A virtual borehole modeling method and system based on fine outcrop characterization
Through a virtual drilling modeling method based on fine outcrop characterization, using outcrop observation data and machine learning technology, a high-precision three-dimensional geological model is constructed, which solves the problem of insufficient geological modeling accuracy in the existing technology, and achieves lower cost and better Highly efficient acquisition of underground geological information.
Patent Information
- Application Number
- CN202311533698.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-17
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2043-11-17
AI Technical Summary
Existing geological modeling methods rely on limited drilling data, resulting in insufficient model accuracy and reliability, and high drilling costs, limiting the number and density of drilling holes.
Using virtual drilling modeling method based on fine characterization of outcrop, select typical sedimentary strata points, use outcrop fine observation technology to characterize the distribution characteristics of lithology, yield, thickness, and extension range, establish a vertical stratigraphic histogram, and combine it with Machine learning and interpolation operations build a three-dimensional geological model, and use drone high-resolution photography and computer vision algorithms to generate three-dimensional point cloud data, perform feature detection and matching, and build a high-precision three-dimensional geological model.
Without actual drilling, a lower cost and higher efficiency accurate three-dimensional geological model is established through high-precision outcrop characterization technology, which improves the accuracy and reliability of the model.
Smart Images

Figure CN117496090B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of geological exploration technology, and in particular to a virtual borehole modeling method and system based on fine outcrop characterization. Background Art
[0002] In geological exploration and resource assessment, borehole data is an important means of obtaining underground geological information. However, drilling operations are costly and time-consuming, which limits the number and density of boreholes. Existing geological modeling methods often rely on limited borehole data, resulting in insufficient model accuracy and reliability. Therefore, a new modeling method that is cost-effective and can improve the accuracy of geological models is needed. Summary of the invention
[0003] In order to overcome the deficiencies of the prior art, the object of the present invention is to provide a virtual borehole modeling method and system based on fine outcrop characterization.
[0004] To achieve the above object, the present invention provides the following solutions:
[0005] A virtual borehole modeling method based on fine outcrop characterization, comprising:
[0006] Select a plurality of typical sedimentary strata points respectively, and characterize the distribution characteristics of the lithology, occurrence, thickness and extension range of each outcrop layer of the typical sedimentary strata points based on the fine outcrop observation technology;
[0007] Establishing each vertical sequence stratigraphic column chart according to the distribution characteristics; the vertical sequence stratigraphic column chart is used to reflect the vertical changes of the actual strata;
[0008] Constructing a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample drill core column;
[0009] Based on machine learning and interpolation calculation methods, a three-dimensional geological model is constructed according to the modeling data set.
[0010] Preferably, it also includes:
[0011] The three-dimensional geological model is corrected according to the outcrop data acquired in real time, so as to correct the three-dimensional geological model in real time.
[0012] Preferably, multiple typical sedimentary strata points are selected respectively, and the distribution characteristics of the lithology, occurrence, thickness and extension range of each layer of the outcrop at the typical sedimentary strata points are described based on the fine outcrop observation technology, including:
[0013] Deploy a drone to take high-resolution photos of the typical sedimentary strata points, and use oblique photography technology to capture images of the typical sedimentary strata points at different angles;
[0014] Processing the images at different angles to generate three-dimensional point cloud data;
[0015] The three-dimensional point cloud data is analyzed, and an outcrop stratigraphic profile is drawn according to the distribution characteristics, and the sequence and characteristics of the rock layers are recorded to obtain the distribution characteristics.
[0016] Preferably, processing the images at different angles to generate three-dimensional point cloud data includes:
[0017] Performing feature detection on the images at different angles based on a computer vision algorithm to obtain feature detection points;
[0018] Performing feature matching on the feature detection points to obtain a three-dimensional structure;
[0019] The three-dimensional structure is three-dimensionally reconstructed using preset camera parameters to obtain the three-dimensional point cloud data.
