Intelligent drawing method and system of geological map

Abstract

The invention discloses an intelligent drawing method and system for a geological map, and relates to the technical field of geological mapping. The method comprises the following specific steps: acquiring multi-source geological data of a target area; carrying out fusion, cleaning, denoising and normalization processing on the multi-source geological data, and carrying out data difference and gridding operation to obtain preprocessed data; carrying out geologic body recognition from the preprocessed data by utilizing a machine learning algorithm to obtain geologic body boundary data; carrying out automatic labeling and rendering operation on the geologic body boundary data obtained through identification, and drawing a geological map by using a computer graphics technology; and evaluating the drawn geological map, checking the accuracy and integrity of the geological map, and performing optimization and improvement according to an evaluation result. According to the invention, geologic body identification and geologic body comprehensive operation are carried out based on a machine learning algorithm, the working efficiency is improved, and a wide idea is provided for intelligent geologic mapping.

Description

Technical Field

[0001] The present invention relates to the technical field of geological mapping, and in particular to an intelligent drawing method and system of geological maps. Background Art

[0002] Geological mapping is a technology that converts geological data into geological graphics. It not only meets the needs of exploration work, but also provides important support for geological research and application. Geological mapping has gone through the development process from traditional paper mapping to digital mapping. Digital mapping reduces the workload and difficulty of geologists, but it does not solve the problem of traditional paper mapping that is difficult to ensure the quality of maps due to different personal experience and skills. In order to solve this problem, geological mapping needs to develop in the direction of automation and intelligence. Therefore, for technical personnel in this field, how to realize the intelligent drawing of geological maps is an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for intelligently drawing a geological map to solve the problems raised in the background technology.

[0004] To achieve the above object, the present invention provides the following solutions: On the one hand, a method for intelligently drawing a geological map is provided, characterized in that the specific steps include the following:

[0005] Acquire multi-source geological data of the target area;

[0006] The multi-source geological data are merged, cleaned, denoised, and normalized, and data difference and gridding operations are performed to obtain pre-processed data;

[0007] Using a machine learning algorithm, geological body identification is performed from the preprocessed data to obtain geological body boundary data;

[0008] Automatically marking and rendering the identified geological body boundary data, and drawing a geological map using computer graphics technology;

[0009] Evaluate the drawn geological maps to check their accuracy and completeness, and optimize and improve them based on the evaluation results.

[0010] Preferably, the specific steps of identifying geological bodies from the preprocessed data using a machine learning algorithm are:

[0011] After performing image cropping, text recognition, and text elimination on the pre-processed data, a main image area and a legend are obtained;

[0012] Performing a color segmentation operation on the main image area based on the K-Means algorithm and repairing the edge area at the same time;

[0013] The processed geological body is subjected to edge detection and vectorization operations, and is simplified and smoothed.

[0014] Get the geological body boundary data.

[0015] Preferably, it also includes automatically connecting stratum boundaries based on contour line interpolation according to the geological body boundary data, and the specific steps are:

[0016] Determine the orientation of the stratum boundary based on the V-shaped rule according to the geological body boundary data;

[0017] After determining the orientation of the stratigraphic boundary, n new contour lines are interpolated between every two contour lines within the specified area;

[0018] Estimate the location of geological outcrops through original contour lines and new contour lines;

[0019] The geological outcrop points are connected to obtain the inferred stratigraphic boundaries and smoothed to complete the automatic connection of stratigraphic boundaries.

[0020] Preferably, the multi-source geological data includes geological reports, geological maps, remote sensing images, and databases.

[0021] Preferably, the specific steps of automatically marking the identified geological body boundary data are:

[0022] The geological body is divided into a first geological body and a second geological body according to whether the geological code can be accommodated in the geological body area, wherein the first geological body accommodates the geological code in the area, and the geological code of the second geological body is placed outside the area;

[0023] respectively providing candidate locations of the first geological body and the second geological body, and evaluating the candidate locations by comprehensively considering multiple factors;

[0024] Based on the candidate location evaluation method, single location labeling and multi-location labeling are realized through sorting and particle swarm algorithm.

