A method and system for automatically generating a two-dimensional seismic velocity model in oil exploration

Abstract

The present application relates to a kind of two-dimensional seismic velocity model automatic generation method and system in petroleum exploration, it includes: with diversity training sample to generate curved interface with combination linear function, sine function, based on stratum parameter generated by random number generator automatically generates two-dimensional layered velocity model;Extract the shape of multiple mushroom images as the basic form of salt dome, and after the basic form of salt dome is handled in posture, superimpose one of the mushroom images on the two-dimensional layered velocity model that rises upward, generate salt dome two-dimensional velocity model;With two-dimensional layered velocity model as basis, generate normal fault and reverse fault, construct two-dimensional fault velocity model;Determine the similarity between all two-dimensional layered velocity model, salt dome two-dimensional velocity model and two-dimensional fault velocity model, eliminate high similarity velocity model, obtain the diversity of two-dimensional seismic velocity model.The present application can provide the diversity of data guarantee for data-based seismic velocity inversion;In the field of oil and gas exploration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil and gas exploration, and particularly to a method and system for automatically generating a two-dimensional seismic velocity model in oil exploration. BACKGROUND

[0002] With the continuous development and progress of machine learning technology represented by deep learning, researchers of seismic exploration put forward a new idea of seismic velocity inversion based on machine learning, the key of which is to construct a diverse training sample set, each sample of which is composed of a seismic shot record (sample) and its corresponding velocity model (label). However, such a sample set cannot be constructed according to the basic principles of classical machine learning, that is, first collect seismic shot records, and then expertly label the velocity model. Therefore, researchers use the technical route of first generating a velocity model and then synthesizing a seismic record. Since deep learning requires extremely high configuration of computing resources, a large number of studies on velocity inversion still need to be carried out on two-dimensional velocity models. Therefore, how to construct a large number of diverse two-dimensional velocity models has become a key step in the research and development of this technology.

[0003] Currently, for three-dimensional velocity models, the geometric shapes of curved stratum interfaces and curved fault surfaces are generated based on the principles of computational geometry. The complex construction method of fold and fault velocity models proposed in existing documents is used for structural interpretation of three-dimensional seismic data. The existing documents only consider the simplified fault velocity model of the flat fault surface that penetrates the entire model, and on the other hand, the salt dome velocity model is constructed by using the Gaussian function (narrow at the top and wide at the bottom) to superimpose a relatively flat fold model, which is applied to three-dimensional velocity inversion. In geology, it is generally believed that salt domes are formed by magma eruption and cause the upward uplift of the surrounding strata. The salt dome model proposed in the existing document has a large deviation from the actual geological situation. In addition, neither of the two technologies performs similarity analysis on the generated velocity model, making it difficult to guarantee the diversity of the model. Overall, these two technologies focus on generating three-dimensional velocity models, and there are two shortcomings in simplifying to two-dimensional models: first, if a part of the two-dimensional velocity model is directly extracted, the computing resources will be wasted, and highly similar velocity models may appear; second, the calculation process is still too complex and tedious if it is directly simplified to a two-dimensional case. Therefore, it is necessary to develop an independent two-dimensional velocity model construction technology as a new research idea. SUMMARY

[0004] To solve the above problems, the present application aims to provide a method and system for automatically generating a two-dimensional seismic velocity model in oil exploration, which generates a velocity model with diversity and can provide diverse data guarantee for data-based seismic velocity inversion.

[0005] To achieve the above object, the present application adopts the following technical scheme: a two-dimensional seismic velocity model automatic generation method in petroleum exploration, comprising:

[0006] The diversity training samples are used to generate curved interfaces in combination with linear functions and sine functions, and the two-dimensional layered velocity model is automatically generated based on the stratum parameters generated by the random number generator;

[0007] The shapes of various mushroom images are extracted as the basic shapes of salt domes, and after the basic shapes of the salt domes are processed in poses, one of the mushroom images is superimposed on the upwardly protruding two-dimensional layered velocity model to generate a salt dome two-dimensional velocity model conforming to geological conditions;

[0008] Based on the two-dimensional layered velocity model, normal and reverse faults are generated to construct a two-dimensional fault velocity model;

[0009] The similarities between all two-dimensional layered velocity models, salt dome two-dimensional velocity models and two-dimensional fault velocity models are determined, the velocity models with high similarity are removed, and a two-dimensional seismic velocity model with diversity is obtained.

