A lithology prediction method, device, equipment, medium and product in a target area
By training a target well velocity curve prediction model and a virtual well simulated velocity curve, combined with an inversion algorithm, the problem of low lithology prediction accuracy caused by the lack of actual well velocity curves was solved, and more accurate lithology prediction was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA NAT PETROLEUM CORP
- Filing Date
- 2024-12-12
- Publication Date
- 2026-06-12
Smart Images
Figure CN122194333A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of exploration technology, and in particular to a method, apparatus, equipment, medium and product for predicting lithology in a target area. Background Technology
[0002] Constrained sparse pulse inversion is an important technique for lithological prediction in oil and gas exploration. Typically, in areas with available 3D seismic data, the basic data used in the inversion algorithm includes seismic data and actual well velocity curves. However, in actual scientific research and production, actual well velocity curves are often missing, which significantly reduces the accuracy of lithological prediction. Summary of the Invention
[0003] This invention provides a method, apparatus, equipment, medium, and product for predicting lithology in a target area, which can improve the accuracy of lithology prediction.
[0004] According to one aspect of the present invention, a method for predicting lithology in a target area is provided, comprising:
[0005] Acquire seismic data within the target area, along with seismic data within the study area and known well logging data, wherein the study area is an adjacent work area to the target area;
[0006] Based on seismic data and well logging data in the study area, the initial well velocity curve prediction model was trained to obtain the target well velocity curve prediction model.
[0007] Based on seismic data within the target area, multiple virtual well simulation velocity curves were determined;
[0008] The simulated velocity curves of each virtual well are input into the velocity curve prediction model of the target well to obtain the actual velocity curves of each virtual well.
[0009] Based on the inversion algorithm, the lithology prediction results in the target area are determined according to the actual velocity curves of each virtual well and the seismic data in the target area.
[0010] According to another aspect of the present invention, a lithology prediction device for a target area is provided, the lithology prediction device for a target area comprising:
[0011] The acquisition module is used to acquire seismic data within the target area, seismic data within the study area, and well logging data from known wells, wherein the study area is an adjacent work area to the target area;
[0012] The training module is used to train the initial well velocity curve prediction model based on seismic data and known well logging data in the study area, so as to obtain the target well velocity curve prediction model.
[0013] The virtual well simulation velocity curve determination module is used to determine multiple virtual well simulation velocity curves based on seismic data within the target area.
[0014] The virtual well actual velocity curve determination module is used to input the simulated velocity curves of each virtual well into the target well velocity curve prediction model to obtain the actual velocity curves of each virtual well.
[0015] The lithology prediction result determination module in the target area is used to determine the lithology prediction result in the target area based on the inversion algorithm, the actual velocity curves of each virtual well and the seismic data in the target area.
[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0017] At least one processor; and
[0018] A memory communicatively connected to the at least one processor; wherein,
[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the lithology prediction method for the target area according to any embodiment of the present invention.
[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the lithology prediction method in the target area according to any embodiment of the present invention.
[0021] According to another aspect of the present invention, a computer program product is provided, which, when executed by a processor, implements the lithology prediction method in a target area as described in any of the embodiments of the present invention.
[0022] This invention, through acquiring seismic data within a target area, comparing it with seismic data within a study area and well logging data from known wells, trains an initial well velocity curve prediction model based on the seismic data within the study area and the well logging data from known wells to obtain a target well velocity curve prediction model. Based on the seismic data within the target area, multiple virtual well simulated velocity curves are determined. These virtual well simulated velocity curves are then input into the target well velocity curve prediction model to obtain the actual velocity curves of each virtual well. Based on an inversion algorithm, the lithology prediction results within the target area are determined according to the actual velocity curves of each virtual well and the seismic data within the target area, thereby improving the accuracy of lithology prediction.
[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0025] Figure 1 This is a flowchart of a lithology prediction method within a target area according to an embodiment of the present invention;
[0026] Figure 2 This is a flowchart of another lithology prediction method within a target area in an embodiment of the present invention;
[0027] Figure 3 This is a flowchart of a method for generating a simulated velocity curve of a known well M2 according to an embodiment of the present invention;
[0028] Figure 4 This is a schematic diagram of the structure of a lithology prediction device in a target area according to an embodiment of the present invention;
[0029] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 the invention 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 a 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.
