Deposition microfacies recognition method and device, electronic equipment and medium

Abstract

A sedimentary microfacies recognition method and device, electronic equipment and medium are disclosed. The method can include: determining a sensitive well logging curve; determining an optimal well logging intrinsic mode function according to the sensitive well logging curve; performing empirical mode decomposition on seismic data of a well-side seismic trace to obtain multiple groups of seismic data intrinsic mode functions, and then determining an optimal seismic data intrinsic mode function; and recognizing a sedimentary microfacies in a target layer seismic data volume according to the optimal seismic data intrinsic mode function. The present application effectively combines the information of seismic and well logging, recognizes the sedimentary microfacies according to the characteristics of the well point sedimentary microfacies sensitive well logging curve, constrains the seismic inversion by the well logging data, improves the resolution of the inversion result, and can effectively recognize the planar sedimentary microfacies of the target layer section.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of oil exploration, more particularly, to a sedimentary microfacies identification method and device, electronic equipment and medium. BACKGROUND

[0002] Sedimentary microfacies identification is the basis of oil and gas exploration and development. Traditional sedimentary microfacies analysis is generally based on personal experience of geologists and a large amount of manual identification, which has poor repeatability and low work efficiency, and is difficult to objectively depict sedimentary microfacies.

[0003] In recent years, the research on conventional planar sedimentary microfacies generally uses logging facies and seismic facies for sedimentary microfacies analysis. Logging facies is defined by studying the combination of logging curve changes to determine the corresponding sedimentary microfacies. For example, wavelet analysis technology is used to establish an accurate stratigraphic framework, and gray system theory analysis technology is used to study the logging facies and sedimentary microfacies of the Fengrichuan oilfield; wavelet analysis is performed on the direction probability density function of the logging curve shape reflecting different sedimentary microfacies, so that the sedimentary microfacies information is mapped from a high-dimensional feature space to a low-dimensional feature vector space composed of a few low-frequency wavelets, and the difference information between different sedimentary microfacies is highlighted; artificial neural network and fractal geometry pattern recognition mathematical methods are applied to follow the thinking mode of geologists to study the sedimentary microfacies interpretation method of logging data; in view of the inadaptability of some existing sedimentary microfacies automatic identification models and algorithms, a method combining genetic-BP algorithm and image processing technology is proposed; principal component analysis and Bayes discriminant analysis methods are used to establish a logging-sedimentary microfacies numerical model of the upper member of the Guan Formation in the Chengdao oilfield; the geological data in the conventional logging data and its interpretation results are combined with the core data, and the characteristics reflecting the change of sedimentary microfacies are extracted through principal component analysis (PCA) and independent component analysis (ICA), respectively, and a support vector machine (SVM) is used to establish a sedimentary microfacies discrimination model, and the sedimentary microfacies of the non-cored well section is automatically identified according to the model. Seismic facies refers to the comprehensive response of a specific sedimentary facies or geological body in the combination of seismic amplitude, phase, continuity and reflection characteristics.

[0004] With the introduction of the concept of "seismic sedimentology", seismic data plays an important role in the identification of sand bodies in braided river delta, meandering river, and lake fan sedimentary systems. For example, to improve the prediction accuracy of reservoir sedimentary microfacies, a waveform-microfacies quantitative characterization comprehensive interpretation technology based on waveform relative change under the constraint of high-precision sequence stratigraphic framework is proposed; Bayes discriminant method is used to establish the correlation between multiple seismic attributes and sedimentary microfacies, and to quantitatively predict channel microfacies; seismic microfacies clustering analysis, seismic along-layer coherence analysis, seismic attribute information optimization, neural network seismic waveform classification, and full three-dimensional reservoir feature inversion are used for seismic microfacies analysis and sedimentary microfacies division in Dagang beach exploration area.

[0005] At present, the field of using three-dimensional seismic data to study sedimentary microfacies in well-seismic combination is developing rapidly at home and abroad. For example, with the help of three-dimensional seismic data, well-seismic combination is fully realized in dense well pattern area, and seismic attributes are reasonably converted into sedimentary parameters, so as to better reproduce the planar distribution of sedimentary microfacies; the seismic information is converted into sedimentary parameters by using well-seismic combination method, so as to establish a river facies sedimentary model to effectively constrain the phase-controlled random modeling; for lithologic and structural-lithologic oil and gas reservoirs, a set of methods of "single well determination of zone, attribute wave form comprehensive edge determination, frequency verification, and mode constraint microfacies mapping" are summarized.

