AI-based attribute-free geological map library building method and system

Abstract

The invention relates to the technical field of geological map construction, in particular to an AI-based attribute-free geological map library construction method and system. The method comprises the following steps: acquiring a remote sensing data set of a to-be-constructed region, analyzing the remote sensing data set, and determining a geological feature information set; analyzing the geological feature information set, performing combined recognition analysis on unit geological features, and determining a geological boundary information set; acquiring a sample data set, and based on the geological boundary information set, performing structural form trend analysis on the sample data set to determine a multi-layer structure information set; analyzing the geological boundary information set and the multi-layer structure information set, and determining each piece of multi-layer structure information and a unified space mapping coordinate set corresponding to the geological boundary; and based on the unified space mapping coordinate set, according to the geological boundary information set and the multilayer structure information set, constructing and outputting an attribute-free geological map. According to the method, the attribute-free geological map can clearly present the spatial relationship between various geological structures and boundaries, and important scientific data reference is provided for geological research.

Description

Technical Field

[0001] The present application relates to the technical field of geological map construction, and in particular to an AI-based attributeless geological map database construction method and system. Background Art

[0002] No attribute geology Figure 1 Generally refers to a geological map that does not contain detailed geological attribute information, such as stratum names, lithology descriptions, structural characteristics, etc. This type of geological map usually only provides basic geological boundaries and morphological information and is often used in situations where it is necessary to show structural relationships or spatial distribution patterns without being affected by specific geological details.

[0003] Existing attributeless geological map construction technology makes it difficult to make accurate analysis of the boundaries and morphology of multi-layer geological structures with complex spatial distribution, resulting in the omission of important and subtle geological features in the constructed attributeless geological maps, which limits geological research based on attributeless geological maps that lack details. Summary of the invention

[0004] The present application provides an AI-based attributeless geological map database construction method and system to solve the above technical problems.

[0005] In a first aspect, the present application provides an AI-based method for building a database of attributeless geological maps, the method comprising:

[0006] Acquire a remote sensing data set of the area to be constructed, analyze the remote sensing data set to determine a geological feature information set; analyze the geological feature information set, perform combined identification analysis on unit geological features, and determine a geological boundary information set; acquire a sample data set, and perform structural morphological trend analysis on the sample data set based on the geological boundary information set to determine a multi-layer structure information set; analyze the geological boundary information set and the multi-layer structure information set to determine a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary; based on the unified spatial mapping coordinate set, construct and output an attributeless geological map according to the geological boundary information set and the multi-layer structure information set.

[0007] Through the above technical scheme, the geological feature information in the remote sensing data set is analyzed, the combination of unit geological features is identified and analyzed, and the dynamic combination and analysis of complex geological structures are realized to construct a geological convenient information set, effectively identify the details in the geological boundary morphology, and enable users to capture subtle geological changes and boundaries in attributeless geological maps, thereby improving the accuracy of attributeless geological maps. Through comprehensive analysis of sample data sets and geological boundary information sets, a multi-layer structure information set is constructed, so that attributeless geological maps can express the relationship and direction between different geological layers. By establishing a unified spatial mapping coordinate set, the spatial consistency of different geological information is ensured, so that attributeless geological maps can clearly present the spatial relationship between various geological structures and boundaries, providing important scientific data references for users to conduct research based on attributeless geological maps.

[0008] Optionally, the remote sensing data set includes spectral data, basic terrain elevation information and regional remote sensing image information, and the step of analyzing the remote sensing data set to determine the geological feature information set includes:

[0009] According to the preset unit analysis area information, the area to be constructed is divided into a number of data extraction areas; the spectral data is analyzed to determine the vegetation index, water index and ice and snow index of each analysis area; the basic terrain elevation information is analyzed to determine the slope information and slope direction information of each data extraction area; according to the vegetation index, the water index, the ice and snow index, the slope information and the slope direction information corresponding to each data extraction area, a number of local feature models are determined; according to the number of local feature models and the regional remote sensing image information, a geological feature information set is determined.

[0010] Through the above technical scheme, the area to be constructed is divided into several data extraction areas, the spectral data is analyzed, the vegetation index, water index and ice and snow index corresponding to the data analysis area are determined, and the slope information corresponding to the data extraction area is determined by analyzing the terrain elevation information. Starting from the above multi-dimensional data, a local feature model reflecting the digital geological characteristics in the data extraction area is constructed. Then, on the basis of the local feature model, the regional remote sensing image information is analyzed to obtain a geological feature information set reflecting the morphological details of the geological boundaries in the area to be constructed, providing a scientific digital information basis for the subsequent construction of attributeless geological maps.

[0011] Optionally, determining a plurality of local feature models according to the vegetation index, the water body index, the ice and snow index, the slope information and the slope aspect information corresponding to each data extraction area includes:

[0012] According to the preset combination rules, several data extraction areas are combined to obtain several characteristic analysis areas; according to the several vegetation indices, several water body indices, several ice and snow indices, several slope information and several slope aspect information corresponding to each characteristic analysis area, the mean value of vegetation index and the standard deviation of vegetation index, the mean value of water body index and the standard deviation of water body index, the mean value of ice and snow index and the standard deviation of ice and snow index, the mean value of slope and the standard deviation of slope, the mean value of slope and the standard deviation of slope aspect are determined respectively; the local characteristic model of each characteristic analysis area is constructed, which is specifically the following expression:

[0013]

[0014] Wherein, M(i,j) is the local feature model corresponding to the feature analysis area at the coordinate (i,j), μ NV is the mean value of the vegetation index, σ NV is the standard deviation of the vegetation index, μ NW is the mean value of the water index, σ NW is the standard deviation of the water index, μ NS is the mean value of the ice and snow index, σ NS is the standard deviation of the ice and snow index, μ SP is the mean slope, σ SP is the standard deviation of the slope, v AS is the mean slope aspect, σ AS is the standard deviation of the aspect.

[0015] Through the above technical solution, several data extraction areas are merged into several feature analysis areas according to preset combination rules to better capture the changes in geological characteristics within the area, and based on the mean and standard deviation of the plant index, water index, ice and snow index, slope information and slope aspect information in the feature analysis area, a local feature model is constructed through mathematical analysis. By scaling the data, the adaptability of the local feature model to different data sets and complex geological conditions is improved, so that the local feature model can comprehensively reflect the geological characteristics in the feature analysis area.

[0016] Optionally, determining a geological feature information set according to the plurality of local feature models and the regional remote sensing image information includes:

[0017] Analyze the regional remote sensing image information to determine the gradient direction value of each feature analysis area; based on the gradient direction value, determine the edge strength index of each feature analysis area according to the local feature models, specifically the following formula:

[0018]

[0019] Wherein, E(i,j) is the edge strength index of the feature analysis area at coordinate (i,j), M k (i, j) is the kth eigenvalue in the local feature model corresponding to the current feature analysis area, θ is the gradient direction value, w k is the preset influence weight of the feature type corresponding to the kth feature value; and constructs the geological feature information set according to the edge strength index corresponding to each feature analysis area.

[0020] Through the above technical solution, using mathematical analysis methods, according to the gradient direction pointing value and the local feature model, through the designed mathematical formula, the edge strength index reflecting whether the feature analysis area is located on the geological boundary is scientifically and accurately quantified, providing scientific quantitative data for the subsequent determination of the geological boundary details in the area to be constructed.

