Three-dimensional balance simulation method and device of strike-slip structure based on deep learning

Abstract

The invention provides a three-dimensional balance simulation method and device for a strike-slip structure based on deep learning, and relates to the technical field of strike-slip structure oil-gas exploration and evaluation design, and the method comprises the steps: determining the parameters of the strike-slip structure, so as to build a strike-slip structure development and evolution model; and determining a three-dimensional balance model of the strike-slip structure according to the strike-slip structure development and evolution model and the deep learning model. Therefore, the three-dimensional balance model suitable for the strike-slip structure area is established by utilizing geometric and kinematic sensitive parameters of the strike-slip structure characteristics, spatial variation parameters of the strike-slip structure characteristics and the deep learning model, manual operation is reduced, and strike-slip structure types, deformation degrees, deformation differences and spatial distribution characteristics of the strike-slip structure are provided for the strike-slip structure area. Effective three-dimensional space technical information is provided for reservoir forming history and exploration of the strike-slip structure oil and gas reservoir, the strike-slip structure oil and gas reservoir favorable reservoir forming blocks can be preferably selected, the prediction accuracy of the strike-slip structure oil and gas enrichment favorable blocks is improved, and the efficiency and cost of exploration evaluation of the complex structural zone oil and gas reservoir are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of strike-slip structure oil and gas exploration, evaluation and design, and in particular to a three-dimensional equilibrium simulation method and device for strike-slip structures based on deep learning. Background Art

[0002] The equilibrium simulation of strike-slip structures is a technical problem that needs to be solved in the long term for basin structural restoration and oil and gas exploration.

[0003] Existing balanced profiling techniques are only applicable to non-strike-slip tectonic zones and are not suitable for balanced simulation of tectonic evolution in strike-slip zones. This results in ineffective balanced simulation of strike-slip tectonic development and evolution, makes it difficult to correlate strike-slip deformation processes with oil and gas response mechanisms, and complicates the prediction of oil and gas enrichment and preservation zones within strike-slip tectonic systems, hindering oil and gas exploration in strike-slip zones. Furthermore, current balanced profiling techniques rely on manual or computer-assisted analysis, making them ineffective in resolving complex strike-slip tectonic geological problems. Consequently, there is an urgent need to develop balanced simulation methods for strike-slip structures.

[0004] In response to the problems of the prior art, the present invention provides a three-dimensional equilibrium simulation method and device for strike-slip structures based on deep learning. Summary of the Invention

[0005] In response to the problems of the current existing technology, the present invention provides a three-dimensional equilibrium simulation method and device for strike-slip structures based on deep learning, the method comprising:

[0006] Determine the parameters of strike-slip structures to establish a development and evolution model of strike-slip structures;

[0007] Based on the strike-slip structure development and evolution model and the deep learning model, a three-dimensional equilibrium model of the strike-slip structure is determined.

[0008] According to one embodiment of the present invention, the deep learning model includes: a first deep learning model, a second deep learning model, a third deep learning model and a fourth deep learning model;

[0009] The three-dimensional equilibrium model of the strike-slip structure is determined by the following steps:

[0010] Based on the strike-slip tectonic development and evolution model, a two-dimensional equilibrium profile model is established;

[0011] Based on the two-dimensional equilibrium profile model and the first deep learning model, a two-dimensional equilibrium profile inversion model is established, and in combination with the two-dimensional equilibrium profile model and the second deep learning model, an inversion three-dimensional equilibrium model is established;

[0012] Based on the inversion three-dimensional equilibrium model and the third deep learning model, a forward three-dimensional equilibrium model is established, and the three-dimensional equilibrium model of the strike-slip structure is determined by combining the inversion three-dimensional equilibrium model and the fourth deep learning model.

[0013] According to one embodiment of the present invention, a two-dimensional equilibrium cross-section model is established by the following steps:

[0014] Based on the strike-slip tectonic development and evolution model, a two-dimensional equilibrium profile is established to restore the evolution history from the strike-slip fault to the seismic geological profile;

[0015] Based on the two-dimensional balanced section, the coupling relationship between the fault throw, dip, stratum contact relationship, tearing point, fracture combination relationship, fold amplitude and two-dimensional section balance of the two-plate faults is simulated to establish the two-dimensional balanced section model.

[0016] According to one embodiment of the present invention, a two-dimensional equilibrium profile inversion model is established by the following steps:

[0017] Determine, based on the two-dimensional balanced profile model and the first deep learning model, the relationship between the fault throw, dip, stratigraphic contact relationship, tearing point, fracture combination relationship, and expansion rate, erosion amount, and structural amplitude of the two-plate faults, so as to establish the two-dimensional balanced profile inversion model;

[0018] The method further comprises:

[0019] The seismic geological profile is balanced inverted based on the two-dimensional balanced profile inversion model to establish a two-dimensional balanced profile of the strike-slip structure to restore the fault formation evolution history, and obtain the expansion rate, erosion amount, and structural amplitude that characterize the deformation degree of the strike-slip structure.

