Continental facies shale oil and gas horizontal well target window optimization method, device, equipment and medium

Abstract

The invention relates to the technical field of geological exploration, in particular to a continental facies shale oil and gas horizontal well target window optimization method, device and equipment and a medium. The method comprises the following steps: acquiring a lithofacies division result of the inland facies shale oil and gas horizontal well in a target work area; longitudinal lithofacies distribution of the first continental facies shale oil and gas horizontal well is determined, logging curve characteristics of target points in each lithofacies are counted, and a lithofacies recognition sample library is established; establishing a lithofacies identification plate based on the lithofacies identification sample library, and identifying a function relationship between different logging curves of each lithofacies through the lithofacies identification plate; and by means of the function relation, the transverse distribution rule of the interlayer in the stratum of each continental facies shale oil and gas horizontal well in the target work area is longitudinally calibrated, and the target window range of each continental facies shale oil and gas horizontal well is determined. The sweet spot horizon of the whole area can be accurately and efficiently determined, and the target window of the continental facies shale oil and gas horizontal well is preferably selected.

Description

Technical Field

[0001] This disclosure relates to the field of geological exploration technology, and in particular to a method, apparatus, equipment and medium for optimizing the target window of a horizontal well in continental shale oil and gas. Background Technology

[0002] Lithofacies is a comprehensive reflection of the sedimentary and mineralogical characteristics of rocks. It refers to rocks or rock groups formed under specific sedimentary conditions that possess unique lithology (such as mineral composition, structure, sedimentary texture, and organic matter content). Current techniques primarily involve artificially classifying shale lithofacies using core samples, whole-rock mineral content, and organic matter content. Clearly, obtaining core samples from core wells for lithofacies analysis offers the highest reliability and accuracy. However, this method is limited by the availability of core wells, missing wellbore data, and the high cost of experimental analysis, making regional lithofacies classification and the optimal selection of horizontal well target windows difficult.

[0003] Among related technologies, some schemes utilize machine learning to intelligently process well logging curves for intelligent facies classification of continental shale. Geological evaluation of horizontal well target windows mainly focuses on single-factor analysis such as rock and mineral composition, reservoir characteristics, and structural preservation, then comprehensively considers "geology + engineering" to optimize the horizontal well target window. However, these technologies focus on the study of individual shale samples, and face considerable difficulties in identification, prediction, promotion, and application, failing to accurately and efficiently identify sweet spots across the entire area. Summary of the Invention

[0004] This disclosure provides a method, apparatus, equipment, and medium for optimizing target windows in horizontal wells for continental shale oil and gas, so as to accurately and efficiently identify sweet spots in the entire area and optimize target windows in horizontal wells for continental shale oil and gas.

[0005] In a first aspect, this disclosure provides a method for optimizing the target window in a horizontal well for continental shale oil and gas, including:

[0006] Obtain the lithofacies classification results for horizontal wells of continental shale oil and gas in the target work area;

[0007] Determine the vertical lithofacies distribution of horizontal wells in the first continental shale oil and gas field, statistically analyze the logging curve characteristics of target points in each lithofacies, and establish a lithofacies identification sample library;

[0008] A lithofacies identification chart is established based on a lithofacies identification sample library, and the functional relationship between different logging curves for each lithofacies is identified through the lithofacies identification chart.

[0009] Using the aforementioned functional relationship, the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target work area is vertically calibrated, and the target window range of each continental shale oil and gas horizontal well is determined.

[0010] In some embodiments, the lithofacies classification results include: the lithofacies type of the first horizontal well determined based on organic matter abundance, sedimentary structures, and whole-rock mineral composition.

[0011] In some embodiments, the vertical lithofacies distribution of the first continental shale oil and gas horizontal well is determined, the logging curve characteristics of target points in each lithofacies are statistically analyzed, and a lithofacies identification sample library is established, including:

[0012] Using lithological scanning logging data from horizontal wells in the first continental shale oil and gas field, the vertical lithofacies distribution of the horizontal wells in the first continental shale oil and gas field was determined;

[0013] Select target points in each lithofacies along the vertical direction of the first continental shale oil and gas horizontal well;

[0014] The characteristics of the logging curves at each target point are statistically analyzed and depth correction is performed to obtain a lithofacies identification sample library.