[0025] By adopting the above technical solution, the following beneficial technical effects are achieved: geological bodies are classified and automatically labeled according to the process of automatic labeling of map elements. This method can label geological bodies of different shapes and areas with conflicting geological codes, and the labeling effect of complex geological bodies is better than other methods.

[0026] Preferably, the geological map also includes geological body comprehensive operations during the compilation process, and the geological body comprehensive operations include geological body merging, elimination of tiny geological bodies and geological body smoothing.

[0027] Preferably, the specific process of merging geological bodies is: using the longitude and latitude of the geological body center, the subtype identifier and the geological age category as data sources, performing cluster analysis on the spatial distribution of the geological ages of different types of geological bodies, and merging geological bodies according to the cluster analysis results.

[0028] On the other hand, a geological map intelligent drawing system is provided, which includes a data acquisition module, a preprocessing module, a geological body identification module, a drawing module, and an evaluation module; wherein:

[0029] The data acquisition module is used to acquire multi-source geological data of the target area;

[0030] The preprocessing module is used to fuse, clean, denoise, normalize, and perform data difference and gridding operations on the multi-source geological data to obtain preprocessed data;

[0031] The geological body identification module is used to identify the geological body from the preprocessed data using a machine learning algorithm to obtain geological body boundary data;

[0032] The drawing module is used to automatically mark and render the identified geological body boundary data, and draw a geological map using computer graphics technology;

[0033] The evaluation module is used to evaluate the drawn geological map, check its accuracy and completeness, and optimize and improve it according to the evaluation results.

[0034] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: geological body identification and comprehensive operation of geological bodies are performed based on machine learning algorithms, which improves work efficiency and provides broad ideas for intelligent geological mapping; automatic connection of stratum boundaries based on contour line interpolation can more accurately calculate the coordinates of geological outcropping points and thus reduce the errors of stratum boundaries; after the geological map is drawn, its accuracy and completeness are evaluated, and it is optimized according to the evaluation results, and a feedback mechanism is set to further improve the accuracy of intelligent drawing of geological maps. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 is a flow chart of the method of the present invention;

[0037] Figure 2It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0038] 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 only 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.

[0039] The purpose of the present invention is to provide an intelligent method for drawing a geological map. Figure 1 As shown, the specific steps include the following:

[0040] S1. Obtain multi-source geological data of the target area;

[0041] S2, fusing, cleaning, denoising, and normalizing multi-source geological data, performing data difference and gridding operations to obtain pre-processed data;

[0042] S3, using machine learning algorithms to identify geological bodies from preprocessed data and obtain geological body boundary data;

[0043] S4, automatically marking and rendering the identified geological body boundary data, and drawing a geological map using computer graphics technology;

[0044] S5. Evaluate the drawn geological map, check its accuracy and completeness, and optimize and improve it based on the evaluation results.

[0045] Furthermore, in step S1, the multi-source geological data includes geological reports, geological maps, remote sensing images, and databases.

[0046] Furthermore, data preprocessing is performed in step S2, wherein data fusion of multi-source geological data can improve data integrity. After fusing these data, a more complete geological picture can be obtained to make up for the information missing from a single data source; data reliability is enhanced: multiple data sources can verify each other to reduce data uncertainty.

[0047] Data cleaning can improve data quality: geological data may be interfered by various factors during the collection process, resulting in erroneous or incomplete data. Through data cleaning, these erroneous data can be removed so that subsequent analysis can be based on accurate data; reduce analysis errors: if the data is not cleaned, erroneous data may cause deviations in the analysis results.

[0048] Data denoising can highlight effective signals: geological signals are often mixed with noise, and denoising operations can separate real geological signals from noise, making geological features more clearly displayed; improve model accuracy: when performing geological modeling and other operations, noisy data will affect the accuracy of the model.

[0049] Data normalization can eliminate the impact of dimensions and unify these data of different dimensions into a dimensionless range, which is convenient for comprehensive comparison and analysis; improve algorithm performance: when using some data analysis algorithms, data normalization can speed up the convergence of the algorithm.