[0006] However, there are certain limitations in using logging or seismic data alone for sedimentary microfacies analysis. It is difficult to compare wells within a short-term cycle, and it is difficult to control the regional planar sedimentary facies belt. Seismic data has great advantages for regional research, and the sedimentary microfacies identification method based on three-dimensional seismic work area is currently relatively mature, but in a relatively large two-dimensional seismic work area, because the longitudinal and lateral resolution is less than the target body, the predecessors can only do sedimentary subfacies. Well-seismic combination is generally implemented in three-dimensional seismic work area with high well spacing, which is not suitable for two-dimensional work area.

[0007] Therefore, it is necessary to develop a sedimentary microfacies identification method, device, electronic equipment and medium based on upscaling frequency coupling.

[0008] The information disclosed in the background section of this application is only intended to deepen the understanding of the general background of the application, and should not be regarded as acknowledging or implying in any form that the information constitutes prior art known to those skilled in the art. SUMMARY

[0009] The present application provides a sedimentary microfacies identification method, device, electronic equipment and medium, which effectively combines seismic and logging information, identifies sedimentary microfacies according to the characteristics of well point sedimentary microfacies sensitive logging curve, and improves the resolution of the inversion result by using logging data to constrain seismic inversion, so as to effectively identify the planar sedimentary microfacies of the target layer.

[0010] In a first aspect, the embodiments of the present disclosure provide a sedimentary microfacies identification method, comprising:

[0011] determining a sensitive logging curve;

[0012] determining an optimal logging intrinsic mode function according to the sensitive logging curve;

[0013] performing empirical mode decomposition on seismic data of a well-side seismic trace to obtain a plurality of groups of seismic data intrinsic mode functions, and then determining an optimal seismic data intrinsic mode function;

[0014] According to the optimal seismic data intrinsic mode function, sedimentary microfacies are identified in a seismic data volume of a target layer.

[0015] Preferably, determining the optimal logging intrinsic mode function according to the sensitive logging curve comprises:

[0016] Performing empirical mode decomposition on the sensitive logging curve to obtain a plurality of groups of logging intrinsic mode functions;

[0017] Establishing a corresponding relationship between each group of logging intrinsic mode functions and sedimentary microfacies to determine the optimal logging intrinsic mode function.

[0018] Preferably, determining the optimal logging intrinsic mode function comprises:

[0019] Determining a logging intrinsic mode function that has a good corresponding relationship with a sedimentary microfacies division interface, and recording the logging intrinsic mode function as the optimal logging intrinsic mode function.

[0020] Preferably, determining the optimal seismic data intrinsic mode function comprises:

[0021] Calculating a seismic data intrinsic mode function that has the best matching relationship with the optimal logging intrinsic mode function, and recording the seismic data intrinsic mode function as the optimal seismic data intrinsic mode function.

[0022] Preferably, according to the optimal seismic data intrinsic mode function, sedimentary microfacies are identified in a seismic data volume of a target layer.

[0023] Importing the optimal seismic data intrinsic mode function as a recognition marker into the seismic data volume of the target layer;

[0024] Through a K-nearest neighbor deep learning frequency inversion method, sedimentary microfacies are identified from the recognized seismic data volume.

[0025] As a specific implementation manner of the embodiments of the present disclosure,

[0026] In a second aspect, the embodiments of the present disclosure further provide a sedimentary microfacies identification device, comprising:

[0027] A sensitive logging curve determination module determines a sensitive logging curve;

[0028] An optimal logging intrinsic mode function determination module determines an optimal logging intrinsic mode function according to the sensitive logging curve;

[0029] An optimal seismic data intrinsic mode function determination module performs empirical mode decomposition on seismic data of a wellside seismic trace to obtain a plurality of groups of seismic data intrinsic mode functions, and further determines an optimal seismic data intrinsic mode function;

[0030] The identification module identifies sedimentary microfacies in the seismic data volume of the target layer according to the optimal seismic data intrinsic mode function.

[0031] Preferably, determining the optimal logging intrinsic mode function according to the sensitive logging curve comprises:

[0032] Performing empirical mode decomposition on the sensitive logging curve to obtain a plurality of groups of logging intrinsic mode functions;

[0033] Establishing a corresponding relationship between each group of logging intrinsic mode functions and the sedimentary microfacies, and determining the optimal logging intrinsic mode function.