[0021] Optionally, analyzing the basic terrain elevation information to determine the slope information and slope aspect information of each data extraction area includes:

[0022] According to the basic terrain elevation information, the horizontal coordinate value, the vertical coordinate value and the elevation value of the center point of each data extraction area are determined; according to the horizontal coordinate value, the vertical coordinate value and the elevation value, the slope direction value of each data extraction area is determined, and the slope direction value is used as the slope information, which is specifically the following formula:

[0023]

[0024] Wherein, SP is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value; according to the horizontal coordinate value, the vertical coordinate value and the elevation value, the slope direction value of each data extraction area is determined, and the slope direction value is used as the slope information, which is specifically the following formula:

[0025]

[0026] Among them, AS is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value.

[0027] Through the above technical scheme, mathematical analysis methods are used to scientifically quantify the slope direction value reflecting the slope size of the data extraction area and the slope aspect value reflecting the slope direction based on the horizontal coordinate value, vertical coordinate value and elevation value of the center point of the data extraction area through mathematical formulas, so as to clarify the local slope and slope aspect corresponding to each data extraction area, and provide accurate data basis for the construction of local feature models.

[0028] Optionally, analyzing the geological feature information set, performing combined identification analysis on unit geological features, and determining a geological boundary information set includes:

[0029] According to the edge strength index corresponding to each of the feature analysis areas in the geological feature information set, the edge strength mean and the edge strength standard deviation are determined; according to the edge strength index, the edge strength mean and the edge strength standard deviation, the boundary orientation value of each of the feature analysis areas is determined, specifically as follows:

[0030]

[0031] Among them, B(i,j) is the boundary pointing value of the feature analysis area at the coordinate (i,j), E(i,j) is the edge strength index of the feature analysis area at the coordinate (i,j), mean(E) is the edge strength mean, σ(E) is the edge strength standard deviation, and α is a preset adjustment coefficient; based on the distribution position of each feature analysis area in the area to be constructed, according to the boundary pointing value of each feature analysis area, the geological boundary features in adjacent feature analysis areas are combined to determine the geological boundary information set.

[0032] Through the above technical solution, mathematical analysis methods are used to automatically quantify the boundary orientation value corresponding to each feature analysis area based on the edge strength index, edge strength mean and edge strength standard deviation through mathematical expressions, so as to quickly and accurately mark all feature analysis areas located on the geological boundary, providing data basis for clearly presenting the geological boundary morphological details in subsequent attributeless geological maps.

[0033] Optionally, the sample data set includes a number of sample extraction coordinates, a number of sample cross-section image data and a number of sample interception depths, and the structural morphology trend analysis is performed on the sample data set based on the geological boundary information set to determine the multi-layer structure information set, including:

[0034] Analyze the cross-sectional image data of each of the samples to determine a number of structural stratification boundaries; analyze the geological boundary information set based on the extraction coordinates of each of the samples and the interception depth of each of the samples to determine a number of structural strike information; generate a number of multi-layer structural texture strike images based on the several structural strike information and the several structural stratification boundaries; construct the multi-layer structural information set based on the extraction coordinates of the several samples and the several multi-layer structural texture strike images.

[0035] Through the above technical scheme, the sample cross-section data is analyzed, the structural stratification boundaries reflecting the boundaries between different geological layers are identified and extracted, and the geological boundary information is intelligently analyzed based on the sample extraction coordinates and the sample interception depth, and the structural trend information reflecting the trends of different geological layers is derived. The structural trend information and structural stratification boundaries are comprehensively analyzed to generate a multi-layer structural texture trend image, and a multi-layer structural information set is constructed based on the sample extraction coordinates and the multi-layer structural texture trend image, so that the multi-layer structural information set can truly reflect the position and trend of different geological layers underground in the area to be constructed, thereby making the subsequent attributeless geological map more comprehensive in the spatial dimension.

[0036] Optionally, the analyzing the geological boundary information set and the multi-layer structure information set to determine a unified spatial mapping coordinate set of each multi-layer structure information and a corresponding geological boundary includes:

[0037] According to the distribution position of each of the feature analysis areas within the area to be constructed, a unified spatial coordinate system is established for all the combined geological boundary features in the geological boundary information set to determine the geological boundary feature coordinate set; based on the geological boundary feature coordinate set, a multi-layer structure coordinate set is determined according to the relative position of each of the sample extraction coordinates and the corresponding feature analysis area; based on the geological boundary feature coordinate set and the multi-layer structure coordinate set, the unified spatial mapping coordinate set is determined.

[0038] Through the above technical scheme, unified spatial coordinates are established for the data in the geological boundary information set representing the state of the surface geological boundary in the area to be constructed and the multi-layer structure information set representing the direction of the underground multi-layer geological structure in the area to be constructed, so as to obtain the geological boundary feature coordinate set and the multi-layer structure coordinate set, which effectively avoids the misalignment problem between data in different information sets, ensures that the changes in surface geological characteristics and underground geological characteristics are all based on a unified spatial coordinate system, and improves the application value of attributeless geological maps.

[0039] Optionally, constructing and outputting an attributeless geological map based on the unified spatial mapping coordinate set and according to the geological boundary information set and the multi-layer structure information set includes:

[0040] Based on the unified spatial mapping coordinate set, the geological boundary information set and the multi-layer structure information set are structured to determine boundary vector data and structure vector data; based on a preset geographic information drawing model, a geological boundary morphology map and several multi-layer geological structure trend maps are drawn respectively according to the boundary vector data and the structure vector data, and according to the unified spatial mapping coordinate set, several multi-layer geological structure trend maps are indexed and mapped on the geological boundary morphology map to construct and output the attributeless geological map.

[0041] Through the above technical scheme, the geological boundary information set and the multi-layer structure information set are structured and processed to obtain boundary vector data and structure vector data, ensuring the consistency of data format. Then, through the preset geographic information drawing model, the geological boundary morphology map and several multi-layer geological structure trend maps are drawn in a unified spatial coordinate system, and the position of the multi-layer geological structure trend map is indexed and mapped, so that users can clearly know the relative position of the multi-layer geological structure trend map representing the underground geological structure trend and the geological boundary morphology map, accurately convey geological information, and avoid mutual interference between geological boundaries and multi-layer geological structures.

[0042] In a second aspect, the present application provides an AI-based attributeless geological map database building system, the system comprising:

[0043] A feature analysis module, used to obtain a remote sensing data set of the area to be constructed, analyze the remote sensing data set, and determine a geological feature information set;

[0044] A boundary analysis module is used to analyze the geological feature information set, perform combined identification analysis on unit geological features, and determine the geological boundary information set;

[0045] A structural analysis module, used to obtain a sample data set, and based on the geological boundary information set, perform structural morphology trend analysis on the sample data set to determine a multi-layer structural information set;

[0046] A coordinate mapping module, used for analyzing the geological boundary information set and the multi-layer structure information set, and determining a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary;

[0047] An output module is constructed to construct and output an attributeless geological map based on the unified space mapping coordinate set, according to the geological boundary information set and the multi-layer structure information set. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0050] Figure 2 A flowchart of a method for building a database of attributeless geological maps based on AI provided in one embodiment of the present application;

[0051] Figure 3A schematic diagram of the structure of an attributeless geological map database building system based on AI is provided in one embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0054] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0055] Existing attributeless geological map construction technology makes it difficult to make accurate analysis of the boundaries and morphology of multi-layer geological structures with complex spatial distribution, resulting in the omission of important and subtle geological features in the constructed attributeless geological maps, which limits geological research based on the lack of detail in the attributeless geological maps.

