Method, device, medium and electronic equipment for determining microbial carbonate rock phase

Abstract

The present application provides a method and related equipment for determining microbial carbonate rock facies. At least one data set is determined through lithofacies data, and the similarity between the lithofacies data in each data set is greater than a similarity threshold, which can reduce data imbalance. Then, importance analysis is performed on multiple logging curves to determine a target logging curve. A target prediction model is constructed based on the at least one data set and the target logging curve to identify the microbial carbonate rock facies based on the target prediction model, which can improve the accuracy of identifying microbial carbonate rock facies.

Description

Technical Field

[0001] The present application relates to the technical field of exploration and development of microbial carbonate oil and gas reservoirs, and in particular to a method, device, medium and electronic equipment for determining the lithofacies of microbial carbonate rocks. Background Art

[0002] Microbial carbonate reservoirs have been a hotspot for exploration and development in recent years, particularly in the deepwater South Atlantic, where a series of world-class oil and gas discoveries have been made. However, due to the cost constraints of coring in deepwater exploration and development, core data is limited. Furthermore, the complex lithofacies of microbial carbonate reservoirs, with similar mineral compositions and significant overlap in well logging characteristics, make existing identification methods inaccurate (less than 50%) and difficult to meet production needs. Summary of the Invention

[0003] In response to the above problems, the present application provides a method, device, medium and electronic equipment for determining the lithofacies of microbial carbonate rocks.

[0004] The present application provides a method for determining microbial carbonate rock facies, comprising:

[0005] Obtaining petrographic data of microbial carbonate rocks in a target area and a plurality of well logging curves of sample wells in the target area;

[0006] determining at least one data set based on the petrographic data, wherein the similarity between the petrographic data in each data set is greater than a similarity threshold;

[0007] Conduct importance analysis on multiple logging curves and determine the target logging curve;

[0008] A target prediction model is determined based on at least one data set and the target well log curve, so as to identify the microbial carbonate facies based on the target prediction model.

[0009] In some embodiments, determining at least one data set based on the petrographic data comprises:

[0010] dividing the lithofacies data into at least one data set based on geological stratification information of the target area;

[0011] Determining lithofacies less than a preset threshold based on core data of the target area;

[0012] Remove the lithofacies data corresponding to the rock phases whose values ​​are smaller than the preset threshold in each data set.

[0013] In some embodiments, performing sensitivity and importance analysis on multiple well logging curves to determine a target well logging curve includes:

[0014] Perform importance analysis on multiple logging curves to obtain importance calculation results;

[0015] Sorting the importance calculation results to obtain an importance ranking result;

[0016] The well logging curve corresponding to the importance calculation result greater than a preset importance threshold in the importance ranking result is determined as the target well logging curve.

[0017] In some embodiments, the target logging curves include: a natural gamma ray spectrum logging potassium curve, a natural gamma ray spectrum logging thorium curve, and a natural gamma ray spectrum logging uranium curve.

[0018] In some embodiments, the constructing a target prediction model based on at least one data set and the target well logging curve includes:

[0019] Obtaining an initial model of a target algorithm, wherein the target algorithm includes: K-nearest neighbor algorithm, decision tree algorithm, logistic regression algorithm, support vector machine algorithm, gradient boosting decision tree algorithm, and random forest algorithm;

[0020] Each initial model is trained using the target well logging curve as input and each data set as output;

[0021] And determine the accuracy of each initial model after training;

[0022] A target prediction model is determined based at least on the accuracy.

[0023] In some embodiments, the method further comprises:

[0024] Determine the training time of each initial model;

[0025] The determining as the target prediction model at least based on the accuracy rate includes:

[0026] A target prediction model is determined based on the training time and the accuracy.

[0027] In some embodiments, the target prediction model is obtained based on initial model training of a random forest algorithm.

[0028] The present application provides a device for determining microbial carbonate rock facies, comprising:

[0029] A first acquisition module is used to acquire petrographic data of microbial carbonate rocks in a target area and multiple well logging curves of sample wells in the target area;

[0030] A first determining module is configured to determine at least one data set based on the lithofacies data, wherein the similarity between the lithofacies data in each data set is greater than a similarity threshold;

[0031] The second determination module is used to perform importance analysis on multiple logging curves and determine the target logging curve;

[0032] The third determination module is configured to determine a target prediction model based on at least one data set and the target well logging curve, so as to identify the microbial carbonate rock facies based on the target prediction model.

