is greater.

[0037] Specifically, calculate the The mean of the Euclidean distances of the region to all other regions. The area whose Euclidean distance is less than the preset distance threshold is taken as the first The neighborhood area of ​​the area; for each neighborhood area, the The average Euclidean distance between the region and all regions and the The product of the reciprocal of the Euclidean distance between the region and the neighborhood region is used as the distance weight of the neighborhood region; the distance weight of each neighborhood region is taken as the Soil data and In the region The numerical difference of each soil data item is multiplied by the corresponding distance weight and summed, and then divided by the number of neighboring areas to obtain the In the region Neighborhood difference of soil data.

[0038] For example, after the distance weight is introduced, In the region The neighborhood difference of the soil data satisfies the relationship:

[0039] In the formula, For the In the region Neighborhood difference of soil data, For the The total number of neighboring regions of a region, For the Region and The Euclidean distance between neighboring regions is For the The average Euclidean distance between a region and all regions, For the The neighborhood area Item soil data value, For the In the region Item soil data value.

[0040] By adjusting the distance weight, the contribution of different neighboring areas to the difference of the central area can be balanced. Although distant areas also have a certain correlation, their influence is relatively small, so their weight is also relatively low. This can avoid the deviation of the overall difference calculation result caused by abnormal data in individual distant areas.

[0041] Then, the spatial heterogeneity index of the region is obtained according to the degree of neighborhood difference of each data in each region, that is, the relationship is satisfied:

[0042] In the formula, For the The spatial heterogeneity index of a region, is the number of items of soil data collected, For all regions The weight of the soil data, For the In the region Neighborhood difference of soil data, For the The mean of the neighborhood differences of all soil data items in a region.

[0043] in, ; In the formula, For all regions The weight of the soil data, For all regions Global Moran's index for soil data.

[0044] Indicates In the region The difference between the neighborhood difference of the soil data and the average neighborhood difference of all data. The higher the value, the greater the difference between the neighborhood difference of all data, that is, the neighborhood difference of all data is not uniform, which may mean that the data in this area is abnormal or special.

[0045] Indicates The result of normalizing the Moran index of the soil data (the global Moran index range is (-1, 1)). The Moran index is an indicator to measure the spatial autocorrelation of data. The closer the value is to 1, the stronger the positive correlation is. The closer the value is to -1, the stronger the negative correlation is. The closer the value is to 0, the no significant autocorrelation is. In the spatial heterogeneity index formula, The smaller the Moran's index of a soil data item is, the weaker the autocorrelation of the data is, and the lower the reference degree of the gap of the data is.

[0046] The spatial heterogeneity of each region is quantified by combining neighborhood dissimilarity and Moran's index. Neighborhood dissimilarity reflects the difference between the data within the region and the neighborhood data, while Moran's index provides additional information on the spatial autocorrelation of the data. These two factors work together to enable the spatial heterogeneity index to more comprehensively reflect the spatial heterogeneity characteristics of the region.

[0047] It should be noted that The calculation of also provides another calculation method, which satisfies the relationship:

[0048] In the formula, For all regions The weight of the soil data, For all regions The global Moran index of the soil data, is a constant.

[0049] Finally, the The local Moran index of the soil data is The inverse of the product of the spatial heterogeneity indexes of the regions is taken as the Region No. The abnormal degree of correlation of the soil data. That is, the relationship is:

[0050] In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region.

[0051] The above correlation abnormality provides another calculation formula:

[0052] In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region.

[0053] This formula is different from the first formula for calculating the degree of abnormal correlation in that it uses The absolute value of ensures that even if the local Moran index is negative, its contribution to the degree of correlation anomaly is positive, thus fully considering the directionality of spatial autocorrelation.

[0054] The above correlation abnormality degree also provides another calculation formula:

[0055] In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region, , All are weights.

[0056] This calculation formula is different from the first formula for calculating the degree of abnormal correlation in that the weight coefficient is used and To balance the contribution of the two indicators, the analysis results can be adjusted according to the specific situation. For example, if the local Moran index is more important for the relevance of a specific data set, you can increase On the contrary, if the spatial heterogeneity index is more critical, you can increase The value of .

[0057] Then the correlation anomaly degree of all soil data is obtained.

[0058] S3: Mark the area where the correlation anomaly degree of soil data is greater than the preset anomaly threshold as an abnormal area, and formulate treatment measures for the abnormal area.