[0056] Based on this, the present application provides an AI-based attributeless geological map database construction method and system. Through comprehensive analysis of sample data sets and geological boundary information sets, a multi-layer structure information set is constructed, so that the attributeless geological map can express the relationship and direction between different geological layers, and by establishing a unified spatial mapping coordinate set, the spatial consistency of different geological information is ensured, so that the attributeless geological map can clearly present the spatial relationship between various geological structures and boundaries, and provide important scientific data references for users to conduct research based on attributeless geological maps. The specific implementation method can refer to the following embodiments.

[0057] Figure 1 A schematic diagram of an application scenario provided for this application. In the process of constructing an attributeless geological map, the method provided by this application is applied to accurately present the surface geological boundary morphology and underground geological structure direction in the construction area, so as to help improve the efficiency and effect of geological research based on attributeless maps.

[0058] Specifically, the method provided in the present application is applied to any server, which communicates with a remote sensing data collection device, obtains a remote sensing data set provided by the remote sensing data collection device and a sample data set provided by a geological prospector through the server, analyzes the geological feature information in the remote sensing data set, and performs combined identification and analysis of unit geological features, thereby realizing dynamic combination and analysis of complex geological structures, so as to construct a geological convenient information set, effectively identify details in geological boundary morphology, and enable users to capture subtle geological changes and boundaries in attributeless geological maps, thereby improving the accuracy of attributeless geological maps, and constructing a multi-layer structure information set through comprehensive analysis of sample data sets and geological boundary information sets, so that attributeless geological maps can express the relationship and direction between different geological layers, and by establishing a unified spatial mapping coordinate set, ensure the consistency of different geological information in space, so that attributeless geological maps can clearly present the spatial relationship between various geological structures and boundaries, and provide important scientific data references for users to conduct research based on attributeless geological maps. The specific implementation method can refer to the following embodiments.

[0059] Figure 2 The following is a flowchart of a method for building a database of non-attributed geological maps based on AI provided in one embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes:

[0060] S201, obtaining a remote sensing data set of the area to be constructed, analyzing the remote sensing data set, and determining a geological feature information set.

[0061] The area to be constructed may be the corresponding area for which a geological map needs to be constructed currently.

[0062] The remote sensing data set may be data reflecting the geological conditions in the area to be constructed obtained by analyzing the area to be constructed using remote sensing data collection equipment, such as artificial satellites, using remote sensing analysis technology.

[0063] The geological feature information set may be a collection of information used to reflect the geological features in the area to be constructed.

[0064] Specifically, remote sensing technology has the advantages of wide area coverage and rapid acquisition. It can provide a large amount of basic data for the drawing of attributeless geological maps. Compared with simple ground exploration, remote sensing technology is more cost-effective. Through remote sensing data collection equipment, the geology of the area to be constructed is analyzed, and remote sensing data sets are collected to achieve a preliminary and extensive survey of the geology of the area to be constructed. Then, mathematical analysis methods are used to extract information that can reflect the geological characteristics of the area to be constructed, so as to construct a geological characteristic information set, which provides a scientific and important data basis for the subsequent further analysis of the geological boundary morphological details in the area to be constructed.

[0065] S202: Analyze the geological feature information set, perform combined identification analysis on unit geological features, and determine the geological boundary information set.

[0066] Unit geological characteristics can be characteristic information obtained through analysis that reflects the local geological boundary morphology.

[0067] Combined identification analysis can be an analytical process of combining and identifying different local geological boundary forms.

[0068] The geological boundary information set may be an information set reflecting the geological boundary morphology in the area to be constructed.

[0069] Specifically, since the geological feature information set contains all the geological feature information in the area to be constructed, if the geological feature information set is directly analyzed as a whole, the calculation burden will be too heavy, and it is very easy to cause the loss of geological feature details in the analysis results. By mathematically analyzing the geological feature information corresponding to different local areas in the area to be constructed in the geological feature information set, the geological boundary morphological characteristics of different local areas are accurately extracted, and the geological boundary morphological characteristics in different local areas are combined and identified to construct a geological boundary information set, which provides the geological boundary feature details in the area to be constructed for the construction of the attributeless geological map, thereby improving the precision and accuracy of the attributeless geological map.

[0070] S203, obtaining a sample data set, and performing structural morphology trend analysis on the sample data set based on the geological boundary information set to determine a multi-layer structure information set.

[0071] The sample data set may be core sample data used to reflect the geological structure characteristics of the area to be constructed.

[0072] Structural morphology trend analysis can be a process of deducing and analyzing the geological structure trend reflected in the core sample based on the geological boundary information set.

[0073] The multi-layer structure information set may be a collection of information reflecting the direction of the underground multi-layer geological structure in the area to be constructed.

[0074] Specifically, the geological boundary morphology can reflect the superficial changes of geological characteristics in the area to be constructed. In order to make the attributeless geological map more comprehensively reflect the geological characteristics in the area to be constructed, it is necessary to analyze the local underground multi-layer geological structure changes reflected by the core samples in the area to be constructed on the basis of the geological boundaries. Combined with the changing trends of the surface geological characteristics reflected by the geological boundaries, the changing trends of the underground multi-layer geological structure characteristics in the area to be constructed are deduced. The scientific analysis of the geological characteristics of the area to be constructed from different spatial dimensions has been realized, making the attributeless geological map constructed subsequently more comprehensive, so as to help relevant geological researchers to conduct more scientific geological research.

[0075] S204: Analyze the geological boundary information set and the multi-layer structure information set to determine a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary.

[0076] The unified space mapping coordinate set may be a set of corresponding coordinates of each information in the geological boundary information set and the multi-layer structure information set in the unified space coordinate system.

[0077] Specifically, after obtaining the geological boundary information set reflecting the changes in surface geological characteristics in the area to be constructed and the multi-layer structure information set reflecting the changes in underground geological characteristics, in order to avoid the misalignment problem between data in different information sets, a unified spatial mapping coordinate set is obtained by establishing and mapping the information in the geological boundary information set and the multi-layer structure information set, ensuring that the changes in surface geological characteristics and underground geological characteristics are both based on a unified spatial coordinate system. This allows relevant professionals who conduct scientific research with reference to attributeless geological maps to accurately combine the surface geological characteristics and underground geological characteristics in the area to be constructed, conduct scientific research on the overall geological characteristics in the area to be constructed, and ensure the consistency and comparability of surface geological characteristics and underground geological characteristics in space, which is particularly important for drawing correct geological research conclusions.

[0078] S205: Based on the unified spatial mapping coordinate set, according to the geological boundary information set and the multi-layer structure information set, construct and output an attributeless geological map.

[0079] An attributeless geological map is a geological map that does not contain detailed geological attribute information and focuses on displaying geological structure morphology.

[0080] Specifically, on the basis of a unified spatial mapping coordinate set, geological analysis techniques such as GIS (Geographic Information System) are used to perform spatial coordinate-based visualization processing on geological boundary information sets and multi-layer structure information sets, and different line types, colors or symbols are used to draw different geological features and boundaries to construct an attributeless geological map, which is then provided to corresponding users through human-computer interaction devices such as high-definition display screens for user research reference.