[0020] According to one embodiment of the present invention, an inversion three-dimensional equilibrium model is established by the following steps:

[0021] Based on the two-dimensional equilibrium profile inversion model, the two-dimensional equilibrium profile model, the three-dimensional seismic data and the second deep learning model, an inversion three-dimensional equilibrium simulation is performed to obtain an inversion three-dimensional equilibrium model of the development and evolution history of the strike-slip structure, and obtain the expansion rate, erosion amount and structural amplitude that characterize the three-dimensional spatial deformation degree of the strike-slip structure.

[0022] According to one embodiment of the present invention, a forward three-dimensional equilibrium model is established by the following steps:

[0023] Based on the inverted three-dimensional equilibrium model, forward parameters of the three-dimensional equilibrium section are set, and forward simulation of the three-dimensional equilibrium section is performed using the third deep learning model to establish the forward three-dimensional equilibrium model, thereby obtaining the expansion rate, erosion amount, and structural amplitude that characterize the three-dimensional spatial deformation degree of the strike-slip structure;

[0024] The forward modeling parameters of the three-dimensional balanced profile include: the nature of the strike-slip structure, fault throw, dip angle, stratum contact relationship, tearing point and fault combination relationship.

[0025] According to one embodiment of the present invention, a three-dimensional equilibrium model of the strike-slip structure is established by the following steps:

[0026] Calculating the degree of agreement between the inverse three-dimensional equilibrium model and the forward three-dimensional equilibrium model based on the fourth deep learning model;

[0027] If the degree of fit is greater than a target threshold, the model whose degree of fit reaches the target threshold is determined as the three-dimensional equilibrium model of the strike-slip structure.

[0028] According to one embodiment of the present invention, the parameters of the strike-slip structure include: properties, fault throw, dip, stratum contact relationship, tearing point, fault combination relationship and type;

[0029] The strike-slip tectonic development and evolution model is established through the following steps:

[0030] The three-dimensional seismic data are interpreted to determine the parameters of the strike-slip structure and to establish a development and evolution model of the strike-slip structure.

[0031] According to another aspect of the present invention, a storage medium is provided, which contains a series of instructions for executing the method steps described in any one of the above.

[0032] According to another aspect of the present invention, there is also provided a three-dimensional equilibrium simulation device for strike-slip structures based on deep learning, which performs any of the above methods, and the device comprises:

[0033] The first determination module is used to determine the parameters of the strike-slip structure to establish a strike-slip structure development and evolution model;

[0034] The second determination module is used to determine the three-dimensional equilibrium model of the strike-slip structure based on the strike-slip structure development and evolution model and the deep learning model.

[0035] The present invention provides a deep learning-based three-dimensional equilibrium simulation method and device for strike-slip structures, which has the following advantages over existing technologies:

[0036] 1) The present invention utilizes the geometric and kinematic sensitive parameters of strike-slip structural characteristics and their spatial variation parameters and deep learning models to establish a three-dimensional equilibrium model suitable for strike-slip structural areas, reducing manual operations and providing strike-slip structural types, deformation degrees, deformation differences, and their spatial distribution characteristics for strike-slip structural areas, providing effective technical information for strike-slip structural oil and gas exploration;

[0037] 2) The present invention applies a three-dimensional equilibrium simulation method for strike-slip structures to perform three-dimensional equilibrium simulation of strike-slip structural areas to determine the development and evolution of strike-slip structures, deformation history, and lateral spatial evolution characteristics and laws. On this basis, the degree of structural deformation of sub-level structural units in the strike-slip structural area is evaluated based on the obtained parameter evaluation indicators such as expansion rate, erosion amount, and structural amplitude, thereby improving the efficiency of oil and gas exploration, improving the efficiency of in-depth evaluation of oil and gas reservoirs in oil and gas exploration, and accelerating the progress of oil and gas exploration;

[0038] 3) The present invention organically integrates various geometric and kinematic parameters in the study of strike-slip structural deformation. Based on the parameter evaluation index of strike-slip structure and the deep learning model, it learns the three-dimensional equilibrium model of strike-slip structure development under the constraints of forward and inverse modeling, and establishes a three-dimensional equilibrium model of strike-slip structure that conforms to the geological conditions of the region. The model is used to characterize the longitudinal deformation degree and difference of each evolutionary stage of the strike-slip structure, the deformation degree and difference of each unit structure in the horizontal direction, and the spatial distribution characteristics, so as to select favorable blocks for oil and gas exploration in the strike-slip structural area, improve the prediction accuracy of favorable blocks, improve the efficiency of oil and gas exploration, and reduce the exploration and evaluation cost of oil and gas reservoirs in complex structural belts.

[0039] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained through the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0041] Figure 1 A flowchart of a three-dimensional equilibrium simulation method of strike-slip structures based on deep learning according to an embodiment of the present invention is shown;

[0042] Figure 2 A block diagram of a three-dimensional equilibrium simulation device for strike-slip structures based on deep learning according to an embodiment of the present invention is shown.

[0043] In the accompanying drawings, the same reference numerals are used for the same parts. In addition, the accompanying drawings are not drawn according to the actual scale. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions and advantages of the present invention more clear, embodiments of the present invention are described in further detail below with reference to the accompanying drawings.

