Electrical characteristic identification method and system applied to sand body

Abstract

The invention relates to the technical field of substance or object detection, in particular to an electrical characteristic identification method and system applied to a sand body, and the method comprises the steps: obtaining a standard electrical characteristic data set and a standard geological data set of the sand body in a target region; executing primary sand body type estimation; performing feature determination on the standard electrical feature data set; uploading the determined features to a deep learning model to obtain a type A recognition model; performing feature determination on the geological data of the target area; uploading the determined features to a deep learning model to obtain a B identification model; fusing the type A identification model and the type B identification model to obtain an optimal identification model; and based on the optimal recognition model, electrical characteristic recognition is executed, and the sand body type selectable range is obtained. According to the invention, the accuracy of identifying the electrical characteristics of the sand body is effectively ensured, and the method is suitable for identifying the electrical characteristics of the sand body with high precision and complex geological conditions.

Description

Technical Field

[0001] The present application relates to the technical field of detection of substances or objects, and in particular to an electrical property identification method applied to sand bodies, and also relates to an identification system. Background Art

[0002] In the exploration and development process of oil and gas, accurately identifying the characteristics of sand bodies plays a key role in evaluating reservoir quality. Traditional means of identifying sand body characteristics, such as methods based on core analysis, geological modeling, etc., although having certain effects, are costly and inefficient, and it is difficult to effectively cover large areas. Geophysical logging technology can obtain information such as the electrical properties of underground geological bodies. However, existing methods for identifying sand body characteristics using electrical properties still have great room for improvement in terms of accuracy and adaptability to complex geological conditions.

[0003] There is a Chinese invention patent application with a publication date of May 21, 2019, a publication number of CN109782360A, and a title of "A Method for Detecting Deep Sand Bodies in Low-Resistivity Covered Areas", which discloses that in a uranium metallogenic prospective area, survey lines are arranged according to the main tectonic direction, the number of known boreholes ≥ 1, at least one of the survey lines passes through one of the known boreholes, and high-precision GPS and forest compasses are used for measuring point positioning; a continuous tensor observation device and a station-type pole arrangement method are used to carry out broadband magnetotelluric measurement; impedance calculation is performed on the collected data to obtain apparent resistivity and phase information, two-dimensional data inversion is carried out, and an inverted resistivity cross-section diagram is drawn according to the inversion result; according to the exposure results of the known boreholes, the inverted resistivity cross-section diagram is finely stratified, and the electrical properties of ore-bearing sand bodies are extracted; according to the electrical properties of the sand bodies, artificial intelligence technologies such as neural network methods are used to predict the distribution range of deep sand bodies.

[0004] The foregoing technical solution solves problems such as low sounding resolution in low-resistivity covered areas and high difficulty in sand body identification, and has achieved excellent results in sand body prediction, but cannot better improve the accuracy and efficiency of sand body characteristic identification. Summary of the Invention

[0005] The inventors have found through research that: Conventional methods often have difficulty effectively distinguishing different types of sand bodies with similar electrical properties and cannot accurately reflect the heterogeneity inside the sand bodies, which leads to deviations in reservoir evaluation and further affects the formulation and implementation effect of oil and gas exploitation plans.

[0006] The purpose of the present application is to provide an electrical property identification method and system applied to sand bodies, and by fusing a type A identification model and a type B identification model to obtain an optimal identification model, to solve the technical problem that the prior art cannot provide a sand body electrical property identification method with relatively high accuracy.

[0007] According to one aspect of the present application, there is provided a method for identifying the electrical characteristics of sand bodies, which is executed by a processor and includes: obtaining a standard electrical characteristic data set of sand bodies in a target area, and obtaining a standard geological data set of the target area; performing an initial estimation of sand body types based on the geological data set of the target area; performing feature determination on the standard electrical characteristic data set based on a supervised learning algorithm; uploading the determined features to a deep learning model to obtain a Type A identification model; performing feature determination on the geological data of the target area based on a supervised learning algorithm; uploading the determined features to a deep learning model to obtain a Type B identification model; fusing the Type A identification model and the Type B identification model to obtain an optimal identification model; performing electrical characteristic identification based on the optimal identification model, and generating a visualization chart containing sand body types, and comparing the visualization chart with the initially estimated sand body types to obtain an optional range of sand body types.