[0010] Further, the two-dimensional layered velocity model is generated, comprising:

[0011] The size and gridding interval of the two-dimensional layered velocity model are determined;

[0012] The stratum thickness value range is set, the left and right end stratum thicknesses of the two-dimensional layered velocity model are randomly generated, the left and right end strata are paired, and a straight line stratum interface is generated;

[0013] The curved interface of each stratum interface is calculated;

[0014] Based on the straight line stratum interface and the curved interface, the velocity value range and the minimum interval value of adjacent layer velocities are set, a series of layer velocities are randomly generated, and after being incrementally sorted, the layer velocities are assigned to each stratum to obtain a layered velocity model;

[0015] The layered velocity model is gridded, converted into a velocity matrix, and a two-dimensional layered velocity model is obtained.

[0016] Further, the left and right end strata are paired, comprising: when the cumulative thicknesses of the left and right ends both exceed a preset ground depth, the maximum number of strata is calculated.

[0017] Further, the basic shapes of the salt domes are processed in poses, comprising:

[0018] After the basic shapes of the salt domes are processed by combination of four operations of translation, scaling, rotation and distortion, the basic shapes are superimposed on the upwardly protruding two-dimensional layered velocity model.

[0019] Further, the generation of the salt dome two-dimensional velocity model comprises:

[0020] The collected mushroom images are converted into black and white images and scaled to a two-dimensional layered velocity matrix size;

[0021] A layered velocity matrix that is upwardly convex is generated using the generation method of the two-dimensional layered velocity model;

[0022] A mushroom black and white image is randomly selected, and one of the following operations is randomly selected: scaling down, scaling down + rotating, and scaling down + twisting, to generate a new mushroom image;

[0023] A center point is randomly selected in a set area, a velocity value is assigned to the mushroom part of the new mushroom image, and the new mushroom image is translated and superimposed on the layered velocity model to form a salt dome velocity model.

[0024] Further, the generation of the normal and reverse faults includes:

[0025] The starting point and the ending point of the fault line, the sliding direction and the distance of the fault are randomly selected, the sliding range of the fault block and the blank area are determined, the fault block is slid using the translation operation of the image, and the hanging wall of the fault is translated downward and upward to form a normal fault and a reverse fault, respectively.

[0026] Further, the generation of the two-dimensional fault velocity model includes:

[0027] A two-dimensional layered velocity matrix is obtained based on the two-dimensional layered velocity model, the starting point range and the ending point range of the fault line are defined in the upper left area and the lower right area of the two-dimensional layered velocity matrix, respectively, and the starting and ending points of the fault line are randomly generated in the two areas to define the range of the hanging wall of the fault.

[0028] The range of the fault sliding distance is set, the sliding distance value is randomly generated, and the sliding direction of the fault is randomly selected.

[0029] The blank area that appears after the sliding of the hanging wall of the fault is determined, the normal fault is filled with the velocity of the previous layer before sliding, the reverse fault is filled with the velocity of the next layer before sliding, and the fault velocity model is generated.

[0030] A two-dimensional seismic velocity model automatic generation system in oil exploration includes:

[0031] The two-dimensional layered velocity model generation module generates a curved interface using a combination of linear functions and sine functions based on stratigraphic parameters generated by a random number generator, and automatically generates a two-dimensional layered velocity model.

[0032] The salt dome two-dimensional velocity model generation module extracts the shapes of a plurality of mushroom images as the basic form of the salt dome, processes the basic form of the salt dome, and superimposes one of the mushroom images on the upwardly convex two-dimensional layered velocity model to generate a salt dome two-dimensional velocity model that conforms to geological conditions.

[0033] A two-dimensional fault velocity model generation module generates normal and reverse faults based on the two-dimensional layered velocity model, and constructs a two-dimensional fault velocity model;

[0034] A final model determination module determines the similarity between all two-dimensional layered velocity models, two-dimensional salt dome velocity models and two-dimensional fault velocity models, eliminates high-similarity velocity models, and obtains a two-dimensional seismic velocity model with diversity.

[0035] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the above methods.

[0036] A computing device comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the above methods.