[0034] Preferably, determining the optimal logging intrinsic mode function comprises:

[0035] Determining a logging intrinsic mode function that has a good corresponding relationship with the sedimentary microfacies division interface as the optimal logging intrinsic mode function.

[0036] Preferably, determining the optimal seismic data intrinsic mode function comprises:

[0037] Calculating a seismic data intrinsic mode function that has the best matching relationship with the optimal logging intrinsic mode function as the optimal seismic data intrinsic mode function.

[0038] Preferably, identifying the sedimentary microfacies in the seismic data volume of the target layer according to the optimal seismic data intrinsic mode function comprises:

[0039] Importing the optimal seismic data intrinsic mode function as a recognition mark into the seismic data volume of the target layer;

[0040] Identifying the sedimentary microfacies from the recognized seismic data volume by a K-nearest neighbor deep learning frequency inversion method.

[0041] In a third aspect, the embodiments of the present disclosure further provide an electronic device, which comprises:

[0042] A memory storing executable instructions;

[0043] A processor running the executable instructions in the memory to implement the sedimentary microfacies identification method.

[0044] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable storage medium storing a computer program, which is executed by a processor to implement the sedimentary microfacies identification method.

[0045] The method and device of the present application have other characteristics and advantages, which will be apparent from or will be set forth in more detail in the accompanying drawings and the subsequent detailed description, which together serve to explain certain principles of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0046] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout the figures, and in which:

[0047] Figure 1 A flow chart showing the steps of a depositional facies identification method according to one embodiment of the present application.

[0048] Figure 2 A schematic diagram showing a determined depositional facies type according to one embodiment of the present application.

[0049] Figure 3a and Figure 3b A schematic diagram showing different depositional facies well logging sensitivity curves GR and RD according to one embodiment of the present application.

[0050] Figure 4 A schematic diagram showing 8 sets of logging eigenmode functions according to one embodiment of the present application.

[0051] Figure 5 A schematic diagram showing 8 sets of seismic data eigenmode functions according to one embodiment of the present application.

[0052] Figure 6 A schematic diagram showing depositional subfacies seismic attribute features according to one embodiment of the present application.

[0053] Figure 7 A schematic diagram showing a depositional facies well tie profile according to one embodiment of the present application.

[0054] Figure 8 A block diagram of a depositional facies identification device according to one embodiment of the present application.

[0055] BRIEF DESCRIPTION OF DRAWINGS

[0056] 201, sensitive well logging curve determination module; 202, optimal logging eigenmode function determination module; 203, optimal seismic data eigenmode function determination module; 204, identification module. DETAILED DESCRIPTION

[0057] Preferred embodiments of the present application will be described in more detail below. Although the following describes preferred embodiments of the present application, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein.

[0058] The present application provides a method for depositing microfacies recognition, comprising:

[0059] Determine sensitive well logging curves.

[0060] Specifically, by making AC, GR, SP and other curve histograms, analyze and find well logging curves that are more sensitive to changes in sedimentary microfacies.

[0061] According to the sensitive well logging curves, determine the optimal well logging intrinsic mode function; in one example, determining the optimal well logging intrinsic mode function according to the sensitive well logging curves comprises: performing empirical mode decomposition on the sensitive well logging curves to obtain multiple groups of well logging intrinsic mode functions; establishing a correspondence between each group of well logging intrinsic mode functions and sedimentary microfacies to determine the optimal well logging intrinsic mode function. In one example, determining the optimal well logging intrinsic mode function comprises: determining a well logging intrinsic mode function that has a good correspondence with the sedimentary microfacies division interface, and recording it as the optimal well logging intrinsic mode function.

[0062] Specifically, when the sedimentary microfacies determined according to the well logging data is determined, the sensitive well logging curves at the corresponding depth are selected for empirical mode decomposition (EMD), and multiple groups of intrinsic mode function (IMF) components can be obtained. Different IMFs represent different scale information in the well logging data.

[0063] Analyze the correspondence between different IMFs in the well logging data and the sedimentary microfacies. Select a group of IMFs in the well logging data, so that both have a good correspondence with the sedimentary microfacies division interface, and record it as the optimal well logging intrinsic mode function.

[0064] Perform empirical mode decomposition on the seismic data of the well seismic trace to obtain multiple groups of seismic data intrinsic mode functions, and further determine the optimal seismic data intrinsic mode function; in one example, determining the optimal seismic data intrinsic mode function comprises: calculating the seismic data intrinsic mode function that best matches the optimal well logging intrinsic mode function, and recording it as the optimal seismic data intrinsic mode function.

