Well-seismic joint sedimentary facies modeling method, system, device and medium

Abstract

This invention belongs to the field of oil and gas seismic exploration and development, specifically disclosing a well-seismic combined sedimentary facies modeling method, system, equipment, and medium. The method includes: S1, determining the planar distribution of lithofacies and sedimentary facies in a single well; S2, performing synthetic record calibration by combining 3D seismic data; S3, clustering and classifying seismic waveforms of geological target layers based on the characteristics of well-side seismic data, and establishing a sedimentary facies label library associated with well logging; S4, constructing a neural network prediction model and training the model; S5, inputting 3D seismic data and well logging data of the target area into the trained neural network prediction model, and outputting the planar distribution of sedimentary facies; S6, correcting the planar distribution of sedimentary facies using well logging facies samples at the well points to obtain the spatial distribution of sedimentary facies. This invention effectively utilizes well-seismic data, improving the accuracy of sedimentary facies identification. This invention is suitable for characterizing the spatial distribution of sedimentary facies.

Description

Technical Field

[0001] This invention belongs to the field of oil and gas seismic exploration and development, specifically a well-seismic combined sedimentary facies modeling method, system, equipment and medium. Background Technology

[0002] my country's oil and gas reservoirs are mainly terrestrial, and sandstone reservoirs are important target layers for increasing reserves and production in oilfields. Studying the evolution of sedimentary facies can reconstruct paleochannels and reflect channel changes, which is of great guiding significance for the reconstructive interpretation of sandstone development. For a long time, the identification of sedimentary facies has been a key research area and a difficult problem in the process of oil and gas exploration and development. In the past, comprehensive geological studies relying on outcrops, well logging, core samples, and analytical data have basically clarified the source direction from a macroscopic perspective, but the accuracy of the study is insufficient on a planar scale due to the limited amount of drilling data.

[0003] While well logging facies analysis alone offers high lateral resolution, it suffers from low vertical resolution. Inter-well sedimentary facies analysis is often speculative, leading to debates about its accuracy and precision. Although seismic data quality and resolution have improved with advancements in seismic acquisition and processing technologies, the single seismic amplitude information is inherently ambiguous and cannot be directly applied to lithology or main channel prediction. This results in strong ambiguity in sedimentary facies identification, making it difficult to meet the high-precision sedimentary facies identification requirements of oil and gas field exploration and development. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, equipment, and medium for well-seismic combined sedimentary facies modeling, which effectively utilizes well-seismic data to improve the vertical and horizontal resolution of sedimentary facies, enhance the accuracy of sedimentary microfacies identification, and finely characterize the spatial distribution of sedimentary facies.

[0005] To achieve the above objectives, the present invention employs the following technical methods: A method for combined well-seismic sedimentary facies modeling includes the following steps performed sequentially: S1. Obtain well logging data, perform well logging facies analysis, and determine the planar distribution of lithofacies and sedimentary facies in a single well; S2. Based on the planar distribution of lithofacies and sedimentary facies in single wells, and combined with three-dimensional seismic data, all wells in the work area are synthetically recorded and calibrated, and the geological strata are calibrated to their corresponding seismic reflection characteristics. S3. Based on the calibration results of the synthetic record and combined with the characteristics of the well-side seismic data, the seismic waveforms of the geological target layer are clustered and classified. The seismic waveforms corresponding to different types of sedimentary microstructures in the well logging are analyzed, and the seismic waveforms are classified and numbered to obtain a sedimentary facies label library associated with the well logging. S4. Construct a neural network prediction model. Use the classification results of well logging sedimentary microfacies in the sedimentary facies label library, combined with 3D seismic data, as the input of the neural network prediction model. Use the corresponding seismic waveform classification and the distribution of the classification results on the plane as the output to train the neural network prediction model. S5. Input the 3D seismic data and well logging data of the target work area into the trained neural network prediction model, and the trained neural network prediction model outputs the sedimentary facies plane distribution of the target work area. S6. Correct the planar distribution of sedimentary facies using well logging facies samples at the well point to obtain the spatial distribution of sedimentary facies.

[0006] As a limitation, step S1 specifically involves: analyzing the typical sedimentary facies of the core well and the corresponding logging curve response, combining the lithology and sedimentary cycles reflected by the drilling core and core test data, and classifying the lithofacies and sedimentary facies of the single well according to the lithological combination and sedimentary microfacies characteristic curves, combined with the sedimentary background, to obtain the planar distribution of the lithofacies and sedimentary facies of the single well.