[0020] Preferably, constructing a three-dimensional geological model according to the modeling data set based on machine learning and interpolation calculation methods includes:
[0021] Preprocessing the modeling data to obtain preprocessed data;
[0022] Performing feature selection on the preprocessed data to obtain modeling features; the modeling features include: lithology, mineral content, density and magnetism;
[0023] Inputting the modeling features into a trained machine learning model to obtain geological attribute data;
[0024] Performing interpolation on the geological attribute data to obtain an interpolation result;
[0025] Performing gridding conversion according to the interpolation result to obtain a three-dimensional grid;
[0026] The three-dimensional grid is smoothed and refined to obtain the three-dimensional geological model.
[0027] A virtual drilling modeling system based on fine outcrop characterization, comprising:
[0028] A characterization module is used to select a plurality of typical sedimentary strata points respectively, and characterize the distribution characteristics of the lithology, occurrence, thickness, and extension range of each outcrop layer of the typical sedimentary strata points based on the fine outcrop observation technology;
[0029] A histogram building module, used to build each vertical sequence stratigraphic histogram according to the distribution characteristics; the vertical sequence stratigraphic histogram is used to reflect the vertical changes of the actual strata;
[0030] A data set construction module, used to construct a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample drill core column;
[0031] The model building module is used to build a three-dimensional geological model according to the modeling data set based on machine learning and interpolation operation methods.
[0032] Preferably, it also includes:
[0033] The correction module is used to correct the three-dimensional geological model according to the outcrop data obtained in real time, so as to correct the three-dimensional geological model in real time.
[0034] Preferably, the characterization module comprises:
[0035] A deployment unit is used to deploy a drone to take high-resolution photos of the typical sedimentary stratum points, and use an oblique photography technique to capture images of the typical sedimentary stratum points at different angles;
[0036] A point cloud processing unit, used to process the images at different angles to generate three-dimensional point cloud data;
[0037] The analysis unit is used to analyze the three-dimensional point cloud data, and draw an outcrop stratigraphic profile according to the distribution characteristics, and record the sequence and characteristics of the rock layers to obtain the distribution characteristics.
[0038] Preferably, the point cloud processing unit comprises:
[0039] A feature detection subunit, used to perform feature detection on the images at different angles based on a computer vision algorithm to obtain feature detection points;
[0040] A feature matching subunit, used for performing feature matching on the feature detection points to obtain a three-dimensional structure;
[0041] The reconstruction subunit is used to perform three-dimensional reconstruction on the three-dimensional structure using preset camera parameters to obtain the three-dimensional point cloud data.
[0042] Preferably, the model building module comprises:
[0043] A modeling data preprocessing unit, used to preprocess the modeling data to obtain preprocessed data;
[0044] A feature selection unit, used to perform feature selection on the preprocessed data to obtain modeling features; the modeling features include: lithology, mineral content, density and magnetism;
[0045] A machine learning unit, used for inputting the modeling features into a trained machine learning model to obtain geological attribute data;
[0046] An interpolation unit, used for performing interpolation on the geological attribute data to obtain an interpolation result;
[0047] A gridding unit, used for performing gridding conversion according to the interpolation result to obtain a three-dimensional grid;
[0048] The model building unit is used to smooth and refine the three-dimensional grid to obtain the three-dimensional geological model.
[0049] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0050] The present invention provides a virtual borehole modeling method and system based on fine outcrop characterization, the method comprising: selecting a plurality of typical sedimentary strata points respectively, and characterizing the distribution characteristics of the lithology, occurrence, thickness, and extension range of each layer of the outcrop of the typical sedimentary strata points according to the fine outcrop observation technology; establishing each vertical sequence stratigraphic column chart according to the distribution characteristics; the vertical sequence stratigraphic column chart is used to reflect the vertical changes of the actual strata; constructing a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample borehole core column; and constructing a three-dimensional geological model according to the modeling data set based on machine learning and interpolation operation methods. The present invention can establish an accurate three-dimensional geological model at a lower cost and higher efficiency without actual drilling through high-precision outcrop characterization technology. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] 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.
[0052] Figure 1 A flow chart of a method provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0053] 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.
[0054] The purpose of the present invention is to provide a virtual borehole modeling method and system based on fine outcrop characterization, which can establish an accurate three-dimensional geological model at a lower cost and higher efficiency without actual drilling through high-precision outcrop characterization technology.