[0015] In some embodiments, a lithofacies identification chart is established based on a lithofacies identification sample library, and the functional relationship between different logging curves for each lithofacies is identified through the lithofacies identification chart, including:

[0016] The logging curve features of each lithofacies target point in the lithofacies identification sample library are used as the logging response features of each lithofacies. A cross plot is established, and the cross plot is used as a lithofacies identification chart to identify the functional relationship between different logging curves of each lithofacies.

[0017] In some embodiments, during the drilling process of a first continental shale oil and gas horizontal well, cross plots are continuously established. Each time, the optimal cross plot that identifies the functional relationship between different logging curves of a certain lithofacies is selected, and then a new cross plot that identifies the functional relationship between different logging curves of different lithofacies is established, until the optimal cross plot that identifies the functional relationship between different logging curves of all lithofacies is obtained.

[0018] In some embodiments, a cross-plot graph is constructed using a machine learning method, which includes at least one of decision trees and random forests.

[0019] Secondly, this disclosure provides a preferred target window device for horizontal wells in continental shale oil and gas, comprising:

[0020] The acquisition module is used to obtain the lithofacies classification results of horizontal wells for continental shale oil and gas in the target work area;

[0021] A module was established to determine the vertical lithofacies distribution of horizontal wells in the first continental shale oil and gas field, to statistically analyze the logging curve characteristics of target points in each lithofacies, and to establish a lithofacies identification sample library.

[0022] The identification module is used to establish a lithofacies identification chart based on the lithofacies identification sample library, and to identify the functional relationship between different logging curves for each lithofacies through the lithofacies identification chart;

[0023] The preferred module is used to use the aforementioned functional relationship to vertically calibrate the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target work area, and to determine the target window range of each continental shale oil and gas horizontal well.

[0024] Thirdly, this disclosure provides a computer device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.

[0025] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in the first aspect.

[0026] Fifthly, this disclosure provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the method described in the first aspect.

[0027] This disclosure provides a method, apparatus, equipment, and medium for optimizing target windows in continental shale oil and gas horizontal wells. By obtaining the lithofacies classification results of continental shale oil and gas horizontal wells in the target area, the vertical lithofacies distribution of the first continental shale oil and gas horizontal well in the current target area is determined. The logging curve characteristics of target points in each lithofacies are statistically analyzed, and a lithofacies identification sample library is established. Then, based on the lithofacies identification sample library, a lithofacies identification chart is established to identify the functional relationship between different logging curves of each lithofacies. Using this functional relationship, the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target area can be vertically calibrated, and the target window range of each continental shale oil and gas horizontal well can be determined. Continental shale is characterized by complex lithofacies types, rapid vertical and horizontal variations, and well-developed interlayers. In the case of limited geological data from exploration wells, this disclosure can achieve high-precision, low-time-consuming, and low-cost lithofacies classification, providing a scientific basis for the efficient identification of geological sweet spots in the entire region. It is beneficial for the optimal selection of horizontal well target windows in continental shale and provides a geological basis for segmented fracturing of horizontal wells, showing good application prospects. Attached Figure Description

[0028] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0029] Figure 1 A schematic diagram of the process for optimizing the target window in a continental shale oil and gas horizontal well, provided in an embodiment of this disclosure;

[0030] Figure 2A whole-rock mineral division triangulation diagram provided for embodiments of this disclosure;

[0031] Figure 3 A comprehensive columnar section of the vertical facies division of the shale in the Dongyuemiao section of well FY10 provided in this embodiment of the disclosure;

[0032] Figure 4 The logging response characteristics of different lithofacies in the Dongyuemiao section of well FY10 provided in this embodiment of the present disclosure;

[0033] Figure 5 This is a lithofacies logging cross-plot of the Dongyuemiao section of well FY10 provided in an embodiment of this disclosure;

[0034] Figure 6 The preferred target window for the north-south transverse horizontal well in the Dongyuemiao section of the Fuxing area is provided in the embodiments of this disclosure.