[0037] The present application has the following advantages due to the above technical solutions:

[0038] The present application is based on image processing technology, combined with random number generator in statistics to automatically generate various model parameters, and proposes a new automatic generation technology of layered, salt dome and fault two-dimensional velocity model, which provides data guarantee with diversity for seismic velocity inversion based on data. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a flow chart of a two-dimensional seismic velocity model automatic generation method in petroleum exploration in an embodiment of the present application;

[0040] Figure 2a is a curved stratum interface (unit: meter) diagram of a two-dimensional layered velocity model in an embodiment of the present application;

[0041] Figure 2b is a gridded stratum model (interval: 10 meters) diagram of a two-dimensional layered velocity model in an embodiment of the present application;

[0042] Figure 2c is a velocity model diagram obtained after filling an increasing velocity value in a two-dimensional layered velocity model in an embodiment of the present application;

[0043] Figure 3 is a black and white image of twenty salt dome patterns from a mushroom image in an embodiment of the present application;

[0044] Figure 4a is a generated uplift stratum interface model (left) of a two-dimensional salt dome velocity model in an embodiment of the present application, and a layered velocity model (right) obtained after filling a velocity value;

[0045] Figure 4b is a basic form model of a salt dome selected in a two-dimensional salt dome velocity model in an embodiment of the present application (left), and a superimposed salt dome model is generated by translation / reduction / rotation / twist operation (right);

[0046] Figure 4c is a two-dimensional salt dome velocity model in an embodiment of the present application, in which the transformed salt dome style is superimposed on a doming layered velocity model to construct a two-dimensional salt dome velocity model;

[0047] Figure 5a is a layered velocity model in an embodiment of the present application, in which a two-dimensional normal fault velocity model is generated, the start and end points of the fault line (the middle diagonal white solid line) are determined, the area before the hanging wall of the fault slides (the narrow white dotted line, the middle diagonal white solid line, and the bottom and right boundary lines) is circled, the area after the fault slides (the wide white dotted line, the middle diagonal white solid line, and the bottom and right boundary lines) is circled, the blank area generated after the sliding is determined (the area between the two dotted lines), and the velocity value of the previous layer is filled in;

[0048] Figure 5b is a two-dimensional velocity model containing a normal fault finally generated in an embodiment of the present application;

[0049] Figure 6a is a normal fault of the four fault velocity models generated in an embodiment of the present application;

[0050] Figure 6b is a reverse fault of the four fault velocity models generated in an embodiment of the present application;

[0051] Figure 6c is a left-right flipped model of a normal fault of the four fault velocity models generated in an embodiment of the present application;

[0052] Figure 6d is a left-right flipped model of a reverse fault of the four fault velocity models generated in an embodiment of the present application. DETAILED DESCRIPTION

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of, rather than all of, the embodiments of the present application. Based on the described embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0054] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0055] The data-based seismic velocity inversion technique needs a large number of diverse training samples, i.e., seismic shot records and their corresponding velocity models. Due to the limitation of computing resources, current research work still needs to be carried out on two-dimensional velocity models, so that establishing a fast and effective two-dimensional velocity model becomes a basic data preparation work. The present application uses image processing technology to establish an efficient construction method of two-dimensional layered, salt dome and fault velocity models. A linear function plus a sine function is used to generate a curved interface of strata to construct a two-dimensional layered velocity model. Twenty mushroom images are collected, and one image is randomly selected and stacked on the upwardly protruding layered velocity model after image operations such as translation, reduction, rotation and distortion to generate a two-dimensional salt dome velocity model. Based on the two-dimensional layered velocity model, the sliding range, distance and direction of the hanging wall of the fault are determined, the hanging wall is translated downward to generate a normal fault, the hanging wall is translated upward to generate a reverse fault, and the blank area after sliding is filled to construct two-dimensional normal and reverse fault velocity models. In order to ensure the diversity of the generated two-dimensional velocity models, first, a statistical random number generator is used to automatically and randomly generate key parameters of various models, such as the bending degree of the strata interface, the layer velocity, the reduction ratio, the sliding distance, etc.; second, the Pearson correlation coefficient or the image structural similarity is used to remove velocity models with high similarity. The three kinds of two-dimensional velocity models constructed by the present application can provide strong data guarantee for the data-based seismic velocity inversion technique.

