Ore body prediction method based on three-dimensional geological modeling and geological big data analysis

Abstract

The invention discloses an ore body prediction method based on three-dimensional geological modeling and geological big data analysis. The method comprises the following steps: S1, establishing a database of a deep edge research area of a mine; s2, establishing a three-dimensional geological model of the research area; s3, constructing a three-dimensional intelligent prediction model of the demonstration area, taking a known ore body model as prior information and geology and geophysical variables as three-dimensional integrated information based on three-dimensional variable data of strata, ore bodies, fractures, geochemical exploration and geophysical exploration in the three-dimensional geologic model, and carrying out target area prediction work; and S4, delineating a prospecting target area, and delineating a favorable prospecting target area by utilizing the constructed three-dimensional intelligent prospecting prediction model and combining geological information of the research area. According to the method, the complementarity of multi-source heterogeneous data is fully utilized, and scientific basis and technical support are provided for quantitative prediction of the deep concealed ore body in combination with the spatial analysis capability of three-dimensional geological modeling and the high efficiency of big data analysis.

Description

Technical Field

[0001] This invention relates to the field of mineral exploration prediction technology, and in particular to a method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis. Background Technology

[0002] Predicting geological and mineral resources is a comprehensive, systematic, and highly challenging task. Regional geological exploration involves a vast amount of diverse data, requiring technicians to not only quantitatively and qualitatively analyze geological data and charts but also refer to satellite positioning data, remote sensing imagery, geochemical data, and more. Integrating existing geological data with geological phenomena has become a key focus and challenge for geologists in predicting geological and mineral resources. Due to the sheer volume of data, traditional manual statistical and verification methods are proving extremely difficult. With the increasing number of data sources, solutions utilizing computer equipment and digital technologies to predict mineral resources have been proposed. Through data management, analysis, and processing, accurate assessments of large-scale mineral resources can be achieved. Currently, geological engineering units have implemented a series of explorations and practices in this area, defining mineral resource prediction as the process of assessing mineral reserves in unexplored areas. Previously, mineral deposit prediction was largely based on the subjective judgment of geological experts to determine the prospective extent and scope of deposits. However, as the difficulty of geological prospecting increases, prospecting units are beginning to focus their efforts on regional geological and mineral resource prediction.

[0003] Based on this, the present invention discloses a method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis. Summary of the Invention

[0004] This invention provides a method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis. Combining the spatial analysis capabilities of three-dimensional geological modeling with the efficiency of big data analysis, it provides a scientific basis and technical support for the quantitative prediction of deep concealed ore bodies.

[0005] According to one aspect of this disclosure, a method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis is provided, the method comprising: S1, Establish a database for the deep edge research area of ​​the mine; S2, Establish a three-dimensional geological model of the study area; S3, construct a three-dimensional intelligent prediction model for the demonstration area. Based on the three-dimensional variable data of strata, ore bodies, faults, geochemical exploration, and geophysical exploration in the three-dimensional geological model, use the known ore body model as prior information and the geological and geophysical variables as three-dimensional integrated information to carry out target area prediction work. S4. Mineral exploration target area delineation: Using the constructed three-dimensional intelligent mineral exploration prediction model and combined with the geological information of the study area, favorable mineral exploration target areas are delineated.

[0006] In one possible implementation, a database of the deep-edge research area of ​​the mine is established, including: Collect multi-source heterogeneous geological data, including geological information, geochemical information, geophysical information, remote sensing information, drilling information, and mineral resource data of the study area; Standardization processing was performed on multi-source heterogeneous geological data to obtain a multi-scale, multi-element mineral exploration dataset for the study area; Standardization processes include data cleaning, format standardization, and semantic normalization to eliminate data redundancy and inconsistency and ensure data quality.