[0035] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0036] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0038] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0039] For intelligent facies classification of continental shale, machine learning is used to intelligently process well logging curves. Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Combined Classifiers (CCs) are among the machine learning methods that have been successfully applied to facies identification and classification under different geological conditions. With the ongoing exploration and development of continental shale, the era of big data has arrived. Big data refers to datasets whose volume and attribute variations exceed the collection, storage, management, and analysis capabilities of existing databases and related software tools. The vast amount of well logging data from each exploration well constitutes big data itself. This disclosure utilizes intelligent analysis of well logging data to scientifically and effectively clarify the facies distribution characteristics within a region, taking into account the heterogeneous distribution of continental shale.

[0040] For the geological evaluation of horizontal well target windows, relevant technologies mainly focus on single-factor analysis such as rock and mineral composition, reservoir characteristics, and structural preservation. Subsequently, the "geology + engineering" factors are comprehensively considered to optimize the horizontal well target window.

[0041] However, the aforementioned technologies mainly focus on the study of individual shale samples, which leads to significant difficulties in identification, prediction, promotion, and application. They cannot accurately and efficiently identify sweet spot strata across the entire region. Lithofacies, as a comprehensive reflection of the physical and chemical properties of rocks, can provide a favorable basis for identifying sweet spot strata across the entire region if accurately identified. The geological evaluation of target windows in horizontal wells in continental shale still suffers from limitations such as considering only one factor, failing to organically combine various geological evaluation elements, and being constrained by missing wellbore data and limited coring wells. This disclosure provides a method, apparatus, equipment, and medium for optimizing target windows in horizontal wells for continental shale oil and gas. By obtaining the lithofacies classification results of horizontal wells in the target area, the vertical lithofacies distribution of the first horizontal well in the current target area is determined. The logging curve characteristics of target points in each lithofacies are statistically analyzed, and a lithofacies identification sample library is established. Then, based on the lithofacies identification sample library, a lithofacies identification chart is established to identify the functional relationship between different logging curves of each lithofacies. Using this functional relationship, the lateral distribution pattern of interlayers within the formation of each horizontal well in the target area can be vertically calibrated, and the target window range of each horizontal well in the continental shale oil and gas area can be determined. Continental shale is characterized by complex lithofacies types, rapid vertical and horizontal variations, and well-developed interlayers. In the case of limited geological data from exploration wells, this disclosure can achieve high-precision, low-time-consuming, and low-cost lithofacies classification, providing a scientific basis for the efficient identification of geological sweet spots in the entire region. It is beneficial for the optimal selection of horizontal well target windows in continental shale and provides a geological basis for segmented fracturing of horizontal wells, showing good application prospects.

[0042] Example 1

[0043] Figure 1 This is a flowchart illustrating a method for optimizing the target window in a continental shale oil and gas horizontal well, as provided in this embodiment. Figure 1 As shown, a method for optimizing the target window in a horizontal well for continental shale oil and gas includes:

[0044] Step S11: Obtain the lithofacies classification results of the continental shale oil and gas horizontal wells in the target work area.

[0045] Before step S11, it is necessary to conduct a fine division of the single-well lithofacies of continental shale oil and gas horizontal wells in the target work area. In a specific embodiment, during the division, analysis and testing methods such as TOC (Total Organic Carbon) analysis, core observation, thin-section observation, whole-rock X-ray diffraction, and scanning electron microscopy are used to accurately divide and identify the lithofacies of typical wells that have been drilled to the continental shale oil and gas reservoir in the target work area. The lithofacies division results include the lithofacies types of the first horizontal well defined based on organic matter abundance, sedimentary structures, and whole-rock mineral composition. The "organic matter abundance + sedimentary structure + whole-rock mineral composition" three-factor division method is used to define the lithofacies types of continental shale. When the total organic carbon content is obtained through TOC analysis, TOC > 2% is defined as high carbon, 1% < TOC < 2% is defined as medium carbon, and TOC < 1% is defined as low carbon, thereby characterizing the organic matter abundance. Based on core observation and thin-section observation of microscopic rock samples, according to the developed thickness of the interlayers, the sedimentary structures of continental shale are divided into laminar (thickness < 1 mm), layered (1 mm < thickness < 10 mm), and massive structures (poorly developed bedding). The clay minerals, felsic minerals (quartz + feldspar), and carbonate minerals mainly developed in continental shale are used as the three end-members for describing the main mineral composition of sedimentary rocks. Following the traditional petrological nomenclature (50%, 25%) and considering the mixed part (the sum of the contents of any two minerals is greater than 70%), the mud shale area, siltstone area, ash (dolomite) rock area, and mixed rock area are divided. The division results are as Figure 2 shown.