[0007] As a limitation, the characteristics of the well-side seismic data in step S3 include seismic amplitude energy, amplitude shape, time difference, waveform shape, and reflection characteristics.

[0008] As a limitation: the specific steps for clustering and classifying seismic waveforms in step S3 are as follows: set the initial number of categories and the grid parameters for seismic trace spacing, perform statistical analysis on the seismic data according to single traces, obtain the types of seismic waveform features and the correlation between the types of seismic waveform features, use the sedimentary microfacies of well logging as a constraint, and combine the correlation and the proportion of seismic waveforms to remove seismic waveforms with small correlation and small proportions, so as to obtain the final seismic waveform clustering and classification results.

[0009] As a limitation, step S6 specifically involves: normalizing different seismic waveform classifications and sedimentary microfacies to ensure their value ranges are within the same range; then performing grid calculations on the planar distribution of sedimentary facies to form a planar distribution map of data sample points that can be grid-corrected; and finally using well logging facies sample points at well points to correct the sedimentary facies grid sample points to obtain the spatial distribution of sedimentary facies.

[0010] This invention also provides a well-seismic combined sedimentary facies modeling system, comprising: The well logging facies analysis module acquires well logging data, performs well logging facies analysis, and determines the planar distribution of lithofacies and sedimentary facies in a single well. The well-seismic joint calibration module, based on the planar distribution of lithofacies and sedimentary facies in a single well and combined with 3D seismic data, performs synthetic record calibration of all wells in the work area and calibrates the geological strata to their corresponding seismic reflection characteristics; The sedimentary facies tag library establishment module, based on the synthetic record calibration results and combined with the characteristics of well-side seismic data, clusters and classifies the seismic waveforms of geological target layers, analyzes the seismic waveforms corresponding to different types of sedimentary micro-logging, and numbers the seismic waveforms to obtain a sedimentary facies tag library associated with well logging. The neural network prediction model construction module constructs a neural network prediction model. It uses the classification results of well logging sedimentary microfacies in the sedimentary facies label library, combined with 3D seismic data, as the input to the neural network prediction model. The corresponding seismic waveform classification and the distribution of the classification results on the plane are used as the output to train the neural network prediction model. The sedimentary facies plane distribution output module inputs the 3D seismic data and well logging data of the target work area into the trained neural network prediction model, and the trained neural network prediction model outputs the sedimentary facies plane distribution of the target work area. The sedimentary facies spatial distribution output module uses well logging facies samples at well points to correct the planar distribution of sedimentary facies and obtain the spatial distribution of sedimentary facies.

[0011] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor calls the computer program in the memory to execute the above-described well-seismic combined sedimentary facies modeling method.

[0012] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, is used to implement the above-described well-seismic combined sedimentary facies modeling method.

[0013] The beneficial effects achieved by this invention, due to the adoption of the above-described solution, compared with the prior art, are as follows: This invention provides a well-seismic combined sedimentary facies modeling method, system, equipment, and medium. It combines the lateral resolution of three-dimensional seismic logging with the longitudinal resolution of well logging to form a high-precision sedimentary facies identification technology process that effectively improves the longitudinal and lateral resolution of sedimentary facies, enhances the identification accuracy of sedimentary facies, and finely depicts the spatial distribution of sedimentary facies. This provides reliable data for seismic data interpretation and reservoir prediction, reduces the drilling risk of research targets, and improves the drilling success rate.

[0014] This invention is applicable to characterizing the spatial distribution of sedimentary phases. Attached Figure Description

[0015] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0016] Figure 1 This is a flowchart of a well-seismic combined sedimentary facies modeling method according to Embodiment 1 of the present invention; Figure 2This is a planar distribution diagram of lithofacies and sedimentary facies in a single well according to Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of the synthesis record calibration in Embodiment 1 of the present invention; Figure 4 This is a diagram showing the types of earthquake waveform features and the correlation between them in Embodiment 1 of the present invention. Figure 5 This is a calibration chart of sedimentary facies, logging facies, and seismic waveforms from Embodiment 1 of the present invention; Figure 6 This is a planar distribution map of sedimentary facies output by the neural network prediction model in Embodiment 1 of the present invention; Figure 7 This is a modified depositional phase plan view of Example 1 of the present invention; Figure 8 This is a spatial distribution diagram of the sedimentary phases in Example 1 of the present invention; Figure 9 This is a structural block diagram of a well-seismic combined sedimentary facies modeling system according to Embodiment 2 of the present invention; Figure 10 This is a schematic diagram of the structure of the electronic device in Embodiment 3 of the present invention. Detailed Implementation

[0017] The present invention will be further described below with reference to the embodiments. However, those skilled in the art should understand that the present invention is not limited to the following embodiments. Any improvements and equivalent changes made based on the specific embodiments of the present invention are within the scope of protection of the claims of the present invention.