[0065] Specifically, the seismic data of the wellside seismic trace is selected for EMD, and a plurality of groups of IMF components can be obtained. The selected IMF in the logging data is used for similarity coefficient calculation with each group of IMFs of the wellside seismic trace. When the similarity coefficient is maximum, the matching of the two is best. Since the IMF in the logging data is determined according to the sedimentary microfacies, it can be considered that the IMF (i.e. scale information) of the seismic data at this time has the highest matching with the sedimentary microfacies, and can most accurately reflect the sedimentary microfacies of the target layer, and is recorded as the optimal seismic data intrinsic mode function.

[0066] According to the optimal seismic data intrinsic mode function, the sedimentary microfacies is identified in the seismic data volume of the target layer. In one example, according to the optimal seismic data intrinsic mode function, the sedimentary microfacies is identified in the seismic data volume of the target layer, including: importing the optimal seismic data intrinsic mode function as a recognition mark into the seismic data volume of the target layer; and identifying the sedimentary microfacies from the recognized seismic data volume by a K nearest neighbor deep learning frequency inversion method.

[0067] Specifically, the optimal seismic data intrinsic mode function is imported as a recognition mark into the seismic data volume of the target layer. The sedimentary microfacies is identified from the recognized seismic data volume by a K nearest neighbor (KNN) deep learning frequency inversion method, that is, by extracting the frequency attribute in the seismic waveform attribute corresponding to the known well sedimentary microfacies, a training model of different sedimentary microfacies is established by a clustering analysis algorithm, and on this basis, machine learning of the training model is realized by combining the KNN nearest neighbor algorithm, so that the sedimentary microfacies prediction of the blind well can be realized.

[0068] The application also provides a sedimentary microfacies identification device, including:

[0069] A sensitive logging curve determination module determines a sensitive logging curve.

[0070] Specifically, the AC, GR, SP and other curve histograms are made to analyze and find the logging curve sensitive to the change of the sedimentary microfacies.

[0071] An optimal logging intrinsic mode function determination module determines an optimal logging intrinsic mode function according to the sensitive logging curve. In one example, the optimal logging intrinsic mode function is determined according to the sensitive logging curve, including: performing empirical mode decomposition on the sensitive logging curve to obtain a plurality of groups of logging intrinsic mode functions; establishing a corresponding relationship between each group of logging intrinsic mode functions and the sedimentary microfacies to determine the optimal logging intrinsic mode function. In one example, the optimal logging intrinsic mode function is determined, including: determining the logging intrinsic mode function having a good corresponding relationship with the sedimentary microfacies division interface, and recording it as the optimal logging intrinsic mode function.

[0072] Specifically, when the sedimentary microfacies is determined according to the logging data, the sensitive logging curve at the corresponding depth is selected for empirical mode decomposition (EMD), and a plurality of intrinsic mode function (IMF) components can be obtained. Different IMFs represent information of different scales in the logging data.

[0073] The corresponding relationship between different IMFs in the logging data and the sedimentary microfacies is analyzed. A certain group of IMFs in the logging data is selected, which has a good corresponding relationship with the sedimentary microfacies division interface, and is recorded as the optimal logging intrinsic mode function.

[0074] The optimal seismic data intrinsic mode function determination module performs empirical mode decomposition on the seismic data of the well-side seismic trace to obtain a plurality of groups of seismic data intrinsic mode functions, and further determines the optimal seismic data intrinsic mode function. In one example, determining the optimal seismic data intrinsic mode function includes: calculating the seismic data intrinsic mode function that best matches the optimal logging intrinsic mode function, and recording it as the optimal seismic data intrinsic mode function.

[0075] Specifically, the seismic data of the well-side seismic trace is selected for EMD, and a plurality of IMF components can be obtained. The similarity coefficients are calculated by applying the selected IMFs in the logging data to each group of IMFs of the well-side seismic trace. When the similarity coefficient is the largest, the matching of the two is the best. Since the IMFs in the logging data are determined according to the sedimentary microfacies, it can be considered that the seismic data IMF (i.e. scale information) at this time has the highest matching with the sedimentary microfacies, and can most accurately reflect the sedimentary microfacies of the target layer, and is recorded as the optimal seismic data intrinsic mode function.

