Carbonate deposition environment intelligent identification method, device and medium
By using the intelligent interpretation model of carbonate deposition environment, the multi-dimensional logging data of drilling wells was processed and the data resampling method was combined to construct a balanced training sample set, which solved the problem of unsatisfactory recognition effect of carbonate deposition environment in the existing technology and achieved higher recognition accuracy.
Patent Information
- Application Number
- CN202510326420.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-19
- Publication Date
- 2025-07-01
AI Technical Summary
The existing carbonate deposition environment identification methods have poor division effects in practical applications, and the traditional methods have limitations on interpretation results due to experience, making it difficult to effectively identify the carbonate deposition environment.
A method for intelligent identification of carbonate deposition environment is provided, which is recognized by obtaining multi-dimensional logging data of drilling and using the trained intelligent interpretation model of carbonate deposition environment. During the training process, this model uses data resampling method to build the target training sample set, effectively alleviating the problem of imbalance in the distribution of sample categories.
It improves the identification accuracy of the carbonate deposition environment, and can more accurately identify the sedimentary environment type of carbonate rock system, overcoming the limitations of the interpretation results of traditional methods that are restricted by experience.
Smart Images
Figure CN120234715A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of geological sedimentary environment analysis, and particularly to an intelligent identification method, device and medium for carbonate sedimentary environment. Background Art
[0002] In the field of oil and gas resource exploration and development, the sedimentary environment is an important basis for oil and gas exploration prediction in oil and gas bearing basins, providing important guidance for understanding the origin, development and distribution laws of the three major reservoir forming elements of source rocks, reservoirs and caps. At present, well logging data and core segments obtained from oil and gas drilling are widely used to reconstruct the distribution pattern of the sedimentary environment in the deep underground, which is of great significance for predicting favorable exploration target facies areas. However, the multi-solution of sedimentary environment characteristics and the subjectivity of manual interpretation bring difficulties to the identification work, and the traditional interpretation methods are limited by experience in the interpretation results. In addition, due to the small difference in the characteristics of sediments formed in different carbonate sedimentary environments and the poor discrimination of well logging parameters, the existing methods for identifying carbonate sedimentary environments have unsatisfactory classification effects in practical applications. Summary of the Invention
[0003] The purpose of the present application is to provide an intelligent identification method, device and medium for carbonate sedimentary environment, which can improve the identification accuracy of carbonate sedimentary environment.
[0004] To achieve the above purpose, the present application provides the following solutions:
[0005] In the first aspect, the present application provides an intelligent identification method for carbonate sedimentary environment, including:
[0006] Obtain multi-dimensional well logging data of the well drilling of the carbonate rock formation to be identified;
[0007] Taking the multi-dimensional well logging data of the well drilling of the carbonate rock formation to be identified as input, and using the trained intelligent interpretation model of carbonate sedimentary environment to output the sedimentary environment type of the well drilling of the carbonate rock formation to be identified, wherein the target training sample set in the training process of the intelligent interpretation model of carbonate sedimentary environment is data constructed by a data resampling method.
[0008] In the second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the intelligent identification method for carbonate sedimentary environment described in the first aspect above.
[0009] In the third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the intelligent identification method for carbonate sedimentary environment described in the first aspect above.
[0010] According to the specific embodiments provided by this application, this application has the following technical effects:
[0011] This application provides a method, device, and medium for intelligent identification of carbonate deposition environments. The method includes: using a trained intelligent interpretation model for carbonate deposition environments to process multi-dimensional logging data of a well to be identified in a carbonate rock formation series, and outputting the type of deposition environment of the well to be identified in the carbonate rock formation series. Among them, the target training sample set in the training process of the intelligent interpretation model for carbonate deposition environments is data constructed by using a data resampling method, which can effectively alleviate the problem of unbalanced class distribution of carbonate deposition environment samples and improve the identification accuracy of carbonate deposition environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.