[0059] Based on the correlation anomaly degree of all soil data calculated in the above step S2, when the soil data of a certain area shows a high correlation anomaly degree, it means that the spatial autocorrelation between the soil data in the area is low, that is, the correlation between the data is not strong, and there may be problems such as uneven data distribution, mutation or outliers.

[0060] Specifically, calculate the mean and standard deviation of the degree of correlation anomaly of any soil data in all areas, take the sum of the mean and the standard deviation as the anomaly threshold, mark the areas where the degree of correlation anomaly of soil data is greater than the anomaly threshold as abnormal areas, and formulate treatment measures for abnormal areas (such as conducting in-depth analysis of abnormal areas to find out the causes of data anomalies, which may be caused by pollution sources, geological conditions or other environmental factors, and technical personnel can further formulate remediation plans).

[0061] An embodiment of the present invention also discloses an intelligent analysis system for land resource information data based on cloud computing, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an intelligent analysis method for land resource information data based on cloud computing according to the present invention is implemented.

[0062] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0063] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0064] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0065] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. An intelligent analysis method for land resource information data based on cloud computing, characterized in that: include: Divide the land into regions to obtain multiple regions, and construct a data set for each region; the data set includes three soil data items: soil nutrients, pH, and vegetation coverage; Obtaining the local Moran's index of each soil data item in each region, and calculating the spatial heterogeneity index of each region, and taking the inverse of the product of the local Moran's index of the soil data and the spatial heterogeneity index as the correlation abnormality degree of the corresponding soil data; Mark the area where the correlation anomaly degree of soil data is greater than the preset anomaly threshold as an abnormal area, and formulate treatment measures for the abnormal area; The spatial heterogeneity index satisfies the relationship: ; In the formula, For the The spatial heterogeneity index of a region, is the number of items of soil data collected, For all regions The weight of the soil data, For the In the region Neighborhood difference of soil data, For the The mean of the neighborhood differences of all soil data items in a region.

2. The intelligent analysis method of land resource information data based on cloud computing according to claim 1 is characterized in that: The process of obtaining the neighborhood difference includes: Calculate the The mean of the Euclidean distances between the region and all other regions. The area whose Euclidean distance is less than the preset distance threshold is taken as the first The neighborhood of a region; Calculate the The first Soil data and In the region The mean of the numerical differences of the soil data is obtained In the region Neighborhood difference of soil data.

3. The intelligent analysis method of land resource information data based on cloud computing according to claim 2 is characterized in that: The process of obtaining the abnormal threshold is as follows: The average value and standard deviation of the correlation anomaly degree of any soil data in all regions are calculated, and the sum of the average value and the standard deviation is used as the anomaly threshold.

4. The intelligent analysis method of land resource information data based on cloud computing according to claim 3 is characterized in that: All areas The weight of each soil data item satisfies the following relationship: ; In the formula, For all regions The weight of the soil data, For all regions Global Moran's index for soil data.

5. The intelligent analysis method of land resource information data based on cloud computing according to claim 1 is characterized in that: The process of obtaining the neighborhood difference includes: Calculate the The mean of the Euclidean distances of the region to all other regions. The area whose Euclidean distance is less than the preset distance threshold is taken as the first The neighborhood of a region; For each neighborhood area, The average Euclidean distance between the region and all regions and the The product of the reciprocal of the Euclidean distance between a region and the neighborhood region is taken as the distance weight of the neighborhood region; For each neighborhood area Soil data and In the region The numerical difference of each soil data item is multiplied by the corresponding distance weight and summed, and then divided by the number of neighboring areas to obtain the In the region Neighborhood difference of soil data.

6. The intelligent analysis method of land resource information data based on cloud computing according to claim 1 is characterized in that: All the areas The weight of each soil data item satisfies the following relationship: ; In the formula, For all regions The weight of the soil data, For all regions The global Moran index of the soil data, is a constant.

7. The intelligent analysis method of land resource information data based on cloud computing according to claim 1 is characterized in that: The abnormal degree of correlation also satisfies the relationship: ; In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region.

8. The intelligent analysis method of land resource information data based on cloud computing according to claim 1 is characterized in that: The abnormal degree of correlation also satisfies the relationship: ; In the formula, For the In the region The abnormal degree of correlation of soil data, For the In the region The local Moran index of the soil data, For the The spatial heterogeneity index of a region, , All are weights.

9. Intelligent analysis system of land resource information data based on cloud computing, characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent analysis method for land resource information data based on cloud computing according to any one of claims 1 to 8 is implemented.

Images