A comprehensive geological exploration information management system

Through nonlinear dynamic data modeling and high-dimensional data dimensionality reduction technology, the problems of slow geological data processing speed and insufficient accuracy in the existing technology are solved, real-time monitoring and prediction of geological structures and events are realized, and geological exploration is improved The scientific nature of decision-making.

CN118568446BActive Publication Date: 2024-11-19LANGFANG ZHONGTIE PROSPECTING RECONNAISSANCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411050620.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-19
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

The existing geological data management system is slow and has insufficient accuracy when processing large-scale geological data, making it difficult to identify small changes and complex patterns in seismic data and formation information, affecting the accuracy of geological structure and resource assessment, and lacks real-time monitoring tools. This leads to untimely identification of rock formation continuity and potential faults, affecting mining strategies and disaster prevention decisions.

Method used

The nonlinear dynamic data modeling module is used to convert the time series data of formation vibration and pressure changes into multi-dimensional phase space, generate geological dynamic attraction submap, and build a stratigraphic continuity network map based on rock physics and chemical characteristics, and reduce dimensionality through high-dimensional data Key geological characteristics were analyzed and extracted, and geological change patterns were predicted based on these characteristics.

Benefits of technology

It realizes effective capture and prediction of dynamic changes within geology, improves the real-time monitoring capabilities of rock formation continuity and potential faults, enhances the ability to assess geological structure stability and predict geological event development trends, optimizes the data analysis process and improves decision-making Supporting the scientific nature.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118568446B_ABST
    Figure CN118568446B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of geological data management technology, specifically to a comprehensive geological exploration information management system, the system comprising: a nonlinear dynamic data modeling module converts the time series data of stratum vibration and pressure change into a multidimensional phase space, maps the internal dynamic structure of the geology through delayed coordinates, analyzes the key turning points in the reconstructed multidimensional phase space, and generates a geological dynamic attractor diagram. In the present invention, through nonlinear dynamic data modeling, the dynamic changes inside the geology can be effectively captured, the key turning points of the geological structure can be analyzed and predicted, and a rock formation continuity network based on physical and chemical properties can be constructed, so that the monitoring of the continuity between rock formations and potential faults is more intuitive and real-time, and the assessment of the stability of the geological structure is further strengthened. The geological data is processed using advanced dimensionality reduction technology, which effectively reduces the complexity of data processing while retaining key information, thereby making the extraction of geological features more efficient and accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of geological data management, and in particular to a comprehensive geological exploration information management system. Background Art

[0002] The field of geological data management technology involves the collection, storage, processing, analysis and interpretation of data related to the structure, composition and history of the earth. These data usually come from geological exploration, such as seismic surveys, drilling and ground sampling. The key task in this field is to systematize and digitize a large amount of geological information to support a variety of applications such as mineral exploration, oil and gas field development, and geological disaster prevention. Geological data management systems can help scientists and engineers better understand underground structures and material distribution through maps, 3D models and other analytical tools. In addition, this technical field also includes data visualization, sharing and updating to ensure the accuracy and real-time nature of data in scientific research and business decision-making.

[0003] Among them, the comprehensive geological exploration information management system refers to an integrated technical solution for managing and analyzing various data generated during geological exploration. The main purpose of this system is to provide data support for geological exploration, including seismic data, stratigraphic data, sample analysis results, etc., so that geologists and exploration engineers can effectively evaluate the distribution and development potential of underground resources. The system usually includes data acquisition, storage, processing and visualization functions, enabling users to create comprehensive geological models and conduct complex data analysis to guide actual exploration and development activities.