[0032] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.
[0033] Example 1
[0034] Figure 1 This is a flowchart illustrating a lithology prediction method within a target area, provided by an embodiment of the present invention. This embodiment is applicable to situations involving lithology prediction within a target area. The method can be executed by a lithology prediction device within the target area, as described in this embodiment. This device can be implemented using software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps:
[0035] S110: Acquire seismic data within the target area, along with seismic data and well logging data from known wells within the study area.
[0036] In this embodiment, the study area is an adjacent work area to the target area. The distance between the study area and the target area is less than a distance threshold, for example, the distance threshold could be 20 kilometers.
[0037] In this embodiment, the well logging data of known wells within the study area refers to the logging data of known wells that have reached the target layer within the study area. The target area requires research into the lithology of the target layer. The well logging data of known wells may include: actual velocity curves of known wells.
[0038] In this embodiment, the seismic data within the target area includes: seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area. Alternatively, it may include: seismic data within the target area, stacking velocity within the target area, and a seismic interpretation scheme within the target area. The seismic data within the study area includes: seismic reflection coefficient curves and well depth curves of multiple known wells within the study area. Alternatively, it may include: seismic data within the study area, stacking velocity within the study area, and a seismic interpretation scheme within the study area.
[0039] S120. Based on seismic data and well logging data in the study area, the initial well velocity curve prediction model is trained to obtain the target well velocity curve prediction model.
[0040] In this embodiment, the known well logging data includes: the actual velocity curve of the known well. The initial well velocity curve prediction model is a neural network model to be trained. The target well velocity curve prediction model is a trained neural network model.
[0041] In this embodiment, the method for training the initial well velocity curve prediction model based on seismic data and known well logging data within the study area to obtain the target well velocity curve prediction model can be as follows: A training sample set is generated based on the seismic data and known well logging data within the study area; the initial well velocity curve prediction model is then trained based on the training sample set to obtain the target well velocity curve prediction model. Alternatively, the method can be as follows: A training sample set and a test sample set are generated based on the seismic data and known well logging data within the study area; the initial well velocity curve prediction model is trained based on the training sample set; and the trained model is then tested based on the test sample set to obtain the target well velocity curve prediction model.
[0042] In this embodiment, the training sample set can be generated based on seismic data and well logging data within the study area as follows: If the seismic data within the study area includes seismic reflection coefficient curves and well depth curves of multiple known wells within the study area, and the well logging data within the study area includes actual velocity curves of known wells within the study area, then the simulated velocity curves of each known well within the study area are determined based on the seismic reflection coefficient curves and well depth curves of multiple known wells within the study area, and the training sample set is generated based on the simulated velocity curves and actual velocity curves of each known well within the study area. Alternatively, the training sample set can be generated based on the seismic data and well logging data within the study area as follows: If the seismic data within the study area includes simulated velocity curves of each known well within the study area, and the well logging data within the study area includes actual velocity curves of known wells within the study area, then the training sample set is generated based on the simulated velocity curves and actual velocity curves of each known well within the study area. The training sample set can also be generated based on seismic data and well logging data within the study area as follows: If the seismic data within the study area includes seismic data, stacking velocity, and seismic interpretation scheme, then the seismic reflection coefficient curves of multiple known wells within the study area are plotted based on the seismic data and seismic interpretation scheme; the well depth curves of multiple known wells within the study area are plotted based on the seismic interpretation scheme and stacking velocity; the simulated velocity curves of each known well within the study area are determined based on the seismic reflection coefficient curves and well depth curves; and the training sample set is generated based on the simulated velocity curves and actual velocity curves of each known well within the study area.