[0013] Figure 1 It is an application environment diagram of an intelligent identification method for carbonate deposition environments in Embodiment 1 of this application;
[0014] Figure 2 It is a flowchart of an intelligent identification method for carbonate deposition environments provided in Embodiment 1 of this application;
[0015] Figure 3 It is a conceptual diagram of an intelligent identification method for carbonate deposition environments provided in Embodiment 1 of this application;
[0016] Figure 4 It is a log response model diagram of the deposition environment in Embodiment 1 of this application;
[0017] Figure 5 It is a schematic diagram of the principle of the random forest algorithm in Embodiment 1 of this application;
[0018] Figure 6 It is a schematic diagram of the result of processing training samples using the data resampling method in Embodiment 1 of this application, Figure 6 In (A) is a schematic diagram of the result of using oversampling technology for training samples, Figure 6 In (B) is a schematic diagram of the result of using undersampling technology for training samples;
[0019] Figure 7 It is a schematic diagram of the visualized prediction result of the confusion matrix in Embodiment 1 of this application, Figure 7 In (A) is a schematic diagram of the analysis principle of the confusion matrix, Figure 7In (B) is the complete confusion matrix diagram;
[0020] Figure 8 FIG. 4 is a schematic structural diagram of a computer device provided in Embodiment 2 of the present application. Detailed implementation manners
[0021] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.
[0022] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific implementation manners.
[0023] The intelligent carbonate deposition environment recognition method provided in the embodiments of the present application can be applied to an application environment as shown in Figure 1 FIG. 17. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed in the cloud or on other servers. The terminal 102 can send the multi-dimensional logging data of the carbonate rock formation series well to be recognized to the server 104. After receiving the multi-dimensional logging data of the carbonate rock formation series well to be recognized, the server 104 uses the multi-dimensional logging data of the carbonate rock formation series well to be recognized as an input, and outputs the deposition environment type of the carbonate rock formation series well to be recognized by using the trained intelligent carbonate deposition environment interpretation model. Among them, the target training sample set in the training process of the intelligent carbonate deposition environment interpretation model is data constructed by using a data resampling method. The server 104 can feedback the obtained deposition environment type of the carbonate rock formation series well to be recognized to the terminal 102. In addition, in some embodiments, the intelligent carbonate deposition environment recognition method can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly process the multi-dimensional logging data of the carbonate rock formation series well to be recognized by using the intelligent carbonate deposition environment recognition method, or the server 104 can obtain the multi-dimensional logging data of the carbonate rock formation series well to be recognized from the data storage system and process it by using the intelligent carbonate deposition environment recognition method.
[0024] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, and tablet computers. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.
[0025] In an exemplary embodiment, as Figure 2 shown, a method for intelligent identification of carbonate deposition environments is provided. This method is executed by a computer device, and specifically, it can be executed independently by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking the application of this method to Figure 1 the server 104 as an example for illustration, it includes the following steps. Among them:
[0026] S1. Obtain multi-dimensional logging data of the well drilled in the carbonate rock formation system to be identified.
[0027] S2. Use the multi-dimensional logging data of the well drilled in the carbonate rock formation system to be identified as input, and utilize the trained intelligent interpretation model for carbonate deposition environments to output the type of deposition environment of the well drilled in the carbonate rock formation system to be identified. Among them, the target training sample set in the training process of the intelligent interpretation model for carbonate deposition environments is data constructed by using a data resampling method, and the intelligent interpretation model for carbonate deposition environments is a random forest model.
[0028] Since in this embodiment, it is considered that the characteristics of the sediments formed in different carbonate deposition environments have small differences, and their logging parameters have poor discrimination. Especially, single parameters are difficult to distinguish different carbonate deposition environments, making the identification of carbonate deposition environments more difficult than that of clastic rock deposition environments. Although machine learning is an effective method for analyzing multi-dimensional parameters, the lack of reliable calibration samples for carbonate deposition environments will also affect the training effect of machine learning models. Therefore, by adopting the above steps S1 - S2, an intelligent interpretation model for carbonate deposition environments can be trained based on a balanced training sample set. By learning the relationship between the multi-dimensional logging data of carbonate rocks and the type of deposition environment through the intelligent interpretation model for carbonate deposition environments, the identification accuracy of carbonate deposition environments can be improved.
[0029] Next, in combination with the training process of the intelligent interpretation model for carbonate deposition environments, the intelligent identification method for carbonate deposition environments in this embodiment will be specifically explained.
[0030] This embodiment proposes an intelligent identification method for carbonate deposition environments based on the random forest algorithm, which can effectively handle the problem of multiple solutions in data through the characteristics of random forest ensemble learning, thereby improving the efficiency and accuracy of deposition environment identification. This method includes:
[0031] Step 1: Obtain a multi-dimensional logging parameter set of the well drilled in the carbonate rock formation system in the target study area, and establish a classification standard for deposition environments based on core observation and sedimentary facies analysis.