[0004] Existing technologies often face the problems of slow processing speed and insufficient accuracy when processing large-scale geological data. In particular, when analyzing seismic data and stratigraphic information, traditional methods may not be able to effectively identify small changes and complex patterns in the data, thus affecting the accuracy of geological structure and resource assessment. In addition, the lack of effective dynamic monitoring tools leads to untimely identification of rock continuity and potential faults, which in turn affects the decision-making efficiency of mining strategies and disaster prevention. This technical limitation is particularly evident in emergency situations. For example, when a geological disaster is imminent, the response time and processing capacity of the existing system may not be sufficient to provide the necessary support, increasing the difficulty of risk management. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a comprehensive geological exploration information management system.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a comprehensive geological exploration information management system comprises:

[0007] The nonlinear dynamic data modeling module converts the time series data of formation vibration and pressure change into multi-dimensional phase space, maps the internal dynamic structure of the geology through delayed coordinates, analyzes the key turning points in the reconstructed multi-dimensional phase space, and generates a geological dynamic attractor diagram;

[0008] The dynamic assessment module of stratum continuity utilizes the geological dynamic attractor graph and combines the physical and chemical properties of rocks to construct and update the nodes and edges of undirected or directed graphs in real time, monitors stratum continuity and potential faults, and evaluates the stability index of the network by calculating the shortest path between nodes in real time and identifying strongly connected components, thereby generating a stratum continuity network graph;

[0009] The high-dimensional data dimension reduction analysis module uses the structural features in the stratigraphic continuity network diagram to reduce the dimension of the high-dimensional geological data by applying local linear embedding and isometric mapping, extracts key geological features, and establishes a dimension reduction geological feature set;

[0010] The geological change pattern prediction module analyzes key geological structures and dynamic change patterns based on the reduced-dimensional geological feature set, identifies geological structure change trends, predicts the development trends of geological events, and generates geological event prediction analysis results.

[0011] As a further solution of the present invention, the steps of obtaining the geological dynamic attractor graph are specifically as follows:

[0012] Convert the time series data of formation vibration and pressure changes into a multidimensional data point set using the formula:

[0013]

[0014] Map time series data into a high-dimensional space to generate a multidimensional data point set;

[0015] in, Representative moments data, is the time interval, is the number of dimensions;

[0016] Using the multidimensional data point set, the formula is adopted:

[0017]

[0018] Calculate the Euclidean distance between data points and generate a distance matrix;

[0019] in, Represents data points and The distance between is the number of dimensions, is the time interval;

[0020] The key turning points are screened from the distance matrix using the formula:

[0021]

[0022] Get the key turning point set;

[0023] in, represents the set of selected data points, Indicate point With point The distance between For each pair of points and The weights between them are set according to the relative importance of data points or the strength of connection;

[0024] Based on the set of key turning points, the formula is used:

[0025]

[0026] Constructing geological dynamic attractor diagrams;

[0027] in, Represents a quantitative description of the geological dynamic attractor diagram, is the data point, is a scaling parameter that adjusts the influence of distance, making attraction more sensitive or more suppressed.

[0028] As a further solution of the present invention, the steps for obtaining the stratigraphic continuity network diagram are specifically as follows:

[0029] According to the geological dynamic attractor diagram and the physical and chemical properties of rocks, the attractor diagram and characteristic data are fused and the formula is adopted:

[0030]

[0031] Generate preliminary stratigraphic network maps;

[0032] in, Represents a preliminary stratigraphic network diagram, Represents a node, Represents the side, Represents the geological dynamic attractor diagram, Represents physical property data, Represents chemical property data;

[0033] Using the preliminary stratigraphic network diagram, the shortest path between nodes is calculated using the formula:

[0034]

[0035] Calculate the shortest path between nodes and generate the shortest path analysis results between nodes;

[0036] in, Representative Node and The shortest path between represents the weight of the edge, represents the adjustment parameter;

[0037] Using the shortest path analysis results between nodes, the strongly connected components in the network are identified using the formula:

[0038]

[0039] in is the threshold value, generating the strongly connected component analysis result;

[0040] in, represents the strongly connected component, Represents a node, and represents a differentiation node, represents the threshold value;

[0041] Integrate the shortest path analysis results between nodes and the strongly connected component analysis results, using the formula:

[0042]

[0043] Generate stratigraphic continuity network diagrams;

[0044] in, Represents the stratigraphic continuity network diagram, represents the strongly connected component, represents the shortest path between nodes, Represents the network stability index.