[0046] Step S12: Determine the longitudinal lithofacies distribution of the first continental shale oil and gas horizontal well, count the logging curve characteristics of the target points in each lithofacies, and establish a lithofacies identification sample library.

[0047] Lithological composition is one of the main contents of the geological evaluation of shale oil and gas formations. The whole-well ECS (elemental capture spectroscopy) logging data is a relatively common logging technology for determining the rock mineral content in the formation. However, this logging technology uses an americium-beryllium neutron source to continuously emit fast neutrons, and it cannot distinguish the gamma rays of inelastic scattering reactions in the total spectrum, and cannot accurately measure the yields of elements such as carbon and magnesium in the formation. The Litho Scanner developed by Schlumberger in 2012 is an upgraded version of the ECS chemical source logging tool, which can obtain the formation element distribution with high precision and accuracy, and clarify the distribution of mineral content and organic matter content.

[0048] In some embodiments, determining the longitudinal lithofacies distribution of the first continental shale oil and gas horizontal well, counting the logging curve characteristics of the target points in each lithofacies, and establishing a lithofacies identification sample library further includes:

[0049] Step S12a: Using lithological scanning logging data from the first continental shale oil and gas horizontal well, determine the vertical lithofacies distribution of the first continental shale oil and gas horizontal well.

[0050] In this embodiment, the first continental shale oil and gas horizontal well is any typical well within the target work area. Lithology scanning logging data (ECS data) of typical wells obtained using a lithology scanning logging tool are used to clarify the typical vertical lithofacies distribution of a single well.

[0051] Step S12b: Select the target point in each lithofacies of the first continental shale oil and gas horizontal well.

[0052] Step S12c: Statistically analyze the logging curve characteristics of each target point and perform depth correction to obtain a lithofacies identification sample library. The target points are the most typical points among the lithofacies of horizontal wells in first-continental shale oil and gas fields. The lithofacies identification sample library is established by statistically analyzing the logging curve characteristics of these points. Depth correction is performed during the establishment of the sample library to ensure the accuracy of the logging data.

[0053] Step S13: Establish a lithofacies identification chart based on the lithofacies identification sample library, and identify the functional relationship between different logging curves of each lithofacies through the lithofacies identification chart.

[0054] In some embodiments, a lithofacies identification chart is established based on a lithofacies identification sample library, and the functional relationship between different logging curves for each lithofacies is identified through the lithofacies identification chart. This further includes:

[0055] Step S13a: Use the logging curve features of each rock facies target point in the rock facies identification sample library as the logging response features of each rock facies, establish a cross plot, and use the cross plot as a rock facies identification chart to identify the functional relationship between different logging curves of each rock facies.

[0056] In this embodiment, since different rock facies have different response characteristics to various logging curve values, it is necessary to first clarify the logging response characteristics of different rock facies and establish clear boundaries for the rock facies identification chart.

[0057] In some specific implementations, machine learning methods are used to build intersection graphs, including at least one of decision trees (DT) and random forests.

[0058] When using a decision tree to build a cross-plot, where both data training and prediction extend downwards from the root node, a targeted and highly sensitive lithofacies identification chart can be created, identifying the functional relationship between logging curves corresponding to each type of rock.

[0059] In some specific implementations, during the drilling process of a first continental shale oil and gas horizontal well, cross plots are continuously established. Each time, the optimal cross plot that identifies the functional relationship between different logging curves of a certain lithofacies is selected, and then a new cross plot that identifies the functional relationship between different logging curves of different lithofacies is established, until the optimal cross plot that identifies the functional relationship between different logging curves of all lithofacies is obtained.

[0060] In actual construction, new logging data will be continuously generated during drilling. As new data is generated, multiple cross plots can be continuously built. The optimal cross plot is selected one by one to identify a certain lithofacies. The lithofacies are then stripped away step by step to rebuild the cross plot, so that all lithofacies can be identified in the end.