[0076] The recognition module identifies the sedimentary microfacies in the target layer seismic data volume according to the optimal seismic data intrinsic mode function. In one example, the recognition module identifies the sedimentary microfacies in the target layer seismic data volume according to the optimal seismic data intrinsic mode function includes: importing the optimal seismic data intrinsic mode function as a recognition mark into the target layer seismic data volume; and identifying the sedimentary microfacies from the recognized seismic data volume by the K-nearest neighbor deep learning frequency inversion method.

[0077] Specifically, the optimal seismic data intrinsic mode function is introduced as a discriminant sign into a seismic data volume of a research target layer. A sedimentary microfacies is identified from the identified seismic data volume by using a K nearest neighbor (KNN) deep learning frequency inversion method, that is, by extracting a frequency attribute in a seismic waveform attribute corresponding to a sedimentary microfacies of a known well, a training model of different sedimentary microfacies is established by using a clustering analysis algorithm, and on this basis, a machine learning is performed on the training model by using a minimum neighbor algorithm KNN, so that a sedimentary microfacies of a blind well can be predicted.

[0078] The present application also provides an electronic device, comprising: a memory storing executable instructions; a processor running the executable instructions in the memory to implement the above-mentioned sedimentary microfacies identification method.

[0079] The present application also provides a computer readable storage medium storing a computer program, which is executed by a processor to implement the above-mentioned sedimentary microfacies identification method.

[0080] In order to facilitate understanding of the scheme and effects of the embodiments of the present application, four specific application examples are given below. Those skilled in the art should understand that the examples are only for the convenience of understanding the present application, and any specific details thereof are not intended to limit the present application in any way.

[0081] Example 1

[0082] Figure 1 A flowchart showing the steps of the sedimentary microfacies identification method according to an embodiment of the present application is shown.

[0083] As shown in Figure 1 , the sedimentary microfacies identification method comprises: step 101, determining a sensitive well logging curve; step 102, determining an optimal well logging intrinsic mode function according to the sensitive well logging curve; step 103, performing empirical mode decomposition on seismic data of a well-side seismic trace to obtain a plurality of groups of seismic data intrinsic mode functions, and then determining an optimal seismic data intrinsic mode function; and step 104, identifying a sedimentary microfacies in a target layer seismic data volume according to the optimal seismic data intrinsic mode function.

[0084] Figure 2 A schematic diagram of a determined sedimentary microfacies type according to an embodiment of the present application is shown.

[0085] Taking a certain group of sedimentary systems in a certain basin as an example, the sedimentary facies are determined through core observation, thin section identification, etc., and are divided into four typical sedimentary subfacies (intra-platform beach, inter-beach sea, platform flat, lagoon), which can be further divided into five sedimentary microfacies, such as Figure 2 sand beach, cloud flat, micritic limestone, dolomitic limestone, and dolomitic limestone, as shown in

[0086] Figure 3a and Figure 3b shows a schematic diagram of different deposition microfacies well sensitivity curves GR and RD according to one embodiment of the application.

[0087] Figure 4 shows a schematic diagram of 8 groups of well inherent mode functions according to one embodiment of the application.

[0088] Figure 5 shows a schematic diagram of 8 groups of seismic data inherent mode functions according to one embodiment of the application.

[0089] By analyzing its logging response characteristics, it is found that the two curves of GR and RD are relatively sensitive to the deposition microfacies, as shown in Figure 3a , Figure 3b By making a synthetic record, the GR and RD logging data in the depth domain are converted to the time domain. When the deposition microfacies determined according to the geological research target is determined, the GR and RD logging data in the corresponding period are selected for empirical mode decomposition to obtain different IMFs. As shown in Figure 4 , Figure 5 The selected IMFs in the GR and RD logging data are applied for similarity calculation with each group of IMFs of the well seismic trace, and when the similarity coefficient is maximum, the matching of the two is best, as shown in Table 1.

[0090] Table 1

[0091]

[0092] Figure 6 shows a schematic diagram of the seismic attribute characteristics of the sedimentary subfacies according to one embodiment of the application.

[0093] The analysis of the identified seismic facies characteristics shows that the western part of the basin as a whole shows medium-weak amplitude medium-difficult continuous parallel-subparallel reflection, and locally shows hill-shaped and chaotic reflection, and the wedge-shaped progradation reflection shows "U-shaped" and nearly symmetrical "striped" distribution. The basin eastwardly transitions from the "S-shaped" wedge-shaped reflection zone to medium-strong amplitude good continuous sheet reflection and medium-weak amplitude medium-difficult continuous parallel-subparallel reflection, as shown in Figure 6 .