[0045] As a further solution of the present invention, the step of obtaining the reduced-dimensional geological feature set is specifically as follows:

[0046] Using the structural characteristics of the stratigraphic continuity network diagram, a local linear embedding method is applied, using the formula:

[0047]

[0048] Calculate local neighborhood embedding and generate local embedding mapping results;

[0049] in, represents the weight, represents a data point;

[0050] Combined with the local embedding mapping results, the isometric mapping method is used, through the formula:

[0051]

[0052] Optimize the distance mapping of global geological data and generate isometric mapping results;

[0053] in, represents the core distance adjustment factor;

[0054] Integrate the local embedding mapping results and the isometric mapping results, using the formula:

[0055]

[0056] Optimize the dimensionality reduction process and generate dimensionality reduction results;

[0057] in, represents the adjustment coefficient;

[0058] From the dimensionality reduction results, key geological features are extracted using the formula:

[0059]

[0060] Generate a reduced dimension geological feature set;

[0061] in, Represents geological features.

[0062] As a further solution of the present invention, the steps for obtaining the geological event prediction and analysis results are specifically as follows:

[0063] Based on the reduced dimension geological feature set, key geological structures are analyzed using the formula:

[0064]

[0065] Calculate the significance of key geological structures and generate key geological structure analysis results;

[0066] in, Represents key geological structure analysis results, represents the correlation coefficient, represents the feature item, represents the number of features;

[0067] According to the analysis results of the key geological structures, the dynamic change mode is analyzed using the formula:

[0068]

[0069] Quantify the trend of geological structure changes and generate dynamic change pattern analysis results;

[0070] in, Represents the results of the dynamic change pattern analysis, represents the rate of change, Represents key geological structure analysis results, represents the number of features;

[0071] The dynamic change pattern analysis results are used, using the formula:

[0072]

[0073] Determine the most significant change trend and generate geological structure change trend identification results;

[0074] in, Represents the identification result of geological structure change trend, Indicates the strength of the trend;

[0075] Based on the identification results of the geological structure change trend, the development trend of geological events is predicted using the formula:

[0076]

[0077] Integrate all change trends to generate geological event prediction and analysis results;

[0078] in, Represents the results of geological event prediction and analysis. represents the prediction parameter, Represents the identification result of geological structure change trend, Represents the number of features.

[0079] Compared with the prior art, the advantages and positive effects of the present invention are:

[0080] In the present invention, through nonlinear dynamic data modeling, the dynamic changes within the geology can be effectively captured, and the key turning points of the geological structure can be analyzed and predicted. The construction of a rock layer continuity network based on physical and chemical properties makes the monitoring of the continuity between rock layers and potential faults more intuitive and real-time, and further strengthens the assessment of the stability of the geological structure. The application of advanced dimensionality reduction technology to process geological data effectively reduces the complexity of data processing while retaining key information, thereby making the extraction of geological features more efficient and accurate. The above-mentioned processing method not only optimizes the data analysis process, but also enhances the ability to predict the development trend of geological events, providing more scientific data support for geological exploration and related decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 is a system flow chart of the present invention;

[0082] Figure 2 A flow chart of the steps for obtaining the geological dynamic attractor diagram of the present invention;

[0083] Figure 3 A flow chart of the steps for obtaining a stratigraphic continuity network diagram of the present invention;

[0084] Figure 4 The flowchart of the steps of obtaining the dimension-reduced geological feature set of the present invention;

[0085] Figure 5 The present invention is a flowchart of the steps for obtaining the geological event prediction and analysis results. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0087] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. Example

[0088] See also Figure 1 , a comprehensive geological exploration information management system includes:

[0089] The nonlinear dynamic data modeling module converts the time series data of formation vibration and pressure change into multi-dimensional phase space, maps the internal dynamic structure of the geology through delayed coordinates, analyzes the key turning points in the reconstructed multi-dimensional phase space, and generates a geological dynamic attractor diagram;

[0090] The dynamic assessment module of formation continuity uses geological dynamic attractor graphs and combines the physical and chemical properties of rocks to construct and update the nodes and edges of undirected or directed graphs in real time, monitor the continuity of rock formations and potential faults, and evaluate the stability index of the network by calculating the shortest path between nodes in real time and identifying strongly connected components, thus generating a formation continuity network graph;

[0091] The high-dimensional data dimension reduction analysis module uses the structural features in the stratigraphic continuity network diagram, applies local linear embedding and isometric mapping to reduce the dimension of high-dimensional geological data, extract key geological features, and establish a dimension reduction geological feature set;

[0092] The geological change pattern prediction module analyzes key geological structures and dynamic change patterns based on the reduced-dimensional geological feature set, identifies the trend of geological structure changes, predicts the development trend of geological events, and generates geological event prediction analysis results.