[0056] In one embodiment of the present application, a method for automatically generating a two-dimensional seismic velocity model in oil exploration is provided. In this embodiment, as shown in Figure 1 the method includes the following steps:

[0057] 1) The diversity training samples are combined with a linear function and a sine function to generate a curved interface, and a two-dimensional layered velocity model is automatically generated based on the strata parameters generated by the random number generator; wherein the strata parameters include strata thickness and bending, layer velocity;

[0058] 2) The shapes of a plurality of mushroom images are extracted as the basic form of the salt dome, and after the basic form of the salt dome is handled in a posture, one of the mushroom images is stacked on the upwardly protruding two-dimensional layered velocity model to generate a two-dimensional salt dome velocity model in accordance with geological conditions;

[0059] 3) Based on the two-dimensional layered velocity model, generate normal and reverse faults, and build a two-dimensional fault velocity model;

[0060] 4) Determine the similarity between all two-dimensional layered velocity models, salt dome two-dimensional velocity models, and two-dimensional fault velocity models, eliminate high-similarity velocity models, and obtain a diverse two-dimensional seismic velocity model.

[0061] In the above step 1), in the present embodiment, the generated two-dimensional layered velocity model is also gridded into matrix data form, and the two-dimensional velocity model is visually displayed as an image, as shown in Figures 2a to 2c .

[0062] In the above step 1), the two-dimensional layered velocity model is generated, including the following steps:

[0063] 1.1) Determine the size and gridding interval Δ of the two-dimensional layered velocity model;

[0064] In the present embodiment, the size of the two-dimensional layered velocity model includes the ground distance d x and the depth d z , where the upper left vertex is the origin, the x-axis is from left to right, and the z-axis is from top to bottom. The two-dimensional velocity model is mathematically expressed by a matrix V m╳n (where m and n are the number of points in the z and x directions, respectively), and visually displayed as an image (as shown in Figure 2c ).

[0065] 1.2) Set the range of stratum thickness [h min , h max ], randomly generate the stratum thickness at the left and right ends of the two-dimensional layered velocity model, pair the strata at the left and right ends, and generate straight stratum interfaces; where h min is the minimum stratum thickness; h max is the maximum stratum thickness;

[0066] 1.3) Calculate the curved interface of each stratum interface;

[0067] In the present embodiment, the curved interface is calculated using the formula ρ i h i sin(2πα i x+β i ), as shown in Figure 2a , where h i is the minimum stratum thickness at the interface, ρ i is a scale factor controlling the degree of fluctuation, α i controls the degree of curvature of the interface, and β i is the depth of the left endpoint. All three parameters are randomly generated within the specified range, and i represents the number of stratum interfaces.

[0068] 1.4) Based on the straight and curved stratigraphic interfaces, set the velocity range and the minimum interval value of adjacent layer velocities, randomly generate a series of layer velocities, and assign them to each layer in ascending order to obtain a layered velocity model to meet the geological rule of increasing velocity with depth;

[0069] 1.5) Grid the layered velocity model (as shown in FIG. 1) to convert it into a velocity matrix V and obtain a two-dimensional layered velocity model (as shown in FIG. 2). Figure 2b Figure 2c

[0070] In step 1.2) above, the left and right ends of the strata are paired, specifically: when the cumulative thickness of the left and right ends exceeds the preset ground depth d z , the maximum number of strata is calculated.

[0071] In each of the above steps, after step 1.5), a step of similarity rejection is further included: the Pearson correlation coefficient or image structural similarity between the current layered velocity model and the existing velocity model is calculated, and if the minimum value is less than a set threshold, the model is saved, otherwise the velocity model is discarded, to ensure the diversity of the generated velocity model.

[0072] Preferably, the threshold value of the Pearson correlation coefficient is 0.95, and the threshold value of the image structural similarity is 0.90. If the Pearson correlation coefficient is <0.95 or the image structural similarity is <0.90, the two-dimensional layered velocity model with high similarity is rejected.

[0073] In step 2) above, the basic form of the salt dome is processed in a pose, specifically:

[0074] After the basic form of the salt dome is processed by a combination of translation, scaling, rotation, and distortion, it is superimposed on the upwardly protruding two-dimensional layered velocity model.

[0075] In step 2) above, the generation of the salt dome two-dimensional velocity model includes the following steps:

[0076] 2.1) Convert the collected multiple mushroom images to black and white images and scale them to the size m×n of the two-dimensional layered velocity matrix;

[0077] In this embodiment, 20 mushroom images (as shown in FIG. 3) are preferred as the basic form of the salt dome; Figure 3

[0078] Among them, the structural similarity of the 20 mushroom images is less than 0.86.