[0043] Optionally, the seismic data in the study area includes: seismic reflection coefficient curves of multiple known wells in the study area and well depth curves of multiple known wells in the study area;
[0044] Based on seismic data and known well logging data within the study area, the initial well velocity curve prediction model was trained to obtain the target well velocity curve prediction model, including:
[0045] Based on the seismic reflection coefficient curves and well depth curves of multiple known wells in the study area, the simulated velocity curves of each known well in the study area are determined.
[0046] In this embodiment, the method for determining the simulated velocity curve of each known well in the study area based on the seismic reflection coefficient curve and the well depth curve of multiple known wells in the study area can be as follows: the seismic reflection coefficient curve and the well depth curve of multiple known wells in the study area are trend-merged to obtain the simulated velocity curve of each known well in the study area.
[0047] Based on the logging data of each known well in the study area, the actual velocity curves of each known well in the study area are plotted.
[0048] A training sample set is created based on the simulated velocity curves and actual velocity curves of each known well in the study area.
[0049] In this embodiment, the training sample set includes: simulated velocity curve samples and actual velocity curves corresponding to the simulated velocity curve samples. The simulated velocity curves of each known well in the study area are used as simulated velocity curve samples, and the actual velocity curves of each known well in the study area are used as actual velocity curves corresponding to the simulated velocity curve samples.
[0050] Based on the training sample set, the initial well velocity curve prediction model is trained to obtain the target well velocity curve prediction model.
[0051] In this embodiment, the method for training the initial well velocity curve prediction model based on the training sample set to obtain the target well velocity curve prediction model can be as follows: input the simulated velocity curves of known wells in the training sample set into the initial well velocity curve prediction model to obtain the predicted velocity curves of the known wells; determine the difference between the predicted velocity curves of the known wells and the actual velocity curves of the known wells corresponding to the simulated velocity curves of the known wells based on the loss function; and train the parameters of the initial well velocity curve prediction model based on the difference between the predicted velocity curves of the known wells and the actual velocity curves of the known wells corresponding to the simulated velocity curves of the known wells to obtain the target well velocity curve prediction model.
[0052] Optionally, based on the training sample set, the initial well velocity curve prediction model is trained to obtain the target well velocity curve prediction model, including:
[0053] Based on the training sample set, the initial well velocity curve prediction model is trained to obtain a trained well velocity curve prediction model.
[0054] A test sample set is created based on the simulated velocity curves of multiple known wells in the study area and the actual velocity curves of multiple known wells in the study area.
[0055] In this embodiment, the intersection of the samples in the test sample set and the samples in the training sample set is empty. That is, the samples in the test sample set are all different from the samples in the training sample set.
[0056] In this embodiment, the test sample set can be created by using the simulated velocity curves and actual velocity curves of multiple known wells in the study area as a basis: generating a training sample set based on a portion of the simulated velocity curves and actual velocity curves of multiple known wells in the study area, and generating a test sample set based on another portion of the curves.
[0057] The simulated velocity curves of known wells in the study area of the test sample set are input into the trained well velocity curve prediction model to obtain the predicted velocity curves of known wells in the study area.
[0058] If the correlation coefficient between the predicted velocity curve of a known well in the study area and the actual velocity curve of a known well in the study area is greater than or equal to the correlation coefficient threshold, then the trained well velocity curve prediction model is determined as the target well velocity curve prediction model.
[0059] In this embodiment, the correlation coefficient between the predicted velocity curves and the actual velocity curves of known wells in the study area can be obtained by performing an intersection analysis on the predicted velocity curves and the actual velocity curves of known wells in the study area. The closer the angle between the normalized fitting line and the horizontal axis is to 45°, the closer the fitting result is to the actual curve, the higher the accuracy of the prediction result, and the larger the correlation coefficient.
[0060] S130: Based on seismic data within the target area, determine the simulated velocity curves of multiple virtual wells.
[0061] In this embodiment, the method for determining the simulated velocity curves of multiple virtual wells based on seismic data within the target area can be as follows: If the seismic data within the target area includes seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area, then the simulated velocity curves of multiple virtual wells are determined based on these curves. If the seismic data within the target area includes seismic data, stacking velocity, and seismic interpretation scheme, then the seismic reflection coefficient curves of multiple virtual wells within the target area are plotted based on the seismic data and interpretation scheme; the well depth curves of multiple virtual wells within the target area are plotted based on the interpretation scheme and stacking velocity; and the simulated velocity curves of each virtual well within the target area are determined based on these curves.