[0033] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, any one of the above-mentioned methods for determining the microbial carbonate rock facies is executed.

[0034] An embodiment of the present application provides a computer storage medium, which stores a computer program that can be executed by one or more processors and can be used to implement any of the above-mentioned methods for determining the microbial carbonate rock facies.

[0035] The present application provides a method, device, medium, and electronic device for determining microbial carbonate rock facies. The method determines at least one data set through lithofacies data, wherein the similarity between the lithofacies data in each data set is greater than a similarity threshold, thereby reducing data imbalance. An importance analysis is then performed on multiple well logging curves to determine a target well logging curve. A target prediction model is constructed based on the at least one data set and the target well logging curve to identify the microbial carbonate rock facies based on the target prediction model, thereby improving the accuracy of identifying the microbial carbonate rock facies. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Hereinafter, the present application will be described in more detail based on embodiments with reference to the accompanying drawings.

[0037] Figure 1 A schematic diagram of a process for determining the lithofacies of microbial carbonate rocks provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of the implementation process of another method for determining the petrographic phase of microbial carbonate rocks provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of calculation results provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of the structure of a device for determining microbial carbonate rock facies provided in an embodiment of the present application;

[0041] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0042] In the drawings, like components are given like reference numerals, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0044] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0045] If similar descriptions of "first\second\third" appear in the application documents, the following explanation will be added. In the following description, the terms "first\second\third" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0047] Before introducing the embodiments of the present application, a brief introduction to the problems in the related art is given:

[0048] In oil and gas exploration and development, lithologic identification is fundamental to reservoir description and evaluation. The most direct method for lithologic identification is observation of cores and thin sections. However, due to the limited number of coring wells and cores, lithologic identification based solely on coring data cannot meet production needs. Well logging data can provide rock physical response characteristics throughout the entire wellbore and has been widely used in lithologic interpretation and identification (Burke et al. 1969; Porter et al. 1969; Doventon 1994; Grana et al. 2012; Caté et al. 2017; Ao et al. 2018). Well logging lithologic identification methods, such as logging lithologic interpretation and intersection plot methods, primarily rely on establishing logging curve feature templates or lithologic charts for lithologic identification (Burke et al. 1969; Porter et al. 1969; Clavier et al. 1976). These methods are suitable for sandstone and mudstone formations with simple lithology and are usually time-consuming, but the identification accuracy of strata with complex lithology is low.

[0049] Driven by the trends in data science and artificial intelligence, machine learning-based quantitative lithologic identification methods have become a hot topic in recent years (Grana et al., 2012; Caté et al., 2017; Ao et al., 2018; Gu et al., 2019; Liu et al., 2020; Chang et al., 2021). Their advantage lies in their ability to efficiently identify complex lithologies by combining multidimensional features. Previous studies have optimized lithologic prediction using various machine learning algorithms, such as decision trees (Tan et al., 2010), support vector machines (Deng et al., 2017), random forests (Ao et al., 2018; Xie et al., 2018), and neural networks (Benaouda et al., 1999; Gu et al., 2019).

[0050] For carbonate rocks, simple lithologic identification cannot meet research and production needs; lithofacies identification and description are required. Machine learning-based lithologic identification methods have been widely applied to carbonate formations with complex lithofacies. Qiand Carr (2006) used six well logging features and applied a neural network to predict six carbonate lithofacies in the St. Louis limestone in Hugoton Bay, southwestern Kansas. Lin et al. (2016) established a well logging feature map and combined it with a support vector machine algorithm to learn six logging features to identify six carbonate lithofacies in the Pre-Caspian Basin. Liu et al. (2016) used natural gamma ray spectroscopy logging to identify Cambrian limestone and dolomite in the Tadong Uplift of the Tarim Basin by analyzing the overlay relationship between U, Th, and K curves. Microbial carbonate rocks have complex lithofacies. According to the classification schemes of Dunham (1962), Riding (2000), and Terra et al. (2009), microbial carbonate rocks can be divided into stromatolite, spherulite, and lamellar limestone, as well as modified breccia, grainstone, argillaceous limestone, granular marl, crystalline limestone, dolomite, and silicified carbonate rocks. Due to the complex lithofacies and the difficulty in identification, there is currently no effective identification method.