[0079] 2.2) Generate a two-dimensional layered velocity matrix V (as shown in FIG. 4) using the two-dimensional layered velocity model generation method; Figure 4a ​​​​

[0080] 2.3) Randomly select a mushroom black and white image, and randomly select one of the operations of shrinking, shrinking + rotation, and shrinking + distortion to generate a new mushroom image Figure 4b .

[0081] 2.4) Randomly select a center point in a set area, assign a velocity value to the mushroom part of the new mushroom image, and then translate and superimpose it on the layered velocity model to form a salt dome velocity model, as shown in Figure 4c .

[0082] In the above steps, after step 2.4), a similarity elimination step is further included: similarity detection is performed, and according to a preset similarity threshold, velocity models with small similarity are retained. The similarity elimination in step 1) is the same as described above.

[0083] In step 3) above, normal and reverse faults are generated, specifically:

[0084] Randomly select the starting point and ending point of the fault line, the sliding direction and distance of the fault, determine the sliding range of the fault block and the blank area, and use the translation operation of the image to slide the fault block, and translate the hanging wall of the fault downward and upward to form normal faults and reverse faults.

[0085] In step 3) above, the generation of a two-dimensional fault velocity model includes the following steps:

[0086] 3.1) Based on a two-dimensional layered velocity model, obtain a two-dimensional layered velocity matrix V, define the starting point range and ending point range of the fault line in the upper left area and lower right area of the two-dimensional layered velocity matrix V, and randomly generate the starting and ending points of the fault line in these two areas to circumscribe the range of the hanging wall of the fault Figure 5a .

[0087] 3.2) Set the range of fault sliding distance, randomly generate a sliding distance value, and randomly select a sliding direction to slide the hanging wall of the fault Figure 5a .

[0088] 3.3) Determine the blank area that appears after the sliding of the hanging wall of the fault, fill the normal fault with the velocity of the previous layer, fill the reverse fault with the velocity of the next layer, and generate a fault velocity model Figure 5b .

[0089] In this embodiment, after step 3.3), further including: randomly determining whether to perform a left-right flipping operation on the velocity model, if so, flipping the velocity model (as shown in Figures 6a to 6d .

[0090] In each of the above steps, after step 3.3), a step of similarity elimination is further included: similarity detection is performed, and a velocity model with small similarity is reserved according to a preset similarity threshold. The similarity elimination in step 1) is the same as the above.

[0091] In an embodiment of the present application, a two-dimensional seismic velocity model automatic generation system in oil exploration is provided, which comprises:

[0092] The two-dimensional layered velocity model generation module generates a two-dimensional layered velocity model automatically based on the stratum parameters generated by the random number generator by combining the linear function and the sine function to generate a curved interface for the diversity training sample.

[0093] The salt dome two-dimensional velocity model generation module extracts the shapes of a plurality of mushroom images as the basic shapes of the salt dome, performs posture processing on the basic shapes of the salt dome, and then superimposes one of the mushroom images on the two-dimensional layered velocity model that is upwardly raised to generate a salt dome two-dimensional velocity model that conforms to the geological conditions.

[0094] The two-dimensional fault velocity model generation module generates normal faults and reverse faults based on the two-dimensional layered velocity model to construct a two-dimensional fault velocity model.

[0095] The final model determination module determines the similarities between all the two-dimensional layered velocity models, the salt dome two-dimensional velocity models and the two-dimensional fault velocity models, eliminates the velocity models with high similarity, and obtains the two-dimensional seismic velocity models with diversity.

[0096] The system provided in the embodiment is used to execute the above method embodiments, and the specific process and detailed content are referred to the above embodiments, which will not be described herein.

[0097] In an embodiment of the present application, a computing device structure is provided, which can be a terminal, and can include a processor, a communications interface, a memory, a display screen and an input device. The processor, the communications interface and the memory can communicate with each other through a communication bus. The processor is configured to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, which is executed by the processor to implement a method for automatically generating a two-dimensional seismic velocity model in oil exploration. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communications interface is configured to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a management network, NFC (near field communication) or other technologies. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computing device, or an external keyboard, touchpad or mouse, etc. The processor can call the logical instructions in the memory to execute the following method: generating a curved interface by combining a linear function and a sine function based on a plurality of diversity training samples, automatically generating a two-dimensional layered velocity model based on stratum parameters generated by a random number generator; extracting the shape of a plurality of mushroom images as the basic morphology of a salt dome, and after posture processing of the basic morphology of the salt dome, superimposing one of the mushroom images onto the two-dimensional layered velocity model that rises upward to generate a salt dome two-dimensional velocity model that conforms to geological conditions; generating normal and reverse faults based on the two-dimensional layered velocity model to construct a two-dimensional fault velocity model; determining the similarity between all two-dimensional layered velocity models, salt dome two-dimensional velocity models and two-dimensional fault velocity models, eliminating velocity models with high similarity, and obtaining a plurality of two-dimensional seismic velocity models.