[0045] Currently, due to the limitations of the "mass conservation" principle of non-strike-slip structural equilibrium profiles, the non-strike-slip structural equilibrium profile method cannot be directly and effectively applied to the problem of structural equilibrium simulation and spatially differential deformation in strike-slip tectonic areas with "mass non-conservation" in structural profiles. The emergence of deep learning technology has provided a new technical solution for three-dimensional equilibrium simulation of strike-slip tectonic evolution. With the deepening of oil and gas exploration, in addition to oil and gas reservoirs under extensional and compressional tectonic systems, a number of oil and gas reservoirs under the control of strike-slip tectonic systems have been discovered in recent years. Restoring strike-slip structural equilibrium, determining the extent of strike-slip structural deformation, and determining the stages of superimposed transformation are key aspects of exploration and evaluation of these types of oil and gas reservoirs.

[0046] Therefore, it is urgent to develop a new method for simulating the tectonic evolution equilibrium in strike-slip tectonic areas, so as to accurately determine the development and evolution stages, degree of superposition and transformation, degree of deformation and its spatial variation of strike-slip tectonic structures, and then clarify the differences in strike-slip tectonic characteristics and differences in oil and gas enrichment and preservation, so as to provide accurate geological information for oil and gas exploration and favorable target evaluation in strike-slip tectonic areas. This is not only conducive to predicting the spatial distribution law of oil and gas enrichment and preservation, but also can better guide deep oil and gas exploration in strike-slip tectonic areas, improve exploration efficiency and reduce exploration risks.

[0047] In the prior art (CN106842293A), a balanced profile restoration method based on the ancient topographic features of the delta front is mentioned. This prior art is a balanced profile restoration method for analyzing the tectonic development and evolution history of the delta front. It is a two-dimensional restoration method that takes into account the original form of the ancient landform; it is different from the three-dimensional balanced simulation method and application scenario in the present invention. At the same time, this prior art uses the ancient slope angle of the stratum sedimentary period as the reference plane to complete the restoration of each period of tectonic evolution during the delta front deposition. The parameter selection accurately restores the ancient slope angle and stratum compaction, and the human factor has a greater impact. In addition, this method can only restore the schematic restoration of the sedimentary style of the delta front evolution process, without considering the influence of structural deformation, etc., and cannot provide better constraints and guidance for oil and gas exploration. It is different from the operating steps in the present invention.

[0048] The prior art (3D Structural Simulation Method - Research on Body Balancing Technology) focuses on the principles and recovery steps of body balancing technology used in 3D structural simulation. The method is relatively simple, performing only conventional fault and deformation recovery, which differs from the operational steps of the present invention. This prior art provides a general introduction to 3D body balancing technology, but in specific applications, it fails to provide targeted analysis of compression, extension, and strike-slip structures, resulting in relatively crude results. This differs from the application targets of the present invention.

[0049] The prior art (Balanced Profile Restoration and Tectonic Evolution Analysis of Typical Seismic Profiles in the Longmenshan Fold-Thrust Belt) utilizes Geo-sec's two-dimensional balanced profile structural restoration technology for analysis of the Longmenshan Fold-Thrust Belt, primarily targeting the restoration of structures formed by the superposition of multiple periods of compression; this differs from the application scenario of the present invention. Furthermore, the balanced profile restoration technology employed in this prior art primarily relies on geometric principles, imposing quantitative constraints on elements such as area, layer length, displacement, and shortening within the profile. This primarily involves horizontal layer flattening of the two-dimensional profile, making it suitable for deformation recovery in extensional and compressional tectonic settings and ineffective for strike-slip tectonic balance restoration.

[0050] In the prior art (the study of the fracture system for three-dimensional structural balance restoration in the Yunjin area of ​​southern Sichuan), three-dimensional modeling and three-dimensional structural balance restoration technology were used, which mainly included five steps: seismic data preparation, fault model establishment, stratum model establishment, inspection of stratum and fault model structure, and three-dimensional structural balance restoration. The balance recovery method used in this prior art sets the inclination angle of the fault in the seismic reflection profile, trajectory, contact relationship between strata and faults, and strata, and the like. The parameter selection is all artificially selected, and the results fluctuate greatly depending on the parameter selection. This is different from the steps of the three-dimensional balance simulation in the present invention. In the present invention, by establishing a three-dimensional balance model, the influence of human factors can be effectively reduced.

[0051] In response to the above-mentioned defects of the prior art, the present invention provides a three-dimensional equilibrium simulation method and device for strike-slip structures based on deep learning. Figure 1 A flowchart of a three-dimensional equilibrium simulation method of strike-slip structures based on deep learning according to an embodiment of the present invention is shown. The method includes:

[0052] S101, determine the parameters of strike-slip structures to establish a strike-slip structure development and evolution model;

[0053] S102: Determine a three-dimensional equilibrium model of the strike-slip structure based on the strike-slip structure development and evolution model and the deep learning model.