[0094] Figure 7 shows a schematic diagram of the sedimentary microfacies well-to-well correlation profile according to one embodiment of the application.

[0095] On the basis of the corresponding sedimentary subfacies of the seismic facies, the well-to-well correlation profile is controlled by single-well sedimentary microfacies calibration and the seismic attribute determined in Table 1, as shown in Figure 7The sedimentary microfacies are identified by using the KNN machine learning method according to the seismic instantaneous frequency of different sedimentary microfacies.

[0096] Example 2

[0097] Figure 8 A block diagram of a sedimentary microfacies identification device is shown according to an embodiment of the present application.

[0098] As shown in the figure, the sedimentary microfacies identification device comprises: Figure 8

[0099] A sensitive logging curve determination module 201 determines a sensitive logging curve.

[0100] An optimal logging intrinsic mode function determination module 202 determines an optimal logging intrinsic mode function according to the sensitive logging curve.

[0101] An optimal seismic data intrinsic mode function determination module 203 performs empirical mode decomposition on seismic data of a well-side seismic trace to obtain a plurality of groups of seismic data intrinsic mode functions, and further determines an optimal seismic data intrinsic mode function.

[0102] An identification module 204 identifies sedimentary microfacies in a target layer seismic data volume according to the optimal seismic data intrinsic mode function.

[0103] As an optional solution, the determination of the optimal logging intrinsic mode function according to the sensitive logging curve comprises:

[0104] Performing empirical mode decomposition on the sensitive logging curve to obtain a plurality of groups of logging intrinsic mode functions.

[0105] Establishing a corresponding relationship between each group of logging intrinsic mode functions and sedimentary microfacies to determine the optimal logging intrinsic mode function.

[0106] As an optional solution, the determination of the optimal logging intrinsic mode function comprises:

[0107] Determining a logging intrinsic mode function having a good corresponding relationship with a sedimentary microfacies division interface, and recording it as the optimal logging intrinsic mode function.

[0108] As an optional solution, the determination of the optimal seismic data intrinsic mode function comprises:

[0109] Calculating a seismic data intrinsic mode function having the best matching with the optimal logging intrinsic mode function, and recording it as the optimal seismic data intrinsic mode function.

[0110] As an optional solution, the identification of the sedimentary microfacies in the target layer seismic data volume according to the optimal seismic data intrinsic mode function comprises: ​

[0111] The optimal seismic data intrinsic mode function is introduced as a discriminant sign into the target layer seismic data volume;

[0112] The sedimentary microfacies is identified from the identified seismic data volume by a K nearest neighbor deep learning frequency inversion method.

[0113] Example 3

[0114] The present disclosure provides an electronic device, which includes a memory storing executable instructions, and a processor running the executable instructions in the memory to implement the above-described sedimentary microfacies identification method.

[0115] The electronic device according to an embodiment of the present disclosure includes a memory and a processor.

[0116] The memory is configured to store non-transitory computer-readable instructions. Specifically, the memory can include one or more computer program products, which can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM), cache, and / or the like. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, and / or the like.

[0117] The processor can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions. In an embodiment of the present disclosure, the processor is configured to run the computer-readable instructions stored in the memory.

[0118] Those skilled in the art should understand that, in order to solve the technical problem of how to obtain a good user experience effect, the present embodiment can also include well-known structures such as a communication bus, an interface, and the like, which should also be included in the protection scope of the present disclosure.

[0119] Detailed descriptions of the present embodiment can be referred to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0120] Example 4

[0121] The present disclosure provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the above-described sedimentary microfacies identification method.

[0122] A computer readable storage medium according to embodiments of the present disclosure has non-transitory computer readable instructions stored thereon. When the non-transitory computer readable instructions are run by a processor, all or part of the steps of the method of the embodiments of the present disclosure described above are performed.

[0123] The computer readable storage medium described above includes, but is not limited to, an optical storage medium (for example, a CD-ROM and a DVD), a magneto-optical storage medium (for example, an MO), a magnetic storage medium (for example, a magnetic tape or a moving hard disk), a medium having a built-in rewritable nonvolatile memory (for example, a memory card), and a medium having a built-in ROM (for example, a ROM cartridge).