[0061] In other specific implementations, a random forest method is used to select continental shale lithofacies such as high-carbon layered clayey shale and medium-carbon massive clayey shale as categories, and well logging curves such as GR, AC, DEN, CNL, and RT as feature parameters. Random sampling and random feature selection are used to build several decision trees, and the classification result is determined through a voting mechanism.

[0062] The steps of the random forest method include:

[0063] Step 1: Determine the training parameters for the random forest, such as the training sample set S (well logging curves), the feature attribute set F (the correspondence between well logging curve features and lithofacies in the lithofacies identification sample library), the number of decision trees n, and the number of random features m.

[0064] Step 2: Extract the same number of samples with replacement from the training sample set S to form the training sample set Sa.

[0065] Before performing step 2, data normalization processing should be performed on various logging curves. The input curve values ​​are mapped to [0, 1] using the maximum and minimum normalization functions, meaning that the maximum value of the set of curve values ​​is 1 and the minimum value is 0.

[0066] The definition is as follows:

[0067]

[0068] Where, x * x represents the normalized data. min x is the minimum value of the sample data. max This represents the maximum value of the sample data. After normalization, all well logging data values ​​are within the interval [0, 1].

[0069] Step 3: Extract m features without replacement from the feature attribute set F, and retain only the data of these m features in the training sample set Sa to form the training sample set Sb.

[0070] Step 4: Train a CART decision tree using the training sample Sb.

[0071] Step 5: Repeat steps 2 to 4 n times to obtain n decision trees.

[0072] Step 6: Obtain the final result by summarizing the votes and output it.

[0073] In some possible implementations, both decision trees and random forests may be used to build the cross-plot, and the results of the two methods may be fused and corrected.

[0074] Step S14: Using this function relationship, vertically calibrate the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target work area, and determine the target window range of each continental shale oil and gas horizontal well.

[0075] In one specific implementation, the lateral distribution pattern of carbonate interlayers within the formation is clarified by comparing the vertical alignment of different wells. Key well locations, including the aforementioned typical wells (i.e., horizontal wells in the first continental shale oil and gas formation), are arranged laterally using software such as Gxplorer and ResForm. By establishing lithofacies identification charts for different work areas, the continuous vertical lithofacies of a single well can be quickly and conveniently identified using multiple sets of conventional logging data. The established lithofacies identification standards are then applied to other single wells in the current target work area (study area) to clarify the lateral lithofacies distribution pattern in different well areas and optimize the target window for horizontal wells.

[0076] The method in this embodiment can overcome difficulties such as limited core wells, missing wellbore data, and expensive experimental analysis under complex geological conditions of continental shale. It can achieve rapid and effective classification of lithofacies types of target wells, establish a lithofacies identification sample library, combine a large number of logging curves with machine learning methods to establish mapping relationships, effectively establish charts to determine boundaries, clarify the logging response characteristics of different lithofacies, summarize the distribution law of lateral lithofacies in different well areas, optimize the target window of horizontal wells, and provide geological basis for staged fracturing of horizontal wells.

[0077] Example 2

[0078] Corresponding to Embodiment 1, this embodiment provides a target window optimization device for horizontal wells in continental shale oil and gas, comprising:

[0079] The acquisition module is used to obtain the lithofacies classification results of horizontal wells for continental shale oil and gas in the target work area;

[0080] A module was established to determine the vertical lithofacies distribution of horizontal wells in the first continental shale oil and gas field, to statistically analyze the logging curve characteristics of target points in each lithofacies, and to establish a lithofacies identification sample library.

[0081] The identification module is used to establish a lithofacies identification chart based on the lithofacies identification sample library, and to identify the functional relationship between different logging curves for each lithofacies through the lithofacies identification chart;

[0082] The preferred module is used to vertically calibrate the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target work area using functional relationships, and to determine the target window range of each continental shale oil and gas horizontal well.

[0083] For details on the specific implementation of the above modules, please refer to Embodiment 1. These details will not be repeated in this embodiment.

[0084] Example 3

[0085] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in Embodiment 1.