[0008] In some embodiments, the process of obtaining a standard electrical characteristic data set of sand bodies in a target area and obtaining a standard geological data set of the target area is as follows: obtaining the electrical characteristic data of the sand bodies in the target area according to geophysical logging equipment; performing standardization processing on the electrical characteristic data of the sand bodies in the target area to obtain normalized electrical characteristic data; analyzing the changes in the geophysical field according to geophysical methods to obtain a geological structure data set, and integrating the geological structure data set according to a geographic information system; performing an interpolation algorithm on the geological structure data set and the normalized electrical characteristic data to fill in the missing data, and obtaining a standard electrical characteristic data set and a standard geological data set.

[0009] In some embodiments, the process of performing an initial estimation of sand body types based on the geological data set of the target area is as follows: cleaning the core analysis data, logging data, and regional geological background data in the geological data of the target area to obtain a standard data set; establishing an initial sand body type estimation model for the standard data set in combination with statistical methods; uploading the sand bodies with undetermined types in the target area to the estimation model to obtain the initial estimation result of the sand body types.

[0010] In some embodiments, the process of performing feature determination on the standard electrical characteristic data set based on a supervised learning algorithm is as follows: constructing a resistivity coefficient of variation based on the standard electrical characteristics; performing feature selection using a random forest algorithm, and calculating the advantage scores of the standard electrical characteristics and the resistivity coefficient of variation for classifying sand body characteristics; removing the standard electrical characteristics and the resistivity coefficient of variation with advantage scores lower than the set threshold to obtain the determined features, where the determined features at least include the standard electrical characteristics.

[0011] In some embodiments, the process of uploading the determined features to a deep learning model to obtain an A-type identification model is as follows: input the standard electrical features of the determined features into a convolutional neural network; based on the loss function, obtain the difference between the prediction result of the convolutional neural network and the true label; adjust the model parameters based on the gradient descent algorithm to obtain the A-type identification model.

[0012] In some embodiments, the process of performing feature determination on the geological data of the target area based on a supervised learning algorithm is as follows: divide the geological data of the target area to obtain a training set and a test set; perform training based on a random forest; based on the training results, determine the most contributing features to obtain the determined features.

[0013] In some embodiments, the process of uploading the determined features to a deep learning model to obtain a B-type identification model is as follows: input the geological data of the determined features into a convolutional neural network; based on the loss function, obtain the difference between the prediction result of the convolutional neural network and the true label; adjust the model parameters based on the gradient descent algorithm to obtain the B-type identification model.

[0014] In some embodiments, the process of fusing the A-type identification model and the B-type identification model to obtain an optimal identification model is as follows: construct a meta-model, and fuse the standard electrical feature dataset and the standard geological dataset to obtain a fused dataset; divide the fused dataset to obtain a training set and a test set; perform optimization on the A-type identification model and the B-type identification model based on the training set to obtain an optimized set; input the optimized set into the constructed meta-model to train the meta-model; perform predictions on the A-type identification model and the B-type identification model in sequence based on the test set to obtain a prediction dataset; input the prediction dataset into the meta-model for fusion to obtain the optimal identification model.

[0015] In some embodiments, based on the optimal identification model, perform electrical feature identification and generate a visualization chart containing sand body types, and compare the visualization chart with the initially estimated sand body types to obtain the optional range of sand body types. The process is as follows: input the newly collected sand body electrical feature data of the target area into the optimal identification model to obtain the sand body characteristic identification result; generate a visualization chart containing sand body types based on visualization software; compare the visualization chart with the initial estimation result to obtain the optional sand body types.

[0016] According to another aspect of the present application, there is provided an electrical property feature recognition system for sand bodies. The system includes a processor and further includes: an acquisition module for acquiring a standard electrical property feature data set of sand bodies in a target area and acquiring a standard geological data set of the target area; an estimation module for performing an initial estimation of sand body types based on the geological data set of the target area; a verification module for performing feature determination on the standard electrical property feature data set based on a supervised learning algorithm, uploading the determined features to a deep learning model to obtain a Type A recognition model, performing feature determination on the geological data of the target area based on a supervised learning algorithm, uploading the determined features to a deep learning model to obtain a Type B recognition model; a fusion module for fusing the Type A recognition model and the Type B recognition model to obtain an optimal recognition model; and an execution module for performing electrical property feature recognition based on the optimal recognition model, generating a visualization chart containing sand body types, and performing a comparison based on the visualization chart and the initially estimated sand body types to obtain an optional range of sand body types.