[0055] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0056] Figure 1 A flow chart of a method provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides a virtual borehole modeling method based on fine outcrop characterization, comprising:
[0057] Step 100: Select multiple typical sedimentary strata points respectively, and characterize the distribution characteristics of lithology, occurrence, thickness, and extension range of each outcrop layer of the typical sedimentary strata points based on the outcrop fine observation technology;
[0058] Step 200: establishing each vertical sequence stratigraphic column chart according to the distribution characteristics; the vertical sequence stratigraphic column chart is used to reflect the vertical changes of the actual strata;
[0059] Step 300: constructing a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample drill core column;
[0060] Step 400: construct a three-dimensional geological model according to the modeling data set based on machine learning and interpolation calculation methods.
[0061] Preferably, it also includes:
[0062] The three-dimensional geological model is corrected according to the outcrop data acquired in real time, so as to correct the three-dimensional geological model in real time.
[0063] Preferably, multiple typical sedimentary strata points are selected respectively, and the distribution characteristics of the lithology, occurrence, thickness and extension range of each layer of the outcrop at the typical sedimentary strata points are described based on the fine outcrop observation technology, including:
[0064] Deploy a drone to take high-resolution photos of the typical sedimentary strata points, and use oblique photography technology to capture images of the typical sedimentary strata points at different angles;
[0065] Processing the images at different angles to generate three-dimensional point cloud data;
[0066] The three-dimensional point cloud data is analyzed, and an outcrop stratigraphic profile is drawn according to the distribution characteristics, and the sequence and characteristics of the rock layers are recorded to obtain the distribution characteristics.
[0067] Specifically, this embodiment deploys drones to take high-resolution photos of the target area; uses oblique photography technology to capture images at different angles to obtain three-dimensional information; and processes the captured images to generate high-precision three-dimensional point cloud data.
[0068] Furthermore, this embodiment also applies RTK (real-time kinematic differential technology), using RTK GPS equipment to accurately position on the ground to assist in the accurate setting of ground control points for drone images and ensure the spatial position accuracy of the three-dimensional model.
[0069] Preferably, processing the images at different angles to generate three-dimensional point cloud data includes:
[0070] Performing feature detection on the images at different angles based on a computer vision algorithm to obtain feature detection points;
[0071] Performing feature matching on the feature detection points to obtain a three-dimensional structure;
[0072] The three-dimensional structure is three-dimensionally reconstructed using preset camera parameters to obtain the three-dimensional point cloud data.
[0073] Furthermore, this embodiment analyzes drone and RTK data to identify the lithology, occurrence, thickness and extension range of different strata. Draw a detailed outcrop stratigraphic profile to record the order and characteristics of the strata. Based on the observation data, a vertical sequence stratigraphic column is established for each outcrop to ensure that the column accurately reflects the vertical changes of the actual strata; and according to the geological background and research needs, multiple representative sedimentary stratigraphic points are selected. Detailed outcrop observations and data collection are carried out at these points to establish multiple typical sequence stratigraphic columns: the data of each selected point is processed to establish a sequence stratigraphic column; ensure that each column can represent the typical stratigraphic sequence in its area.
[0074] Furthermore, this embodiment combines outcrop data with drill core columns: combining the sequence stratigraphic column of the outcrop with the existing drill core data. This embodiment can increase the number of data samples and improve the accuracy and reliability of the model through the above method.
[0075] Preferably, constructing a three-dimensional geological model according to the modeling data set based on machine learning and interpolation calculation methods includes:
[0076] Preprocessing the modeling data to obtain preprocessed data;
[0077] Performing feature selection on the preprocessed data to obtain modeling features; the modeling features include: lithology, mineral content, density and magnetism;
[0078] Inputting the modeling features into a trained machine learning model to obtain geological attribute data;
[0079] Performing interpolation on the geological attribute data to obtain an interpolation result;
[0080] Performing gridding conversion according to the interpolation result to obtain a three-dimensional grid;
[0081] The three-dimensional grid is smoothed and refined to obtain the three-dimensional geological model.
[0082] Specifically, this embodiment selects a suitable machine learning model, such as random forest, support vector machine, neural network, etc., according to the modeling characteristics. The model is trained using known geological data to predict the geological properties of unknown data points. Finally, the performance of the model is evaluated using methods such as cross-validation.