[0062] Optionally, the seismic data within the target area includes: seismic reflection coefficient curves of multiple virtual wells within the target area and well depth curves of multiple virtual wells within the target area;
[0063] Based on seismic data within the target area, multiple virtual well simulation velocity curves were determined, including:
[0064] Based on the seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area, the simulated velocity curves of multiple virtual wells are determined.
[0065] In this embodiment, the method for determining the simulated velocity curves of multiple virtual wells based on the seismic reflection coefficient curves and well depth curves of multiple virtual wells in the target area can be as follows: the seismic reflection coefficient curves and well depth curves of multiple virtual wells in the target area are trend-merged to obtain the simulated velocity curves of multiple virtual wells.
[0066] Optionally, based on the seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area, multiple virtual well simulation velocity curves are determined, including:
[0067] The seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area are trend-merged to obtain multiple virtual well simulated velocity curves.
[0068] S140, input the simulated velocity curves of each virtual well into the target well velocity curve prediction model to obtain the actual velocity curves of each virtual well.
[0069] S150, based on the inversion algorithm, determines the lithology prediction results in the target area according to the actual velocity curves of each virtual well and the seismic data in the target area.
[0070] In this embodiment, the method for determining the lithology prediction results in the target area based on the inversion algorithm, according to the actual velocity curves of each virtual well and the seismic data in the target area, can be as follows: Based on the inversion algorithm, a three-dimensional wave impedance data volume is determined according to the actual velocity curves of each virtual well and the seismic data in the target area; according to the wave impedance value range corresponding to each lithology type, the three-dimensional wave impedance data volume is sculpted to obtain the distribution status information of each lithology type in the target area.
[0071] Optionally, based on the inversion algorithm, and according to the actual velocity curves of each virtual well and the seismic data within the target area, the lithological prediction results within the target area are determined, including:
[0072] Based on the inversion algorithm, a three-dimensional wave impedance data volume is determined according to the actual velocity curves of each virtual well and the seismic data in the target area.
[0073] In this embodiment, the inversion algorithm is a mathematical algorithm used in the seismic industry for predicting subsurface reservoirs. Based on the reflection coefficients of seismic data and combined with well data (from which wave impedance curves can be calculated), the algorithm simulates the wave impedance information of various subsurface strata, which is the reservoir prediction result—a three-dimensional wave impedance data volume consistent with the seismic data.
[0074] Obtain the range of wave impedance values corresponding to each lithology type.
[0075] In this embodiment, the lithological types may include: source rocks, sandstone, volcanic rocks, carbonates, sand, mud, etc.
[0076] In this embodiment, the method for obtaining the wave impedance value range corresponding to each lithology type can be: determining the wave impedance value range corresponding to each lithology type based on the product of the logging velocity curve and density curve corresponding to each lithology type of the known well.
[0077] Based on the wave impedance value range corresponding to each lithology type, the three-dimensional wave impedance data volume is sculpted to obtain the distribution status information of each lithology type in the target area.
[0078] In this embodiment, the logging velocity curves and density curves of the sand, mud, and volcanic rock in the well are known. The product of the two is the wave impedance curve, which can be used to obtain the wave impedance value range of the sand, mud, and volcanic rock. Then, the wave impedance value of the three-dimensional wave impedance data volume obtained by inversion is divided according to this range, thereby forming the range of sand, mud, and volcanic rock in this area.
[0079] In a specific example, such as Figure 2 As shown, the specific process of lithology prediction in the target area is as follows:
[0080] Based on the logging data of the known well M1 in the study area, the actual velocity curve of the known well M1 in the study area is plotted. Based on the logging data of the known well M2 in the study area, the actual velocity curve of the known well M2 in the study area is plotted.