[0081] Through the method provided in this embodiment, the geological feature information in the remote sensing data set is analyzed, the combination of unit geological features is identified and analyzed, and the dynamic combination and analysis of complex geological structures are realized to construct a geological convenient information set, effectively identify the details in the geological boundary morphology, and enable users to capture subtle geological changes and boundaries in attributeless geological maps, thereby improving the accuracy of attributeless geological maps. Through comprehensive analysis of sample data sets and geological boundary information sets, a multi-layer structure information set is constructed, so that the attributeless geological map can express the relationship and direction between different geological layers, and by establishing a unified spatial mapping coordinate set, the spatial consistency of different geological information is ensured, so that the attributeless geological map can clearly present the spatial relationship between various geological structures and boundaries, providing important scientific data references for users to conduct research based on attributeless geological maps.

[0082] In some embodiments, the area to be constructed is divided into several data extraction areas according to preset unit analysis area information; spectral data is analyzed to determine the vegetation index, water body index and ice and snow index of each analysis area; basic terrain elevation information is analyzed to determine the slope information and slope aspect information of each data extraction area; according to the vegetation index, water body index, ice and snow index, slope information and slope aspect information corresponding to each data extraction area, several local feature models are determined; according to the several local feature models and regional remote sensing image information, a geological feature information set is determined.

[0083] Remote sensing datasets include spectral data, basic terrain elevation information, and regional remote sensing image information.

[0084] The spectral data may be spectral data collected by remote sensing data collection equipment, such as artificial satellites, by transmitting electromagnetic waves to the ground of the area to be constructed.

[0085] The basic terrain elevation information may be information collected through remote sensing technology that reflects the terrain elevation in the area to be constructed.

[0086] The regional remote sensing image information may be surface image information of the area to be constructed collected by remote sensing technology.

[0087] The preset unit analysis region information may be preset information including the size and number of unit regions into which the area to be constructed is divided. The preset unit analysis region information may be set according to the actual situation of the area to be constructed.

[0088] The data extraction area may be the smallest unit area for geological data analysis and extraction obtained by dividing the area to be constructed according to preset unit analysis area information.

[0089] The vegetation index can be used to quantitatively reflect the vegetation coverage in the data extraction area. The vegetation index can be calculated using the following formula (1):

[0090]

[0091] Among them, NV is the vegetation index, N is the near-infrared band index in the spectral data, and R is the red light band index in the spectral data.

[0092] The water body index can be a quantitative data used to reflect the distribution of water bodies in the data extraction area. The water body index can be calculated using the following formula (2):

[0093]

[0094] Among them, NW is the water body index, G is the green light band index in the spectral data, and N is the near-infrared band index in the spectral data.

[0095] The ice and snow index can be used to quantify the ice and snow coverage in the data extraction area. Since ice and snow have strong reflection in the green light band, the ice and snow index can be calculated by the following formula (3):

[0096]

[0097] Among them, ND is the ice and snow index, G is the green light band index in the spectral data, and S is the shortwave infrared band index in the spectral data.

[0098] The slope information may be information reflecting the change of terrain slope in the data extraction area.

[0099] The aspect information may be information reflecting the change of terrain aspect in the data extraction area.

[0100] The local feature model may be a data model containing local geological features within a unit data extraction area.

[0101] Specifically, according to the preset unit analysis area information, the area to be constructed is divided into several data extraction areas, which is helpful to dynamically control the analysis granularity and achieve a more detailed analysis of geological characteristics within an acceptable computing pressure. In the process of analyzing geological characteristics, since a large area of ​​surface cover will cover the actual geological morphology, the surface cover will have a direct impact on the analysis accuracy of geological characteristics, but at the same time, the characteristics of the surface cover can also reversely confirm the changes in geological morphology. For example, the vegetation coverage density in the fault area will change significantly, and the continuity of water coverage will also change significantly. Therefore, the vegetation coverage, water distribution and vegetation coverage in the comprehensive data extraction area can comprehensively reflect the surface geological characteristics, and the vegetation coverage, water distribution and vegetation coverage can be quantified according to spectral data through mathematical analysis, that is, the vegetation index, water index and ice and snow index are calculated respectively by formulas 1-3.

[0102] Furthermore, in the process of surface geological morphology analysis, the influence of terrain cannot be ignored. The shaping of geological features is affected by the terrain. For example, steep slopes with large slopes are prone to erosion, while steep slopes with small slopes are prone to deposition. The slope information and aspect information reflected by the terrain in the data extraction area are analyzed and extracted to reflect the influence of slope information and aspect information on geological morphology. Then, the vegetation index, water body index, ice and snow index, slope information and aspect information are integrated. Through mathematical analysis, a local feature model corresponding to each data extraction area is constructed, which can express the geological boundary characteristics of the data extraction area through mathematical quantitative data. According to the local feature model, the regional remote sensing images are further mathematically analyzed to achieve accurate positioning of the geological boundary morphology and construct a geological feature information set that can reflect the details of the geological boundary morphology in the area to be constructed.

[0103] Through the method provided in this embodiment, the area to be constructed is divided into several data extraction areas, the spectral data is analyzed, the vegetation index, water index and ice and snow index corresponding to the data analysis area are determined, and the slope information corresponding to the data extraction area is determined by analyzing the terrain elevation information. Starting from the above multi-dimensional data, a local feature model reflecting the digital geological characteristics in the data extraction area is constructed, and then on the basis of the local feature model, the regional remote sensing image information is analyzed to obtain a geological feature information set reflecting the morphological details of the geological boundaries in the area to be constructed, thereby providing a scientific digital information basis for the subsequent construction of attributeless geological maps.

[0104] In some embodiments, according to a preset combination rule, a plurality of data extraction areas are combined to obtain a plurality of characteristic analysis areas; according to a plurality of vegetation indices, a plurality of water body indices, a plurality of ice and snow indices, a plurality of slope information and a plurality of aspect information corresponding to each characteristic analysis area, a mean value of vegetation index and a standard deviation of vegetation index, a mean value of water body index and a standard deviation of water body index, a mean value of ice and snow index and a standard deviation of ice and snow index, a mean value of slope and a standard deviation of slope, a mean value of aspect and a standard deviation of aspect corresponding to each characteristic analysis area are respectively determined; and a local characteristic model of each characteristic analysis area is constructed, which is specifically the following expression (4):

[0105]

[0106] Among them, M(i,j) is the local feature model of the feature analysis area corresponding to the coordinate (i,j), μ NV is the mean value of vegetation index, σ NV is the standard deviation of vegetation index, μ NW is the mean value of water index, σ NW is the standard deviation of water index, μ NS is the mean value of the ice and snow index, σ NS is the standard deviation of the ice and snow index, μSP is the mean slope, σ SP is the slope standard deviation, μ AS is the mean slope aspect, σ AS is the aspect standard deviation.

[0107] The preset combination rule may be a preset rule for combining a plurality of data extraction areas. The preset combination rule may be set to 3×3, or may be set as required.

[0108] The feature analysis region may be an analysis region obtained by combining several data extraction regions and convenient for extracting geological boundary features.

[0109] The above-mentioned mean and standard deviation can be understood as the mathematically defined mean value and standard deviation of corresponding parameters in several data extraction areas contained in the feature analysis area.