[0051] Microbial carbonate reservoirs have been a hotspot for exploration and development in recent years, particularly in the deepwater South Atlantic, where a series of world-class oil and gas discoveries have been made. However, due to the cost constraints of coring in deepwater exploration and development, core data is limited. Furthermore, the complex lithofacies of microbial carbonate reservoirs, with similar mineral compositions and significant overlap in well logging characteristics, make existing identification methods inaccurate (less than 50%) and difficult to meet production needs.

[0052] To address the problems existing in the related art, embodiments of the present application provide a method for determining microbial carbonate rock facies, which is applicable to electronic devices such as computers and mobile terminals. The functions implemented by the method for determining microbial carbonate rock facies provided in embodiments of the present application can be implemented by a processor of the electronic device calling program code, wherein the program code can be stored in a computer storage medium.

[0053] Example 1

[0054] The present invention provides a method for determining the petrographic phase of microbial carbonate rocks. Figure 1 A schematic diagram of the implementation process of a method for determining microbial carbonate rock facies provided in an embodiment of the present application is shown in FIG. Figure 1 Shown, including:

[0055] Step S101 : obtaining lithofacies data of microbial carbonate rocks in a target area and a plurality of well logging curves of sample wells in the target area.

[0056] In the embodiment of the present application, the target area can be a deep-sea area or an area on land. In the embodiment of the present application, the lithofacies can include: limestone, coccolithic microbial rock, granular limestone, lamellar rock, coccolithic microbial rock, etc., and the lithofacies data is the composition of each lithofacies. In an embodiment of the present application, the sample well is a drilled well, and the logging curves may include: natural gamma ray (GR) logging curve, deuranium natural gamma ray (CGR) logging curve, photoelectric absorption cross section index (PE) logging curve, density (DEN) logging curve, neutron (CNL) logging curve, nuclear magnetic resonance free water porosity (CMFF) logging curve, nuclear magnetic resonance effective porosity (CMRP_3MS) logging curve, nuclear magnetic resonance total porosity (TCMR) logging curve, acoustic wave (AC) logging curve, formation true resistivity (RT) logging curve, formation flushing zone resistivity (RXO) logging curve, natural gamma ray spectrum logging potassium (K) logging curve, thorium (TH) logging curve and uranium (U) logging curve.

[0057] In the embodiment of the present application, the petrographic data of the microbial carbonate rock in the target area and the multiple logging curves of the sample wells in the target area can be obtained through input of the input device, or the petrographic data of the microbial carbonate rock in the target area and the multiple logging curves of the sample wells in the target area can be obtained through the network.

[0058] Step S102: determining at least one data set based on the lithofacies data, wherein the similarity between the lithofacies data in each data set is greater than a similarity threshold.

[0059] In an embodiment of the present application, the lithofacies data can be divided into at least one data set based on the geological stratification information of the target area; lithofacies below a preset threshold are determined based on the core data of the target area; and lithofacies data corresponding to lithofacies below the preset threshold in each data set are removed. The core data is experimentally obtained data on the composition of each core. In an embodiment of the present application, the same data set corresponds to a geological layer or group, and the similarity between the lithofacies data in each data set within the same data set is greater than the similarity threshold, indicating that the lithofacies distribution within the same layer or group is similar and relatively stable.

[0060] In the embodiment of the present application, multiple data sets may be included. For example, the lithofacies data are divided into a data set corresponding to an upper layer segment and a data set corresponding to a lower layer segment.

[0061] In the embodiment of the present application, in order to reduce the difficulty of training, the lithofacies data in each data set that is less than a preset threshold can be removed. In the embodiment of the present application, the proportion of data corresponding to the main lithologic type in each data set is greater than 85%.

[0062] In the embodiment of the present application, determining at least one data set through lithofacies data can enhance the geological constraints of the lithofacies data and reduce the imbalance of the data.

[0063] Step S103: performing importance analysis on multiple well logging curves to determine a target well logging curve.

[0064] In this embodiment of the present application, a significance analysis can be performed on multiple well logging curves to determine a target well logging curve. In this embodiment of the present application, a significance analysis can be performed on multiple well logging curves to obtain a calculated result; the calculated result is sorted to obtain a sorted result; and the well logging curve corresponding to the sorted result that exceeds a significance threshold is determined as the target well logging curve. In this embodiment of the present application, the significance calculation result is distributed between 0 and 1, with a larger value indicating a greater role of the feature in the prediction.