[0098] In addition, the logical instructions in the memory described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application or parts of the present application that essentially contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0099] Those skilled in the art can understand that the structure of the computing device described above is only part of the structure related to the scheme of the present application, and does not constitute a limitation on the computing device to which the scheme of the present application is applied. A specific computing device can include more or fewer components, or combine certain components, or have a different arrangement of components.

[0100] In an embodiment of the present application, a computer program product is provided, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions that, when executed by a computer, enable the computer to perform the method provided by any of the above method embodiments, for example including: generating curved interfaces by combining linear functions and sine functions with diversity training samples, automatically generating two-dimensional layered velocity models based on formation parameters generated by a random number generator; extracting the shapes of a plurality of mushroom images as the basic morphology of salt domes, and after posture processing of the basic morphology of the salt domes, superimposing one of the mushroom images onto the two-dimensional layered velocity model that rises upward to generate a salt dome two-dimensional velocity model that conforms to geological conditions; generating normal and reverse faults based on the two-dimensional layered velocity model to construct a two-dimensional fault velocity model; determining the similarity between all two-dimensional layered velocity models, salt dome two-dimensional velocity models, and two-dimensional fault velocity models, eliminating velocity models with high similarity to obtain a diversity of two-dimensional seismic velocity models.

[0101] In an embodiment of the present application, a non-transitory computer readable storage medium is provided, which stores server instructions, the computer instructions causing a computer to perform the method provided by any of the above embodiments, for example including: generating curved interfaces by combining linear functions and sine functions with diversity training samples, automatically generating two-dimensional layered velocity models based on formation parameters generated by a random number generator; extracting the shapes of a plurality of mushroom images as the basic morphology of salt domes, and after posture processing of the basic morphology of the salt domes, superimposing one of the mushroom images onto the two-dimensional layered velocity model that rises upward to generate a salt dome two-dimensional velocity model that conforms to geological conditions; generating normal and reverse faults based on the two-dimensional layered velocity model to construct a two-dimensional fault velocity model; determining the similarity between all two-dimensional layered velocity models, salt dome two-dimensional velocity models, and two-dimensional fault velocity models, eliminating velocity models with high similarity to obtain a diversity of two-dimensional seismic velocity models.

[0102] The computer readable storage medium provided by the above embodiments has similar implementation principles and technical effects to the above method embodiments, and will not be described here.

[0103] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure One one or more flow or blocks Figure One one or more flow or blocks

[0104] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure One one or more flow or blocks Figure One one or more flow or blocks

[0105] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure One one or more flow or blocks Figure One one or more flow or blocks

[0106] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified or equivalent replacements can be made to some of the technical features; and the modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for automatically generating a two-dimensional seismic velocity model in oil exploration, characterized in that, The method comprises the steps of: Generating a curved interface by combining a linear function and a sine function with a diversity training sample, and automatically generating a two-dimensional layered velocity model based on stratum parameters generated by a random number generator; Extracting the shape of a plurality of mushroom images as the basic shape of a salt dome, and superimposing one of the mushroom images onto the two-dimensional layered velocity model after posture processing of the basic shape of the salt dome to generate a two-dimensional salt dome velocity model conforming to geological conditions; Generating normal and reverse faults based on the two-dimensional layered velocity model to construct a two-dimensional fault velocity model; Determining the similarity between all two-dimensional layered velocity models, two-dimensional salt dome velocity models and two-dimensional fault velocity models, eliminating high-similarity velocity models to obtain a plurality of two-dimensional seismic velocity models with diversity.

