Intelligent exploration data analysis system and method

Abstract

The invention discloses an intelligent exploration data analysis system and method, and relates to the technical field of geological exploration, and the system comprises a test module, an analysis module and a prediction module. According to the method, geological electromagnetic and stratum original data are collected in a multi-dimensional mode, forward modeling and inversion are carried out on electromagnetic data, the relation between underground conductivity and an electromagnetic field can be accurately simulated, data errors are effectively reduced, the electromagnetic data processing accuracy is improved, a geological unit calculates a seismic wave field based on wave equation numerical simulation, and the electromagnetic data processing accuracy is improved. The prediction wave field and the observation wave field are substituted into an objective function, the stratum velocity and density are accurately inverted, the geological data processing precision is guaranteed, the joint unit organically combines an electromagnetic inversion objective function, an earthquake full-waveform inversion objective function and a parameter correlation constraint term through a joint optimization formula, multi-source data depth fusion is achieved, and the geological data processing precision is guaranteed. The limitation of single data processing is avoided, and the underground geological condition is reflected more comprehensively.

Description

Technical Field

[0001] The present invention relates to the technical field of geological exploration, and particularly relates to an intelligent exploration data analysis system and method. Background Art

[0002] Geotechnical exploration is a process of systematically investigating and analyzing geological bodies, aiming to provide reliable geological data and basic parameters for engineering projects. Through geotechnical exploration, the geological conditions below the ground surface can be understood in detail, including soil layer structure, rock layer distribution, groundwater level, and physical and mechanical properties of soil and rock. These information is crucial for the safety and stability of engineering design and construction. The exploration results help engineers evaluate the adaptability of the geological environment, identify potential geological risks, and provide a scientific basis for formulating appropriate foundation design schemes; Electrical prospecting is a geophysical prospecting method that discovers and studies geological structures based on the electrical property differences of rock and ore.

[0003] Currently, in the prior art, traditional one-dimensional and two-dimensional detection technologies are difficult to meet the needs of detecting complex geological structures and deep resources. At the same time, when electromagnetic signals propagate in underground media, they will be affected by the skin effect, and the signal intensity rapidly attenuates with the increase of depth, resulting in limited detection depth and difficulty in obtaining complete information of deep geological structures. Moreover, the electrical parameters of underground media are affected by various factors, and the complexity of these factors leads to the multi-solution nature of electromagnetic data interpretation, increasing the difficulty of accurately identifying geological bodies and reducing the reliability of exploration results.

[0004] Therefore, an intelligent exploration data analysis system and method are proposed to solve the above problems. Summary of the Invention

[0005] The main purpose of the present invention is to provide an intelligent exploration data analysis system and method to solve the problems raised in the above background.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is: an intelligent exploration data analysis system, the system includes a test module, an analysis module, and a prediction module;

[0007] The test module is used to observe underground electromagnetic anomalies through large-depth three-dimensional electromagnetic detection, collect the corresponding original data generated, and collect geological information data using seismic exploration instruments, and preprocess and transmit it to the analysis module;

[0008] The analysis module is used to receive the original data and geological information data, perform forward and inverse calculations on the original data, perform full waveform inversion on the geological information data at the same time, jointly optimize the original data inversion function and the geological information data inversion function, and construct a model for the jointly optimized function through SimPEG;

[0009] The prediction module constructs a function model based on the jointly optimized function and evaluates geological risks in combination with historical disaster data.

[0010] Preferably, the test module includes a collection module, a preprocessing module and a transmission module;

[0011] The acquisition module is used to collect raw data generated by deep three-dimensional electromagnetic detection, and to collect geological information data using seismic exploration instruments. The deep three-dimensional electromagnetic detection includes three-dimensional time-frequency domain induced polarization method, transient electromagnetic method, controlled source audio frequency magnetotelluric method and magnetotelluric method. The seismic exploration instrument includes induction detector, piezoelectric detector and laser detector;

[0012] The preprocessing module is used to perform data cleaning, normalization and format conversion on the collected raw data and geological information data;

[0013] The transmission module is used to transmit the pre-processed data to the analysis module through the Wi-Fi module.

[0014] Preferably, the analysis module includes an original unit, a geological unit, a combined unit and a construction unit.