[0018] Example 1: A Well-Seismic Combined Seismic Facies Modeling Method This embodiment uses the combined well-seismic sedimentary facies modeling method to predict the spatial distribution of sedimentary facies in a certain region. This region is an important area for the outward distribution of a gas field. The region has a large area and great exploration potential. The He8 member of the Lower Shihezi Formation of the Upper Paleozoic Permian is the main producing layer in this region. The He8 member of the Shihezi Formation is mainly a typical continental delta front subfacies. The distribution of underwater distributary channel sand bodies varies rapidly laterally, with channel widths ranging from 0.5 to 2.5 km, single-layer sand thicknesses ranging from 3 to 15 m, and cumulative sand thicknesses ranging from 5 to 20 m.

[0019] This embodiment presents a method for combined well-seismic sedimentary facies modeling, such as... Figure 1 As shown, the steps are performed sequentially: S1. Obtain logging data and perform logging facies analysis. Analyze the typical sedimentary facies of the core well and the corresponding logging curve response. In this embodiment, the logging curve uses the natural gamma curve. Combined with the lithology and sedimentary cycles reflected in the drilling core and core test data, and based on the lithological assemblage and sedimentary microfacies characteristic curves, combined with the sedimentary background, the lithofacies and sedimentary facies of the single well are divided to obtain the planar distribution of the lithofacies and sedimentary facies of the single well, such as... Figure 2 As shown, typical wells and corresponding sedimentary microfacies of the lower section of the Shihezi Formation in this area were analyzed. Single-well facies analysis diagrams of some wells, namely wells S404, S219 and N1, were listed. The sedimentary microfacies corresponding to wells S404, S219 and N1 are subaqueous distributary channel, frontal sheet sand and interdistributary bay, respectively.

[0020] S2. Based on the planar distribution of lithofacies and sedimentary facies in individual wells, and combined with 3D seismic data, all wells in the work area were subjected to synthetic record calibration, and geological strata were mapped to their corresponding seismic reflection characteristics. The results of the synthetic record calibration are as follows: Figure 3 As shown, well logging facies analysis reveals the coexistence of three sedimentary microfacies: underwater distributary channels, frontal sheet sands, and interdistributary bays. To further characterize the sedimentary microfacies variations of underwater distributary channels and interdistributary bays, the underwater distributary channels can be further subdivided into two secondary microfacies: the underwater main distributary channel and the underwater distributary channel flanks. The underwater main distributary channel exhibits a large sand body thickness, with well logging facies predominantly box-shaped, and seismic reflections showing medium-to-strong peak reflections and bright spot characteristics. The representative well is L20-26. The underwater distributary channels... The flanks are located at the edge of the sand body, mainly composed of multiple sets of thin sand bodies. The logging facies is mainly bell-shaped, and the seismic reflection is a medium-strong peak reflection at the edge, represented by wells L26-27. The leading edge sheet-like sand subfacies has thin single sand bodies with abrupt contact with the upper and lower mudstones. The logging facies shows a finger-shaped shape, and the seismic reflection is a medium-strong peak lens reflection, represented by well L21. The underwater distributary bay is mainly composed of mudstone. The logging facies shows a linear shape, and the seismic reflection is weak to blank, represented by well L74.