[0007] In one possible implementation, the database includes: Geological information: mainly includes geological maps, geological reports, structural information, and stratigraphic information. Geological information needs to be digitized and its spatial coordinates unified for use in 3D modeling. Geochemical information: Covers geochemical data at different scales, including the abundance and distribution of major and trace elements. Data normalization and outlier detection are required for geochemical information. Different scales include: 1:200,000, 1:50,000, and 1:10,000. Geophysical information includes gravity data, aeromagnetic data, and electrical resistivity data, which need to be extracted using inversion and interpretation techniques to obtain physical property information related to the ore body; Remote sensing information: mainly using remote sensing image data obtained through public channels, combined with alteration information extraction technology, to construct a remote sensing image database for the study area; Drilling Information: Organize exploration and analysis data from various boreholes in the study area. Spatial processing of the borehole data is required to ensure spatial consistency between the data and the three-dimensional geological model. Mineral resource information: This includes information on known mineral deposits and mineralization points in the study area. Spatial overlay analysis is required to extract the spatial distribution characteristics related to the ore bodies.

[0008] In one possible implementation, a three-dimensional intelligent prediction model for the demonstration area is constructed, including: Direct calculation: Direct spatial analysis of 3D models such as ore bodies and strata to extract their spatial distribution characteristics; Distance calculation: For structural features such as fractures and alteration zones, calculate the distances from them to the fracture surface and alteration zone, and use them as input variables for the prediction model; Interpolation calculation: The grade and resistivity of heavy metal elements are calculated using the interpolated three-dimensional model to ensure the continuity and spatial consistency of the data.

[0009] In one possible implementation, the machine learning model construction adopts random forest and gradient boosting tree algorithms, and a hyperparameter optimization method based on grid search and cross-validation. The grid search traverses all possible hyperparameter combinations, and the model performance is evaluated by combining cross-validation. Finally, the parameter combination with the highest score is selected to achieve automated hyperparameter optimization.

[0010] In one possible implementation, the delineation of the mineral exploration target area includes: Target area prediction: Based on the probability distribution map or classification results output by the model, delineate the mineral exploration target area; Target area verification: The predicted target area is verified in the field through expert demonstration and drilling operations to obtain the verification results; Results optimization: The model is optimized and adjusted based on the validation results to improve the accuracy and effectiveness of mineral exploration prediction.

[0011] Compared with the prior art, the beneficial effects of the present invention are: The orebody prediction method based on 3D geological modeling and geological big data analysis disclosed in this invention innovatively integrates a three-in-one technical architecture of "3D geological modeling - multi-source geological data fusion - machine learning parameter optimization". By constructing a spatially coupled model of a geological-geophysical-geochemical 3D data field and employing data processing and analysis techniques such as machine learning and deep learning, it achieves ore prospecting prediction in deep and peripheral areas of mines. This method fully utilizes the complementarity of multi-source heterogeneous data, combines the spatial analysis capabilities of 3D geological modeling with the efficiency of big data analysis, and provides a scientific basis and technical support for the quantitative prediction of deep concealed orebodies. Attached Figure Description

[0012] Figure 1 A flowchart illustrating an embodiment of the present disclosure of a method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis is shown. Detailed Implementation

[0013] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0014] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0015] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0016] According to one aspect of this disclosure, a method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis is provided, the method comprising: S1, Establish a database for the deep edge research area of ​​the mine; S2, Establish a three-dimensional geological model of the study area; S3, construct a three-dimensional intelligent prediction model for the demonstration area. Based on the three-dimensional variable data of strata, ore bodies, faults, geochemical exploration, and geophysical exploration in the three-dimensional geological model, use the known ore body model as prior information and the geological and geophysical variables as three-dimensional integrated information to carry out target area prediction work. S4. Mineral exploration target area delineation: Using the constructed three-dimensional intelligent mineral exploration prediction model and combined with the geological information of the study area, favorable mineral exploration target areas are delineated.

[0017] In one possible implementation, a database of the deep-edge research area of ​​the mine is established, including: Collect multi-source heterogeneous geological data, including geological information, geochemical information, geophysical information, remote sensing information, drilling information, and mineral resource data of the study area; Standardization processing was performed on multi-source heterogeneous geological data to obtain a multi-scale, multi-element mineral exploration dataset for the study area; Standardization processes include data cleaning, format standardization, and semantic normalization to eliminate data redundancy and inconsistency and ensure data quality.