[0015] Preferably, the original unit is used to perform forward modeling and inversion on the collected original data, and the calculation steps are as follows:

[0016] Step 1: Define the scope of the detection area, define the underground conductivity distribution σ(r) based on geological prior information, divide the model units, assign corresponding conductivity values to each unit, and select the frequency domain finite element method to divide the detection area into multiple small units. Approximately solve the Maxwell equations for each unit to form an overall stiffness matrix.

[0017] Step 2: Based on the frequency domain wave equation:

[0018] in, × represents the curl operator, E represents the electric field intensity vector; k represents the wave number; i represents the imaginary unit, w represents the angular frequency; μ represents the magnetic permeability; J s represents the source current density vector; σ represents the conductivity;

[0019] Step 3: Substitute the known angular frequency, magnetic permeability and source current density vector to obtain each unit electric field strength vector E;

[0020] Step 4: Use regularized least squares inversion, the inversion formula is as follows:

[0021]

[0022] Among them, O EMRepresents the objective function for electromagnetic inversion, Represents the observed electromagnetic data, Represents the electromagnetic data predicted by forward modeling based on the underground conductivity distribution σ, Represents the spatial gradient of the conductivity σ, Represents the regularization parameter.

[0023] Preferably, the geological unit is used to calculate the geological objective function, and the steps are as follows:

[0024] S1: Initialize the model and set the initial models of the formation velocity u(r) and density p(r);

[0025] S2: Using the initial model, numerically simulate the seismic wavefield u p (s,r,t,u,p);

[0026] S3: Substitute the predicted wavefield u p (s,r,t,u,p) and the observed wavefield u o into the objective function, and the formula is as follows:

[0027]

[0028] where O SE represents the objective function of seismic full waveform inversion, and u o (s,r,t) represents the seismic wavefield observed at the source s, receiver r, and time t, and u p (s,r,t,u,p) represents the simulated seismic wavefield.

[0029] Preferably, the joint unit is used to jointly optimize the objective function of seismic full waveform inversion and the objective function of electromagnetic inversion, and the joint formula is:

[0030] O j =αO EM +βO SM +δO CE ;

[0031] where O j represents the joint objective function, α, β, and δ respectively represent the weight coefficients of the objective function of electromagnetic inversion, the objective function of seismic full waveform inversion, and the parameter correlation constraint term, O CE represents the parameter correlation constraint term, O EM represents the objective function of electromagnetic inversion, and O SE represents the objective function of seismic full waveform inversion.

[0032] Preferably, the construction unit constructs a function model with the joint objective function through SimPEG.

[0033] Preferably, the prediction module includes a collection unit and a prediction unit;

[0034] The collection unit is used to collect historical disaster data in the past by a data collector.

[0035] Preferably, the prediction unit is used to evaluate geological risks, and the steps are as follows:

[0036] Step 1: Calculate the geological risk probability, and the calculation formula is as follows:

[0037]

[0038] Among them, P(y = 1∣x; θ) represents the conditional geological risk probability given the input feature x and the model parameter θ, y represents the dependent variable, x represents the independent variable vector, θ represents the model parameter, and e represents the natural constant;

[0039] Step 2: Set the risk threshold Q = 0.5. When P(y = 1∣x; θ) is greater than Q, it is determined that the current geology is a high risk. If it does not exceed or is equal to Q, it is determined to be a low risk.

[0040] An intelligent exploration data analysis method includes the following steps:

[0041] (1): Enter the test module: Observe the underground electromagnetic anomaly body, collect the corresponding raw data generated, and collect geological information data, and perform processing;

[0042] (2): Enter the analysis module: Receive the raw data and geological information data, perform forward and inverse calculations on the raw data, perform full waveform inversion on the geological information data at the same time, and build a model after joint optimization;

[0043] (3): Enter the prediction module: Based on the geological model and electromagnetic anomaly distribution constructed by the analysis module, combined with historical geological disaster data and relevant risk assessment algorithms, compare and evaluate the geological risks existing in the exploration area.

[0044] The present invention has the following beneficial effects:

[0045] 1. In the present invention, by collecting multi-dimensional raw data of underground electromagnetic anomalies through the collection module, the electromagnetic characteristics information of underground media is obtained from different dimensions and depths, the underground electromagnetic distribution is comprehensively outlined, and geological information data is accurately collected, covering key parameters such as formation velocity and density, and the formation structure characteristics are completely presented, providing sufficient data support for subsequent analysis. At the same time, the collected data is preprocessed, making the collected data relatively more real and accurate, reducing the burden on subsequent data preprocessing, and ensuring the accuracy of the data processing of the entire system.