[0021] S3. Based on the calibration results of the synthetic record and combined with the characteristics of the well-side seismic data, which include seismic amplitude energy, amplitude morphology, time difference, waveform shape and reflection characteristics, the seismic waveforms of the geological target layer are clustered and classified. The seismic waveform classifications corresponding to different types of sedimentary microstructures in the well logging are analyzed, and the seismic waveform classifications are numbered to obtain a sedimentary facies label library associated with the well logging. In the clustering and classification process, attention is paid to the selection of the initial number of clusters for waveform clustering and the grid parameter selection for seismic trace spacing. The number of clusters depends on the research objective and the level of understanding of the data. A small number of clusters results in overly coarse results, while a large number of clusters results in overly detailed results. More than 15-20 clusters are usually difficult to interpret. Based on geological analysis, it is generally recommended that the initial number of clusters for artificial classification be as large as possible, ideally twice that of well logging sedimentary microfacies classification. To avoid the seismic data failing to reflect well logging sedimentary microfacies changes due to an insufficient number of clusters, the number of clusters is expanded from 6 to 8. Therefore, in this embodiment, the initial number of clusters for seismic waveform clustering is set to 8. The selection of the grid parameter for seismic trace spacing is based on the distribution patterns of geological targets, especially for strata with rapid lithological changes in terrestrial clastic rocks, where the grid radius should tend to be small. In this embodiment, a 50 CDP trace spacing is preferred. With the initial number of clusters set to 8 and the seismic trace spacing grid parameter set to 50 CDP, the seismic data is statistically analyzed on a single trace basis to obtain the types of seismic waveform features and the correlations between these types. Figure 4 As shown; using sedimentary microfacies from well logging as constraints, and combining correlation and seismic waveform proportions, seismic waveforms with weak correlation and small proportions are eliminated, resulting in the final seismic waveform clustering classification result. In this embodiment, the clustering classification result is 5 categories. Figure 5 The diagram shows calibration charts for sedimentary facies, well logging facies, and seismic waveforms. The delta front facies shows well-developed underwater distributary main channel reservoirs with thick individual and composite sand bodies. Well logging facies are columnar and box-shaped, respectively. Seismic waveforms are classified into two types: ① and ②. Type ① is a medium-to-strong peak reflection with a peak-to-peak width greater than 18 ms and a shape that is wider at the top and narrower at the bottom. Type ② is also a medium-to-strong peak reflection with a peak width of 12-18 ms and a shape that is narrower at the top and wider at the bottom. The underwater distributary channel flanks reflect the geological characteristics of thin sand bodies on the main channel flanks. The logging facies are bell-shaped and funnel-shaped, and the seismic waveforms are classified into two types: ③ and ④. The ③ type of seismic reflection is a medium-to-weak peak reflection with a peak width of 8-12 ms and a waveform that is narrower at the top and wider at the bottom. The ④ type of seismic reflection is a medium-to-weak peak reflection with a peak width of 8-12 ms and a waveform that is narrower at the top and wider at the bottom. The interdistributary bay at the delta front reflects relatively underdeveloped sandstone, with mudstone as the main body. The logging facies are linear, and the seismic waveform is classified into type ⑤, which is mainly a weak peak-blank reflection with a peak width of less than 8 ms.

[0022] S4. Construct a neural network prediction model. Use the classification results of well logging sedimentary microfacies in the sedimentary facies label library, combined with 3D seismic data, as the input to the neural network prediction model. Use the corresponding seismic waveform classification and the distribution of the classification results on the plane, superimposed with the corresponding well logging symbols, as the output to train the neural network prediction model.

[0023] S5. Input the 3D seismic data and well logging data of the target work area, Box 8, into the trained neural network prediction model. The trained neural network prediction model outputs the sedimentary facies plane distribution of the target work area, Box 8, such as... Figure 6 As shown, the sedimentary facies plane distribution output by the neural network prediction model can be manually intervened to remove outliers, improve the accuracy of the sedimentary facies plane distribution, and obtain a corrected sedimentary facies plane map, as shown. Figure 7 As shown.

[0024] S6. Normalize the different seismic waveform classifications and sedimentary microfacies to ensure their value ranges are within the same range. Assign values ​​of 1, 2, 3, 4, and 5 to the five seismic waveform classifications, respectively. Assign values ​​of 1, 3, and 5 to the underwater distributary channels, underwater distributary channel flanks, and underwater interdistributary bays of the sedimentary microfacies classifications, respectively. Then, perform grid calculations on the planar distribution of sedimentary facies to generate a planar distribution map of data samples that can be grid-corrected. Finally, use well logging facies samples at well points to correct the sedimentary facies grid samples to obtain the spatial distribution of sedimentary facies, such as... Figure 8 As shown, the spatial distribution of sedimentary facies in the He8 section was finely depicted, the spatial distribution patterns of different subfacies in the continental delta front were clarified, and the location of the main channel was further clarified. Of the 25 wells deployed based on the sedimentary facies results, 21 wells encountered sand bodies in the main channel, with an average gas layer thickness of 6.4m, effectively guiding the deployment of exploration and evaluation well locations. At the same time, the sedimentary facies research results were used to guide geostatistical inversion prediction, resulting in stronger reservoir regularity, conformity to geological laws, and higher precision. The completion drilling verification of the He8 section of the Shihezi Formation had a consistency rate of 84.6%, and the drilling success rate was significantly improved by 50%. Four wells obtained high-yield industrial gas flows of one million cubic meters.