[0032] Step 2: Based on the geological-logging response mapping relationship, construct a logging response template for deposition environments that includes lithological characteristics and electrical characteristics.
[0033] Step 3: Perform normalization processing on the multi-dimensional logging data of the selected coring section, as shown in Equation (1):
[0034]
[0035] In the formula, x i is the i-th logging data in the original dataset, x max is the maximum value of the dataset, x min is the minimum value of the dataset, and x i,scale is the logging value of the i-th sample after normalization.
[0036] Step 4: Use resampling to generate a target training sample set from the divided training sample set.
[0037] Step 5: Use the random forest algorithm combined with the target training sample set to train the intelligent interpretation model for carbonate deposition environment.
[0038] The training process is as follows:
[0039] (1) Optimize the random forest algorithm using the data resampling method. The data resampling method includes oversampling and undersampling. Among them, the oversampling process is as follows:
[0040] (a) Calculate the Euclidean distance between the minority class samples and find their k nearest neighbors;
[0041] (b) Randomly select 1 nearest neighbor for each minority class sample to generate interpolation samples, and the interpolation weights are randomly selected in the interval (0, 1).
[0042] The undersampling process is as follows:
[0043] (c) Calculate the distance from each majority class sample to the nearest minority class sample;
[0044] (d) Retain the first N majority class samples in ascending order of distance, where N is equal to the total number of minority class samples after oversampling.
[0045] (e) Finally, combine the selected N majority class samples with the minority class samples to obtain a balanced training set (i.e., the target training sample set).
[0046] (2) Tune the parameters of the model through grid search combined with cross-validation, find the optimal parameter combination of the model, and obtain the optimized intelligent interpretation model for carbonate deposition environment.
[0047] Step 6: Use evaluation metrics such as precision, recall, accuracy, and F1-score to evaluate the accuracy and performance of the optimized model in combination with the test sample set.
[0048] The accuracy and performance of the evaluation model are evaluated using Equations (2)-(5):
[0049]
[0050] Where, Accuracy represents the accuracy rate, TP represents true positive, TN represents true negative, FP represents false positive, FN represents false negative, precision represents the precision rate, recall represents the recall rate, and F1-score is the harmonic mean of the precision rate and the recall rate.
[0051] Step Seven: Input the multi-dimensional logging data of the carbonate rock formation to be identified into the trained intelligent interpretation model of carbonate sedimentary environment, and the final prediction result can be obtained.
[0052] The following introduces the above process in combination with specific examples. As Figure 3 shown, the intelligent identification method of carbonate sedimentary environment includes:
[0053] (1) The selected core section in this embodiment is the carbonate rock formation of the Changxing Formation in the Upper Permian in the Yuanba area of northeastern Sichuan. The lithology mainly consists of dolomite, argillaceous limestone, bioclastic limestone, and dolomite-bearing limestone. Four sedimentary environments, namely open platform, restricted platform, platform margin reef flat, and platform margin slope, are divided according to core observation and sedimentary facies analysis as characteristic labels.
[0054] (2) Based on the geological-logging response mapping relationship of the core section in the study area, a logging response template for sedimentary environment containing lithological characteristics and electrical characteristics is constructed, as Figure 4 shown.
[0055] (3) Five types of logging data, namely natural gamma logging (GR), density logging (DEN), acoustic time logging (AC), spontaneous potential logging (SP), and compensated neutron logging (CNL), are selected in this embodiment and normalized so that each index is at the same order of magnitude. The formula is as shown in Equation (1).
[0056] (4) The data set is divided into a training sample set and a test sample set according to 7:3. Among them, the training sample set is used for model learning, and the test sample set is used to evaluate the accuracy and performance of the final model. In this embodiment, the logging data of 5 wells are used for model training and testing, and another well is selected for external blind testing of the model.
[0057] (5) The random forest algorithm is adopted in this embodiment. As Figure 5As shown in the figure, the steps of the random forest algorithm are as follows: Randomly select N samples for each tree through bootstrap sampling. Under the condition that the feature dimension of each sample is M, randomly select m features (m < M) from M features to form a feature subset, and select the optimal feature for splitting to generate the left and right subtrees of the decision tree. The integrated N decision trees are independent of each other, and the classification result is determined by voting. The decision tree with more votes finally makes the decision.