[0110] Specifically, in the data extraction stage, the area to be constructed is divided into several data extraction areas with smaller granularity, which effectively ensures the accuracy of the data. When constructing the local feature model, in order to better capture the changes of geological features in the area, it is necessary to merge the data extraction areas with smaller granularity into several feature analysis areas with larger granularity according to the preset combination rules. Since local details are very important in complex terrain or geological structure, the local mean and standard deviation can capture the slight variation and anomaly of geological features and help identify the dynamic changes of potential geological features. At the same time, normalizing different features helps to reflect the performance of different features at similar scales. Therefore, according to the mean and standard deviation of plant index, water index, ice and snow index, slope information and aspect information in the feature analysis area, the corresponding local feature model is constructed through expression (4) to comprehensively reflect the performance of geological features in the feature analysis area.

[0111] Through the method provided in this embodiment, several data extraction areas are merged into several feature analysis areas according to preset combination rules to better capture the changes in geological characteristics within the area, and based on the mean and standard deviation of the plant index, water index, ice and snow index, slope information and slope aspect information in the feature analysis area, a local feature model is constructed through mathematical analysis. By scaling the data, the adaptability of the local feature model to different data sets and complex geological conditions is improved, so that the local feature model can comprehensively reflect the geological feature performance in the feature analysis area.

[0112] In some embodiments, the regional remote sensing image information is analyzed to determine the gradient direction pointing value of each feature analysis region; based on the gradient direction pointing value, according to a number of local feature models, the edge strength index of each feature analysis region is determined, specifically as follows:

[0113]

[0114] Where E(i,j) is the edge strength index of the feature analysis area at coordinate (i,j), M k (i, j) is the kth eigenvalue in the local feature model corresponding to the current feature analysis area, θ is the gradient direction value, and w k The preset influence weight of the feature type corresponding to the kth eigenvalue is obtained; and a geological feature information set is constructed according to the edge strength index corresponding to each feature analysis area.

[0115] The gradient direction pointing value can be the direction of change of the image gradient in the image area occupied by each feature analysis area in the regional remote sensing image information. The gradient direction pointing value is an angle value between 0 and 360 degrees. The gradient direction pointing value can be obtained by convolution operation, such as using the Sobel operator to calculate the image gradient in the horizontal and vertical directions in the feature analysis area, and then calculating the image gradient through the inverse tangent function.

[0116] The edge strength index may be a quantitative index reflecting the probability that the current feature analysis region is on a geological boundary. The larger the edge strength index is, the greater the probability that the current feature analysis region is on a geological boundary is.

[0117] The preset influence weight may be a weight value that expresses the influence of different features on the edge strength index. The preset influence weight may be set through expert experience or obtained through fitting analysis of authoritative geological research data.

[0118] Specifically, through formula (5) The degree of change of each eigenvalue in the local feature model in the corresponding image gradient direction is calculated by presetting the influence weight w k The contribution of different features to the edge front is adjusted, and finally the overall edge strength index corresponding to the current feature analysis area is calculated. The edge strength index represents the comprehensive change rate of the feature values ​​in multiple local feature models along the image gradient direction in a given feature analysis area. In this way, different local features are combined to identify and quantify the local mutation properties of the image, that is, the edge, which is mapped to the corresponding geological boundary in the remote sensing image information in practice, thereby reflecting the probability that each feature analysis area is located on the geological boundary.

[0119] Through the method provided in this embodiment, mathematical analysis methods are used, according to the gradient direction pointing value and the local feature model, and through the designed mathematical formula, the edge strength index reflecting whether the feature analysis area is located on the geological boundary is scientifically and accurately quantified, thereby providing scientific quantitative data for the subsequent determination of the geological boundary details in the area to be constructed.

[0120] In some embodiments, the horizontal coordinate value, the vertical coordinate value and the elevation value of the center point of each data extraction area are determined according to the basic terrain elevation information; the slope direction value of each data extraction area is determined according to the horizontal coordinate value, the vertical coordinate value and the elevation value, and the slope direction value is used as the slope information, which is specifically the following formula (6):

[0121]

[0122] Wherein, SP is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value; according to the horizontal coordinate value, the vertical coordinate value and the elevation value, the slope direction value of each data extraction area is determined, and the slope direction value is used as the slope information, which is specifically the following formula (7);

[0123]

[0124] Among them, AS is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value.

[0125] The elevation value may be a digital elevation value corresponding to the center point of the data extraction area in the basic terrain elevation information.

[0126] The slope orientation value may be an orientation value reflecting the slope corresponding to the data extraction area in the area to be constructed. The larger the slope orientation value is, the larger the terrain slope corresponding to the data extraction area is.

[0127] The aspect direction value may be a direction value reflecting the aspect corresponding to the data extraction area in the area to be constructed. The aspect direction value is an angle value, which is used to indicate the aspect angle.

[0128] Specifically, through formula (6) and The rates of change of the terrain in the horizontal and vertical directions are described respectively. Based on the slope calculation formula, the intensity of the slope is expressed by the sum of the squares of the above two. At the same time, through formula (7), the inverse tangent function is used to process the ratio of the rates of change of the terrain in the horizontal and vertical directions to obtain the direction angle of the slope, that is, the slope aspect. Through the above two formulas, the slope information and slope aspect information of the data extraction area can be scientifically quantified.

[0129] Through the method provided in this embodiment, mathematical analysis methods are used to scientifically quantify the slope direction value reflecting the slope size of the data extraction area and the slope aspect direction value reflecting the slope direction based on the horizontal coordinate value, vertical coordinate value and elevation value of the center point of the data extraction area through mathematical formulas, so as to clarify the local slope and slope aspect corresponding to each data extraction area, and provide accurate data basis for the construction of the local feature model.

[0130] In some embodiments, the edge strength mean and the edge strength standard deviation are determined according to the edge strength index corresponding to each feature analysis area in the geological feature information set; the boundary orientation value of each feature analysis area is determined according to the edge strength index, the edge strength mean and the edge strength standard deviation, which is specifically the following expression (8):

[0131]

[0132] Among them, B(i,j) is the boundary pointing value of the feature analysis area at the coordinate (i,j), E(i,j) is the edge strength index of the feature analysis area at the coordinate (i,j), mean(E) is the edge strength mean, σ(E) is the edge strength standard deviation, and α is the preset adjustment coefficient; based on the distribution position of each feature analysis area in the area to be constructed and according to the boundary pointing value of each feature analysis area, the geological boundary features in adjacent feature analysis areas are combined to determine the geological boundary information set.

[0133] The edge strength mean may be an average value of edge strength indices calculated by integrating the edge strength indices corresponding to all feature analysis areas in the area to be constructed.

[0134] The edge strength standard deviation may be a standard deviation of an edge strength index calculated based on the edge strength mean value by a standard deviation quantization formula.

[0135] The preset adjustment coefficient may be a value used to adjust the influence of the edge strength standard deviation in the process of determining the boundary orientation value. The preset adjustment coefficient may be obtained through fitting analysis of authoritative geological data.

[0136] The boundary pointing value can be a quantitative value for determining whether the feature analysis area is on a geological boundary. The boundary pointing value is a binary value. If the boundary pointing value is 1, it indicates that the current feature analysis area is on a geological boundary. If the boundary pointing value is 0, it indicates that the current feature analysis area is not on a geological boundary.

[0137] Specifically, when the edge strength index in the feature analysis area satisfies E(i,j)>mean(E)+α·σ(E) in expression (8), the boundary pointing value of the current feature analysis area is set to 1. The specific process is that when the edge strength index in the feature analysis area exceeds mean(E)+α·σ(E) (the influence of the standard deviation is adjusted by the preset adjustment coefficient), it is considered that the edge strength index exceeds the typical strength range. At this time, the boundary pointing value of the feature analysis area is set to 1. The above process uses the mean and standard deviation to determine the geological boundary reflected by the "mutation". If the edge strength index does not meet the above conditions, the boundary pointing value of the feature analysis area is set to 0.

