Geological overburden interpolation method based on ebk regression analysis

Abstract

The present application provides a kind of geological overburden interpolation method based on EBK regression analysis, specific steps are as follows: step S1: according to data acquisition structure extraction geological overburden data;Step S2: for transmission and transformation engineering survey data, cleaning and pretreatment are carried out, while the terrain elevation data and slope data of experimental area are prepared;Step S3: exploratory analysis is carried out on the cleaned data, the spatial distribution mode and numerical distribution of geological overburden data are determined to be transformed, and the correlation of interpretation variable is prepared and judged;Step S4: regression analysis is carried out using geological prior knowledge and topographic data, and the numerical value of the exploration point drilling is fitted to obtain the semi-variogram function distribution, to predict the numerical value of the interpolation region.

Description

Technical Field

[0001] This invention belongs to the field of power transmission and transformation engineering survey data processing technology, specifically involving a geological overburden interpolation method based on EBK regression analysis. Background Technology

[0002] The surveying process for power transmission and transformation projects generates a large amount of data, but the use of this data is often limited to specific projects. Collecting geological exploration data from past projects and using statistical methods to analyze and interpolate the data to create geological distribution maps of relevant attributes has significant engineering application benefits. To meet the needs of geological overburden mapping, it is necessary to design data interpolation methods with geoscientific characteristics.

[0003] Existing statistical methods are generally divided into deterministic interpolation methods and geostatistical methods. The main deterministic methods are: inverse distance weighting method, polynomial interpolation method, and radial basis function method. The main idea is to fit a polynomial or distance weighting function to the input data and use the function to calculate the value at a specified location.

[0004] One of the most important types of geostatistical methods is the kriging method. The kriging method assumes that the interpolated content has spatial autocorrelation. It uses the input sample to statistically analyze the distribution parameters of geological attribute values ​​in a specific area, and uses the distribution mode and spatial variability function to predict the probability of values ​​at a specified location.

[0005] Taking Kriging interpolation as an example, it generally includes the following steps:

[0006] Step 1, Data Extraction: Obtain geological overburden data and borehole locations.

[0007] Step 2, Data Cleaning: Clean up exploration points with incorrect attribute types in the geological data; perform spatial visualization operations on the geological data to remove data points outside the experimental area.

[0008] Step 3: Ordinary Kriging Interpolation

[0009] a. Importing exploration point data

[0010] b. Select an appropriate exponential semivariogram based on the geological data, estimate the semivariogram for all exploration point data, and obtain a definite semivariogram.

[0011] c. Calculate the distance between the interpolation location and the data of nearby exploration points, use the semivariogram function to calculate the semivariogram of the interpolation location and the corresponding exploration point data, and use the exploration point distance as the weight to calculate the final predicted value of the location.

[0012] Traditional methods require minimal human intervention and involve relatively simple procedures, enabling rapid and effective acquisition of geological distribution characteristics over a wide area. However, they cannot accurately predict the thickness of overburden in unsampled areas solely based on exploration point data. Furthermore, because geological overburden data is unstable, the lack of prior regional division of the data makes it impossible to effectively control the influence of the sample data, leading to biases in variance estimation. Summary of the Invention

[0013] Existing technical solutions, whether deterministic or geostatistical, demonstrate good interpolation performance when data distribution is sufficient and uniform. However, in specific engineering projects, complex geological conditions often fail to meet the computational requirements. To address this issue, this invention employs EBK combined with regression analysis for interpolation prediction of geological overburden.

[0014] EBK: Empirical Bayesian Kriging, an interpolation method in statistics.

[0015] The steps of this invention are as follows: Step S1: Extract geological overburden data based on the data acquisition structure; Step S2: Clean and preprocess the survey data for power transmission and transformation projects, and simultaneously prepare the topographic elevation and slope data of the experimental area; Step S3: Perform exploratory analysis on the cleaned data, determine the spatial distribution and numerical distribution of the geological overburden data, transform them, and prepare and judge the correlation of explanatory variables; Step S4: Use prior geological knowledge and topographic data to perform regression analysis, fit the borehole values ​​at the exploration points to obtain the semi-variogram distribution, and use this to make numerical predictions for the interpolation area.

[0016] The present invention specifically adopts the following technical solution:

[0017] A geological overburden interpolation method based on EBK regression analysis, characterized by the following steps:

[0018] Step S1: Data Extraction: Based on the characteristics of the data structure, read the geological data and spatial location of the exploration points from the geological exploration point information collection table;

[0019] Step S2: Geological data cleaning and preparation of explanatory variables: Clean up exploration points with incorrect attribute types in the geological data; perform spatial visualization operations on the geological data, remove data points outside the experimental area, and prepare the elevation data required for geographic regression; use the elevation data to calculate the slope at each location in the experimental area.

[0020] Step S3: Data exploration: This step involves understanding the relevant statistical information of the data itself to determine the interpolation method for subsequent steps.

[0021] Step S4: Perform EBK regression analysis to calculate the predicted values ​​for the locations of all experimental areas.