[0081] Based on the seismic data and interpretation scheme within the study area, seismic reflection coefficient curves for known wells M1 and M2 are plotted. Based on the seismic interpretation scheme and stacking velocity within the study area, well depth curves for known wells M1 and M2 are plotted. Based on the seismic reflection coefficient and well depth curves of known well M1, the simulated velocity curve of known well M1 is determined. Similarly, based on the seismic reflection coefficient and well depth curves of known well M2, the simulated velocity curve of known well M2 is determined. In this embodiment, the specific method for plotting the seismic reflection coefficient curves for known wells M1 and M2 based on the seismic data and interpretation scheme within the study area can be as follows: Based on the seismic data and interpretation scheme within the study area, seismic profile maps passing through known well M1 and known well M2 are determined. Seismic profiles passing through known well M1 are extracted to obtain the seismic reflection coefficient curve of well M1. Similarly, seismic profiles passing through known well M2 are extracted to obtain the seismic reflection coefficient curve of well M2. Based on the seismic data and stacking velocity within the study area, the well depth curves of known wells M1 and M2 can be plotted as follows: Based on the seismic data and stacking velocity within the study area, velocity field information profiles passing through known wells M1 and M2 are determined. The velocity field information profile passing through known well M1 is extracted to obtain the well depth curve of well M1. The velocity field information profile passing through known well M2 is extracted to obtain the well depth curve of well M2. For example, it could be as follows: Figure 3 As shown, the seismic profile of the known well M2 (x-axis: reflection coefficient, y-axis: depth (in meters)) is extracted to obtain the seismic reflection coefficient curve of the known well M2 (x-axis: reflection coefficient, y-axis: depth (in meters)). The velocity field information profile of the known well M2 (x-axis: velocity (in meters per second), y-axis: depth (in meters)) is extracted to obtain the well depth curve of the known well M2 (x-axis: velocity (in meters per second), y-axis: depth (in meters)). The seismic reflection coefficient curve and the well depth curve of the known well M2 are then combined to obtain the simulated velocity curve of the known well M2.
[0082] A neural network model is trained based on the simulated velocity curve and the actual velocity curve of the known well M1 within the study area, resulting in a trained neural network model. In this embodiment, 3249 sample points are sampled, each including: a simulated velocity curve sample and the corresponding actual velocity curve (e.g., the simulated velocity curve and the actual velocity curve of the known well M1). The distribution range of the simulated and actual velocity curves is analyzed using histograms and cross plots. Neural network learning analysis can divide the simulated and actual velocity curves into 12 phase bands. The numerical distribution range and weight of different phase bands are shown in Table 1.
[0083] Table 1
[0084]
[0085]
[0086] Furthermore, a matching model for the relationship between the simulated speed curve and the actual speed curve is established, which is the neural network model.
[0087] The simulated velocity curve of the known well M2 in the study area is input into the trained neural network model to obtain the predicted velocity curve of the known well M2 in the study area.
[0088] Obtain the correlation coefficient between the predicted velocity curve of the known well M2 in the study area and the actual velocity curve of the known well M2 in the study area.
[0089] If the correlation coefficient between the predicted velocity curve of well M2 in the study area and the actual velocity curve of well M2 in the study area is greater than or equal to 0.8, then the trained neural network model is determined as the target well velocity curve prediction model. In this embodiment, through curve shape comparison and intersection analysis, it can be seen that the predicted velocity curve output by the model is close to the actual velocity curve, with a correlation coefficient of 0.83, proving that the curve predicted by the model meets the prerequisite for the next step of constrained sparse pulse inversion.
[0090] Based on the seismic data and seismic interpretation scheme within the target area, the seismic reflection coefficient curves of virtual wells N1 and N2 within the target area are plotted. Based on the seismic interpretation scheme and stacking velocity within the target area, the well depth curves of virtual wells N1 and N2 within the target area are plotted. Based on the seismic reflection coefficient curve and well depth curve of virtual well N1 within the target area, the simulated velocity curve of virtual well N1 within the target area is determined. Based on the seismic reflection coefficient curve and well depth curve of virtual well N2 within the target area, the simulated velocity curve of virtual well N2 within the target area is determined.