[0018] In one possible implementation, the database includes: Geological information: mainly includes geological maps, geological reports, structural information, and stratigraphic information. Geological information needs to be digitized and its spatial coordinates unified for use in 3D modeling. Geochemical information: Covers geochemical data at different scales, including the abundance and distribution of major and trace elements. Data normalization and outlier detection are required for geochemical information. Different scales include: 1:200,000, 1:50,000, and 1:10,000. Geophysical information includes gravity data, aeromagnetic data, and electrical resistivity data, which need to be extracted using inversion and interpretation techniques to obtain physical property information related to the ore body; Remote sensing information: mainly using remote sensing image data obtained through public channels, combined with alteration information extraction technology, to construct a remote sensing image database for the study area; Drilling Information: Organize exploration and analysis data from various boreholes in the study area. Spatial processing of the borehole data is required to ensure spatial consistency between the data and the three-dimensional geological model. Mineral resource information: This includes information on known mineral deposits and mineralization points in the study area. Spatial overlay analysis is required to extract the spatial distribution characteristics related to the ore bodies.

[0019] In one possible implementation, a three-dimensional intelligent prediction model for the demonstration area is constructed, including: Direct calculation: Direct spatial analysis of 3D models such as ore bodies and strata to extract their spatial distribution characteristics; Distance calculation: For structural features such as fractures and alteration zones, calculate the distances from them to the fracture surface and alteration zone, and use them as input variables for the prediction model; Interpolation calculation: The grade and resistivity of heavy metal elements are calculated using the interpolated three-dimensional model to ensure the continuity and spatial consistency of the data.

[0020] In one possible implementation, the machine learning model construction adopts random forest and gradient boosting tree algorithms, and a hyperparameter optimization method based on grid search and cross-validation. The grid search traverses all possible hyperparameter combinations, and the model performance is evaluated by combining cross-validation. Finally, the parameter combination with the highest score is selected to achieve automated hyperparameter optimization.

[0021] In one possible implementation, the delineation of the mineral exploration target area includes: Target area prediction: Based on the probability distribution map or classification results output by the model, delineate the mineral exploration target area; Target area verification: The predicted target area is verified in the field through expert demonstration and drilling operations to obtain the verification results; Results optimization: The model is optimized and adjusted based on the validation results to improve the accuracy and effectiveness of mineral exploration prediction.

[0022] This method combines multi-source data fusion with 3D modeling techniques and automated optimization of machine learning algorithms. It is applicable to the following scenarios: Deep mineral exploration: Providing efficient and accurate prediction solutions for deep areas that are difficult to explore using traditional geological methods.

[0023] Mineral exploration in peripheral areas: Using the spatial analysis capabilities of 3D models, potential mineral exploration target areas are delineated.

[0024] Quantitative prediction of mineral resources: Combining known ore body information and geophysical and chemical data to achieve quantitative prediction of mineral resources.

[0025] By combining 3D geological modeling with geological big data analysis techniques, a complete method for predicting deep concealed ore bodies has been constructed. This method not only fully utilizes the complementarity of multi-source data but also significantly improves the efficiency and accuracy of mineral exploration prediction through automated optimization of machine learning algorithms. Future work will further enhance the reliability of prediction results through target area validation and model optimization, providing a scientific basis for mineral exploration in deep and peripheral mining areas.

[0026] This innovative approach integrates a three-pronged technical architecture: 3D geological modeling, multi-source geoscientific data fusion, and machine learning parameter optimization. By constructing a spatially coupled model of a 3D geological-geophysical-geochemical data field and employing data processing and analysis techniques such as machine learning and deep learning, it enables mineral exploration prediction in deep and peripheral mining areas. This method fully leverages the complementarity of multi-source heterogeneous data, combines the spatial analysis capabilities of 3D geological modeling with the efficiency of big data analysis, and provides a scientific basis and technical support for the quantitative prediction of deep, concealed ore bodies.