[0058] (6) In this embodiment, a resampling method combining SMOTE and Nearmiss-1 is adopted. First, the SMOTE oversampling technique is performed on the training sample set, and then the Nearmiss-1 undersampling technique is performed to balance the distribution of the training samples and improve the model's recognition ability for minority classes. Specifically as follows:
[0059] SMOTE is an oversampling technique that generates new samples by interpolation to increase the number of minority class samples, as shown in (A) of Figure 6 .
[0060] (a) Assume that the minority class sample set is S = {x1, x2,..., x n}, where each x i is a feature vector. For each minority class sample x i , calculate its distance from other minority class samples x j in the set, as shown in Equation (6):
[0061] d(x i , x j ) = ||x i - x j ||, j ≠ i (6);
[0062] (b) According to the calculated distance, find the k nearest neighbors of x i . Among the k nearest neighbor samples, randomly select one x n as the reference point for generating a new sample. Interpolate between x i and x n to generate a new sample, as shown in Equation (7):
[0063] x new = x i + δ · (x n - x i ) (7);
[0064] In the formula, δ ∼ U(0, 1) is a uniformly distributed random number in the interval [0, 1]. For each sample x i in the minority class, repeat the above steps (a)-(b) to generate a predetermined number of new samples.
[0065] The NearMiss-1 algorithm is an undersampling technique for dealing with class imbalance problems. Its core idea is to select the most representative majority-class samples based on distance metrics, as shown in Figure 6 as shown in (B) of
[0066] (c) For each majority-class sample, calculate its distance to all minority-class samples.
[0067] (d) Select the K nearest minority-class samples to it. Calculate the average value of these K distances, and sort the average distances calculated for all majority-class samples.
[0068] (e) Select the first N majority-class samples with the smallest average distances, where N is the number of minority-class samples.
[0069] (f) Finally, combine the selected majority-class samples with the minority-class samples to obtain a balanced training sample set.
[0070] (7) During the process of model optimization, grid search combined with k-fold cross-validation is used to find the optimal parameter combination. Since the data scale used is small, the value of K is taken as 5. During the five-fold cross-validation process, the target training sample set is randomly divided into five equal parts, and one of them is selected as the validation set in turn, and the remaining four parts are used for model training. Grid search traverses the preset parameter space, evaluates the performance of each parameter combination, and finally determines the optimal parameter combination based on the cross-validation score. In subsequent applications, this model is directly used to predict the sedimentary environment of new logging data.
[0071] (8) The accuracy, precision, recall, and F1-score are used to evaluate the performance of the optimized model (see Table 1). The weighted average of the precision, recall, and F1-score of the optimized random forest model, as well as the overall accuracy, are all 0.96. The model has a good classification effect and the recognition ability for minority-class samples has been improved.
[0072] Table 1 Performance evaluation of the intelligent recognition model for carbonate sedimentary environment
[0073]
[0074] Visualize the prediction results through the confusion matrix. For the analysis of the confusion matrix, the larger the diagonal data, the more accurate the prediction of the sedimentary environment. The principle is as shown in Figure 7 as shown in (A) of Figure 7 The complete confusion matrix diagram can be seen in
[0075] (9) Input the logging data of the well to be identified into the optimized intelligent interpretation model for carbonate sedimentary environment to obtain the prediction result of the sedimentary environment of the well to be identified.
[0076] In this embodiment, through data preprocessing, training set balancing, and model parameter tuning, an intelligent interpretation model for carbonate sedimentary environment is constructed, which can accurately meet the research requirements for carbonate sedimentary environment identification, and significantly improve the prediction efficiency and accuracy.
[0077] This application also provides an application scenario that applies the above intelligent identification method for carbonate sedimentary environment. Specifically: The intelligent identification method for carbonate sedimentary environment provided in this embodiment can be applied in the scenarios of geological exploration and oil and gas resource development. This scenario includes a data collection link, a data analysis and feature extraction link, and a sedimentary environment identification and evaluation link. The intelligent identification method for carbonate sedimentary environment provided in this embodiment belongs to the key technology in the sedimentary environment identification and evaluation link. This method can improve the exploration efficiency and accuracy, and is widely applied in fields such as oil and gas field exploration and mineral resource development.
[0078] Embodiment 2
[0079] This embodiment provides a computer device, which can be a server or a terminal, and its internal structure diagram can be as Figure 8 shown. This computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of this computer device is used to store the data in the intelligent identification method for carbonate sedimentary environment. The input / output interface of this computer device is used to exchange information between the processor and external devices. The communication interface of this computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it realizes an intelligent identification method for carbonate sedimentary environment in Embodiment 1.