[0017] Compared with the prior art, the present application has the following advantages and beneficial effects: By fusing the Type A recognition model and the Type B recognition model, the present application obtains an optimal recognition model and performs electrical property feature recognition based on the optimal recognition model, effectively ensuring the accuracy of sand body electrical property feature recognition, and distinguishing from the limitations brought by the single-layer model recognition in the prior art, which cannot be adapted to the sand body electrical property feature recognition with high precision and complex geological conditions. At the same time, the present application performs a comparison based on the visualization chart and the initially estimated sand body types to obtain an optional range of sand body types, realizing the precise determination of sand body types, and distinguishing from the situation in the prior art where there are many confusing options when determining sand body types. The determination range of sand body types in the present application is more precise. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 is a flowchart of the electrical property feature recognition method of the present application;

[0020] Figure 2 is a structural diagram of the recognition system of the present application;

[0021] Figure 3 is a schematic diagram of a visualization chart of the present application;

[0022] Figure 4 is another schematic diagram of the visualization chart of the present application;

[0023] Figure 5 It is a scenario diagram of the identification system used in this application. Detailed implementation manners

[0024] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying Figures 1-5 drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments.

[0025] Embodiment 1

[0026] Figure 1 It is a flowchart of the electrical property identification method applied to sand bodies provided in this embodiment, and this method is executed by a processor. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application-Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0027] The method of this application breaks through the limitations of the prior art, improves the accuracy and efficiency of sand body electrical property identification, and provides a more reliable basis for oil and gas exploration and development. The method specifically includes:

[0028] Obtain the standard electrical property feature dataset of sand bodies in the target area, and obtain the standard geological dataset of the target area. In some possible implementation manners, obtain the electrical property feature data of sand bodies in the target area according to geophysical logging equipment. Among them, the geophysical logging equipment may be a resistivity logging tool, a spontaneous potential logging tool, an acoustic logging tool, etc. In this embodiment, a resistivity logging tool is preferably used. The electrical property feature data of sand bodies in the target area, and this data may be resistivity, spontaneous potential, acoustic travel time, etc. In this embodiment, resistivity is preferably used. Perform standardization processing on the electrical property feature data of sand bodies in the target area to obtain normalized electrical property feature data, eliminate the differences in measurement ranges and units of different logging equipment for the collected electrical property feature data of sand bodies in the target area, make the data comparable, and then perform normalization processing using the standardization formula to normalize the electrical property feature data to the [0, 1] interval. The standardization formula is

[0029]

[0030] Among them, X is the original data, that is, the electrical property characteristic data of the sand body in the target area collected; μ is the data mean; σ is the data standard deviation.

[0031] Next, analyze the changes in the geophysical field according to geophysical methods to obtain a geological structure data set, and integrate the geological structure data set according to the geographic information system. The geophysical methods can be gravity exploration, magnetic exploration, electrical exploration, seismic exploration, etc. By analyzing the changes in the geophysical field, the underground geological structure and the properties of geological bodies can be inferred, so as to obtain information such as geological structures, stratigraphic distributions, and potential mineral resources. According to the geological structure data set, based on the geographic information system (GIS) technology, the geological structure data is integrated and managed to establish a geological structure data set.

[0032] Finally, perform an interpolation algorithm on the geological structure data set and the normalized electrical property characteristic data to fill in the missing data, and obtain a standard electrical property characteristic data set and a standard geological data set. That is, for the abnormally high values in the resistivity data, combine adjacent data points and geological background to judge whether it is a measurement error. If so, replace it with the weighted average of adjacent data.

[0033] Perform an initial estimation of the sand body type based on the geological data set of the target area. According to the geological data set of the target area, the initial sand body type can be obtained, which can realize the limitation of the later sand body type and effectively distinguish the relatively wide limitation range of the sand body type in the prior art.