[0054] Strike-slip structure parameters may include: properties, fault throw, dip, stratigraphic contact relationships, tear points, fault combination relationships, and types. For example, two-dimensional and three-dimensional forward and inversion simulations can be performed based on the strike-slip structure development and evolution model and the deep learning model, respectively, to determine a three-dimensional equilibrium model of the strike-slip structure.

[0055] Furthermore, the strike-slip tectonic evolution model can be used to determine the evaluation parameters used in the deep learning model to characterize the development and evolution of strike-slip tectonic structures and the degree of deformation. These evaluation parameters include horizontal slip distance, vertical fault throw, strike-slip direction, tear point and the corresponding relationship between the two plates, and oblique slip distance and direction. The selection criteria for these evaluation parameters are: they must be able to distinguish the types and variations of strike-slip structures along the structural strike in the study area; and they must effectively reflect the clear and orderly variation of the degree of deformation along the structural strike. Thus, the strike-slip tectonic evolution model can be used to determine the evaluation criteria used in the deep learning model, thereby establishing the parameter types and standards for the deep learning model.

[0056] Among them, the deep learning model can be used to obtain the geometric parameter types and numerical standards for evaluating the development, evolution, and deformation degree of restored strike-slip structures. Geometric parameter types can include: expansion rate, erosion amount, and structural amplitude. The selection criteria for geometric parameter types are: they must be able to distinguish the strike-slip structural deformation mode and its changes along the structural dip of the study area; they must be able to effectively reflect the clear and orderly changes in the degree of strike-slip structural deformation along the structural dip. In this way, the geometric parameter types and their corresponding numerical standards can effectively reflect the degree of strike-slip structural deformation, so as to more accurately evaluate the established two-dimensional equilibrium profile inversion model, inversion three-dimensional equilibrium model, forward three-dimensional equilibrium model, three-dimensional equilibrium model, and other models.

[0057] The present invention uses the geometric and kinematic sensitive parameters of strike-slip structural characteristics and their spatial variation parameters and deep learning models to establish a three-dimensional equilibrium model suitable for strike-slip structural areas, reducing manual operations and providing strike-slip structural types, deformation degrees, deformation differences and their spatial distribution characteristics for strike-slip structural areas, providing effective technical information for strike-slip structural oil and gas exploration.

[0058] The present invention applies a three-dimensional equilibrium simulation method for strike-slip structures to perform three-dimensional equilibrium simulation on strike-slip structural areas to determine the development and evolution of strike-slip structures, deformation history, and lateral spatial evolution characteristics and laws. On this basis, the degree of structural deformation of sub-level structural units in the strike-slip structural area is evaluated based on obtained parameter evaluation indicators such as expansion rate, erosion amount, and structural amplitude, thereby improving the efficiency of oil and gas exploration, improving the efficiency of in-depth evaluation of oil and gas reservoirs in oil and gas exploration, and accelerating the progress of oil and gas exploration.

[0059] The present invention organically integrates various geometric and kinematic parameters used in strike-slip structural deformation research. Based on the parameter evaluation index of strike-slip structure and the deep learning model, the present invention learns the three-dimensional equilibrium model of strike-slip structure development under the constraints of forward and inverse modeling, and establishes a three-dimensional equilibrium model of strike-slip structure that conforms to the geological conditions of the region. The model is used to characterize the longitudinal deformation degree and difference of the strike-slip structure in each evolutionary stage, the deformation degree and difference of each unit structure in the horizontal direction, and the spatial distribution characteristics, so as to select favorable blocks for oil and gas exploration in strike-slip structural areas, improve the prediction accuracy of favorable blocks, improve the efficiency of oil and gas exploration, and reduce the exploration and evaluation cost of oil and gas reservoirs in complex structural belts.

[0060] In a possible embodiment, the deep learning model includes: a first deep learning model, a second deep learning model, a third deep learning model, and a fourth deep learning model;

[0061] The three-dimensional equilibrium model of strike-slip structures is determined by the following steps:

[0062] Based on the strike-slip tectonic development and evolution model, a two-dimensional equilibrium profile model was established;

[0063] Based on the two-dimensional equilibrium profile model and the first deep learning model, a two-dimensional equilibrium profile inversion model is established, and the two-dimensional equilibrium profile model and the second deep learning model are combined to establish an inverted three-dimensional equilibrium model;

[0064] Based on the inversion three-dimensional equilibrium model and the third deep learning model, a forward three-dimensional equilibrium model is established. Combined with the inversion three-dimensional equilibrium model and the fourth deep learning model, the three-dimensional equilibrium model of the strike-slip structure is determined.

[0065] Among them, a two-dimensional equilibrium profile model from a strike-slip fault to a seismic geological profile (i.e., forward modeling) can be established based on the strike-slip structure development and evolution model. Then, the two-dimensional equilibrium profile model is input into the first deep learning model to establish a two-dimensional equilibrium profile inversion model from the seismic geological profile to the strike-slip fault (i.e., inversion). Afterwards, the two-dimensional equilibrium profile model and the two-dimensional equilibrium profile inversion model are input into the second deep learning model to establish an inversion three-dimensional equilibrium model. Then, the inversion three-dimensional equilibrium model is input into the third deep learning model to establish a forward three-dimensional equilibrium model. Finally, the forward three-dimensional model and the inversion three-dimensional model are input into the fourth deep learning model to determine the three-dimensional equilibrium model of the strike-slip structure. In this way, the three-dimensional balance can be completed automatically, which reduces manual operations, improves the accuracy and efficiency of the three-dimensional balance processing, and increases the dimension of the balance simulation.