[0080] Those skilled in the art can understand, Figure 8The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.
[0081] Embodiment 3
[0082] This embodiment provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, a method for intelligent identification of carbonate deposition environment in Embodiment 1 is implemented.
[0083] Embodiment 4
[0084] This embodiment provides a computer program product including a computer program, and when the computer program is executed by a processor, a method for intelligent identification of carbonate deposition environment in Embodiment 1 is implemented.
[0085] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.
[0086] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memories (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0087] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.
[0088] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.
[0089] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.
Claims
1. A method for intelligently identifying a carbonate deposition environment, characterized in that: The method for intelligently identifying a carbonate deposition environment comprises: Acquire multi-dimensional logging data of the carbonate formation to be identified; The multi-dimensional logging data of the drilling of the carbonate rock formation to be identified is taken as input, and the sedimentary environment type of the drilling of the carbonate rock formation to be identified is output using the trained carbonate depositional environment intelligent interpretation model, wherein the target training sample set of the carbonate depositional environment intelligent interpretation model during the training process is data constructed using a data resampling method.
2. The method for intelligent identification of carbonate deposition environment according to claim 1, characterized in that: The training process of the carbonate deposition environment intelligent interpretation model specifically includes: Acquire an original training sample set, wherein the original training sample set includes different types of sedimentary environment sample data of known carbonate rock core sections and corresponding multi-dimensional logging sample data; Processing the original training sample set using a data resampling method to obtain a target training sample set; Grid search combined with cross validation is used to adjust the parameters of the carbonate sedimentary environment intelligent interpretation model to determine the optimal parameter combination; The target training sample set is used to train the carbonate deposition environment intelligent interpretation model with the optimal parameter combination to obtain a trained carbonate deposition environment intelligent interpretation model.
3. The method for intelligent identification of carbonate deposition environment according to claim 1, characterized in that: The carbonate deposition environment intelligent interpretation model is a random forest model.
4. The method for intelligently identifying carbonate deposition environments according to claim 1, characterized in that: The multi-dimensional logging data includes natural gamma logging data, density logging data, acoustic time difference logging data, natural potential logging data and compensated neutron logging data.
5. The method for intelligent identification of carbonate deposition environment according to claim 1, characterized in that: The sedimentary environment types include open platform, restricted platform, platform margin reef beach and platform margin slope.
6. The method for intelligently identifying carbonate deposition environments according to claim 2, characterized in that: The original training sample set is processed by a data resampling method to obtain a target training sample set, specifically including: The minority class sample set is processed by using an oversampling technique to obtain a newly added training sample set, wherein the minority class sample set refers to a training sample subset whose number of training samples corresponding to the sedimentary environment type is less than a first quantity threshold, and the training sample subset refers to a set formed by sedimentary environment sample data of the same type in the original training sample set and corresponding multidimensional logging sample data; The majority class sample set is processed using undersampling technology according to the newly added training sample set to obtain a target training sample set, wherein the majority class sample set refers to the training sample subset whose number of training samples corresponding to the sedimentary environment type is greater than the second number threshold.
7. The method for intelligently identifying carbonate deposition environments according to claim 6, characterized in that: The oversampling technology is used to process the minority class sample set to obtain a new training sample set, which includes: Calculate a first distance between each minority class sample in the minority class sample set and other minority class samples; Determine K nearest neighbor samples of each of the minority class samples according to the first distance; Generate new training samples according to the nearest neighbor samples and the corresponding minority class samples; The newly added training sample set is obtained according to the original minority class sample and each of the new training samples.
8. The method for intelligently identifying carbonate deposition environments according to claim 7, characterized in that: According to the newly added training sample set, the majority class sample set is processed by using undersampling technology to obtain the target training sample set, which specifically includes: Calculating a second distance between each majority class sample in the majority class sample set and the target sample, wherein the target sample refers to all minority class samples in the newly added training sample set; Determine a target majority class sample according to the second distance; The target majority class samples and the minority class sample set are combined to obtain a target training sample set.
9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for intelligently identifying a carbonate deposition environment according to any one of claims 1 to 8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for intelligently identifying a carbonate deposition environment according to any one of claims 1 to 8 is implemented.