[0138] Through the method provided in this embodiment, mathematical analysis methods are used to automatically quantify the boundary orientation value corresponding to each feature analysis area based on the edge strength index, edge strength mean and edge strength standard deviation through mathematical expressions, so as to quickly and accurately mark all feature analysis areas located on the geological boundary, thereby providing a data basis for clearly presenting the geological boundary morphological details in subsequent attributeless geological maps.

[0139] In some embodiments, each sample cross-sectional image data is analyzed to determine a number of structural stratification boundaries; based on the extraction coordinates of each sample and the interception depth of each sample, a geological boundary information set is analyzed to determine a number of structural strike information; based on the number of structural strike information and the number of structural stratification boundaries, a number of multi-layer structural texture strike images are generated; based on the extraction coordinates of the number of samples and the number of multi-layer structural texture strike images, a multi-layer structural information set is constructed.

[0140] The sample data set includes a number of sample extraction coordinates, a number of sample cross-sectional image data, and a number of sample interception depths.

[0141] The sample extraction coordinates may be the longitude and latitude coordinates corresponding to the current core sample collection point, and the sample extraction coordinates may be obtained through records of geological prospectors when collecting core samples.

[0142] The sample cross-section image data may be image data corresponding to the longitudinal cross-section of the core sample, and the sample cross-section image data may be obtained by geological prospectors analyzing the longitudinal cross-section of the core sample using professional image acquisition equipment.

[0143] The sample cutting depth may be the collection depth of the core sample, and the sample cutting depth may be obtained through the records of geological prospectors when collecting the core sample.

[0144] The structural layering boundary can be the dividing line between different geological layers reflected in the cross section of the core sample.

[0145] The structural strike information may be strike information of different geological layers derived by combining geological boundary information sets.

[0146] The multi-layer structure texture trend image may be image information generated to express the structural trend of multiple underground geological layers.

[0147] Specifically, due to the influence of sedimentation, there are dividing lines between different geological layers. The evolution interface image data is analyzed by the edge detection algorithm in the image analysis technology to determine several structural stratification boundaries. Then, through AI technology, such as the convolutional neural network trained with a large amount of geological data, the trends of different underground geological layers are deduced according to the morphological changes of the geological boundaries corresponding to the sample extraction coordinates and the sample interception depth. In combination with several structural stratification boundaries, a two-dimensional image for describing the trends of different geological layers is generated, that is, a multi-layer structural texture trend image. Then, a multi-layer structural information set is constructed with the sample extraction coordinates as the index and the corresponding multi-layer structural texture trend image as the content.

[0148] Through the method provided in this embodiment, the sample cross-section data is analyzed, the structural stratification boundaries reflecting the boundaries between different geological layers are identified and extracted, and based on the sample extraction coordinates and the sample interception depth, the geological boundary information is intelligently analyzed to derive the structural trend information reflecting the trends of different geological layers. The structural trend information and the structural stratification boundaries are comprehensively analyzed to generate a multi-layer structural texture trend image, and a multi-layer structural information set is constructed based on the sample extraction coordinates and the multi-layer structural texture trend image, so that the multi-layer structural information set can truly reflect the positions and trends of different geological layers underground in the area to be constructed, thereby making the subsequently obtained attributeless geological map more comprehensive in the spatial dimension.

[0149] In some embodiments, according to the distribution position of each feature analysis area in the area to be constructed, a unified spatial coordinate system is established for all combined geological boundary features in the geological boundary information set to determine the geological boundary feature coordinate set; based on the geological boundary feature coordinate set, according to the relative position of each sample extraction coordinate and the corresponding feature analysis area, a multi-layer structure coordinate set is determined; based on the geological boundary feature coordinate set and the multi-layer structure coordinate set, a unified spatial mapping coordinate set is determined.

[0150] The geological boundary feature coordinate set may be a set containing coordinate information corresponding to all geological boundaries in a unified spatial coordinate system.

[0151] The multi-layer structure coordinate set may be a set of coordinate information corresponding to all multi-layer structure texture images in a unified space coordinate system.

[0152] Specifically, the unification of the coordinate system can ensure that each geological feature is accurately positioned on the map, which is convenient for generating accurate and reliable attributeless geological maps. This has direct application value for subsequent geological research based on attributeless geological maps. By integrating the corresponding latitude and longitude positions of each feature analysis area in reality, GIS technology is used to establish a unified spatial coordinate system for the geological boundary features of the geological boundary information set to construct a geological boundary feature coordinate set. On this basis, according to the relative position of each sample extraction coordinate in the corresponding feature analysis area, the coordinate information of each multi-layer structure texture trend image in the unified spatial coordinate system is generated to construct a multi-layer structure coordinate set. The geological boundary feature coordinate set and the multi-layer structure coordinate set are combined to construct a unified spatial mapping coordinate set.

[0153] Through the method provided in this embodiment, unified spatial coordinates are established for the data in the geological boundary information set representing the state of the surface geological boundary in the area to be constructed and the multi-layer structure information set representing the direction of the underground multi-layer geological structure in the area to be constructed, so as to obtain the geological boundary feature coordinate set and the multi-layer structure coordinate set, which effectively avoids the misalignment problem between data in different information sets, ensures that the changes in surface geological characteristics and underground geological characteristics are all based on a unified spatial coordinate system, and improves the application value of attributeless geological maps.

[0154] In some embodiments, based on a unified spatial mapping coordinate set, the geological boundary information set and the multi-layer structure information set are structured to determine the boundary vector data and the structure vector data; based on a preset geographic information drawing model, a geological boundary morphology map and several multi-layer geological structure trend maps are drawn respectively according to the boundary vector data and the structure vector data, and according to the unified spatial mapping coordinate set, several multi-layer geological structure trend maps are indexed and mapped on the geological boundary morphology map to construct and output an attributeless geological map.

[0155] The boundary vector data may be data in a vector data format corresponding to the information in the geological boundary information set.

[0156] The structural vector data may be data in a vector data format corresponding to information in a multi-layer structural information set.

[0157] The preset geographic information drawing model may be a technical model for generating geological maps based on massive parameters, such as GIS.

[0158] The geological boundary morphology map may be an attributeless two-dimensional geological image used to describe the morphology of different surface geological boundaries in the area to be constructed.

[0159] The multi-layer geological structure trend map may be an attribute-free two-dimensional geological image describing the trends of different underground geological structures in the area to be constructed.

[0160] Specifically, through vector data format conversion tools, such as GDAL (Geospatial Data Abstraction Library), the geological boundary information set and the multi-layer structure information set are structured and converted into corresponding vector data formats, such as boundary vector data and structure vector data in GeoJSON format, and then a preset geographic information drawing model, such as GIS, is used to draw a geological boundary morphology map and several multi-layer geological structure trend maps using different lines and colors in a unified spatial coordinate system according to the boundary vector data and the structure vector data, and the multi-layer geological structure trend map is indexed and mapped according to the relative position of the surface geological boundary and the underground multi-layer structure in the unified spatial mapping coordinate set, thereby realizing the construction and output of the attributeless geological map.