[0093] The geological dynamic attractor diagram specifically includes key turning points, multidimensional phase space, and delayed coordinate mapping. The stratigraphic continuity network diagram specifically includes nodes and edges of undirected or directed graphs, rock continuity, and potential faults. The reduced-dimensional geological feature set specifically includes key geological features, high-dimensional geological data, and structural features. The geological event prediction and analysis results specifically include key geological structures, dynamic change patterns, and development trends of geological events.

[0094] See also Figure 2 , the specific steps for obtaining the geological dynamic attractor diagram are:

[0095] Convert the time series data of formation vibration and pressure changes into a multidimensional data point set using the formula:

[0096]

[0097] Map time series data into a high-dimensional space to generate a multidimensional data point set;

[0098] in, Representative moments data, is the time interval, is the number of dimensions;

[0099] Using a multidimensional data point set, the formula is:

[0100]

[0101] Calculate the Euclidean distance between data points and generate a distance matrix;

[0102] in, Represents data points and The distance between is the number of dimensions, is the time interval;

[0103] To screen key turning points from the distance matrix, use the formula:

[0104]

[0105] Get the key turning point set;

[0106] in, represents the set of selected data points, Indicate point With point The distance between For each pair of points and The weights between them are set according to the relative importance of data points or the strength of connection;

[0107] Based on the set of key turning points, use the formula:

[0108]

[0109] Constructing geological dynamic attractor diagrams;

[0110] in, Represents a quantitative description of the geological dynamic attractor diagram, is the data point, is a scaling parameter that adjusts the influence of distance, making attraction more sensitive or more suppressed.

[0111] formula:

[0112]

[0113] Parameters

[0114] : Single moment The data value is assumed to be the intensity of formation vibration.

[0115] : Time interval, used to define the sampling interval of data points in the time series.

[0116] : The embedding dimension, i.e., the number of delayed time series included in the vector.

[0117] Calculation example

[0118] Assumptions is the intensity value of earthquake monitoring, time The data point is 5.0, the time interval Set to 1 hour, embed dimension Set to 3.

[0119] Calculation process:

[0120] hour,

[0121] When assuming

[0122] When assuming

[0123] therefore,

[0124] This vector reflects the time The earthquake intensity values ​​at the first three consecutive time points.

[0125] formula:

[0126]

[0127] Parameters

[0128] The starting point for the differenced time series.

[0129] Embedding dimension.

[0130] Calculation example

[0131] Continue to use data and .

[0132] Calculation process:

[0133]

[0134]

[0135]

[0136]

[0137]

[0138] Distance value represents vector and The Euclidean distance between them reflects the degree of fit between the two time series points.

[0139] formula:

[0140]

[0141] Parameter details:

[0142] : The set of selected data points.

[0143] : Data points and The distance between.

[0144] : Each pair of points and The weights between them are set according to their relative importance or connection strength.

[0145] Calculation example

[0146] Suppose three data points are selected , and assume that the weights of these points are is 1 (i.e., all relationships between points are equally important).

[0147] From the already calculated , assuming .

[0148] Calculation process:

[0149]

[0150]

[0151]

[0152]

[0153] This value represents a collection of data points The sum of weighted distances between all points in . Select the set of key turning points that minimizes this value In this example, because the weights are the same, the sum of all points is the same, and the key turning point set is directly obtained .

[0154] formula:

[0155]

[0156] Parameters

[0157] : Quantitative description of geological dynamic attractor diagrams.

[0158] : data point.

[0159] : Scaling parameter used to adjust the influence of distance.