[0022] Further, in step S3, firstly, based on the characteristics of the overburden thickness, a step size of 0.2m is set, and the frequency of each histogram is counted. The histogram is used to observe whether the overburden thickness values ​​at the exploration point exhibit a normal distribution. If the data is not normally distributed, one of the transformation methods, including logarithmic transformation, square root transformation, and reciprocal transformation, is used to convert the data distribution into a normal distribution. Secondly, the relationship between the overburden thickness values ​​and the terrain and slope is determined. By creating a three-dimensional scatter plot, the elevation and slope data are used as explanatory variables for function estimation.

[0023] Furthermore, step S4 specifically includes the following steps:

[0024] Step S41: Introduce exploration point data and explanatory variables;

[0025] Step S42: Perform constrained clustering on the exploration points: Specify the cluster size and set the cluster overlap ratio; perform K-means clustering on the exploration points based on size constraints. Assuming there are N exploration points in total, and the upper limit of each cluster is T, then there are K = [N / / T]+1 clusters. Common points are allowed between clusters; calculate the minimum convex boundary for each cluster.

[0026] Step S43: Regression equation estimation; use the least squares method to estimate the regression equations for elevation, slope and overburden thickness within the calculation range of the minimum convex boundary of the cluster;

[0027] Step S44: Estimate the semi-variogram γ1(h) for all clusters generated in step S42, using an exponential function as the function type;

[0028] Step S45: Calculate the simulated values ​​of the locations of all exploration points using the semivariogram and regression equation; and estimate the new semivariogram γ2(h) using the new simulated values;

[0029] Step S46: Repeat step S45 a total of N times to obtain M semi-variograms, and statistically analyze the distribution of the M semi-variograms;

[0030] Step S47: Apply the variogram distribution and regression equation to calculate the predicted values ​​for the locations of all experimental areas.

[0031] Furthermore, a geological overburden interpolation device based on EBK regression analysis is characterized in that it includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the geological overburden interpolation method based on EBK regression analysis as described above.

[0032] Furthermore, a non-transitory computer-readable storage medium storing a computer program, characterized in that: when the computer program is executed by a processor, it implements the geological overburden interpolation method based on EBK regression analysis as described above.

[0033] Compared with existing technologies, the method proposed in this invention and its preferred embodiment is based on the fact that as distance increases, the uncertainty between the predicted value of the interpolation location and the sample point gradually increases, which is consistent with prior geological knowledge. By using clustering to divide the exploration points into clusters, and by fitting the data of these clusters, the overall error distribution pattern is obtained while minimizing variance estimation bias. Simultaneously, while keeping the overall error at a low level, a more accurate prediction of the geological overburden distribution is obtained by combining topographic explanatory variables. Attached Figure Description

[0034] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0035] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0036] Figure 1 is a flowchart of the overall scheme of an embodiment of the present invention. Detailed Implementation

[0037] To make the features and advantages of this patent more apparent and understandable, specific embodiments are provided below for detailed explanation:

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. The components described and shown in the accompanying drawings can generally be combined and designed in different configurations. Therefore, the following detailed description of selected embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but only to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0039] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0040] The purpose of this invention is to provide a geological probability interpolation method based on regression of explanatory variables. When additional geographical explanatory variables are provided, the method can adaptively fit the relevant explanatory variables and utilize these geographical variables to perform geological interpolation of the engineering area.

[0041] like Figure 1 As shown, this invention proposes a geological interpolation method based on EBK regression analysis, comprising the following steps:

[0042] Step S1: Data Extraction: Based on the characteristics of the data structure, use the program to read the geological data and spatial location of the exploration points from the geological exploration point information collection table.

[0043] Step S2: Geological Data Cleaning and Preparation of Explanatory Variables: Clean up exploration points with incorrect attribute types in the geological data; perform spatial visualization operations on the geological data to remove data points outside the experimental area. Simultaneously, prepare the elevation data required for geographic regression and use the elevation data to calculate the slope at each location in the experimental area.

[0044] Step S3: Data Exploration: The purpose of data exploration is to understand the relevant statistical information of the data itself in order to determine the interpolation method in subsequent steps. First, based on the characteristics of the overburden thickness, a step size of 0.2m is set, and the frequency of each histogram is counted. Histograms are used to observe whether the overburden thickness values ​​at the exploration points exhibit a normal distribution. If the data is not normally distributed, logarithmic transformation, square root transformation, and reciprocal transformation are used to convert the data distribution to a normal distribution. In the interpolation process of the overburden thickness data at the exploration points, this method uses logarithmic transformation. Second, the relationship between the overburden thickness values ​​and the terrain and slope is determined. By creating a three-dimensional scatter plot, it can be concluded that the overburden thickness values ​​are correlated with the terrain and slope. This can be explained by the fact that as the elevation of the local area increases, the trend of increasing overburden thickness values ​​in the exploration point sample becomes more obvious. Therefore, it can be determined that elevation and slope data are used as explanatory variables for function estimation.