[0083] Furthermore, this embodiment selects a suitable interpolation method, such as Kriging, radial basis function (RBF), multiple regression analysis, etc., to estimate the geological attributes of unsampled points, and applies the interpolation method in three-dimensional space to generate a continuous distribution of geological attributes.
[0084] Corresponding to the above method, this embodiment further provides a virtual drilling modeling system based on fine outcrop characterization, including:
[0085] A characterization module is used to select a plurality of typical sedimentary strata points respectively, and characterize the distribution characteristics of the lithology, occurrence, thickness, and extension range of each outcrop layer of the typical sedimentary strata points based on the fine outcrop observation technology;
[0086] A histogram building module, used to build each vertical sequence stratigraphic histogram according to the distribution characteristics; the vertical sequence stratigraphic histogram is used to reflect the vertical changes of the actual strata;
[0087] A data set construction module, used to construct a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample drill core column;
[0088] The model building module is used to build a three-dimensional geological model according to the modeling data set based on machine learning and interpolation operation methods.
[0089] Preferably, it also includes:
[0090] The correction module is used to correct the three-dimensional geological model according to the outcrop data obtained in real time, so as to correct the three-dimensional geological model in real time.
[0091] Preferably, the characterization module comprises:
[0092] A deployment unit is used to deploy a drone to take high-resolution photos of the typical sedimentary stratum points, and use an oblique photography technique to capture images of the typical sedimentary stratum points at different angles;
[0093] A point cloud processing unit, used to process the images at different angles to generate three-dimensional point cloud data;
[0094] The analysis unit is used to analyze the three-dimensional point cloud data, and draw an outcrop stratigraphic profile according to the distribution characteristics, and record the sequence and characteristics of the rock layers to obtain the distribution characteristics.
[0095] Preferably, the point cloud processing unit comprises:
[0096] A feature detection subunit, used to perform feature detection on the images at different angles based on a computer vision algorithm to obtain feature detection points;
[0097] A feature matching subunit, used for performing feature matching on the feature detection points to obtain a three-dimensional structure;
[0098] The reconstruction subunit is used to perform three-dimensional reconstruction on the three-dimensional structure using preset camera parameters to obtain the three-dimensional point cloud data.
[0099] Preferably, the model building module comprises:
[0100] A modeling data preprocessing unit, used to preprocess the modeling data to obtain preprocessed data;
[0101] A feature selection unit, used to perform feature selection on the preprocessed data to obtain modeling features; the modeling features include: lithology, mineral content, density and magnetism;
[0102] A machine learning unit, used for inputting the modeling features into a trained machine learning model to obtain geological attribute data;
[0103] An interpolation unit, used for performing interpolation on the geological attribute data to obtain an interpolation result;
[0104] A gridding unit, used for performing gridding conversion according to the interpolation result to obtain a three-dimensional grid;
[0105] The model building unit is used to smooth and refine the three-dimensional grid to obtain the three-dimensional geological model.
[0106] The beneficial effects of the present invention are as follows:
[0107] The present invention provides a novel virtual borehole modeling method, which can establish an accurate three-dimensional geological model at a lower cost and higher efficiency without actual drilling through high-precision outcrop characterization technology.
[0108] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0109] 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 virtual borehole modeling method based on fine outcrop characterization, characterized in that: include: Select a plurality of typical sedimentary strata points respectively, and characterize the distribution characteristics of the lithology, occurrence, thickness and extension range of each outcrop layer of the typical sedimentary strata points based on the fine outcrop observation technology; Establishing each vertical sequence stratigraphic column chart according to the distribution characteristics; the vertical sequence stratigraphic column chart is used to reflect the vertical changes of the actual strata; Constructing a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample drill core column; Based on machine learning and interpolation calculation methods, construct a three-dimensional geological model according to the modeling data set; Select a number of typical sedimentary strata points respectively, and characterize the distribution characteristics of the lithology, occurrence, thickness, and extension range of each layer of the outcrop at the typical sedimentary strata points based on the fine outcrop observation technology, including: Deploy a drone to take high-resolution photos of the typical sedimentary strata points, and use oblique photography technology to capture images of the typical sedimentary strata points at different angles; Processing the images at different angles to generate three-dimensional point cloud data; Analyzing the three-dimensional point cloud data, and drawing an outcrop stratigraphic profile according to the distribution characteristics, recording the sequence and characteristics of the rock layers, so as to obtain the distribution characteristics; Processing the images at different angles to generate three-dimensional point cloud data includes: Performing feature detection on the images at different angles based on a computer vision algorithm to obtain feature detection points; Performing feature matching on the feature detection points to obtain a three-dimensional structure; The three-dimensional structure is three-dimensionally reconstructed using preset camera parameters to obtain the three-dimensional point cloud data.