[0086] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic component, for executing the methods in the above embodiments.

[0087] Example 4

[0088] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0089] Example 5

[0090] This embodiment provides a computer program product, including a computer program / instructions, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0091] Computer-readable storage media can be implemented by any type of volatile or non-volatile storage device or a combination thereof. Computer-readable storage media may include, but are not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, and computer storage media (e.g., hard disks, floppy disks, solid-state drives, removable disks, CD-ROMs, DVD-ROMs, Blu-ray discs, etc.).

[0092] Computer-readable storage media may also store at least one computer-executable program / instruction, such as computer-readable instructions. Computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Computer-readable storage media may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions stored on the computer-readable storage medium, the various methods described above can be performed.

[0093] In addition, the computer device may include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (e.g., keyboard, mouse, speakers, etc.).

[0094] The processor can communicate with external devices via the I / O bus through wired or wireless networks.

[0095] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product / computer program product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0096] Example 6

[0097] Based on the above embodiments, this embodiment provides an application example.

[0098] This invention is applied to the exploration and development of continental shale oil and gas in the Dongyuemiao section of the Fuxing area of ​​the Sichuan Basin.

[0099] (1) Core samples were collected from the Dongyuemiao section of key wells XY1, XY2, and FY10 in the Fuxing area. Through core observation, thin section observation, whole-rock X-ray diffraction, and scanning electron microscopy, the Jurassic continental shale in the Fuxing area of ​​the Sichuan Basin was identified into seven main lithofacies as shown in Table 1, namely, low-carbon massive-layered siltstone, low-carbon massive-layered silty clay shale, low-carbon massive shell limestone, medium-carbon massive-layered bioclastic clay shale, medium-carbon massive clay shale, high-carbon lamellar-layered clay shale, and medium-carbon massive-layered limestone shale.

[0100] Table 1. Lithofacies classification of Jurassic continental shale in the Fuxing area of ​​Sichuan Basin

[0101]

[0102]

[0103] (2) Establish a lithofacies identification sample library. Using lithological scanning logging data from the typical well FY10, and corresponding with the artificial lithofacies classification of well FY10, clarify the following: Figure 3 The typical vertical lithofacies distribution of a single well is shown. The most typical point in each lithofacies is selected, and its logging curve characteristics are statistically analyzed to establish a lithofacies identification sample library.

[0104] (3) Clarify the logging response characteristics of different lithofacies and establish clear boundaries on the chart.

[0105] Logging response characteristics of different lithofacies in the Dongyuemiao section of well FY10, such as Figure 4 As shown, clayey shale exhibits medium natural gamma ray (GR), medium-high compensated neutron density (DEN), medium diameter density (CNL), low resistivity (RD), and high acoustic transit time (AC); silty clayey shale typically exhibits medium-low CNL, medium-high DEN, and medium RD; calcareous shale exhibits relatively high RT, relatively low GR, high DEN, low CNL, and low AC; and shell limestone exhibits low GR, high DEN, low AC, low CNL, high RT, and low TH / U. Figure 5 The cross plot shown clearly illustrates the functional relationships for medium-carbon massive-layered argillaceous shale: CNL > 0.2, DEN < 2.838 - 0.0035 * GR; for high-carbon lamellar-layered clayey shale: CNL < 1.57 - 0.004 * AC, DEN < 2.64 & DEN > 2.838 - 0.0035 * GR; and for medium-carbon massive clayey shale: RT < 10 * (1.04 + 0.003 * GR).

[0106] (4) By longitudinally calibrating different well platforms, the lateral distribution pattern of carbonate interlayers within the formation was clarified. The high-carbon laminar-layered clayey shale developed in layers ② and ④ of the Dongyuemiao section is characterized by high organic matter abundance and well-developed calcareous laminae, making it a target window for horizontal wells. The distribution pattern of carbonate interlayers thicker than 10 cm within the lateral horizontal well target windows in different well areas of the Fuxing region was clarified. Layers ② and ④ are geological sweet spots and are favorable target windows for horizontal wells. The target window optimization results are as follows: Figure 6 As shown.