[0045] Step S4: EBK Regression Analysis:

[0046] Step S41: Introduce exploration point data and explanatory variables (elevation, slope data);

[0047] Step S42: Perform constrained clustering on the exploration points. The cluster size and cluster overlap ratio need to be specified. For the geological cover layer of power transmission and transformation projects at the prefecture-level city level, the cluster size is selected as 300 points and the overlap ratio is selected as 1.2, that is, 20% of the exploration points are reused. Perform K-means clustering based on size constraints on the exploration points [1]. Assuming there are N exploration points in total and the upper limit of each cluster is T, there are K = [N / / T]+1 clusters. Clusters can have common points. Calculate the minimum convex boundary for each cluster.

[0048] Step S43: Regression Equation Estimation. The least squares method is used to estimate the regression equations for elevation, slope, and overburden thickness within the calculation range of the minimum convex boundary of the cluster.

[0049] Step S44: Estimate the semi-variogram function γ1(h) for all clusters generated in step S42, using an exponential function.

[0050] Step S45: Calculate the simulated values ​​for the locations of all exploration points using the semivariogram and regression equation. Then estimate the new semivariogram γ2(h) using the new simulated values.

[0051] Step S46: Repeat step S45 a total of N times to obtain M semi-variograms, and statistically analyze the distribution of the M semi-variograms.

[0052] Step S47: Apply the variogram distribution and regression equation to calculate the predicted values ​​for the locations of all experimental areas.

[0053] References: [1] Tang Haibo, Lin Yuming, Li You. A balanced constraint clustering algorithm based on K-Means[J]. Journal of East China Normal University (Natural Science Edition), 2018(05):164-171.

[0054] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention.

[0055] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0056] The logic program design scheme in the above solution provided in this embodiment can be stored in a computer-readable storage medium in the form of code, and implemented in the form of a computer program. The basic parameter information required for calculation is input through computer hardware, and the calculation result is output.

[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] This invention is described with reference to methods, apparatus (devices), and computer program products according to embodiments of the invention. It should be understood that each process can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing functions specified in one or more processes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the function specified in one or more processes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing a function specified in one or more processes.

[0061] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

[0062] This patent is not limited to the above-described preferred embodiments. Anyone can derive other forms of geological overburden interpolation methods based on EBK regression analysis under the guidance of this patent. All equivalent changes and modifications made within the scope of this patent application shall fall within the scope of this patent.

Claims

1. A geological overburden interpolation method based on EBK regression analysis, characterized in that, Includes the following steps: Step S1: Data Extraction: Based on the characteristics of the data structure, read the geological data and spatial location of the exploration points from the geological exploration point information collection table; Step S2: Geological data cleaning and preparation of explanatory variables: Clean up exploration points with incorrect attribute types in the geological data; perform spatial visualization operations on the geological data, remove data points outside the experimental area, and prepare the elevation data required for geographic regression; use the elevation data to calculate the slope at each location in the experimental area. Step S3: Data exploration: This step involves understanding the relevant statistical information of the data itself to determine the interpolation method for subsequent steps. Step S4: Perform EBK regression analysis to calculate the predicted values ​​for the locations of all experimental areas; In step S3, firstly, based on the characteristics of the overburden layer values, a thickness of 0.2m is set as a step size, and the frequency of each histogram is counted. The histogram is then used to observe whether the overburden layer values ​​at the exploration point exhibit a normal distribution. If the data is not normally distributed, one of the transformation methods, including logarithmic transformation, square root transformation, and reciprocal transformation, is used to convert the data distribution into a normal distribution. Secondly, the relationship between the overburden layer values ​​and the terrain and slope is determined. By creating a three-dimensional scatter plot, the elevation and slope data are used as explanatory variables for function estimation. Step S4 specifically includes the following steps: Step S41: Introduce exploration point data and explanatory variables; Step S42: Perform constrained clustering on the exploration points: Specify the cluster size and set the cluster overlap ratio; perform K-means clustering on the exploration points based on size constraints. Assuming there are N exploration points in total, and the upper limit of each cluster is T, then there are K = [N / / T]+1 clusters. Common points are allowed between clusters; calculate the minimum convex boundary for each cluster. Step S43: Regression equation estimation; use the least squares method to estimate the regression equations for elevation, slope and overburden thickness within the calculation range of the minimum convex boundary of the cluster; Step S44: Estimate the semi-variogram γ1(h) for all clusters generated in step S42, using an exponential function as the function type; Step S45: Calculate the simulated values ​​of the locations of all exploration points using the semivariogram and regression equation; and estimate the new semivariogram γ2(h) using the new simulated values; Step S46: Repeat step S45 a total of N times to obtain M semi-variograms, and statistically analyze the distribution of the M semi-variograms; Step S47: Apply the variogram distribution and regression equation to calculate the predicted values ​​for the locations of all experimental areas.

2. A geological overburden interpolation device based on EBK regression analysis, characterized in that: The invention includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor executes the computer program, it implements the geological overburden interpolation method based on EBK regression analysis as described in claim 1.

3. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the computer program implements the geological overburden interpolation method based on EBK regression analysis as described in claim 1.

Images