[0091] Input the simulated velocity curve of virtual well N1 in the target area into the target well velocity curve prediction model to obtain the actual velocity curve of virtual well N1 in the target area;
[0092] Input the simulated velocity curve of virtual well N2 in the target area into the target well velocity curve prediction model to obtain the actual velocity curve of virtual well N2 in the target area;
[0093] Based on the inversion algorithm, the inversion results are determined according to the actual velocity curves of virtual well N1 and virtual well N2 in the target area, seismic data, and seismic interpretation scheme.
[0094] In this embodiment, seismic data within the target area and the actual velocity curve of virtual well N1 within the target area are used in constrained sparse pulse inversion to output a three-dimensional acoustic impedance data volume. Based on the acoustic impedance value range, the lithology is divided into three facies zones: sandstone, mudstone, and volcanic rock. Based on the divided facies zones, specific rock masses are sculpted to further determine the specific distribution of sandstone, mudstone, and volcanic rock. The acoustic impedance value ranges corresponding to each lithology type are shown in Table 2.
[0095] Table 2
[0096] Wave impedance numerical range Lithology 12000-15000 volcanic rock 10000-12000 sandstone 6000-10000 mudstone
[0097] The technical solution of this embodiment acquires seismic data within the target area, compares it with seismic data within the study area and well logging data from known wells, and trains an initial well velocity curve prediction model based on the seismic data within the study area and the well logging data from known wells to obtain a target well velocity curve prediction model. Based on the seismic data within the target area, multiple virtual well simulated velocity curves are determined. These virtual well simulated velocity curves are then input into the target well velocity curve prediction model to obtain the actual velocity curves of each virtual well. Based on an inversion algorithm, the lithology prediction results within the target area are determined according to the actual velocity curves of each virtual well and the seismic data within the target area, thereby improving the accuracy of lithology prediction.
[0098] Example 2
[0099] Figure 4 This is a schematic diagram of a lithology prediction device for a target area provided in an embodiment of the present invention. This embodiment is applicable to lithology prediction within a target area. The device can be implemented using software and / or hardware, and can be integrated into any device that provides lithology prediction functionality within a target area, such as… Figure 4 As shown, the lithology prediction device in the target area specifically includes: an acquisition module 410, a training module 420, a virtual well simulation velocity curve determination module 430, a virtual well actual velocity curve determination module 440, and a lithology prediction result determination module 450 in the target area.
[0100] The acquisition module is used to acquire seismic data within the target area, seismic data within the study area, and well logging data from known wells, wherein the study area is an adjacent work area to the target area.
[0101] The training module is used to train the initial well velocity curve prediction model based on seismic data and known well logging data in the study area, so as to obtain the target well velocity curve prediction model.
[0102] The virtual well simulation velocity curve determination module is used to determine multiple virtual well simulation velocity curves based on seismic data within the target area.
[0103] The virtual well actual velocity curve determination module is used to input the simulated velocity curves of each virtual well into the target well velocity curve prediction model to obtain the actual velocity curves of each virtual well.
[0104] The lithology prediction result determination module in the target area is used to determine the lithology prediction result in the target area based on the inversion algorithm, the actual velocity curves of each virtual well and the seismic data in the target area.
[0105] The above-described products can perform the methods provided in any embodiment of the present invention, and have the corresponding functional modules and beneficial effects for performing the methods.
[0106] Example 3
[0107] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0108] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0109] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0110] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as lithology prediction methods within the target area.
[0111] In some embodiments, the lithology prediction method within a target area may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lithology prediction method within a target area described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the lithology prediction method within a target area by any other suitable means (e.g., by means of firmware).
[0112] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0113] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0114] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0117] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0118] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0119] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the lithology prediction method for the target area according to any embodiment of the invention.