[0160] : Data points and The distance between.

[0161] Calculation example

[0162] Assumptions Set to 1, known , and assume that their distances are as follows:

[0163]

[0164]

[0165]

[0166] Calculation process:

[0167] For each point , calculate its attractor value.

[0168] calculate The attractor value of is:

[0169]

[0170]

[0171]

[0172]

[0173]

[0174] Attractor Value:

[0175] calculate The attractor value of is:

[0176]

[0177]

[0178]

[0179]

[0180] Attractor Value:

[0181] calculate The attractor value of is:

[0182]

[0183]

[0184]

[0185]

[0186] Attractor Value:

[0187] Computational geological dynamic attractor diagram :

[0188]

[0189] This value Represents the total attraction of the geodynamic attractor diagram, reflecting the combined attraction of all key turning points.

[0190] See also Figure 3 , the specific steps for obtaining the stratigraphic continuity network diagram are as follows:

[0191] According to the geological dynamic attractor diagram and the physical and chemical properties of rocks, the attractor diagram and characteristic data are integrated and the formula is used:

[0192]

[0193] Generate preliminary stratigraphic network maps;

[0194] in, Represents a preliminary stratigraphic network diagram, Represents a node, Represents the side, Represents the geological dynamic attractor diagram, Represents physical property data, Represents chemical property data;

[0195] Using the preliminary stratigraphic network diagram, the shortest path between nodes is calculated using the formula:

[0196]

[0197] Calculate the shortest path between nodes and generate the shortest path analysis results between nodes;

[0198] in, Representative Node and The shortest path between represents the weight of the edge, represents the adjustment parameter;

[0199] Using the shortest path analysis results between nodes, we can identify the strongly connected components in the network using the formula:

[0200]

[0201] in is the threshold value, generating the strongly connected component analysis result;

[0202] in, represents the strongly connected component, Represents a node, and represents a differentiation node, represents the threshold value;

[0203] Integrate the shortest path analysis results between nodes and the strongly connected component analysis results, using the formula:

[0204]

[0205] Generate stratigraphic continuity network diagrams;

[0206] in, Represents the stratigraphic continuity network diagram, represents the strongly connected component, represents the shortest path between nodes, Represents the network stability index.

[0207] formula:

[0208]

[0209] in:

[0210] : represents a node.

[0211] : The edge set, represented by the attractor graph and the chemical properties of rocks derived.

[0212] : Geodynamic attractor diagram, assumed to be calculated by the previous step.

[0213] : A function that combines physics and Chemistry Properties to define the weight of the edge.

[0214] Calculation process:

[0215] Hypothetical geological dynamic attractor diagram Contains 3 nodes, each node represents a rock sample at a location. The connectivity between nodes is determined by the physical distance and chemical fit The weight of the edge is calculated by combining the features. For example:

[0216] The physical distance between node 1 and node 2 unit Chemical similarity .

[0217] Assumptions , which means that the edge weights between nodes that are closer and chemically similar are larger.

[0218] Calculate the edge weight between node 1 and node 2:

[0219]

[0220] Therefore, the preliminary stratigraphic network diagram is constructed to include nodes and edges with the above weights.

[0221] formula:

[0222]

[0223] in:

[0224] : The weight of the edge.

[0225] : Coefficient for adjusting path sensitivity, assuming .

[0226] Calculation process:

[0227] Assume that in addition to the connection between node 1 and node 2 mentioned above, there is also a connection between node 2 and node 3, whose weight is is 0.005. The shortest path from node 1 to node 3 needs to be captured.

[0228] Direct Path:

[0229] Through node 2, the weight is calculated as follows:

[0230]

[0231] Therefore, the weight of the shortest path between node 1 and node 3 is 0.000495.

[0232] formula:

[0233]

[0234] in:

[0235] : Threshold, set to .

[0236] Calculation process:

[0237] For each node, calculate the sum of the inverse of the path weights of all other nodes to this node and check if it is greater than the threshold .

[0238] For Node 1:

[0239]

[0240] because Node 1 does not belong to any strongly connected component.