[0107] The solution disclosed herein achieves high-precision, low-time-consuming, and low-cost lithofacies identification even with limited geological data from exploration wells. By finely classifying lithofacies types in single wells and combining them with lithological scanning logging data, a lithofacies identification sample library is established. A large number of logging curves are combined with machine learning methods to establish mapping relationships, clarify the logging response characteristics of different lithofacies, effectively establish logging response charts (lithofacies identification charts) and determine their boundaries, and summarize the lateral lithofacies distribution patterns in different well areas. This provides a scientific basis for the efficient identification of vertical and horizontal geological sweet spots and is beneficial for the optimal selection of horizontal well target windows in continental shale.

[0108] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0109] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0110] While the embodiments disclosed herein are as described above, the foregoing content is merely for the purpose of facilitating understanding of this disclosure and is not intended to limit this disclosure. Any person skilled in the art to which this disclosure pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope of this disclosure; however, the scope of patent protection of this disclosure shall still be determined by the scope defined in the appended claims.

Claims

1. A method for optimizing the target window in a horizontal well for continental shale oil and gas, characterized in that, include: Obtain the lithofacies classification results for horizontal wells of continental shale oil and gas in the target work area; Determine the vertical lithofacies distribution of horizontal wells in the first continental shale oil and gas field, statistically analyze the logging curve characteristics of target points in each lithofacies, and establish a lithofacies identification sample library; A lithofacies identification chart is established based on a lithofacies identification sample library, and the functional relationship between different logging curves for each lithofacies is identified through the lithofacies identification chart. Using the aforementioned functional relationship, the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target work area is vertically calibrated, and the target window range of each continental shale oil and gas horizontal well is determined.

2. The method according to claim 1, characterized in that, The lithofacies classification results include: the lithofacies type of the first horizontal well determined based on organic matter abundance, sedimentary structure, and whole-rock mineral composition.

3. The method according to claim 1, characterized in that, Determine the vertical lithofacies distribution of horizontal wells in the first continental shale oil and gas formation, statistically analyze the logging curve characteristics of target points in each lithofacies, and establish a lithofacies identification sample library, including: Using lithological scanning logging data from horizontal wells in the first continental shale oil and gas field, the vertical lithofacies distribution of the horizontal wells in the first continental shale oil and gas field was determined; Select target points in each lithofacies along the vertical direction of the first continental shale oil and gas horizontal well; The characteristics of the logging curves at each target point are statistically analyzed and depth correction is performed to obtain a lithofacies identification sample library.

4. The method according to claim 1, characterized in that, A lithofacies identification chart is established based on a lithofacies identification sample library. This chart is used to identify the functional relationships between different logging curves for each lithofacies, including: The logging curve features of each lithofacies target point in the lithofacies identification sample library are used as the logging response features of each lithofacies. A cross plot is established, and the cross plot is used as a lithofacies identification chart to identify the functional relationship between different logging curves of each lithofacies.

5. The method according to claim 4, characterized in that, During the drilling process of horizontal wells in first continental shale oil and gas, cross plots are continuously established. Each time, the optimal cross plot that identifies the functional relationship between different logging curves of a certain lithofacies is selected, and then a new cross plot that identifies the functional relationship between different logging curves of different lithofacies is established, until the optimal cross plot that identifies the functional relationship between different logging curves of all lithofacies is obtained.

6. The method according to claim 4, characterized in that, A cross-plot graph is constructed using machine learning methods, including at least one of decision trees and random forests.

7. A preferred target window device for horizontal wells in continental shale oil and gas, characterized in that, include: The acquisition module is used to obtain the lithofacies classification results of horizontal wells for continental shale oil and gas in the target work area; A module was established to determine the vertical lithofacies distribution of horizontal wells in the first continental shale oil and gas field, to statistically analyze the logging curve characteristics of target points in each lithofacies, and to establish a lithofacies identification sample library. The identification module is used to establish a lithofacies identification chart based on the lithofacies identification sample library, and to identify the functional relationship between different logging curves for each lithofacies through the lithofacies identification chart; The preferred module is used to use the aforementioned functional relationship to vertically calibrate the lateral distribution pattern of the interlayers within the formation of each continental shale oil and gas horizontal well in the target work area, and to determine the target window range of each continental shale oil and gas horizontal well.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.

Images