[0034] In some possible implementation manners, perform data cleaning on the core analysis data, logging data, and regional geological background data in the geological data of the target area to obtain a standard data set. Among them, the core analysis data can be lithology, porosity, permeability, etc., the logging data can be resistivity, acoustic transit time, natural gamma, etc., and the regional geological background data can be stratigraphic sedimentary environment, tectonic evolution. In this embodiment, porosity, resistivity, and stratigraphic sedimentary environment are preferably used as basic data for data cleaning. Next, combine the statistical method with the standard data set to establish an initial sand body type prediction model. Specifically, based on the standard data set, select cluster analysis to establish a sand body type prediction model, use a part of the data with known sand body types as the training set, train and optimize the sand body type prediction model, adjust the parameters of the model to improve the prediction accuracy, use another part of the data as the test set, verify and evaluate the trained model, and calculate evaluation indexes such as the accuracy rate and recall rate of the model to ensure the reliability of the model. Finally, upload the sand body type in the target area that has not been determined to the prediction model to obtain the initial prediction result of the sand body type.

[0035] Based on the supervised learning algorithm, perform feature determination on the standard electrical property feature dataset, upload the determined features to the deep learning model, and obtain the Type A recognition model. In some possible implementation manners, based on the standard electrical properties, construct the resistivity coefficient of variation, that is, define the resistivity coefficient of variation as:

[0036]

[0037] where σ R is the standard deviation of the resistivity data; is the mean resistivity. It should be noted that this parameter can reflect the degree of change in resistivity and can effectively characterize the heterogeneity within the sand body.

[0038] Next, use the random forest algorithm to perform feature selection, calculate the advantage scores of the standard electrical property features and the resistivity coefficient of variation for classifying the sand body characteristics, remove the standard electrical property features and the resistivity coefficient of variation with advantage scores lower than the set threshold, and obtain the determined features. Among them, the determined features at least include the standard electrical property features. For example, after random forest calculation, the advantage score of a certain acoustic wave feature for classifying the sand body permeability is lower than the set threshold, and it will be removed. Immediately afterwards, input the standard electrical property features of the determined features into the convolutional neural network, extract the deep features in the data through multiple convolutional layers and pooling layers, and finally perform classification prediction through the fully connected layer. Further, based on the loss function, obtain the difference between the prediction result of the convolutional neural network and the true label. Among them, the loss function in this implementation is the cross-entropy loss function. Finally, adjust the model parameters based on the gradient descent algorithm to minimize the loss function and obtain the Type A recognition model. Optionally, during the training process, use the early stopping method to prevent the model from overfitting.

[0039] Based on the supervised learning algorithm, perform feature determination on the geological data of the target area, upload the determined features to the deep learning model, and obtain the Type B recognition model. In some possible implementation manners, divide the geological data of the target area to obtain a training set and a test set; perform training based on the random forest; based on the training results, determine the most contributing features to obtain the determined features, where the most contributing feature is the feature with the largest weight ratio of neurons in the neural network. Input the geological data of the determined features into the convolutional neural network; based on the loss function, obtain the difference between the prediction result of the convolutional neural network and the true label; adjust the model parameters based on the gradient descent algorithm to obtain the Type B recognition model.

[0040] Fuse the alpha-type recognition model and the beta-type recognition model to obtain the optimal recognition model. In some possible implementation manners, construct a meta-model, and fuse the standard electrical property feature dataset and the standard geological dataset to obtain a fused dataset; perform partitioning on the fused dataset to obtain a training set and a test set; optimize the alpha-type recognition model and the beta-type recognition model based on the training set to obtain an optimized set; input the optimized set into the constructed meta-model to train the meta-model; perform predictions on the alpha-type recognition model and the beta-type recognition model in sequence based on the test set to obtain a prediction dataset; input the prediction dataset into the meta-model for fusion to obtain the optimal recognition model.