[0066] In a possible embodiment, a two-dimensional equilibrium cross-section model is established by the following steps:

[0067] Based on the strike-slip tectonic development and evolution model, a two-dimensional equilibrium profile is established to restore the evolution history from strike-slip faults to seismic geological profiles;

[0068] Based on the two-dimensional balanced section, the coupling relationship between the fault throw, dip, stratigraphic contact relationship, tearing point, fault combination relationship, fold amplitude and two-dimensional section balance of the two-plate faults was simulated to establish a two-dimensional balanced section model.

[0069] For example, based on the parameters of the strike-slip tectonic development and evolution model and the theory of two-dimensional equilibrium sections, a two-dimensional equilibrium recovery can be performed from the strike-slip fault to the seismic geological section to establish a two-dimensional equilibrium section. Then, through the two-dimensional equilibrium section simulation, the fault throw, dip, stratigraphic contact relationship, tear point, fault combination relationship, and fold amplitude of the two plates can be obtained. The coupling relationship between these parameters and the two-dimensional section equilibrium is then determined to establish a two-dimensional equilibrium section model. In this way, a two-dimensional equilibrium section model suitable for strike-slip tectonic areas can be established, providing a basis for the establishment of a three-dimensional equilibrium model.

[0070] In a possible embodiment, a two-dimensional equilibrium profile inversion model is established by the following steps:

[0071] Based on the two-dimensional balanced profile model and the first deep learning model, the relationship between the fault throw, dip, stratigraphic contact, tear point, fracture combination relationship and expansion rate, erosion amount, and structural amplitude of the two-wall fault is determined to establish a two-dimensional balanced profile inversion model;

[0072] The method also includes:

[0073] Based on the two-dimensional balanced profile inversion model, the seismic geological profile is balanced inverted to establish a two-dimensional balanced profile for restoring the fault formation evolution history of the strike-slip structure, and the expansion rate, erosion amount, and structural amplitude that characterize the deformation degree of the strike-slip structure are obtained.

[0074] The two-dimensional balanced profile model can be used to determine the throw, dip, stratigraphic contact, tear point, fracture combination, expansion rate, erosion volume, and structural amplitude of the two-plate faults. Furthermore, the first deep learning model can be used to determine the relationship between the throw, dip, stratigraphic contact, tear point, fracture combination, expansion rate, erosion volume, and structural amplitude of the two-plate faults, thereby establishing a two-dimensional balanced profile inversion model. This allows the establishment of a two-dimensional balanced profile inversion model suitable for strike-slip tectonic zones, providing a basis for the establishment of a three-dimensional balanced model.

[0075] Based on the 2D balanced section inversion model, a balanced inversion is then performed on other seismic geological sections to establish a 2D balanced section that restores the seismic geological section to the strike-slip fault (i.e., a 2D balanced section that restores the fault formation evolution history through strike-slip tectonic restoration). This 2D balanced section with the strike-slip tectonic restoration fault formation evolution history is then simulated to obtain the expansion and contraction rate, erosion amount, and structural amplitude that characterize the deformation degree of the strike-slip structure. This allows for an accurate assessment of the lateral and longitudinal deformation degrees of the 2D balanced section inversion model within the strike-slip tectonic zone.

[0076] The first deep learning model can be trained in the following way: obtain a training sample set, which includes: a two-dimensional balanced profile model, the fault throw, dip, stratigraphic contact relationship, tearing point, fracture combination relationship and the relationship between the expansion rate, erosion amount, and structural amplitude of the two-plate fault, train the model according to the training sample set, and determine the trained model as the first deep learning model.

[0077] In a possible embodiment, the inversion three-dimensional equilibrium model is established by the following steps:

[0078] Based on the two-dimensional equilibrium profile inversion model, the two-dimensional equilibrium profile model, the three-dimensional seismic data and the second deep learning model, an inversion three-dimensional equilibrium simulation is performed to obtain an inversion three-dimensional equilibrium model of the development and evolution history of the strike-slip structure, and the expansion rate, erosion amount and structural amplitude that characterize the three-dimensional spatial deformation degree of the strike-slip structure are obtained.

[0079] The 2D equilibrium profile inversion model, the 2D equilibrium profile model, and 3D seismic data can be input into a second deep learning model to obtain an inverted 3D equilibrium model of the developmental evolution history of strike-slip structures. This inverted 3D equilibrium model is then simulated to determine the expansion rate, amount of erosion, and structural amplitude. This establishes an inverted 3D equilibrium model suitable for strike-slip tectonic zones, providing a basis for establishing 3D equilibrium models. Furthermore, the degree of 3D lateral and longitudinal deformation in the inverted 3D equilibrium model in strike-slip tectonic zones can be accurately evaluated, constraining the inverted 3D equilibrium model.