[0050] Data interpolation and gridding can refine the description of data distribution and facilitate spatial analysis and visualization: after irregularly distributed geological data are gridded, spatial analysis can be easily performed.

[0051] Furthermore, using machine learning algorithms, the specific steps for identifying geological bodies from preprocessed data are as follows:

[0052] S31, after performing image cropping, text recognition, and text elimination on the pre-processed data, a main image area and a legend are obtained;

[0053] S32, performing color segmentation on the main image area based on the K-Means algorithm, and repairing the edge area at the same time;

[0054] S33, edge detection and vectorization operations are performed on the processed geological body, and simplification and smoothing are performed.

[0055] S34. Obtain geological body boundary data.

[0056] Furthermore, it also includes automatically connecting the stratum boundaries based on the contour line interpolation according to the geological body boundary data, and the specific steps are as follows:

[0057] S341, judging the orientation of the stratum boundary based on the V-shaped rule according to the geological body boundary data;

[0058] S342, after determining the orientation of the stratigraphic boundary, interpolate n new contour lines between every two contour lines within the specified area;

[0059] S343, infer the location of geological outcrops through the original contour lines and the new contour lines;

[0060] S344. Connect the geological outcrop points to obtain the inferred stratigraphic boundaries and perform rounding to complete the automatic connection of the stratigraphic boundaries.

[0061] Stratigraphic boundaries refer to the contact relationship between geological bodies, which refers to the relationship between two geological units or two sets of geological bodies (or strata) of different ages, and are also the boundaries of various geological bodies. The original data and results data of various disciplines, modes, and scales that reflect the geological characteristics of the surface and a certain depth, as well as the mapping methods, experience, and knowledge of geologists in the past century, are converted into a computer-understandable and computable knowledge base; deep learning methods are used to discover the correlation between the geological characteristics of the mapping units and lithology (the most basic geological objects reflected in geological maps), and then the mapping units and lithology are predicted, accurately reflecting and expressing the spatial distribution form, distribution direction, and mutual relationship of geological bodies.

[0062] A geological body is a rock mass surrounded by geological boundaries. When labeling a geological body, it is necessary not only to consider the shape and area of ​​the geological body, but also to consider various elements existing in the geological plan, such as contour lines, rock formations, and special place names. The quality of the labeling is determined by the labeling position, and the visual effects of labeling at different positions are different. How to select one or more suitable locations for labeling from dozens or hundreds of candidate locations is tangled. It is necessary to quantitatively or qualitatively evaluate the quality of the candidate locations in order to select suitable locations from these candidate locations for labeling. Furthermore, the specific steps for automatically labeling the identified geological body boundary data are as follows:

[0063] S41, dividing the geological body into a first geological body and a second geological body according to whether the geological code can be accommodated in the geological body area, the first geological body accommodating the geological code in the area, and the geological code of the second geological body being placed outside the area;

[0064] S42, respectively providing candidate locations of the first geological body and the second geological body, and evaluating the candidate locations by comprehensively considering multiple factors;

[0065] S43. Based on the candidate position evaluation method, single position labeling and multi-position labeling are realized through sorting and particle swarm algorithm.

[0066] By adopting the above technical solution, the following beneficial technical effects are achieved: geological bodies are classified and automatically labeled according to the process of automatic labeling of map elements. This method can label geological bodies of different shapes and areas with conflicting geological codes, and the labeling effect of complex geological bodies is better than other methods.

[0067] Furthermore, the geological map compilation process also includes geological body comprehensive operations, including geological body merging, elimination of small geological bodies and geological body smoothing. The specific process of geological body merging is: taking the longitude and latitude of the geological body center, subtype identification and geological age category as data sources, clustering analysis is performed on the spatial distribution of geological ages of different types of geological bodies, and merging geological bodies according to the clustering analysis results.