[0241] Through similar calculations, it can be determined whether other nodes belong to strongly connected components.

[0242] formula:

[0243]

[0244] in:

[0245] :Network stability index, assuming that the previous analysis shows .

[0246] Calculation process:

[0247] Combines the information of the shortest paths and strongly connected components between all nodes, as well as network stability indicators , construct the final stratigraphic continuity network graph. This graph can show the connection strength between nodes and the overall stability of the network.

[0248] See also Figure 4 , the specific steps for obtaining the dimension-reduced geological feature set are:

[0249] Using the structural characteristics of the stratigraphic continuity network diagram, the local linear embedding method is applied, using the formula:

[0250]

[0251] Calculate local neighborhood embedding and generate local embedding mapping results;

[0252] in, represents the weight, represents a data point;

[0253] Combined with the local embedding mapping results, the isometric mapping method is used, through the formula:

[0254]

[0255] Optimize the distance mapping of global geological data and generate isometric mapping results;

[0256] in, represents the core distance adjustment factor;

[0257] Integrate the local embedding mapping results and the isometric mapping results, using the formula:

[0258]

[0259] Optimize the dimensionality reduction process and generate dimensionality reduction results;

[0260] in, represents the adjustment coefficient;

[0261] Extract key geological features from the dimensionality reduction results using the formula:

[0262]

[0263] Generate a reduced dimension geological feature set;

[0264] in, Represents geological features.

[0265] formula:

[0266]

[0267] Parameter details:

[0268] : Weight coefficient, representing the data point and The relative importance or strength of the connection.

[0269] Data points in high-dimensional space.

[0270] Calculation process and examples:

[0271] Suppose there are three data points , and the weight coefficient .calculate as follows:

[0272]

[0273]

[0274]

[0275] Substituting the values ​​into the formula:

[0276]

[0277] The result 7.6 represents the total distance of the local linear embedding based on the given weights, which can be used for further data analysis and feature extraction.

[0278] formula:

[0279]

[0280] Parameter details:

[0281] : Core distance adjustment factor, used to adjust the point and The perception of distance between them.

[0282] : Euclidean distance calculation.

[0283] Calculation process and examples:

[0284] Using the same data points ,and .calculate as follows:

[0285]

[0286]

[0287]

[0288] Substituting the values ​​into the formula:

[0289]

[0290] The result 9 represents the global distance sum based on the given distance adjustment factor, which is used to globally optimize the data mapping.

[0291] formula:

[0292]

[0293] Parameters

[0294] and is an adjustment coefficient used to balance the influence of local embedding and global mapping in the dimensionality reduction result.

[0295] and They are the results of local embedding and global mapping obtained by the above calculations respectively.

[0296] Calculation process and examples

[0297] Assume that the results are and If you set and ,but:

[0298]

[0299]

[0300] Substituting the values ​​into the formula:

[0301]

[0302] The result 8.44 represents a dimensionally reduced dataset that combines local and global information for further analysis and feature extraction.

[0303] formula:

[0304]

[0305] Parameters

[0306] Represents key geological features extracted from the comprehensive dimensionally reduced dataset.

[0307] Calculation process and examples

[0308] Hypothetical results It is used to identify the key features in the data set. Here, the model is simplified and three key features are identified. The specific extraction method depends on the feature extraction technique used, such as principal component analysis (PCA).

[0309] Assume that these features represent the main direction of change or cluster center in the data set, etc. For example, if represents a geological dataset after dimensionality reduction, They represent key indicators such as stratum density, mineral content and geological age respectively.