[0080] The second deep learning model can be trained in the following way: obtain a training sample set, the training sample set includes: a two-dimensional balanced profile inversion model, a two-dimensional balanced profile model, three-dimensional seismic data, and an inverted three-dimensional balanced model; train the model according to the training sample set, and determine the trained model as the second deep learning model.

[0081] In a possible embodiment, a forward three-dimensional equilibrium model is established by the following steps:

[0082] Based on the inverted 3D equilibrium model, the forward parameters of the 3D equilibrium section are set, and the forward simulation of the 3D equilibrium section is performed using the third deep learning model to establish a forward 3D equilibrium model and obtain the expansion rate, erosion amount, and structural amplitude that characterize the 3D spatial deformation degree of the strike-slip structure;

[0083] The forward modeling parameters of the three-dimensional balanced profile include the nature of the strike-slip structure, fault throw, dip angle, stratigraphic contact relationship, tearing point and fault combination relationship.

[0084] Based on the inverted 3D equilibrium model, the forward parameters of the 3D equilibrium profile can be set. This is then fed into a third deep learning model for forward simulation of the 3D equilibrium profile to establish a forward 3D equilibrium model. This model can then be used to determine the expansion rate, erosion volume, and tectonic amplitude. This establishes a forward 3D equilibrium model suitable for strike-slip tectonic zones, providing a basis for establishing 3D equilibrium models. This allows for accurate evaluation of the lateral and longitudinal deformation levels of the forward 3D equilibrium model in strike-slip tectonic zones and verification of the reliability of the inverted 3D equilibrium model.

[0085] The magnitude and orderly changes of the quantitative values ​​of geometric parameters in forward and inverse 3D equilibrium models of strike-slip structures can effectively express the orderly changes and distribution patterns of spatial deformation in strike-slip structures, establishing a 3D spatial equilibrium model controlled by the coupled control of geometric deformation parameters in multiple directions, including strike and dip. The quantitative values ​​of geometric deformation parameters in forward and inverse 3D equilibrium models of strike-slip structures can effectively distinguish different types of strike-slip structures, establishing a 3D equilibrium model of their coordinated development. The 3D spatial distribution results in forward and inverse 3D equilibrium models of strike-slip structures should be able to reflect the differences in the main controlling factors of oil and gas enrichment in each structural sub-area.

[0086] The third deep learning model can be trained in the following way: obtain a training sample set, the training sample set includes: an inverted three-dimensional equilibrium model, forward parameters of a three-dimensional equilibrium profile, and a forward three-dimensional equilibrium model; train the model according to the training sample set, and determine the trained model as the third deep learning model.

[0087] In a possible embodiment, a three-dimensional equilibrium model of the strike-slip structure is established by the following steps:

[0088] The consistency between the inverse 3D equilibrium model and the forward 3D equilibrium model is calculated based on the fourth deep learning model;

[0089] If the degree of fit is greater than the target threshold, the model with the degree of fit reaching the target threshold is determined as the three-dimensional equilibrium model of the strike-slip structure.

[0090] For example, the target threshold can be determined according to the actual application scenario, and the present invention sets it to 95%. Among them, the inversion three-dimensional equilibrium model and the forward three-dimensional equilibrium model can be input into the fourth deep learning model to determine the degree of fit. If the degree of fit is greater than the target threshold, the model whose degree of fit reaches the target threshold is determined as the three-dimensional equilibrium model of the strike-slip structure. If the degree of fit is less than or equal to the target threshold, the parameters are reset to perform the forward and inversion three-dimensional equilibrium simulation multiple times until the degree of fit reaches the target threshold. In this way, the three-dimensional equilibrium model of the strike-slip structure determined is more accurate, so that the development and evolution period, superposition transformation degree, deformation degree and spatial variation of the strike-slip structure can be accurately determined, and the differences in strike-slip structural characteristics and oil and gas enrichment and preservation can be clarified, providing accurate geological information for oil and gas exploration and favorable target evaluation in strike-slip structural areas, which is not only conducive to predicting the spatial distribution law of oil and gas enrichment and preservation, but also can better guide deep oil and gas exploration in strike-slip structural areas, improve exploration efficiency and reduce exploration risks.

[0091] The fourth deep learning model can be trained in the following way: obtain a training sample set, which includes: an inverse three-dimensional equilibrium model, a forward three-dimensional equilibrium model, and a degree of fit; train the model according to the training sample set, and determine the trained model as the fourth deep learning model.

[0092] In a possible embodiment, a strike-slip tectonic development and evolution model is established by the following steps:

[0093] The three-dimensional seismic data are interpreted to determine the parameters of the strike-slip structure and to establish a model of the development and evolution of the strike-slip structure.

[0094] For example, based on the geological background and strike-slip structure type, the three-dimensional seismic data of the strike-slip structure area can be interpreted with high precision to determine the parameters of the strike-slip structure, and the type of the strike-slip structure can be determined based on the parameters and a strike-slip structure development and evolution model can be established.