[0027] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for predicting ore bodies based on three-dimensional geological modeling and geological big data analysis, characterized in that: The method includes: S1, Establish a database for the deep edge research area of ​​the mine; S2, Establish a three-dimensional geological model of the study area; S3, construct a three-dimensional intelligent prediction model for the demonstration area. Based on the three-dimensional variable data of strata, ore bodies, faults, geochemical exploration, and geophysical exploration in the three-dimensional geological model, use the known ore body model as prior information and the geological and geophysical variables as three-dimensional integrated information to carry out target area prediction work. S4. Mineral exploration target area delineation: Using the constructed three-dimensional intelligent mineral exploration prediction model, combined with the geological information of the study area, favorable mineral exploration target areas are delineated.

2. The orebody prediction method based on three-dimensional geological modeling and geological big data analysis according to claim 1, characterized in that, Establish a database for the study area of ​​deep and peripheral mining areas, including: Collect multi-source heterogeneous geological data, including geological information, geochemical information, geophysical information, remote sensing information, drilling information, and mineral resource data of the study area; Standardization processing was performed on multi-source heterogeneous geological data to obtain a multi-scale, multi-element mineral exploration dataset for the study area; Standardization processes include data cleaning, format standardization, and semantic normalization to eliminate data redundancy and inconsistency and ensure data quality.

3. The orebody prediction method based on three-dimensional geological modeling and geological big data analysis according to claim 2, characterized in that, The database includes: Geological information: mainly includes geological maps, geological reports, structural information, and stratigraphic information. Geological information needs to be digitized and its spatial coordinates unified for use in 3D modeling. Geochemical information: Covers geochemical data at different scales, including the abundance and distribution of major and trace elements. Data normalization and outlier detection are required for geochemical information. Different scales include: 1:200,000, 1:50,000, and 1:10,000. Geophysical information includes gravity data, aeromagnetic data, and electrical resistivity data, which need to be extracted using inversion and interpretation techniques to obtain physical property information related to the ore body; Remote sensing information: mainly using remote sensing image data obtained through public channels, combined with alteration information extraction technology, to construct a remote sensing image database for the study area; Drilling Information: Organize exploration and analysis data from various boreholes in the study area. Spatial processing of the borehole data is required to ensure spatial consistency between the data and the three-dimensional geological model. Mineral resource information: This includes information on known mineral deposits and mineralization points in the study area. Spatial overlay analysis is required to extract the spatial distribution characteristics related to the ore bodies.

4. The orebody prediction method based on three-dimensional geological modeling and geological big data analysis according to claim 1, characterized in that, Constructing a three-dimensional intelligent prediction model for the demonstration area, including: Direct calculation: Direct spatial analysis of 3D models such as ore bodies and strata to extract their spatial distribution characteristics; Distance calculation: For structural features such as fractures and alteration zones, calculate the distances from them to the fracture surface and alteration zone, and use them as input variables for the prediction model; Interpolation calculation: The grade and resistivity of heavy metal elements are calculated using the interpolated three-dimensional model to ensure the continuity and spatial consistency of the data.

5. The orebody prediction method based on three-dimensional geological modeling and geological big data analysis according to claim 4, characterized in that, In terms of machine learning model construction, random forest and gradient boosting tree algorithms were adopted, and a hyperparameter optimization method based on grid search and cross-validation was used. The grid search traversed all possible hyperparameter combinations, and the model performance was evaluated by combining cross-validation. Finally, the parameter combination with the highest score was selected to achieve automated hyperparameter optimization.

6. The orebody prediction method based on three-dimensional geological modeling and geological big data analysis according to claim 4, characterized in that, Mineral exploration target area delineation, including: Target area prediction: Based on the probability distribution map or classification results output by the model, delineate the target area for mineral exploration; Target area verification: The predicted target area is verified in the field through expert demonstration and drilling operations to obtain the verification results; Results optimization: The model is optimized and adjusted based on the validation results to improve the accuracy and effectiveness of mineral exploration prediction.

Images