2. The method for automatically generating a two-dimensional seismic velocity model in oil exploration according to claim 1, wherein, The method for generating a two-dimensional layered velocity model comprises the steps of: Determining the size and grid spacing of the two-dimensional layered velocity model; Setting a stratum thickness value range, randomly generating the left and right end stratum thicknesses of the two-dimensional layered velocity model, pairing the left and right end strata, and generating a straight line stratum interface; Calculating a curved interface for each stratum interface; Based on the straight line stratum interface and the curved interface, setting a velocity value range and a minimum interval value for adjacent layer velocities, randomly generating a series of layer velocities, and assigning the layer velocities to the respective strata after incremental sorting to obtain a layered velocity model; Griding the layered velocity model and converting it into a velocity matrix to obtain a two-dimensional layered velocity model.

3. The method of claim 2, wherein the method is used for petroleum exploration. The method for pairing the left and right end strata comprises the steps of:

4. The method of claim 1, wherein the method is used for automatic generation of 2D seismic velocity model in oil exploration. When the cumulative thicknesses of the left and right ends both exceed a preset ground depth, calculating the maximum number of strata. The method for posture processing of the basic shape of the salt dome comprises the steps of:

5. The method of claim 1, wherein the method is used for automatic generation of 2D seismic velocity model in oil exploration. After the basic shape of the salt dome is processed by a combination of four operations of translation, scaling, rotation and distortion, the processed basic shape is superimposed onto the two-dimensional layered velocity model. The method for generating a two-dimensional salt dome velocity model comprises the steps of: Converting a plurality of collected mushroom images into black and white images and scaling them to the size of the two-dimensional layered velocity matrix; Generating an upwardly protruding layered velocity matrix using the method for generating a two-dimensional layered velocity model; Randomly selecting a mushroom black and white image, and randomly selecting one of the operations of scaling down, scaling down + rotation and scaling down + distortion to generate a new mushroom image; 6. The method for automatically generating a two-dimensional seismic velocity model in oil exploration according to claim 1, wherein, Randomly selecting a center point in a set area, assigning a velocity value to the mushroom part of the new mushroom image, and then translating and superimposing the new mushroom image onto the layered velocity model to form a salt dome velocity model. The method for generating normal and reverse faults comprises the steps of:

7. The method of claim 1, wherein the method is used for petroleum exploration. Randomly selecting the starting point and ending point of a fault line, the sliding direction and distance of the fault, determining the fault block sliding range and blank area, and sliding the fault block using the translation operation of the image to form normal and reverse faults by respectively translating the hanging wall of the fault downward and upward. The method for generating a two-dimensional fault velocity model comprises the steps of: Based on a two-dimensional layered velocity model, a two-dimensional layered velocity matrix is obtained, the starting point range and the ending point range of the fault line are defined in the upper left area and the lower right area of the two-dimensional layered velocity matrix, and the starting and ending points of the fault line are randomly generated in the two areas to define the range of the hanging wall of the fault; Setting a range of fault sliding distance, randomly generating a sliding distance value, and randomly selecting a sliding direction to slide the hanging wall of the fault; The blank area after the hanging wall of the fault slips is determined, the normal fault is filled at the speed of the previous layer before the slip, the reverse fault is filled at the speed of the next layer before the slip, and a fault velocity model is generated.

8. A system for automatically generating a two-dimensional seismic velocity model in oil exploration, characterized by, The method comprises the following steps: A two-dimensional layered velocity model generation module generates a curved interface by combining a linear function and a sine function based on a plurality of diversity training samples, and automatically generates a two-dimensional layered velocity model based on stratum parameters generated by a random number generator; A salt dome two-dimensional velocity model generation module extracts the shapes of a plurality of mushroom images as the basic shapes of the salt dome, processes the basic shapes of the salt dome in terms of posture, and then superimposes one of the mushroom images on the two-dimensional layered velocity model that rises upward to generate a salt dome two-dimensional velocity model that conforms to geological conditions; A two-dimensional fault velocity model generation module generates normal faults and reverse faults based on the two-dimensional layered velocity model to construct a two-dimensional fault velocity model; A final model determination module determines the similarities between all two-dimensional layered velocity models, salt dome two-dimensional velocity models, and two-dimensional fault velocity models, eliminates velocity models with high similarities, and obtains a plurality of two-dimensional seismic velocity models with diversity.

9. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions for: The one or more programs include instructions that when executed by a computing device cause the computing device to perform any of the methods of claims 1-7.

10. A computing device, comprising: The method comprises the following steps: One or more processors, memories, and one or more programs, wherein the one or more programs are stored in the memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods of claims 1-7.

Images