[0095] The deep learning-based three-dimensional equilibrium simulation method for strike-slip structures provided by the present invention may also be used in conjunction with a computer-readable storage medium having a computer program stored thereon. The computer program is executed to implement the deep learning-based three-dimensional equilibrium simulation method for strike-slip structures. The computer program is capable of executing computer instructions, which include computer program code. The computer program code may be in source code form, object code form, executable file, or some intermediate form.

[0096] Computer-readable storage media may include: any entity or device that can carry computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0097] It should be noted that the content contained in computer-readable storage media can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable storage media do not include electrical carrier signals and telecommunications signals.

[0098] According to another aspect of the present invention, a three-dimensional balance simulation device for strike-slip structure based on deep learning is also provided. Figure 2 A block diagram of a three-dimensional equilibrium simulation device for strike-slip structures based on deep learning according to an embodiment of the present invention is shown. Figure 2 As shown, the device includes:

[0099] A first determination module 510 is used to determine parameters of the strike-slip structure to establish a strike-slip structure development and evolution model;

[0100] The second determination module 520 is used to determine the three-dimensional equilibrium model of the strike-slip structure based on the strike-slip structure development and evolution model.

[0101] In summary, the present invention provides a deep learning-based three-dimensional equilibrium simulation method and device for strike-slip structures, which has the following advantages over the existing technology:

[0102] 1) The present invention utilizes the geometric and kinematic sensitive parameters of strike-slip structural characteristics and their spatial variation parameters and deep learning models to establish a three-dimensional equilibrium model suitable for strike-slip structural areas, reducing manual operations and providing strike-slip structural types, deformation degrees, deformation differences, and their spatial distribution characteristics for strike-slip structural areas, providing effective technical information for strike-slip structural oil and gas exploration;

[0103] 2) The present invention applies a three-dimensional equilibrium simulation method for strike-slip structures to perform three-dimensional equilibrium simulation of strike-slip structural areas to determine the development and evolution of strike-slip structures, deformation history, and lateral spatial evolution characteristics and laws. On this basis, the degree of structural deformation of sub-level structural units in the strike-slip structural area is evaluated based on the obtained parameter evaluation indicators such as expansion rate, erosion amount, and structural amplitude, thereby improving the efficiency of oil and gas exploration, improving the efficiency of in-depth evaluation of oil and gas reservoirs in oil and gas exploration, and accelerating the progress of oil and gas exploration;

[0104] 3) The present invention organically integrates various geometric and kinematic parameters in the study of strike-slip structural deformation. Based on the parameter evaluation index of strike-slip structure and the deep learning model, it learns the three-dimensional equilibrium model of strike-slip structure development under the constraints of forward and inverse modeling, and establishes a three-dimensional equilibrium model of strike-slip structure that conforms to the geological conditions of the region. The model is used to characterize the longitudinal deformation degree and difference of each evolutionary stage of the strike-slip structure, the deformation degree and difference of each unit structure in the horizontal direction, and the spatial distribution characteristics, so as to select favorable blocks for oil and gas exploration in the strike-slip structural area, improve the prediction accuracy of favorable blocks, improve the efficiency of oil and gas exploration, and reduce the exploration and evaluation cost of oil and gas reservoirs in complex structural belts.

[0105] It should be understood that the embodiments disclosed herein are not limited to the specific structures, processing steps, or materials disclosed herein, but should extend to equivalent substitutions of these features understood by those skilled in the relevant art. It should also be understood that the terminology used herein is for the purpose of describing specific embodiments only and is not intended to be limiting.

[0106] In the description of the present invention, unless otherwise specified, "plurality" means two or more; terms such as "upper," "lower," "left," "right," "inner," "outer," "front end," "rear end," "head," and "tail" indicate positions or relationships based on those shown in the accompanying drawings. These terms are intended solely to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, terms such as "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0107] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "connected" and "connection" should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integral connection; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediary. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0108] Certain terms are used throughout this application document to indicate specific system components. As will be appreciated by those skilled in the art, different names may be used to indicate the same component, and thus this application document is not intended to distinguish between components that are only different in name but not in function. In this application document, the terms "comprise," "include," and "have" are used in an open format and should therefore be interpreted as meaning "including, but not limited to...". In addition, the terms "substantially," "substantially," or "approximately" that may be used herein refer to industry-accepted tolerances for the corresponding terms. The term "coupling," as used herein, includes direct coupling and indirect coupling via another component, element, circuit, or module, wherein for indirect coupling, the intervening component, element, circuit, or module does not change the information of the signal but can adjust its current level, voltage level, and / or power level. Inferred coupling (e.g., one element is coupled to another element by inference) includes direct and indirect coupling between two elements in the same manner as "coupling."

[0109] References in this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "one embodiment" or "an embodiment" in various places throughout this specification do not necessarily refer to the same embodiment.

[0110] The embodiments of the present invention are presented for purposes of illustration and description and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments are chosen and described in order to better illustrate the principles of the invention and its practical application and to enable those skilled in the art to understand the invention and design various embodiments with various modifications as suited for specific applications.