[0161] Through the method provided in this embodiment, the geological boundary information set and the multi-layer structure information set are structured to obtain boundary vector data and structure vector data, ensuring the consistency of data format, and then through the preset geographic information drawing model, a geological boundary morphological map and several multi-layer geological structure trend maps are drawn in a unified spatial coordinate system, and the position of the multi-layer geological structure trend map is indexed and mapped, so that users can clearly know the relative position of the multi-layer geological structure trend map representing the underground geological structure trend and the geological boundary morphological map, accurately convey geological information, and avoid mutual interference between geological boundaries and multi-layer geological structures.

[0162] Figure 3 A schematic diagram of a structure of an attributeless geological map database building system based on AI provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the AI-based attributeless geological map database building system 300 of this embodiment includes: a feature analysis module 301, a boundary analysis module 302, a structure analysis module 303, a coordinate mapping module 304 and a construction output module 304.

[0163] The feature analysis module 301 is used to obtain a remote sensing data set of the area to be constructed, analyze the remote sensing data set, and determine a geological feature information set;

[0164] The boundary analysis module 302 is used to analyze the geological feature information set, perform combined identification analysis on unit geological features, and determine the geological boundary information set;

[0165] The structural analysis module 303 is used to obtain a sample data set, and based on the geological boundary information set, perform structural morphology trend analysis on the sample data set to determine a multi-layer structural information set;

[0166] A coordinate mapping module 304 is used to analyze the geological boundary information set and the multi-layer structure information set to determine a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary;

[0167] The construction output module 305 is used to construct and output an attributeless geological map based on the unified space mapping coordinate set, according to the geological boundary information set and the multi-layer structure information set.

[0168] Optionally, the feature analysis module 301 is specifically used to: divide the area to be constructed into several data extraction areas according to preset unit analysis area information; analyze the spectral data to determine the vegetation index, water body index and ice and snow index of each analysis area; analyze the basic terrain elevation information to determine the slope information and slope direction information of each data extraction area; determine several local feature models according to the vegetation index, water body index, ice and snow index, slope information and slope direction information corresponding to each data extraction area; determine a geological feature information set according to the several local feature models and the regional remote sensing image information.

[0169] Optionally, when determining a number of local feature models according to the vegetation index, the water index, the ice and snow index, the slope information and the aspect information corresponding to each data extraction area, the feature analysis module 301 is specifically used to: combine the data extraction areas according to a preset combination rule to obtain a number of feature analysis areas; determine the mean value of the vegetation index and the standard deviation of the vegetation index, the mean value of the water index and the standard deviation of the water index, the mean value of the ice and snow index and the standard deviation of the ice and snow index, the mean value of the slope and the standard deviation of the slope, and the mean value of the aspect and the standard deviation of the aspect according to the vegetation index, the water index, the ice and snow index, the slope information and the slope aspect information corresponding to each feature analysis area; construct the local feature model of each feature analysis area, which is specifically the following expression:

[0170]

[0171] Wherein, M(i,j) is the local feature model corresponding to the feature analysis area at the coordinate (i,j), μ NV is the mean value of the vegetation index, σ NV is the standard deviation of the vegetation index, μ NW is the mean value of the water index, σ NW is the standard deviation of the water index, μ NS is the mean value of the ice and snow index, σ NS is the standard deviation of the ice and snow index, μ SP is the mean slope, σ SP is the standard deviation of the slope, μ AS is the mean slope aspect, σ AS is the standard deviation of the aspect.

[0172] Optionally, when determining the geological feature information set according to the local feature models and the regional remote sensing image information, the feature analysis module 301 is specifically used to: analyze the regional remote sensing image information to determine the gradient direction pointing value of each feature analysis area; based on the gradient direction pointing value, determine the edge strength index of each feature analysis area according to the local feature models, specifically the following formula:

[0173]

[0174] Wherein, E(i,j) is the edge strength index of the feature analysis area at coordinate (i,j), M k (i, j) is the kth eigenvalue in the local feature model corresponding to the current feature analysis area, θ is the gradient direction value, w k is the preset influence weight of the feature type corresponding to the kth feature value; and constructs the geological feature information set according to the edge strength index corresponding to each feature analysis area.

[0175] Optionally, when analyzing the basic terrain elevation information and determining the slope information and slope direction information of each data extraction area, the feature analysis module 301 is specifically used to: determine the abscissa value, ordinate value and elevation value of the center point of each data extraction area according to the basic terrain elevation information; determine the slope direction value of each data extraction area according to the abscissa value, the ordinate value and the elevation value, and use the slope direction value as the slope information, which is specifically the following formula:

[0176]

[0177] Wherein, SP is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value; according to the horizontal coordinate value, the vertical coordinate value and the elevation value, the slope direction value of each data extraction area is determined, and the slope direction value is used as the slope information, which is specifically the following formula:

[0178]

[0179] Among them, AS is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value.

[0180] Optionally, the boundary analysis module 302 is specifically used to: determine the edge strength mean and the edge strength standard deviation according to the edge strength index corresponding to each of the feature analysis areas in the geological feature information set; determine the boundary orientation value of each of the feature analysis areas according to the edge strength index, the edge strength mean and the edge strength standard deviation, which is specifically the following expression:

[0181]

[0182] Among them, B(i,j) is the boundary pointing value of the feature analysis area at the coordinate (i,j), E(i,j) is the edge strength index of the feature analysis area at the coordinate (i,j), mean(E) is the edge strength mean, σ(E) is the edge strength standard deviation, and α is a preset adjustment coefficient; based on the distribution position of each feature analysis area in the area to be constructed, according to the boundary pointing value of each feature analysis area, the geological boundary features in adjacent feature analysis areas are combined to determine the geological boundary information set.

[0183] Optionally, the structural analysis module 303 is specifically used to: analyze each of the sample cross-sectional image data to determine a number of structural stratification boundaries; analyze the geological boundary information set based on each sample extraction coordinate and each sample interception depth to determine a number of structural strike information; generate a number of multi-layer structural texture strike images based on the number of structural strike information and the number of structural stratification boundaries; construct the multi-layer structural information set based on the number of sample extraction coordinates and the number of multi-layer structural texture strike images.

[0184] Optionally, the coordinate mapping module 304 is specifically used to: establish a unified spatial coordinate system for all combined geological boundary features in the geological boundary information set according to the distribution position of each feature analysis area in the area to be constructed, and determine a geological boundary feature coordinate set; based on the geological boundary feature coordinate set, determine a multi-layer structure coordinate set according to the relative position of each sample extraction coordinate and the corresponding feature analysis area; determine the unified spatial mapping coordinate set according to the geological boundary feature coordinate set and the multi-layer structure coordinate set.

[0185] Optionally, the construction output module 305 is specifically used to: based on the unified spatial mapping coordinate set, perform structured processing on the geological boundary information set and the multi-layer structure information set to determine the boundary vector data and the structure vector data; based on a preset geographic information drawing model, draw a geological boundary morphology map and several multi-layer geological structure trend maps according to the boundary vector data and the structure vector data, respectively, and index map the several multi-layer geological structure trend maps on the geological boundary morphology map according to the unified spatial mapping coordinate set, to construct and output the attributeless geological map.

[0186] The system of this embodiment can be used to execute the method of any of the above embodiments. The implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. A method for building a database of attributeless geological maps based on AI, characterized in that: include: Acquire a remote sensing data set of the area to be constructed, analyze the remote sensing data set, and determine a geological feature information set; Analyzing the geological feature information set, performing combined identification analysis on unit geological features, and determining a geological boundary information set; Acquire a sample data set, and based on the geological boundary information set, perform structural morphology trend analysis on the sample data set to determine a multi-layer structure information set; Analyzing the geological boundary information set and the multi-layer structure information set to determine a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary; Based on the unified spatial mapping coordinate set, according to the geological boundary information set and the multi-layer structure information set, an attributeless geological map is constructed and output.