[0065] In the embodiment of the present application, the target logging curves may include: a natural gamma ray spectrum logging potassium curve, a natural gamma ray spectrum logging thorium curve, and a natural gamma ray spectrum logging uranium curve.

[0066] Step S104: determining a target prediction model based on at least one data set and the target well logging curve, so as to identify the microbial carbonate lithofacies based on the target prediction model.

[0067] In an embodiment of the present application, an initial model of a target algorithm is obtained, and the target algorithm includes: a K-nearest neighbor algorithm, a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, a gradient boosting decision tree algorithm, and a random forest algorithm; each initial model is trained with a target logging curve as input and each data set as output of each initial model; the accuracy of each initial model after training is determined; and a target prediction model is determined at least based on the accuracy.

[0068] In some embodiments, the training time of each initial model is determined; and the target prediction model is determined based on the training time and the accuracy.

[0069] In an embodiment of the present application, the target prediction model is obtained based on the initial model training of the random forest algorithm.

[0070] In an embodiment of the present application, after determining the target prediction model, after obtaining the natural gamma ray spectrum logging potassium curve, the natural gamma ray spectrum logging thorium curve and the natural gamma ray spectrum logging uranium curve, the natural gamma ray spectrum logging potassium curve, the natural gamma ray spectrum logging thorium curve and the natural gamma ray spectrum logging uranium curve can be input into the model to identify the microbial carbonate rock phase.

[0071] The present application provides a method for determining microbial carbonate rock facies. The method determines at least one data set through lithofacies data, wherein the similarity between the lithofacies data in each data set is greater than a similarity threshold, thereby reducing data imbalance. An importance analysis is then performed on multiple well logging curves to determine a target well logging curve. A target prediction model is constructed based on the at least one data set and the target well logging curve to identify the microbial carbonate rock facies based on the target prediction model, thereby improving the accuracy of identifying the microbial carbonate rock facies.

[0072] Example 2

[0073] Based on the above embodiments, the present invention further provides a method for determining the petrographic phase of microbial carbonate rocks. Figure 2 A schematic diagram of the implementation process of a method for determining microbial carbonate rock facies provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0074] Step S201: Data preprocessing method based on geological characteristics.

[0075] In the examples of this application, based on geological stratification and core data, lithofacies were statistically analyzed by layer and group to determine the main lithofacies types (cumulatively accounting for more than 85%). The lithofacies distribution within the same layer or group is similar and relatively stable. The advantages of this data preprocessing method are mainly reflected in two aspects: first, it strengthens the geological constraints on the original data; second, it reduces data imbalance.

[0076] Step S202: determining key logging curve parameters.

[0077] Microbial carbonate lithofacies can be divided into 12 types. Due to the similar composition of these lithofacies, their logging characteristics overlap significantly, necessitating the identification of sensitive logging parameters. Through sensitivity and importance analysis of 14 conventional well logs, natural gamma ray spectroscopy logging of uranium (U), potassium (K), and thorium (TH) has been identified as key logging parameters for microbial carbonate lithofacies identification.

[0078] Step S203: Optimize the machine learning algorithm.

[0079] The selection of machine learning algorithms is primarily evaluated based on two criteria: learning accuracy and learning time. Using data from practical applications, this paper compared the lithofacies prediction results of six machine learning algorithms: K-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), support vector machine (SVM), gradient boosted decision tree (GBDT), and random forest (RF). The results showed that the random forest (RF) algorithm achieved the highest prediction accuracy for microbial carbonate lithofacies, exceeding 80%.

[0080] The determination of microbial carbonate lithofacies provided in the embodiments of the present application groups and optimizes data under the constraints of geological conditions, providing a reliable basis for the identification of microbial carbonate lithofacies. The important logging parameters for lithofacies classification were determined to be uranium (U), potassium (K), and thorium (TH). Six machine learning algorithms were compared, and the test results showed that the model RF is suitable for the automatic identification of microbial carbonate lithofacies. Therefore, identification through the model RF can effectively and accurately identify microbial carbonate lithofacies with an accuracy rate of more than 80%.

[0081] Example 3

[0082] Based on the aforementioned embodiments, this application provides another specific example of a method for determining microbial carbonate facies. Taking the microbial carbonate rocks of the Lower Cretaceous Barra Velha Formation in a certain basin as an example, the application effects of the present invention are described in detail. Three wells in an oil field in a certain basin were selected, each with 14 well logs. The Barra Velha Formation contains 12 lithofacies. The determination process is as follows:

[0083] Step S1: Data preprocessing based on geological characteristics.