[0111] Although the embodiments disclosed herein are as described above, the contents described herein are merely embodiments for facilitating understanding of the present invention and are not intended to limit the present invention. Any person skilled in the art of the present invention may make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed herein. However, the scope of patent protection of the present invention shall still be subject to the scope defined by the appended claims.

Claims

1. A three-dimensional equilibrium simulation method of strike-slip structure based on deep learning, characterized in that: The method comprises: Determine the parameters of strike-slip structures to establish a development and evolution model of strike-slip structures; Based on the strike-slip structure development and evolution model and the deep learning model, a three-dimensional equilibrium model of the strike-slip structure is determined.

2. The method according to claim 1, wherein The deep learning model includes: a first deep learning model, a second deep learning model, a third deep learning model and a fourth deep learning model; The three-dimensional equilibrium model of the strike-slip structure is determined by the following steps: Based on the strike-slip tectonic development and evolution model, a two-dimensional equilibrium profile model is established; Based on the two-dimensional equilibrium profile model and the first deep learning model, a two-dimensional equilibrium profile inversion model is established, and in combination with the two-dimensional equilibrium profile model and the second deep learning model, an inverted three-dimensional equilibrium model is established; Based on the inversion three-dimensional equilibrium model and the third deep learning model, a forward three-dimensional equilibrium model is established, and the three-dimensional equilibrium model of the strike-slip structure is determined by combining the inversion three-dimensional equilibrium model and the fourth deep learning model.

3. The method according to claim 2, wherein The two-dimensional equilibrium cross-section model is established by the following steps: Based on the strike-slip tectonic development and evolution model, a two-dimensional equilibrium profile is established to restore the evolution history from the strike-slip fault to the seismic geological profile; Based on the two-dimensional balanced section, the coupling relationship between the fault throw, dip, stratum contact relationship, tearing point, fracture combination relationship, fold amplitude and two-dimensional section balance of the two-plate faults is simulated to establish the two-dimensional balanced section model.

4. The method according to claim 3, wherein The two-dimensional equilibrium profile inversion model is established by the following steps: Determine, based on the two-dimensional balanced profile model and the first deep learning model, the relationship between the fault throw, dip, stratigraphic contact relationship, tearing point, fracture combination relationship, and expansion rate, erosion amount, and structural amplitude of the two-plate faults, so as to establish the two-dimensional balanced profile inversion model; The method further comprises: The seismic geological profile is balanced inverted based on the two-dimensional balanced profile inversion model to establish a two-dimensional balanced profile of the strike-slip structure to restore the fault formation evolution history, and obtain the expansion rate, erosion amount, and structural amplitude that characterize the deformation degree of the strike-slip structure.

5. The method according to claim 4, wherein The inversion 3D equilibrium model is established by the following steps: Based on the two-dimensional equilibrium profile inversion model, the two-dimensional equilibrium profile model, the three-dimensional seismic data and the second deep learning model, an inversion three-dimensional equilibrium simulation is performed to obtain an inversion three-dimensional equilibrium model of the development and evolution history of the strike-slip structure, and obtain the expansion rate, erosion amount and structural amplitude that characterize the three-dimensional spatial deformation degree of the strike-slip structure.

6. The method according to claim 5, wherein The forward 3D equilibrium model is established by the following steps: Based on the inverted three-dimensional equilibrium model, forward parameters of the three-dimensional equilibrium section are set, and forward simulation of the three-dimensional equilibrium section is performed using the third deep learning model to establish the forward three-dimensional equilibrium model, thereby obtaining the expansion rate, erosion amount, and structural amplitude that characterize the three-dimensional spatial deformation degree of the strike-slip structure; The forward modeling parameters of the three-dimensional balanced profile include: the nature of the strike-slip structure, fault throw, dip angle, stratum contact relationship, tearing point and fault combination relationship.

7. The method according to claim 6, wherein The three-dimensional equilibrium model of the strike-slip structure is established by the following steps: Calculating the degree of agreement between the inverse three-dimensional equilibrium model and the forward three-dimensional equilibrium model based on the fourth deep learning model; If the degree of fit is greater than a target threshold, the model whose degree of fit reaches the target threshold is determined as the three-dimensional equilibrium model of the strike-slip structure.

8. The method according to any one of claims 1 to 7, wherein The parameters of the strike-slip structure include: nature, fault throw, dip, stratigraphic contact relationship, tear point, fault combination relationship and type; The strike-slip tectonic development and evolution model is established through the following steps: The three-dimensional seismic data are interpreted to determine the parameters of the strike-slip structure and to establish a development and evolution model of the strike-slip structure.

9. A three-dimensional equilibrium simulation device for strike-slip structures based on deep learning, characterized in that: The method according to any one of claims 1 to 8 is performed, wherein the apparatus comprises: The first determination module is used to determine the parameters of the strike-slip structure to establish a strike-slip structure development and evolution model; The second determination module is used to determine the three-dimensional equilibrium model of the strike-slip structure based on the strike-slip structure development and evolution model and the deep learning model.

10. A storage medium, characterized in that: It comprises a series of instructions for executing the method steps according to any one of claims 1-8.

Images