[0046] 2. In the present invention, for the electromagnetic raw data, the original unit performs forward modeling by using the finite element method in the frequency domain in combination with Maxwell's equations and the frequency domain wave equation, and then through regularized least squares inversion calculation, it can accurately simulate the relationship between the underground conductivity and the electromagnetic field, effectively reduce data errors, and improve the accuracy of electromagnetic data processing. The geological unit numerically simulates the seismic wave field based on the wave equation, substitutes the predicted wave field and the observed wave field into the objective function, and accurately inverses the formation velocity and density to ensure the accuracy of geological data processing. The joint unit organically combines the electromagnetic inversion objective function, the seismic full waveform inversion objective function, and the parameter correlation constraint term through the joint optimization formula to achieve deep fusion of multi-source data, avoid the limitations of single data processing, and more comprehensively reflect the underground geological conditions.

[0047] 3. In the present invention, the historical disaster data collected by the collection unit provides rich samples for the model to learn the relationship between geological parameters and the occurrence of disasters, enabling the model to discover potential laws, thereby more accurately predicting risks under the current geological conditions and improving the reliability of prediction. By calculating the risk probability through the logistic regression algorithm, the geological risk is converted into specific numerical values, changing the previous fuzzy qualitative evaluation method, facilitating subsequent arrangements and decisions, and comparing with the set threshold for judgment to effectively avoid high-risk areas and reduce disaster losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flowchart of a method for analyzing intelligent exploration data according to the present invention;

[0049] Figure 2 It is a flowchart of a system for analyzing intelligent exploration data according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] Embodiment 1: Please refer to Figure 1 and Figure 2 The present invention provides a technical solution: an intelligent exploration data analysis system, which includes a test module, an analysis module, and a prediction module;

[0052] The test module is used to observe the underground electromagnetic anomaly through large-depth three-dimensional electromagnetic detection, collect the corresponding raw data, and collect geological information data using a seismic exploration instrument, and preprocess and transmit it to the analysis module;

[0053] The analysis module is used to receive the original data and geological information data, and perform forward modeling and inversion calculations on the original data, perform full waveform inversion on the geological information data, and optimize the inversion function of the original data and the inversion function of the geological information data, and construct a model for the jointly optimized function through SimPEG;

[0054] The prediction module constructs a function model based on the jointly optimized function and combines historical disaster data to assess geological risks.

[0055] The test module includes an acquisition module, a preprocessing module and a transmission module;

[0056] The acquisition module is used to collect the original data generated by deep three-dimensional electromagnetic detection and to collect geological information data using seismic exploration instruments. Deep three-dimensional electromagnetic detection includes three-dimensional time-frequency domain induced polarization method, transient electromagnetic method, controlled source audio frequency magnetotelluric method and magnetotelluric method. Seismic exploration instruments include induction detectors, piezoelectric detectors and laser detectors.

[0057] The preprocessing module is used to clean, normalize and convert the collected raw data and geological information data;

[0058] The transmission module is used to transmit the pre-processed data to the analysis module through the Wi-Fi module.

[0059] In this embodiment, the acquisition module collects raw data of underground electromagnetic anomalies in multiple dimensions, obtains electromagnetic characteristic information of underground media from different dimensions and depths, comprehensively outlines the underground electromagnetic distribution status, and accurately collects geological information data, covering key parameters such as formation velocity and density, and fully presents the formation structure characteristics, providing sufficient data support for subsequent analysis. At the same time, the collected data is preprocessed to make the collected data relatively more real and accurate, thereby reducing the burden of subsequent data preprocessing and ensuring the accuracy of data processing of the entire system.

[0060] Implementation 2: Please refer to Figure 1 and Figure 2 The present invention provides a technical solution: based on implementation one, the analysis module includes an original unit, a geological unit, a joint unit and a construction unit.

[0061] The original unit is used to perform forward modeling and inversion on the collected original data. The calculation steps are as follows:

[0062] Step 1: Define the scope of the detection area, define the underground conductivity distribution σ(r) based on geological prior information, divide the model units, assign corresponding conductivity values to each unit, and select the frequency domain finite element method to divide the detection area into multiple small units. Approximately solve the Maxwell equations for each unit to form an overall stiffness matrix.