[0025] Example 2: A Well-Seismic Combined Sedimentary Facies Modeling System A well-seismic combined sedimentary facies modeling system, such as Figure 9 As shown, it includes: The well logging facies analysis module acquires well logging data, performs well logging facies analysis, analyzes typical sedimentary facies of core wells and their corresponding well logging curve responses. In this embodiment, the well logging curves adopt natural gamma curves. Combined with the lithology and sedimentary cycles reflected by the drilling core and core test data, and based on the lithological assemblage and sedimentary microfacies characteristic curves, combined with the sedimentary background, the lithofacies and sedimentary facies of a single well are divided to obtain the planar distribution of the lithofacies and sedimentary facies of a single well.

[0026] The well-seismic joint calibration module, based on the planar distribution of lithofacies and sedimentary facies in a single well and combined with 3D seismic data, performs synthetic record calibration of all wells in the work area, and calibrates the geological strata to their corresponding seismic reflection characteristics.

[0027] The sedimentary facies label library establishment module, based on the synthetic record calibration results and combined with the characteristics of well-side seismic data (including seismic amplitude energy, amplitude morphology, time difference, waveform shape, and reflection characteristics), clusters and classifies the seismic waveforms of the geological target layers, analyzes the seismic waveform classifications corresponding to different types of sedimentary micro-logging, and assigns numbers to the seismic waveform classifications to obtain a sedimentary facies label library associated with well logging.

[0028] The neural network prediction model construction module constructs a neural network prediction model. It uses the classification results of well logging sedimentary microfacies in the sedimentary facies label library, combined with 3D seismic data, as input to the neural network prediction model. The corresponding seismic waveform classification and the distribution of the classification results on the plane, superimposed with the corresponding well logging symbols, are used as output to train the neural network prediction model.

[0029] The sedimentary facies plane distribution output module inputs the 3D seismic data and well logging data of the target work area Box 8 segment into the trained neural network prediction model. The trained neural network prediction model outputs the sedimentary facies plane distribution of the target work area Box 8 segment. The module can manually intervene in the sedimentary facies plane distribution output by the neural network prediction model to remove outliers, improve the characterization accuracy of the sedimentary facies plane distribution, and obtain a corrected sedimentary facies plane map.

[0030] The sedimentary facies spatial distribution output module normalizes different seismic waveform classifications and sedimentary microfacies to ensure their value ranges are within the same range. Then, it performs grid calculations on the sedimentary facies planar distribution to form a planar distribution map of data sample points that can be grid-corrected. Finally, it uses well logging facies sample points at well points to correct the sedimentary facies grid sample points, thus obtaining the spatial distribution of sedimentary facies.

[0031] Example 3: An electronic device The electronic device of this embodiment includes a memory and a processor. The memory stores a computer program, and the processor calls the computer program in the memory to execute a well-seismic combined sedimentary facies modeling method of Embodiment 1. Figure 10This is a schematic diagram of the structure of the electronic device provided in this embodiment. The electronic device can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), portable Android devices (PADs), portable media players (PMPs), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of this embodiment.

[0032] like Figure 10 As shown, electronic devices may include processing units, such as central processing units (CPUs) and graphics processors (GPUs), which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) or loaded from storage devices into random access memory (RAM). RAM also stores various programs and data required for the operation of the electronic device. The processing unit, ROM, and RAM are interconnected via a bus. Input devices, output devices, communication devices, and storage devices are also connected to the bus via I / O interfaces.

[0033] Typically, the following devices can be connected to the I / O interface: input devices such as touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices such as liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices such as magnetic tapes, hard drives, etc.; and communication devices. Communication devices allow electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 10 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0034] Example 4: A computer-readable medium The computer-readable storage medium of this embodiment stores a computer program, which, when executed by a processor, is used to implement a well-seismic combined sedimentary facies modeling method of Embodiment 1. The computer-readable storage medium of this embodiment may be included in an electronic device; alternatively, it may exist independently and not assembled into an electronic device.

[0035] The computer-readable storage medium of this embodiment may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0036] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit them. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this disclosure.