[0120] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages or a combination thereof. Programming languages include object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0121] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for predicting lithology within a target area, characterized in that, include: Acquire seismic data within the target area, along with seismic data within the study area and known well logging data, wherein the study area is an adjacent work area to the target area; Based on seismic data and well logging data in the study area, the initial well velocity curve prediction model was trained to obtain the target well velocity curve prediction model. Based on seismic data within the target area, multiple virtual well simulation velocity curves were determined; The simulated velocity curves of each virtual well are input into the velocity curve prediction model of the target well to obtain the actual velocity curves of each virtual well. Based on the inversion algorithm, the lithology prediction results in the target area are determined according to the actual velocity curves of each virtual well and the seismic data in the target area.
2. The method according to claim 1, characterized in that, The seismic data within the study area includes: seismic reflection coefficient curves and well depth curves of multiple known wells within the study area; Based on seismic data and known well logging data within the study area, the initial well velocity curve prediction model was trained to obtain the target well velocity curve prediction model, including: Based on the seismic reflection coefficient curves and well depth curves of multiple known wells in the study area, the simulated velocity curves of each known well in the study area are determined. Based on the logging data of each known well in the study area, plot the actual velocity curves of each known well in the study area; A training sample set is created based on the simulated velocity curves and actual velocity curves of each known well in the study area. Based on the training sample set, the initial well velocity curve prediction model is trained to obtain the target well velocity curve prediction model.
3. The method according to claim 2, characterized in that, Based on the training sample set, the initial well velocity curve prediction model is trained to obtain the target well velocity curve prediction model, including: Based on the training sample set, the initial well velocity curve prediction model is trained to obtain a trained well velocity curve prediction model. A test sample set is created based on the simulated velocity curves of multiple known wells in the study area and the actual velocity curves of multiple known wells in the study area, wherein the intersection of the samples in the test sample set and the samples in the training sample set is empty; The simulated velocity curves of known wells in the study area of the test sample set are input into the trained well velocity curve prediction model to obtain the predicted velocity curves of known wells in the study area. If the correlation coefficient between the predicted velocity curve of a known well in the study area and the actual velocity curve of a known well in the study area is greater than or equal to the correlation coefficient threshold, then the trained well velocity curve prediction model is determined as the target well velocity curve prediction model.
4. The method according to claim 1, characterized in that, Based on the inversion algorithm, and according to the actual velocity curves of each virtual well and the seismic data within the target area, the lithological prediction results within the target area are determined, including: Based on the inversion algorithm, the three-dimensional wave impedance data volume is determined according to the actual velocity curves of each virtual well and the seismic data in the target area; Obtain the range of wave impedance values corresponding to each lithology; Based on the wave impedance value range corresponding to each lithology type, the three-dimensional wave impedance data volume is sculpted to obtain the distribution status information of each lithology type in the target area.
5. The method according to claim 1, characterized in that, The seismic data within the target area includes: seismic reflection coefficient curves of multiple virtual wells within the target area and well depth curves of multiple virtual wells within the target area; Based on seismic data within the target area, multiple virtual well simulation velocity curves were determined, including: Based on the seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area, the simulated velocity curves of multiple virtual wells are determined.
6. The method according to claim 5, characterized in that, Based on the seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area, multiple virtual well simulation velocity curves are determined, including: The seismic reflection coefficient curves and well depth curves of multiple virtual wells within the target area are trend-merged to obtain multiple virtual well simulated velocity curves.
7. A lithology prediction device for a target area, characterized in that, include: The acquisition module is used to acquire seismic data within the target area, seismic data within the study area, and well logging data from known wells, wherein the study area is an adjacent work area to the target area; The training module is used to train the initial well velocity curve prediction model based on seismic data and known well logging data in the study area, so as to obtain the target well velocity curve prediction model. The virtual well simulation velocity curve determination module is used to determine multiple virtual well simulation velocity curves based on seismic data within the target area. The virtual well actual velocity curve determination module is used to input the simulated velocity curves of each virtual well into the target well velocity curve prediction model to obtain the actual velocity curves of each virtual well. The lithology prediction result determination module in the target area is used to determine the lithology prediction result in the target area based on the inversion algorithm, the actual velocity curves of each virtual well and the seismic data in the target area.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the lithology prediction method for the target area as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the lithology prediction method for the target area as described in any one of claims 1-6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the lithology prediction method for the target area according to any one of claims 1-6.