[0063] Specifically, defining the scope of the detection area means determining which specific area in the geographical space to study, demarcating its longitude and latitude range or its boundaries in the actual terrain. For example, when studying the underground geological conditions of a certain mountain range area, determine the starting and ending coordinates of the mountain range, its east, west, south, and north boundaries, etc., to define a clear three-dimensional space range and delimit the spatial boundaries for subsequent research and data collection.

[0064] Step 2: Based on the frequency-domain wave equation:

[0065] Where, represents the curl operation symbol, E represents the electric field strength vector; k represents the wave number; i represents the imaginary unit, w represents the angular frequency; μ represents the magnetic permeability; J s represents the source current density vector; σ represents the conductivity;

[0066] Specifically, two are used to perform two curl operations on the electric field strength vector E.

[0067] Step 3: Substitute the known angular frequency, magnetic permeability, and source current density vector to obtain each unit electric field strength vector E;

[0068] Step 4: Use the regularized least-squares inversion, and the inversion formula is as follows:

[0069]

[0070] Where, O EM represents the objective function of electromagnetic inversion, represents the observed electromagnetic data, represents the electromagnetic data predicted according to the forward modeling of the underground conductivity distribution σ, represents the spatial gradient of the conductivity σ, represents the regularization parameter.

[0071] The geological unit is used to calculate the geological objective function, and the steps are as follows:

[0072] S1: Initialize the model and set the initial models of the formation velocity u(r) and density p(r);

[0073] S2: Using the initial model, calculate the seismic wave field u p (s, r, t, u, p) based on the numerical simulation of the wave equation;

[0074] S3: Substitute the predicted wave field u p (s, r, t, u, p) and the observed wave field u o into the objective function, and the formula is as follows:

[0075]

[0076] Among them, O SE represents the objective function of seismic full waveform inversion, and u o (s, r, t) represents the seismic wave field observed at the source s, receiver r, and time t, and u p (s, r, t, u, p) represents the simulated seismic wave field.

[0077] The joint unit is used to jointly optimize the objective function of seismic full waveform inversion and the objective function of electromagnetic inversion. The joint formula is:

[0078] O j = αO EM + βO SE + δO SE ;

[0079] Among them, O j represents the joint objective function, α, β, and δ respectively represent the objective function of electromagnetic inversion, the objective function of seismic full waveform inversion, and the weight coefficients of the parameter correlation constraint term. O CE represents the parameter correlation constraint term ( where f is the lithology conversion function), O EM represents the objective function of electromagnetic inversion, and O SE represents the objective function of seismic full waveform inversion.

[0080] The construction unit constructs a function model with the joint objective function through SimPEG.

[0081] In this embodiment, the original unit performs forward modeling on the electromagnetic original data by using the finite element method in the frequency domain in combination with Maxwell's equations and the frequency domain wave equation, and then calculates through regularized least squares inversion, which can accurately simulate the relationship between the underground conductivity and the electromagnetic field, effectively reduce data errors, and improve the accuracy of electromagnetic data processing. The geological unit numerically simulates the seismic wave field based on the wave equation, substitutes the predicted wave field and the observed wave field into the objective function, and accurately inverses the formation velocity and density to ensure the accuracy of geological data processing. The joint unit organically combines the electromagnetic inversion objective function, the seismic full waveform inversion objective function, and the parameter correlation constraint term through the joint optimization formula, realizes the deep fusion of multi-source data, avoids the limitations of single data processing, and more comprehensively reflects the underground geological conditions.

[0082] Embodiment 3: Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution: Based on Embodiment 1, the collection unit is used for the data collector to collect historical disaster data in the past.

[0083] The prediction unit is used to evaluate geological risks, and the steps are as follows:

[0084] Step 1: Calculate the geological risk probability, and the calculation formula is as follows:

[0085]

[0086] Among them, P(y = 1|x; θ) represents the conditional geological risk probability given the input feature x and the model parameter θ, y represents the dependent variable, x represents the independent variable vector, θ represents the model parameter, and e represents the natural constant;

[0087] Step 2: Set the risk threshold Q = 0.5. When P(y = 1|x; θ) is greater than Q, it is determined that the current geology is of high risk. If it does not exceed or is equal to Q, it is determined to be of low risk.