[0068] On the other hand, a system for intelligently drawing geological maps is provided, such as Figure 2 As shown, it includes a data acquisition module, a preprocessing module, a geological body identification module, a drawing module, and an evaluation module; wherein,

[0069] A data acquisition module, used to acquire multi-source geological data of the target area;

[0070] The preprocessing module is used to fuse, clean, denoise, and normalize multi-source geological data, perform data difference and grid operations, and obtain preprocessed data;

[0071] A geological body identification module is used to identify geological bodies from preprocessed data using a machine learning algorithm and obtain geological body boundary data;

[0072] A drawing module is used to automatically mark and render the identified geological body boundary data and draw geological maps using computer graphics technology;

[0073] The evaluation module is used to evaluate the drawn geological map, check its accuracy and completeness, and optimize and improve it based on the evaluation results.

[0074] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for intelligently drawing a geological map, characterized in that: The specific steps include the following: Acquire multi-source geological data of the target area; The multi-source geological data are merged, cleaned, denoised, and normalized, and data difference and gridding operations are performed to obtain pre-processed data; Using a machine learning algorithm, geological body identification is performed from the preprocessed data to obtain geological body boundary data; Automatically marking and rendering the identified geological body boundary data, and drawing a geological map using computer graphics technology; Evaluate the drawn geological maps to check their accuracy and completeness, and optimize and improve them based on the evaluation results.

2. The intelligent drawing method of a geological map according to claim 1, characterized in that: The specific steps of identifying geological bodies from the preprocessed data using a machine learning algorithm are as follows: After performing image cropping, text recognition, and text elimination on the pre-processed data, a main image area and a legend are obtained; Performing a color segmentation operation on the main image area based on the K-Means algorithm and repairing the edge area at the same time; The processed geological body is subjected to edge detection and vectorization operations, and is simplified and smoothed to obtain the geological body boundary data.

3. The intelligent drawing method of a geological map according to claim 2, characterized in that: The invention also includes automatically connecting the stratum boundaries based on the contour line interpolation according to the geological body boundary data, and the specific steps are as follows: Determine the orientation of the stratum boundary based on the V-shaped rule according to the geological body boundary data; After determining the orientation of the stratigraphic boundary, n new contour lines are interpolated between every two contour lines within the specified area; Estimate the location of geological outcrops through original contour lines and new contour lines; The geological outcrop points are connected to obtain the inferred stratigraphic boundaries and smoothed to complete the automatic connection of stratigraphic boundaries.

4. The intelligent drawing method of a geological map according to claim 1, characterized in that: The multi-source geological data include geological reports, geological maps, remote sensing images, and databases.

5. The intelligent drawing method of a geological map according to claim 1, characterized in that: The specific steps of automatically marking the identified geological body boundary data are as follows: The geological body is divided into a first geological body and a second geological body according to whether the geological code can be accommodated in the geological body area, wherein the first geological body accommodates the geological code in the area, and the geological code of the second geological body is placed outside the area; respectively providing candidate locations of the first geological body and the second geological body, and evaluating the candidate locations by comprehensively considering multiple factors; Based on the candidate location evaluation method, single location labeling and multi-location labeling are realized through sorting and particle swarm algorithm.

6. The intelligent drawing method of a geological map according to claim 1, characterized in that: The geological map compilation process also includes geological body comprehensive operations, which include geological body merging, elimination of tiny geological bodies and geological body smoothing.

7. The intelligent drawing method of a geological map according to claim 6, characterized in that: The specific process of merging geological bodies is as follows: taking the longitude and latitude of the geological body center, the subtype identifier and the geological age category as data sources, performing cluster analysis on the spatial distribution of the geological ages of different types of geological bodies, and merging geological bodies according to the cluster analysis results.

8. An intelligent geological map drawing system, characterized in that: It includes data acquisition module, preprocessing module, geological body identification module, drawing module and evaluation module; among them, The data acquisition module is used to acquire multi-source geological data of the target area; The preprocessing module is used to fuse, clean, denoise, normalize, and perform data difference and gridding operations on the multi-source geological data to obtain preprocessed data; The geological body identification module is used to identify the geological body from the preprocessed data using a machine learning algorithm to obtain geological body boundary data; The drawing module is used to automatically mark and render the identified geological body boundary data, and draw a geological map using computer graphics technology; The evaluation module is used to evaluate the drawn geological map, check its accuracy and completeness, and optimize and improve it according to the evaluation results.

Images