2. The method according to claim 1, characterized in that: The remote sensing data set includes spectral data, basic terrain elevation information and regional remote sensing image information, and the step of analyzing the remote sensing data set to determine the geological feature information set includes: According to the preset unit analysis area information, the area to be constructed is divided into a number of data extraction areas; Analyzing the spectral data to determine a vegetation index, a water index, and an ice and snow index for each analysis area; Analyze the basic terrain elevation information to determine the slope information and slope aspect information of each data extraction area; Determine a plurality of local feature models according to the vegetation index, the water body index, the ice and snow index, the slope information and the slope aspect information corresponding to each data extraction area; A geological feature information set is determined based on the local feature models and the regional remote sensing image information.

3. The method according to claim 2, characterized in that Determining a plurality of local feature models according to the vegetation index, the water body index, the ice and snow index, the slope information and the slope aspect information corresponding to each data extraction area includes: Combining the data extraction regions according to a preset combination rule to obtain a plurality of feature analysis regions; According to the plurality of vegetation indices, the plurality of water body indices, the plurality of ice and snow indices, the plurality of slope information and the plurality of slope aspect information corresponding to each characteristic analysis area, respectively determine the vegetation index mean and vegetation index standard deviation, the water body index mean and water body index standard deviation, the ice and snow index mean and ice and snow index standard deviation, the slope mean and slope standard deviation, the slope aspect mean and slope aspect standard deviation corresponding to each characteristic analysis area; The local feature model of each feature analysis area is constructed, specifically as follows: Wherein, M(i,j) is the local feature model corresponding to the feature analysis area at the coordinate (i,j), μ NV is the mean value of the vegetation index, σ NV is the standard deviation of the vegetation index, μ NW is the mean value of the water index, σ NW is the standard deviation of the water index, μ NS is the mean value of the ice and snow index, σ NS is the standard deviation of the ice and snow index, μ SP is the mean slope, σ SP is the standard deviation of the slope, μ AS is the mean slope aspect, σ AS is the standard deviation of the aspect.

4. The method according to claim 3, characterized in that Determining a geological feature information set according to the local feature models and the regional remote sensing image information includes: Analyze the remote sensing image information of the region to determine the gradient direction value of each feature analysis region; Based on the gradient direction value and according to the local feature models, the edge strength index of each feature analysis area is determined, which is specifically the following formula: Wherein, E(i,j) is the edge strength index of the feature analysis area at coordinate (i,j), M k (i, j) is the kth eigenvalue in the local feature model corresponding to the current feature analysis area, θ is the gradient direction value, w k is the preset influence weight of the feature type corresponding to the kth feature value; The geological feature information set is constructed according to the edge strength index corresponding to each feature analysis area.

5. The method according to claim 2, characterized in that: The step of analyzing the basic terrain elevation information to determine the slope information and the slope aspect information of each data extraction area includes: Determine the horizontal coordinate value, the vertical coordinate value and the elevation value of the center point of each data extraction area according to the basic terrain elevation information; According to the abscissa value, the ordinate value and the elevation value, the slope direction value of each data extraction area is determined, and the slope direction value is used as the slope information, which is specifically the following formula: Wherein, SP is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value; According to the abscissa value, the ordinate value and the elevation value, the aspect value of each data extraction area is determined, and the aspect value is used as the slope information, which is specifically the following formula: Among them, AS is the slope direction value of the current data extraction area, x is the horizontal coordinate value, y is the vertical coordinate value, and z is the elevation value.

6. The method according to claim 4, characterized in that The step of analyzing the geological feature information set, performing combined identification analysis on unit geological features, and determining a geological boundary information set includes: Determine the edge strength mean and the edge strength standard deviation according to the edge strength index corresponding to each of the feature analysis areas in the geological feature information set; According to the edge strength index, the edge strength mean and the edge strength standard deviation, the boundary orientation value of each feature analysis area is determined, specifically as follows: Wherein, B(i,j) is the boundary pointing value of the feature analysis area at the coordinate (i,j), E(i,j) is the edge strength index of the feature analysis area at the coordinate (i,j), mean(E) is the edge strength mean, σ(E) is the edge strength standard deviation, and α is a preset adjustment coefficient; Based on the distribution position of each feature analysis area in the area to be constructed and according to the boundary orientation value of each feature analysis area, the geological boundary features in adjacent feature analysis areas are combined to determine the geological boundary information set.

7. The method according to claim 6, characterized in that The sample data set includes a number of sample extraction coordinates, a number of sample cross-section image data and a number of sample interception depths. Based on the geological boundary information set, the sample data set is subjected to structural morphological trend analysis to determine a multi-layer structure information set, including: Analyze each sample cross-sectional image data to determine a number of structural layer boundaries; Analyzing the geological boundary information set according to each sample extraction coordinate and each sample interception depth to determine a number of structural trend information; Generating a plurality of multi-layer structure texture direction images according to the plurality of structure direction information and the plurality of structure layer boundaries; The multi-layer structure information set is constructed according to the plurality of sample extraction coordinates and the plurality of multi-layer structure texture orientation images.

8. The method according to claim 7, characterized in that The step of analyzing the geological boundary information set and the multi-layer structure information set to determine a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary includes: According to the distribution position of each of the feature analysis areas in the area to be constructed, a unified spatial coordinate system is established for all the combined geological boundary features in the geological boundary information set to determine a geological boundary feature coordinate set; Based on the geological boundary feature coordinate set, determining a multi-layer structure coordinate set according to the relative position of each sample extraction coordinate and the corresponding feature analysis area; The unified space mapping coordinate set is determined according to the geological boundary feature coordinate set and the multi-layer structure coordinate set.

9. The method according to claim 8, characterized in that The method of constructing and outputting an attributeless geological map based on the unified spatial mapping coordinate set and according to the geological boundary information set and the multi-layer structure information set includes: Based on the unified space mapping coordinate set, the geological boundary information set and the multi-layer structure information set are structured to determine boundary vector data and structure vector data; Based on a preset geographic information drawing model, a geological boundary morphology map and several multi-layer geological structure trend maps are drawn respectively according to the boundary vector data and the structure vector data, and according to the unified space mapping coordinate set, several multi-layer geological structure trend maps are indexed and mapped on the geological boundary morphology map to construct and output the attributeless geological map.

10. An AI-based attributeless geological map database building system, characterized in that: include: A feature analysis module, used to obtain a remote sensing data set of the area to be constructed, analyze the remote sensing data set, and determine a geological feature information set; A boundary analysis module is used to analyze the geological feature information set, perform combined identification analysis on unit geological features, and determine the geological boundary information set; A structural analysis module, used to obtain a sample data set, and based on the geological boundary information set, perform structural morphology trend analysis on the sample data set to determine a multi-layer structural information set; A coordinate mapping module, used for analyzing the geological boundary information set and the multi-layer structure information set, and determining a unified spatial mapping coordinate set of each multi-layer structure information and the corresponding geological boundary; An output module is constructed to construct and output an attributeless geological map based on the unified space mapping coordinate set, according to the geological boundary information set and the multi-layer structure information set.

Images