[0088] In this embodiment, the historical disaster data collected by the collection unit provides rich samples for the model to learn the relationship between geological parameters and the occurrence of disasters, enabling the model to discover potential laws, thereby predicting the risks under the current geological conditions more accurately, improving the prediction reliability. By calculating the risk probability through the logistic regression algorithm, the geological risk is converted into specific values, changing the previous fuzzy qualitative evaluation method, facilitating subsequent arrangements and decisions, and comparing with the set threshold for judgment, effectively avoiding high-risk areas and reducing disaster losses.

[0089] In the present invention, an intelligent exploration data analysis system collects multi-dimensional original data of underground electromagnetic anomalies through a collection module, obtains electromagnetic characteristic information of underground media from different dimensions and depths, comprehensively outlines the underground electromagnetic distribution, and accurately collects geological information data, covering key parameters such as formation velocity and density, completely presenting the formation structure characteristics, providing sufficient data support for subsequent analysis. At the same time, the collected data is preprocessed, making the collected data relatively more real and accurate, reducing the burden on subsequent data preprocessing, and ensuring the accuracy of the data processing of the entire system;

[0090] The original unit performs forward modeling on the electromagnetic original data by using the finite element method in the frequency domain in combination with Maxwell's equations and the frequency domain wave equation, and then calculates through regularized least squares inversion, which can accurately simulate the relationship between underground conductivity and electromagnetic field, effectively reducing data errors and improving the accuracy of electromagnetic data processing. The geological unit numerically simulates the seismic wave field based on the wave equation, substitutes the predicted wave field and the observed wave field into the objective function, and accurately inverses the formation velocity and density to ensure the accuracy of geological data processing. The joint unit organically combines the electromagnetic inversion objective function, the seismic full waveform inversion objective function and the parameter correlation constraint term through the joint optimization formula to realize the deep fusion of multi-source data, avoid the limitations of single data processing, and more comprehensively reflect the underground geological conditions;

[0091] An intelligent exploration data analysis method includes the following steps:

[0092] (1): Enter the test module: Observe the underground electromagnetic anomaly body, collect the corresponding original data generated, collect geological information data, and process them;

[0093] (2): Enter the analysis module: Receive the original data and geological information data, perform forward and inverse calculations on the original data, perform full waveform inversion on the geological information data at the same time, and construct a model after joint optimization;

[0094] (3): Enter the prediction module: Based on the geological model and electromagnetic anomaly distribution constructed by the analysis module, combine historical geological disaster data and relevant risk assessment algorithms to compare and evaluate the geological risks existing in the exploration area.

[0095] The historical disaster data collected by the collection unit provides rich samples for the model to learn the relationship between geological parameters and the occurrence of disasters, enabling the model to discover potential laws, thus predicting risks under the current geological conditions more accurately, improving the prediction reliability, calculating the risk probability through the logistic regression algorithm, converting geological risks into specific values, changing the previous fuzzy qualitative evaluation method, facilitating subsequent arrangements and decisions, and comparing with the set threshold for judgment, effectively avoiding high-risk areas and reducing disaster losses;

[0096] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0097] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent exploration data analysis system, characterized in that, The system includes a testing module, an analysis module and a prediction module; The test module is used to observe underground electromagnetic anomalies through deep three-dimensional electromagnetic detection and collect the corresponding raw data, and to collect geological information data using seismic exploration instruments, and transmit it to the analysis module after pre-processing; The analysis module is used to receive raw data and geological information data, and perform forward modeling and inversion calculations on the raw data, perform full waveform inversion on the geological information data, and optimize the raw data inversion function and the geological information data inversion function, and construct a model for the jointly optimized function through SimPEG; The prediction module constructs a function model based on the jointly optimized function and evaluates geological risks in combination with historical disaster data.

2. An intelligent exploration data analysis system according to claim 1, characterized in that, The test module includes an acquisition module, a preprocessing module and a transmission module; The acquisition module is used to collect raw data generated by deep three-dimensional electromagnetic detection, and to collect geological information data using seismic exploration instruments. The deep three-dimensional electromagnetic detection includes three-dimensional time-frequency domain induced polarization method, transient electromagnetic method, controlled source audio frequency magnetotelluric method and magnetotelluric method. The seismic exploration instrument includes induction detector, piezoelectric detector and laser detector; The preprocessing module is used to perform data cleaning, normalization and format conversion on the collected raw data and geological information data; The transmission module is used to transmit the pre-processed data to the analysis module through the Wi-Fi module.