[0124] It will be understood by those skilled in the art that the above description of the embodiments of the present application is only for the purpose of exemplarily illustrating the beneficial effects of the embodiments of the present application, and is not intended to limit the embodiments of the present application to any of the examples given.

[0125] The embodiments of the present application have been described above, and the above description is exemplary and is not exhaustive, and is also not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method of depositing microphase recognition, characterized by, The method comprises the following steps: determining a sensitive well logging curve; determining an optimal well logging intrinsic mode function according to the sensitive well logging curve; performing empirical mode decomposition on seismic data of a wellside seismic trace to obtain multiple groups of seismic data intrinsic mode functions, and then determining an optimal seismic data intrinsic mode function; identifying a sedimentary microfacies in a target layer seismic data volume according to the optimal seismic data intrinsic mode function; wherein, determining the optimal well logging intrinsic mode function according to the sensitive well logging curve comprises: performing empirical mode decomposition on the sensitive well logging curve to obtain multiple groups of well logging intrinsic mode functions; establishing a corresponding relationship between each group of well logging intrinsic mode functions and the sedimentary microfacies to determine the optimal well logging intrinsic mode function; wherein, determining the optimal seismic data intrinsic mode function comprises: calculating a seismic data intrinsic mode function that best matches the optimal well logging intrinsic mode function, and recording the seismic data intrinsic mode function as the optimal seismic data intrinsic mode function; applying the selected IMF in the well logging data to perform similarity coefficient calculation on each group of IMFs of the wellside seismic trace, and when the similarity coefficient is the largest, the matching of the two is the best; wherein, identifying the sedimentary microfacies in the target layer seismic data volume according to the optimal seismic data intrinsic mode function comprises: importing the optimal seismic data intrinsic mode function as a recognition symbol into the target layer seismic data volume; identifying the sedimentary microfacies from the recognized seismic data volume by a K nearest neighbor deep learning frequency inversion method.

2. The depositional microfacies recognition method of claim 1, wherein, determining the optimal well logging intrinsic mode function comprises: determining a well logging intrinsic mode function that has a good corresponding relationship with a sedimentary microfacies division interface, and recording the well logging intrinsic mode function as the optimal well logging intrinsic mode function.

3. A deposited microphase recognition device, characterized by, The method comprises: a sensitive well logging curve determination module that determines a sensitive well logging curve; an optimal well logging intrinsic mode function determination module that determines an optimal well logging intrinsic mode function according to the sensitive well logging curve; an optimal seismic data intrinsic mode function determination module that performs empirical mode decomposition on seismic data of a wellside seismic trace to obtain multiple groups of seismic data intrinsic mode functions, and then determines an optimal seismic data intrinsic mode function; an identification module that identifies a sedimentary microfacies in a target layer seismic data volume according to the optimal seismic data intrinsic mode function; wherein, determining the optimal well logging intrinsic mode function according to the sensitive well logging curve comprises: performing empirical mode decomposition on the sensitive well logging curve to obtain multiple groups of well logging intrinsic mode functions; establishing a corresponding relationship between each group of well logging intrinsic mode functions and the sedimentary microfacies to determine the optimal well logging intrinsic mode function; wherein, determining the optimal seismic data intrinsic mode function comprises: calculating a seismic data intrinsic mode function that best matches the optimal well logging intrinsic mode function, and recording the seismic data intrinsic mode function as the optimal seismic data intrinsic mode function; wherein, identifying the sedimentary microfacies in the target layer seismic data volume according to the optimal seismic data intrinsic mode function comprises: importing the optimal seismic data intrinsic mode function as a recognition symbol into the target layer seismic data volume; identifying the sedimentary microfacies from the recognized seismic data volume by a K nearest neighbor deep learning frequency inversion method.

4. The deposited microphase recognition device of claim 3, wherein, determining the optimal well logging intrinsic mode function comprises: determining a well logging intrinsic mode function that has a good corresponding relationship with a sedimentary microfacies division interface, and recording the well logging intrinsic mode function as the optimal well logging intrinsic mode function. A logging intrinsic mode function corresponding well to the division interface of the sedimentary microfacies is determined, and is denoted as an optimal logging intrinsic mode function.

5. An electronic device, comprising: The electronic device comprises: a memory storing executable instructions; a processor running the executable instructions in the memory to implement the sedimentary microfacies identification method in claim 1 or 2.

6. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the sedimentary microfacies identification method in claim 1 or 2.

Images