[0310] See also Figure 5 , the specific steps for obtaining geological event prediction and analysis results are as follows:

[0311] Based on the reduced dimension geological feature set, key geological structures are analyzed using the formula:

[0312]

[0313] Calculate the significance of key geological structures and generate key geological structure analysis results;

[0314] in, Represents key geological structure analysis results, represents the correlation coefficient, represents the feature item, represents the number of features;

[0315] According to the key geological structure analysis results, the dynamic change mode is analyzed using the formula:

[0316]

[0317] Quantify the trend of geological structure changes and generate dynamic change pattern analysis results;

[0318] in, Represents the results of the dynamic change pattern analysis, represents the rate of change, Represents key geological structure analysis results, represents the number of features;

[0319] Analyze the results using the dynamic change model, using the formula:

[0320]

[0321] Determine the most significant change trend and generate geological structure change trend identification results;

[0322] in, Represents the identification result of geological structure change trend, Indicates the strength of the trend;

[0323] Based on the identification results of geological structure change trends, the development trend of geological events is predicted using the formula:

[0324]

[0325] Integrate all change trends to generate geological event prediction and analysis results;

[0326] in, Represents the results of geological event prediction and analysis. represents the prediction parameter, Represents the identification result of geological structure change trend, Represents the number of features.

[0327] formula:

[0328]

[0329] Parameter interpretation and derivation process:

[0330] : Results of the analysis of key geological structures, quantifying the significance of each structure.

[0331] : Correlation coefficient of key geological structures, indicating the importance of each feature in geological analysis.

[0332] : Geological features extracted from the dimensionally reduced geological feature set.

[0333] : The total number of features.

[0334] Calculation example:

[0335] Assume there are three features , correlation coefficient , eigenvalue .

[0336] Calculation process:

[0337]

[0338] Result analysis:

[0339] What you get Represents the significance score of key geological structures calculated based on weighted correlation coefficients and eigenvalues.

[0340] formula:

[0341]

[0342] Parameter interpretation and derivation process:

[0343] :Dynamic change pattern analysis results, indicating the quantitative trend of geological structure changes.

[0344] : The rate of change obtained from time series analysis quantifies the intensity of change of each geological structure over time.

[0345] : Significance scores for known key geological structures.

[0346] Calculation example:

[0347] Use the previous step Values ​​and assumed rates of change .

[0348] Calculation process:

[0349]

[0350] Result analysis:

[0351] A score representing the trend of key geological structures over time.

[0352] formula:

[0353]

[0354] Parameter interpretation and derivation process:

[0355] : The identification result of geological structure change trend, indicating the most significant one among all change trends.

[0356] Indicates the strength of a single trend.

[0357] Calculation example:

[0358] Assume three trend strengths .

[0359] Calculation process:

[0360]

[0361] Result analysis:

[0362] It means that among the three trends, the most significant trend strength is 5.

[0363] formula:

[0364]

[0365] Parameter interpretation and derivation process:

[0366] :The results of geological event prediction analysis integrate all trends to predict the estimated development of geological events.

[0367] : Prediction parameter, indicating the prediction weight of multiple trends.

[0368] : The most significant trend strength.

[0369] Calculation example:

[0370] Assuming the prediction parameters and the previous .

[0371] Calculation process:

[0372]

[0373] Result analysis:

[0374] Represents the total prediction score for geological time obtained by integrating multiple trends.

[0375] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A comprehensive geological exploration information management system, characterized in that: The system comprises: The nonlinear dynamic data modeling module converts the time series data of formation vibration and pressure change into multi-dimensional phase space, maps the internal dynamic structure of the geology through delayed coordinates, analyzes the key turning points in the reconstructed multi-dimensional phase space, and generates a geological dynamic attractor diagram; The dynamic assessment module of stratum continuity utilizes the geological dynamic attractor graph and combines the physical and chemical properties of rocks to construct and update the nodes and edges of undirected or directed graphs in real time, monitors stratum continuity and potential faults, and evaluates the stability index of the network by calculating the shortest path between nodes in real time and identifying strongly connected components, thereby generating a stratum continuity network graph; The high-dimensional data dimension reduction analysis module uses the structural features in the stratigraphic continuity network diagram to reduce the dimension of the high-dimensional geological data by applying local linear embedding and isometric mapping, extracts key geological features, and establishes a dimension reduction geological feature set; The geological change pattern prediction module analyzes key geological structures and dynamic change patterns based on the reduced-dimensional geological feature set, identifies geological structure change trends, predicts the development trends of geological events, and generates geological event prediction analysis results.