[0084] The lithofacies of the microbial carbonate rocks in the Barra Velha Formation are controlled by paleoenvironment and water bodies, and the lithofacies changes in the vertical direction are regular. The upper interval is dominated by stromatolite, while the lower interval is dominated by coccolithic microbial rocks and lamellar rocks.

[0085] Combined with the sedimentary environment and lithofacies characteristics, the original data (the same lithofacies data in the above embodiment) are divided into two groups: the upper layer section and the lower layer section, that is, two data sets. The lithofacies proportions of the two groups are quite different. For example, the lithofacies with a larger proportion in the upper layer section are stromatolite (42%), coccolith microbial rock (18%) and granular limestone (13%), while the lower layer section is mainly composed of lamellar rock (50%) and coccolith microbial rock (29%). Some lithofacies such as crystalline limestone and dolomite account for less than 5%, which will interfere with the training of the machine learning model. Therefore, lithofacies with a cumulative proportion of more than 85% are selected to enter the model.

[0086] According to the statistical results, the main lithofacies of the upper section are determined to be stromatolime, coccolithic microbial rock, granular limestone, lamellar rock and breccia limestone; the main lithofacies of the lower section are coccolithic microbial rock, lamellar rock and stromatolime.

[0087] Step S2: determining key parameters of well logging response.

[0088] Each well has 14 logs: gamma ray (GR), deuranium-depleted gamma ray (CGR), photoelectric absorption cross section index (PE), density (DEN), neutron ray (CNL), nuclear magnetic resonance free water porosity (CMFF), nuclear magnetic resonance effective porosity (CMRP_3MS), nuclear magnetic resonance total porosity (TCMR), acoustic wave (AC), true formation resistivity (RT), flushed zone resistivity (RXO), and gamma ray spectrometry for potassium (K), thorium (TH), and uranium (U). A decision tree approach was used to analyze the feature importance of each of the 14 logs. The results range from 0 to 1, with larger values ​​indicating a greater predictive value for the feature. Figure 3 A schematic diagram of calculation results provided in an embodiment of the present application is shown as follows: Figure 3 As shown in the figure, the results show that U, K, and TH are the most important logging response parameters, followed by RXO, RT, and PE. Therefore, the target logging curve is determined to be U, K, and TH of the natural gamma ray spectrum logging.

[0089] Step S3: Optimizing a machine learning algorithm.

[0090] In the embodiment of the present application, six machine learning models including K-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), support vector machine (SVM), gradient boosting decision tree (GBDT) and random forest (RF) were selected for training and testing, and the tests and comparisons were performed on the divided data sets to select the optimal model (the same as the target prediction model in the above embodiment). There are 429 data in the upper layer data set and 615 data in the lower layer data set. In each data set, one quarter of the data is used as test data and the rest as training data, and the training data is set to perform five-fold cross-validation in model learning. The selection of the model usually considers two aspects: prediction accuracy and training time. Table 1 shows the lithofacies identification test accuracy and training time of six machine learning models. As shown in Table 1,

[0091] Table 1 Accuracy and training time of lithofacies identification test for six machine learning models

[0092]

[0093]

[0094] As shown in the table, the training and testing results for the upper lithofacies show that RF has the highest test accuracy, at 80.56%, followed by GBDT, at 79.63%. Although the difference between the two test results is not significant, RF takes less time to train than GBDT, resulting in a superior model.

[0095] The lithofacies training test results for the lower interval show that RF has the highest test accuracy, at 85.07%, followed by SVM, at 83.77%. RF and SVM training took 7.24 seconds and 0.27 seconds, respectively. Therefore, if the test results are similar, SVM can be used for prediction.

[0096] Overall, the RF model demonstrates high stability in its lithofacies predictions across both datasets, a finding attributable to the model's inherent characteristics. RF employs a random sampling method with replacement to construct multiple datasets, selecting features at random, effectively overcoming the limited and uneven lithofacies data. Consequently, the RF model demonstrates the best automatic identification of microbial carbonate lithofacies.