[0041] Based on the optimal recognition model, perform electrical property feature recognition and generate a visualization chart containing sand body types. Compare the visualization chart with the initially estimated sand body types to obtain the optional range of sand body types. In some possible implementation manners, input the newly collected sand body electrical property feature data of the target area into the optimal recognition model to obtain the recognition result of sand body characteristics. Based on visualization software, generate a visualization chart containing sand body types, such as Figure 3 、 4 shown. Among them, the visualization software can be ShanHaiJing visualization software or XuanCang visualization software, etc. Compare the initially estimated result based on the visualization chart to obtain the optional sand body types, where the sand body types at least include river sand bodies, lake sand bodies, and marine sand bodies. In this embodiment, the preferred optional sand body is point bar sand bodies.

[0042] Embodiment 2

[0043] Based on the same inventive concept as the electrical property feature recognition method applied to sand bodies in the first embodiment above, such as Figure 2As shown, this embodiment also provides an electrical property feature recognition system for sand bodies, and the system includes a processor. The electrical property feature recognition method for sand bodies in the foregoing embodiment can be divided into one or more modules. One or more modules are stored in the memory and executed by the processor to complete this application. One or more modules can be a series of computer program instruction segments capable of completing specific functions, and this instruction segment is used to describe the execution process of the computer program. For example, the computer program can be divided into an acquisition module, an estimation module, a verification module, a fusion module, and an execution module. The specific functions of each module are as follows: The acquisition module is used to acquire the standard electrical property feature data set of the sand bodies in the target area and acquire the standard geological data set of the target area; the estimation module is used to perform the initial sand body type estimation based on the geological data set of the target area; the verification module is used to perform feature determination on the standard electrical property feature data set based on the supervised learning algorithm; upload the determined features to the deep learning model to obtain the type A recognition model; perform feature determination on the geological data of the target area based on the supervised learning algorithm; upload the determined features to the deep learning model to obtain the type B recognition model; the fusion module is used to fuse the type A recognition model and the type B recognition model to obtain the optimal recognition model; the execution module is used to perform electrical property feature recognition based on the optimal recognition model and generate a visualization chart containing the sand body type, and perform a comparison based on the visualization chart and the initially estimated sand body type to obtain the optional range of the sand body type.

[0044] The specific example of the electrical property feature recognition method for sand bodies in the foregoing Embodiment 1 is equally applicable to the electrical property feature recognition system for sand bodies in this embodiment. Through the foregoing detailed description of the electrical property feature recognition method for sand bodies, those skilled in the art can clearly know the electrical property feature recognition system for sand bodies in this embodiment. Therefore, for the sake of brevity of the specification, it will not be elaborated herein.

[0045] The above shows and describes the basic principles, main features, and advantages of this application. For those skilled in the art, it is obvious that this application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic features of this application. Therefore, in any regard, the embodiments should be regarded as exemplary and non-restrictive. The scope of this application is defined by the appended claims rather than the above description. Therefore, it is intended to include all changes falling within the meaning and scope of the equivalent elements of the claims in this application. Any reference signs in the claims should not be regarded as limiting the claims involved.

[0046] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment contains only an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A method for identifying electrical characteristics of sand bodies, the method being executed by a processor, characterized in that: include: Obtain standard electrical characteristic data sets of sand bodies in the target area, and obtain standard geological data sets in the target area; Perform initial sand body type estimation based on the target area geological dataset; Perform feature determination based on supervised learning algorithms for standard electrical feature datasets; Upload the deep learning model to the determined features to obtain the type A recognition model; Perform feature determination on the geological data of the target area based on supervised learning algorithms; Upload the deep learning model to the determined features to obtain the type B recognition model; The type A recognition model is integrated with the type B recognition model to obtain the optimal recognition model; Based on the optimal recognition model, electrical characteristics recognition is performed, and a visualization chart containing sand body types is generated. Based on the visualization chart and the initial estimated sand body type, a comparison is performed to obtain the optional range of sand body types.

2. The method according to claim 1, characterized in that The process of obtaining the standard electrical characteristic data set of the sand body in the target area and the standard geological data set of the target area is as follows: Obtain electrical characteristic data of sand bodies in the target area using geophysical logging equipment; Performing standardization processing on the electrical characteristic data of the sand body in the target area to obtain normalized electrical characteristic data; Analyze the changes of geophysical fields according to geophysical methods, obtain geological structure data sets, and integrate geological structure data sets according to geographic information systems; An interpolation algorithm is performed on the geological structure data set and the normalized electrical characteristic data to fill in the missing data and obtain a standard electrical characteristic data set and a standard geological data set.