Claims

1. A method for combined well-seismic sedimentary facies modeling, characterized in that, This includes the following steps performed sequentially: S1. Obtain well logging data, perform well logging facies analysis, and determine the planar distribution of lithofacies and sedimentary facies in a single well; S2. Based on the planar distribution of lithofacies and sedimentary facies in single wells, and combined with three-dimensional seismic data, all wells in the work area are synthetically recorded and calibrated, and the geological strata are calibrated to their corresponding seismic reflection characteristics. S3. Based on the calibration results of the synthetic record and combined with the characteristics of the well-side seismic data, the seismic waveforms of the geological target layer are clustered and classified. The seismic waveforms corresponding to different types of sedimentary microstructures in the well logging are analyzed, and the seismic waveforms are classified and numbered to obtain a sedimentary facies label library associated with the well logging. S4. Construct a neural network prediction model. Use the classification results of well logging sedimentary microfacies in the sedimentary facies label library, combined with 3D seismic data, as the input of the neural network prediction model. Use the corresponding seismic waveform classification and the distribution of the classification results on the plane as the output to train the neural network prediction model. S5. Input the 3D seismic data and well logging data of the target work area into the trained neural network prediction model, and the trained neural network prediction model outputs the sedimentary facies plane distribution of the target work area. S6. Correct the planar distribution of sedimentary facies using well logging facies samples at the well point to obtain the spatial distribution of sedimentary facies.

2. The well-seismic combined sedimentary facies modeling method according to claim 1, characterized in that, Step S1 specifically involves: analyzing the typical sedimentary facies of the core well and the corresponding logging curve response; combining the lithology and sedimentary cycles reflected by the drilling core and core test data; and classifying the lithofacies and sedimentary facies of the single well based on the lithological assemblage and sedimentary microfacies characteristic curves, combined with the sedimentary background, to obtain the planar distribution of the lithofacies and sedimentary facies of the single well.

3. A well-seismic combined sedimentary facies modeling method according to claim 1 or 2, characterized in that, The characteristics of the well-side seismic data in step S3 include seismic amplitude energy, amplitude shape, time difference, waveform shape, and reflection characteristics.

4. A well-seismic combined sedimentary facies modeling method according to claim 1 or 2, characterized in that, Step S3 involves clustering and classifying seismic waveforms as follows: setting the initial number of categories and the grid parameters for seismic trace spacing; performing statistical analysis on seismic data according to individual traces to obtain the types of seismic waveform features and the correlation between these types; using well logging sedimentary microfacies as constraints; and combining the correlation and the proportion of seismic waveforms, removing seismic waveforms with low correlation and low proportion to obtain the final seismic waveform clustering and classification results.

5. A well-seismic combined sedimentary facies modeling method according to claim 1 or 2, characterized in that, Step S6 specifically involves: normalizing different seismic waveform classifications and sedimentary microfacies to ensure their value ranges are within the same range; then performing grid calculations on the planar distribution of sedimentary facies to form a planar distribution map of data sample points that can be grid-corrected; and finally using well logging facies sample points at well points to correct the sedimentary facies grid sample points to obtain the spatial distribution of sedimentary facies.

6. A well-seismic combined sedimentary facies modeling system, characterized in that, include: The well logging facies analysis module acquires well logging data, performs well logging facies analysis, and determines the planar distribution of lithofacies and sedimentary facies in a single well. The well-seismic joint calibration module, based on the planar distribution of lithofacies and sedimentary facies in a single well and combined with 3D seismic data, performs synthetic record calibration of all wells in the work area and calibrates the geological strata to their corresponding seismic reflection characteristics; The sedimentary facies tag library establishment module, based on the synthetic record calibration results and combined with the characteristics of well-side seismic data, clusters and classifies the seismic waveforms of geological target layers, analyzes the seismic waveforms corresponding to different types of sedimentary micro-logging, and numbers the seismic waveforms to obtain a sedimentary facies tag library associated with well logging. The neural network prediction model construction module constructs a neural network prediction model. It uses the classification results of well logging sedimentary microfacies in the sedimentary facies label library, combined with 3D seismic data, as the input to the neural network prediction model. The corresponding seismic waveform classification and the distribution of the classification results on the plane are used as the output to train the neural network prediction model. The sedimentary facies plane distribution output module inputs the 3D seismic data and well logging data of the target work area into the trained neural network prediction model, and the trained neural network prediction model outputs the sedimentary facies plane distribution of the target work area. The sedimentary facies spatial distribution output module uses well logging facies samples at well points to correct the planar distribution of sedimentary facies and obtain the spatial distribution of sedimentary facies.

7. An electronic device, characterized in that, It includes a memory and a processor. The memory stores a computer program, and the processor calls the computer program in the memory to execute the well-seismic combined sedimentary facies modeling method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores a computer program that, when executed by a processor, is used to implement the well-seismic combined sedimentary facies modeling method according to any one of claims 1-5.

Images