[0097] Through practical applications, the geological feature data preprocessing method proposed in this invention effectively realizes the classification of microbial carbonate lithofacies datasets by strengthening geological constraints and reducing the complexity and imbalance of dataset samples. In addition, a feature importance analysis of 14 well logging responses revealed that U, K, and Th from natural gamma ray spectroscopy logging are important parameters for identifying microbial carbonate lithofacies. On this basis, by comparing six machine learning models, the RF learning model performed best in the test, and it is believed that this model is suitable for the identification of complex microbial carbonate lithofacies. This method has been applied to the automatic identification of microbial lithofacies in 26 wells in several oil fields in the Santos Basin, Brazil. When compared with the core description results of the coring section, the accuracy rate reached 83.67%.

[0098] Example 4

[0099] Based on the foregoing embodiments, an embodiment of the present application provides a device for determining microbial carbonate rock facies. The modules included in the device, and the units included in each module, can be implemented by a processor in a computer device; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0100] The present application provides a device for determining the petrographic phase of microbial carbonate rocks. Figure 4 A schematic diagram of the structure of a microbial carbonate rock phase provided in the embodiment of this application is shown as follows: Figure 4 As shown, the device 400 for determining microbial carbonate rock facies includes:

[0101] The first acquisition module 401 is used to acquire the petrographic data of microbial carbonate rocks in the target area and multiple logging curves of sample wells in the target area;

[0102] A first determining module 402 is configured to determine at least one data set based on the lithofacies data, wherein the similarity between the lithofacies data in each data set is greater than a similarity threshold;

[0103] The second determination module 403 is used to perform importance analysis on multiple well logging curves and determine a target well logging curve;

[0104] The third determination module 404 is configured to determine a target prediction model based on at least one data set and the target well logging curve, so as to identify the microbial carbonate lithofacies based on the target prediction model.

[0105] In some embodiments, the first determining module includes:

[0106] a grouping unit, which groups the lithofacies data into at least one data set based on geological stratification information of the target area;

[0107] A removal unit is configured to determine lithofacies smaller than a preset threshold based on the core data of the target area; and remove lithofacies data corresponding to lithofacies smaller than the preset threshold from each data set;

[0108] In some embodiments, the second determining module includes:

[0109] The first calculation unit is used to perform importance analysis on multiple logging curves to obtain importance calculation results;

[0110] A sorting unit, configured to sort the importance calculation results to obtain an importance sorting result;

[0111] The first determining unit is configured to determine, in the importance ranking results, a well logging curve corresponding to an importance calculation result greater than a preset importance threshold as a target well logging curve.

[0112] In some embodiments, the target logging curves include: a natural gamma ray spectrum logging potassium curve, a natural gamma ray spectrum logging thorium curve, and a natural gamma ray spectrum logging uranium curve.

[0113] In some embodiments, the third determining module includes:

[0114] An acquisition unit is used to acquire an initial model of a target algorithm, wherein the target algorithm includes: a K-nearest neighbor algorithm, a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, a gradient boosting decision tree algorithm, and a random forest algorithm;

[0115] A training unit is used to train each initial model using the target well logging curve as the input of each initial model and each data set as the output of each initial model;

[0116] A second determining unit is used to determine the accuracy of each initial model after training;

[0117] The third determining unit is configured to determine a target prediction model based at least on the accuracy rate.

[0118] In some embodiments, the method further comprises:

[0119] A fourth determining unit, configured to determine the training time of each initial model;

[0120] The third determining unit is used to determine a target prediction model based on the training time and the accuracy.

[0121] In some embodiments, the target prediction model is obtained based on initial model training of a random forest algorithm.

[0122] It should be noted that, in the embodiment of the present application, if the above-mentioned method for determining the microbial carbonate rock phase is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read Only Memory), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0123] Accordingly, an embodiment of the present application provides a storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps in the method for determining the microbial carbonate rock facies provided in the above embodiment are implemented.

[0124] Example 5

[0125] An embodiment of the present application provides an electronic device; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 5As shown, the electronic device 700 includes: a processor 701, at least one communication bus 702, a user interface 703, at least one external communication interface 704, and a memory 705. The communication bus 702 is configured to facilitate communication between these components. The user interface 703 may include a display screen, and the external communication interface 704 may include standard wired and wireless interfaces. The processor 701 is configured to execute a program for determining microbial carbonate rock facies stored in the memory to implement the steps of the method for determining microbial carbonate rock facies provided in the above-described embodiment.

[0126] The description of the above electronic device and storage medium embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the electronic device and storage medium embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0127] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0128] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0129] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0131] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0132] In addition, all functional units in the embodiments of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the above-mentioned integrated units can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0133] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROMs), magnetic disks, optical disks, and other media that can store program codes.