3. An intelligent exploration data analysis system according to claim 1, wherein, The analysis module includes original unit, geological unit, joint unit and construction unit.

4. An intelligent exploration data analysis system according to claim 3, wherein The original unit is used to perform forward modeling and inversion on the collected original data. The calculation steps are as follows: Step 1: Define the scope of the detection area, define the underground conductivity distribution σ(r) based on geological prior information, divide the model units, assign corresponding conductivity values to each unit, and select the frequency domain finite element method to divide the detection area into multiple small units. Approximately solve the Maxwell equations for each unit to form an overall stiffness matrix. Step 2: Based on the frequency-domain wave equation: Among them, represents the curl operation symbol, E represents the electric field strength vector; k represents the wave number; i represents the imaginary unit, w represents the angular frequency; μ represents the magnetic permeability; J s represents the source current density vector; σ represents the conductivity; Step 3: Substitute the known angular frequency, magnetic permeability and source current density vector to obtain each unit electric field strength vector E; Step 4: Use regularized least squares inversion, the inversion formula is as follows: Among them, O EM represents the objective function of electromagnetic inversion, represents the observed electromagnetic data, represents the electromagnetic data predicted by forward modeling according to the underground conductivity distribution σ, represents the spatial gradient of the conductivity σ, represents the regularization parameter.

5. An intelligent exploration data analysis system according to claim 3, characterized in that The geological unit is used to calculate the geological objective function, the steps are as follows: S1: Initialize the model, set the initial model of formation velocity u(r) and density p(r); S2: Using the initial model, numerically simulate the seismic wave field u based on the wave equation p (s, r, t, u, p); S3: Substitute the predicted wave field u p (s, r, t, u, p) and the observed wave field u o into the objective function, and the formula is as follows: Among them, O SE represents the objective function of seismic full waveform inversion, and u o (s, r, t) represents the seismic wave field observed at the source s, receiver r, and time t, and u p (s, r, t, u, p) represents the simulated seismic wave field calculation.

6. An intelligent exploration data analysis system according to claim 3, characterized in that, The joint unit is used to jointly optimize the objective function of seismic full waveform inversion and the objective function of electromagnetic inversion. The joint formula is: O j = αO EM + βO SE + δO CE ; Among them, O j represents the joint objective function, α, β, and δ respectively represent the objective function of electromagnetic inversion, the objective function of seismic full waveform inversion, and the weight coefficient of the parameter correlation constraint term, O CE represents the parameter correlation constraint term, O EM represents the objective function of electromagnetic inversion, O SE represents the objective function of seismic full waveform inversion.

7. An intelligent exploration data analysis system according to claim 3, characterized in that The construction unit constructs a function model with a joint objective function through SimPEG.

8. An intelligent exploration data analysis system according to claim 1, characterized in that The prediction module includes a collection unit and a prediction unit; The collection unit is used for data collection to collect historical disaster data.

9. An intelligent exploration data analysis system according to claim 8, characterized in that, The prediction unit is used to assess geological risks in the following steps: Step 1: Calculate the geological risk probability. The calculation formula is as follows: Where P(y=1|x;θ) represents the conditional geological risk probability given the input feature x and model parameter θ, y represents the dependent variable, x represents the independent variable vector, θ represents the model parameter, and e represents the natural constant; Step 2: Set the risk threshold Q = 0.

5. When P(y = 1|x; θ) is greater than Q, it is determined that the current geology is of high risk. If it does not exceed or is equal to Q, it is determined to be of low risk.

10. A method for analyzing intelligent exploration data, which refers to an intelligent exploration data analysis system described in any one of claims 1-9, and is characterized in that, It includes the following steps: (1): Enter the test module: Observe the underground electromagnetic anomaly body, collect the corresponding original data generated, and collect geological information data, and process them; (2): Enter the analysis module: Receive the original data and geological information data, perform forward and inverse calculations on the original data, perform full waveform inversion on the geological information data at the same time, and build a model after joint optimization; (3): Enter the prediction module: Based on the geological model and electromagnetic anomaly distribution constructed by the analysis module, combined with historical geological disaster data and relevant risk assessment algorithms, compare and evaluate the geological risks existing in the exploration area.

Images