2. The virtual borehole modeling method based on outcrop fine characterization according to claim 1 is characterized in that: Also includes: The three-dimensional geological model is corrected according to the outcrop data acquired in real time, so as to correct the three-dimensional geological model in real time.
3. The virtual drilling modeling method based on outcrop fine characterization according to claim 1 is characterized in that: Based on machine learning and interpolation operation methods, a three-dimensional geological model is constructed according to the modeling data set, including: Preprocessing the modeling data to obtain preprocessed data; Performing feature selection on the preprocessed data to obtain modeling features; the modeling features include: lithology, mineral content, density and magnetism; Inputting the modeling features into a trained machine learning model to obtain geological attribute data; Performing interpolation on the geological attribute data to obtain an interpolation result; Performing gridding conversion according to the interpolation result to obtain a three-dimensional grid; The three-dimensional grid is smoothed and refined to obtain the three-dimensional geological model.
4. A virtual drilling modeling system based on fine outcrop characterization, characterized in that: include: A characterization module is used to select a plurality of typical sedimentary strata points respectively, and characterize the distribution characteristics of the lithology, occurrence, thickness, and extension range of each outcrop layer of the typical sedimentary strata points based on the fine outcrop observation technology; A histogram building module, used to build each vertical sequence stratigraphic histogram according to the distribution characteristics; the vertical sequence stratigraphic histogram is used to reflect the vertical changes of the actual strata; A data set construction module, used to construct a modeling data set according to each of the vertical sequence stratigraphic column charts and a preset sample drill core column; A model building module, used to build a three-dimensional geological model according to the modeling data set based on machine learning and interpolation operation methods; The characterization module comprises: A deployment unit is used to deploy a drone to take high-resolution photos of the typical sedimentary stratum points, and use an oblique photography technique to capture images of the typical sedimentary stratum points at different angles; A point cloud processing unit, used to process the images at different angles to generate three-dimensional point cloud data; An analysis unit, used to analyze the three-dimensional point cloud data, and draw an outcrop stratigraphic profile according to the distribution characteristics, and record the sequence and characteristics of the rock layers to obtain the distribution characteristics; The point cloud processing unit comprises: A feature detection subunit, used to perform feature detection on the images at different angles based on a computer vision algorithm to obtain feature detection points; A feature matching subunit, used for performing feature matching on the feature detection points to obtain a three-dimensional structure; The reconstruction subunit is used to perform three-dimensional reconstruction on the three-dimensional structure using preset camera parameters to obtain the three-dimensional point cloud data.
5. The virtual drilling modeling system based on outcrop fine characterization according to claim 4 is characterized in that: Also includes: The correction module is used to correct the three-dimensional geological model according to the outcrop data obtained in real time, so as to correct the three-dimensional geological model in real time.
6. The virtual drilling modeling system based on outcrop fine characterization according to claim 4 is characterized in that: The model building module includes: A modeling data preprocessing unit, used to preprocess the modeling data to obtain preprocessed data; A feature selection unit, used to perform feature selection on the preprocessed data to obtain modeling features; the modeling features include: lithology, mineral content, density and magnetism; A machine learning unit, used for inputting the modeling features into a trained machine learning model to obtain geological attribute data; An interpolation unit, used for performing interpolation on the geological attribute data to obtain an interpolation result; A gridding unit, used for performing gridding conversion according to the interpolation result to obtain a three-dimensional grid; The model building unit is used to smooth and refine the three-dimensional grid to obtain the three-dimensional geological model.