3. The method according to claim 2, characterized in that The process of performing the initial sand body type estimation based on the target area geological data set is as follows: Perform data cleaning on the core analysis data, well logging data and regional geological background data in the target area geological data to obtain a standard data set; The standard data set is combined with statistical methods to establish a preliminary sand body type estimation model; The undetermined sand body types in the target area are uploaded to the estimation model to obtain the initial estimation results of the sand body types.

4. The method according to claim 3, characterized in that The process of performing feature determination on the standard electrical feature data set based on the supervised learning algorithm is as follows: Based on the standard electrical characteristics, the resistivity variation coefficient is constructed; The random forest algorithm was used to perform feature selection and calculate the advantage scores of the standard electrical characteristics and resistivity variation coefficient for sand body property classification; The standard electrical characteristics and resistivity variation coefficients whose dominance scores are lower than a set threshold are removed to obtain determined characteristics, wherein the determined characteristics at least include the standard electrical characteristics.

5. The method according to claim 4, characterized in that The process of uploading the determined features to the deep learning model to obtain the type A recognition model is as follows: Input the standard electrical features of the determined features into the convolutional neural network; Based on the loss function, the difference between the prediction result of the product neural network and the true label is obtained; The model parameters are adjusted based on the gradient descent algorithm to obtain the type A recognition model.

6. The method according to claim 5, characterized in that The process of performing feature determination on the target area geological data based on the supervised learning algorithm is as follows: Divide the geological data of the target area to obtain a training set and a test set; Perform training based on random forest; Based on the training results, the most contributing features are determined to obtain the determined features.

7. The method according to claim 6, characterized in that The process of uploading the deep learning model to determine the features and obtaining the type B recognition model is as follows: The geological data of the identified features are fed into a convolutional neural network; Based on the loss function, the difference between the prediction result of the product neural network and the true label is obtained; The model parameters are adjusted based on the gradient descent algorithm to obtain the type B recognition model.

8. The method according to claim 7, characterized in that The process of fusing the type A recognition model with the type B recognition model to obtain the optimal recognition model is as follows: Construct a meta-model and fuse the standard electrical characteristic data set with the standard geological data set to obtain a fused data set; Partition the fused data set to obtain a training set and a test set; Optimize the type A recognition model and the type B recognition model based on the training set to obtain an optimized set; Based on the optimization set, the constructed meta-model is passed in to train the meta-model; Based on the test set, the type A recognition model and the type B recognition model are predicted in turn to obtain a prediction data set; The prediction data set is passed into the meta-model for fusion to obtain the optimal recognition model.

9. The method according to claim 8, characterized in that The process of performing electrical characteristic recognition based on the optimal recognition model, generating a visualization chart containing sand body types, and performing comparison based on the visualization chart and the initially estimated sand body types to obtain the optional range of sand body types is as follows: Input the newly acquired sand body electrical characteristic data in the target area into the optimal identification model to obtain the sand body characteristic identification results; Generate visualization charts containing sand body types based on visualization software; Compare the initial estimation results based on visual charts to obtain optional sand body types.

10. A system for identifying electrical characteristics of sand bodies, the system comprising a processor, characterized in that: Also includes: An acquisition module, the acquisition module is used to acquire a standard electrical characteristic data set of sand bodies in the target area and a standard geological data set of the target area; An estimation module, the estimation module is used to perform a primary sand body type estimation based on a target area geological data set; A verification module, the verification module is used to perform feature determination on the standard electrical characteristic data set based on a supervised learning algorithm; upload the deep learning model to the determined features to obtain a type A recognition model; perform feature determination on the geological data of the target area based on a supervised learning algorithm; upload the deep learning model to the determined features to obtain a type B recognition model; A fusion module, wherein the fusion module is used to fuse the type A recognition model with the type B recognition model to obtain an optimal recognition model; An execution module is used to perform electrical feature recognition based on an optimal recognition model, generate a visualization chart containing sand body types, compare the visualization chart with the initially estimated sand body types, and obtain an optional range of sand body types.

Images