2. The comprehensive geological exploration information management system according to claim 1, characterized in that: The steps for obtaining the geological dynamic attractor map are specifically as follows: Convert the time series data of formation vibration and pressure changes into a multidimensional data point set using the formula: Map time series data into a high-dimensional space to generate a multidimensional data point set; in, Representative moments data, is the time interval, is the number of dimensions; Using the multidimensional data point set, the formula is adopted: Calculate the Euclidean distance between data points and generate a distance matrix; in, Represents data points and The distance between is the number of dimensions, is the time interval; The key turning points are screened from the distance matrix using the formula: Get the key turning point set; in, represents the set of selected data points, Indicate point With point The distance between For each pair of points and The weights between them are set according to the relative importance of data points or the strength of connection; Based on the set of key turning points, the formula is used: Constructing geological dynamic attractor diagrams; in, Represents a quantitative description of the geological dynamic attractor diagram, is the data point, is a scaling parameter that adjusts the influence of distance, making attraction more sensitive or more suppressed.

3. The comprehensive geological exploration information management system according to claim 2, characterized in that: The steps for obtaining the stratigraphic continuity network diagram are specifically as follows: According to the geological dynamic attractor diagram and the physical and chemical properties of rocks, the attractor diagram and characteristic data are fused and the formula is adopted: Generate preliminary stratigraphic network maps; in, Represents a preliminary stratigraphic network diagram, Represents a node, Represents the side, Represents the geological dynamic attractor diagram, Represents physical property data, Represents chemical property data; Using the preliminary stratigraphic network diagram, the shortest path between nodes is calculated using the formula: Calculate the shortest path between nodes and generate the shortest path analysis results between nodes; in, Representative Node and The shortest path between represents the weight of the edge, represents the adjustment parameter; Using the shortest path analysis results between nodes, the strongly connected components in the network are identified using the formula: in is the threshold value, generating the strongly connected component analysis result; in, represents the strongly connected component, Represents a node, and represents a differentiation node, represents the threshold value; Integrate the shortest path analysis results between nodes and the strongly connected component analysis results, using the formula: Generate stratigraphic continuity network diagrams; in, Represents the stratigraphic continuity network diagram, represents the strongly connected component, represents the shortest path between nodes, Represents the network stability index.

4. The comprehensive geological exploration information management system according to claim 3, characterized in that: The steps for obtaining the dimension-reduced geological feature set are specifically as follows: Using the structural characteristics of the stratigraphic continuity network diagram, a local linear embedding method is applied, using the formula: Calculate local neighborhood embedding and generate local embedding mapping results; in, represents the weight, represents a data point; Combined with the local embedding mapping results, the isometric mapping method is used, through the formula: Optimize the distance mapping of global geological data and generate isometric mapping results; in, represents the core distance adjustment factor; Integrate the local embedding mapping results and the isometric mapping results, using the formula: Optimize the dimensionality reduction process and generate dimensionality reduction results; in, represents the adjustment coefficient; From the dimensionality reduction results, key geological features are extracted using the formula: Generate a reduced dimension geological feature set; in, Represents geological features.

5. The comprehensive geological prospecting information management system according to claim 4, characterized in that: The steps for obtaining the geological event prediction and analysis results are specifically as follows: Based on the reduced dimension geological feature set, key geological structures are analyzed using the formula: Calculate the significance of key geological structures and generate key geological structure analysis results; in, Represents key geological structure analysis results, represents the correlation coefficient, represents the feature item, represents the number of features; According to the analysis results of the key geological structures, the dynamic change mode is analyzed using the formula: Quantify the trend of geological structure changes and generate dynamic change pattern analysis results; in, Represents the results of the dynamic change pattern analysis, represents the rate of change, Represents key geological structure analysis results, represents the number of features; The dynamic change pattern analysis results are used, using the formula: Determine the most significant change trend and generate geological structure change trend identification results; in, Represents the identification result of geological structure change trend, Indicates the strength of the trend; Based on the identification results of the geological structure change trend, the development trend of geological events is predicted using the formula: Integrate all change trends to generate geological event prediction and analysis results; in, Represents the results of geological event prediction and analysis. represents the prediction parameter, Represents the identification result of geological structure change trend, Represents the number of features.