[0134] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0135] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for determining microbial carbonate rock facies, characterized in that: include: Obtaining petrographic data of microbial carbonate rocks in a target area and a plurality of well logging curves of sample wells in the target area; determining at least one data set based on the petrographic data, wherein the similarity between the petrographic data in each data set is greater than a similarity threshold; Wherein, determining at least one data set based on the lithofacies data includes: dividing the lithofacies data into at least one data set based on geological stratification information of the target area; Determining lithofacies less than a preset threshold based on core data of the target area; Remove the lithofacies data corresponding to the rock phases smaller than the preset threshold in each data set; The step of dividing the lithofacies data into at least one data set based on the geological stratification information of the target area includes: According to the geological stratification information of the target area, the lithofacies data is divided into a data set corresponding to an upper layer section and a data set corresponding to a lower layer section; wherein the main lithofacies of the upper layer section are stromatolitic limestone, spherulitic microbialite, granular limestone, lamellar rock and breccia limestone, and the main lithofacies of the lower layer section are spherulitic microbialite, lamellar rock and stromatolitic limestone; Performing importance analysis on multiple logging curves to determine target logging curves; wherein the target logging curves include natural gamma ray spectrum logging potassium curve, natural gamma ray spectrum logging thorium curve and natural gamma ray spectrum logging uranium curve; A target prediction model is determined based on at least one data set and the target well log curve, so as to identify the microbial carbonate facies based on the target prediction model.

2. The method according to claim 1, characterized in that The performing of importance analysis on multiple well logging curves to determine a target well logging curve includes: Perform importance analysis on multiple logging curves to obtain importance calculation results; Sorting the importance calculation results to obtain an importance ranking result; The well logging curve corresponding to the importance calculation result greater than a preset importance threshold in the importance ranking result is determined as the target well logging curve.

3. The method according to claim 1, characterized in that The determining of a target prediction model based on at least one data set and the target well logging curve comprises: Obtaining an initial model of a target algorithm, wherein the target algorithm includes: K-nearest neighbor algorithm, decision tree algorithm, logistic regression algorithm, support vector machine algorithm, gradient boosting decision tree algorithm, and random forest algorithm; Each initial model is trained using the target well logging curve as input and each data set as output; Determine the accuracy of each initial model after training; A target prediction model is determined based at least on the accuracy.

4. The method according to claim 3, characterized in that The method further comprises: Determine the training time of each initial model; The determining of the target prediction model based at least on the accuracy rate includes: A target prediction model is determined based on the training time and the accuracy.

5. The method according to claim 4, characterized in that The target prediction model is obtained based on the initial model training of the random forest algorithm.

6. A device for determining microbial carbonate rock facies, characterized in that: include: A first acquisition module is used to acquire petrographic data of microbial carbonate rocks in a target area and multiple well logging curves of sample wells in the target area; A first determining module is configured to determine at least one data set based on the lithofacies data, wherein the similarity between the lithofacies data in each data set is greater than a similarity threshold; Wherein, the first determining module is further configured to: dividing the lithofacies data into at least one data set based on geological stratification information of the target area; Determining lithofacies less than a preset threshold based on core data of the target area; Remove the lithofacies data corresponding to the rock phases smaller than the preset threshold in each data set; Wherein, the first determining module is further configured to: According to the geological stratification information of the target area, the lithofacies data is divided into a data set corresponding to an upper layer section and a data set corresponding to a lower layer section; wherein the main lithofacies of the upper layer section are stromatolitic limestone, spherulitic microbialite, granular limestone, lamellar rock and breccia limestone, and the main lithofacies of the lower layer section are spherulitic microbialite, lamellar rock and stromatolitic limestone; The second determination module is configured to perform importance analysis on the plurality of well logging curves to determine a target well logging curve; wherein the target well logging curves include a natural gamma ray spectrum logging potassium curve, a natural gamma ray spectrum logging thorium curve, and a natural gamma ray spectrum logging uranium curve; The third determination module is configured to determine a target prediction model based on at least one data set and the target well logging curve, so as to identify the microbial carbonate rock facies based on the target prediction model.

7. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method for determining the microbial carbonate rock facies according to any one of claims 1 to 5 is executed.

8. A computer-readable storage medium, characterized in that The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the method for determining the microbial carbonate rock facies as claimed in any one of claims 1 to 5.

Images