Geologic body identification method, device, apparatus, and storage medium

Abstract

This application provides a method, apparatus, device, and storage medium for identifying geological bodies, belonging to the field of seismic exploration technology. The method includes: acquiring multiple reflection coefficients; adjusting the multiple reflection coefficients based on the geological body category to obtain a reflection data volume; processing the reflection data volume based on a three-dimensional point spread function to obtain a sample seismic data volume; training a geological body identification model based on the sample seismic data volume; and predicting the location of a target seismic data volume based on the trained geological body identification model to obtain the location of geological bodies belonging to the specified geological body category within the target stratigraphic region. The above technical solution can improve the recognition performance of the geological body identification model, and thus, when predicting the target seismic data volume obtained from exploration based on the trained geological body identification model, the location of the geological body can be identified more accurately.

Description

Technical Field

[0001] This application relates to the field of seismic exploration technology, and in particular to a method, apparatus, equipment and storage medium for identifying geological bodies. Background Technology

[0002] In the field of seismic exploration technology, the interpretation of geological bodies such as caves and collapses is fundamental to the interpretation of seismic data in carbonate reservoirs. "Interpretation" specifically refers to identifying the location of caves or collapses within the formation. How to identify the location of caves or collapses based on seismic data is a key focus of research in this field.

[0003] In related technologies, traditional cave interpretation is mostly done manually. Interpreters typically use seismic properties to assist in interpreting caves and collapses. However, manual interpretation is very inefficient, requiring a significant amount of time and effort. As oil and gas exploration continues to deepen, seismic data is also increasing, making manual interpretation insufficient to meet production demands. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for identifying geological bodies, thereby improving the accuracy of geological body identification. The technical solution is as follows:

[0005] On the one hand, a method for identifying geological bodies is provided, the method comprising:

[0006] Multiple reflection coefficients are obtained, which are used to simulate the properties of reflected seismic wavelets at multiple locations in multiple strata in three-dimensional space.

[0007] Based on the geological body category, the multiple reflection coefficients are adjusted to obtain a reflection data volume, which is used to simulate the reflection characteristics of geological bodies belonging to the geological body category;

[0008] The reflection data volume is processed based on the three-dimensional point spread function to obtain the sample seismic data volume. The three-dimensional point spread function is used to represent the propagation properties of the seismic wavelet in time and space. The sample seismic data volume is used to simulate the characteristics of geological bodies belonging to the geological body category.

[0009] Based on the sample seismic data, a geological body identification model is trained, and the trained geological body identification model is used to identify the location of geological bodies belonging to the geological body category in the strata;

[0010] Based on the trained geological body identification model, the target seismic data volume is predicted to obtain the location of geological bodies belonging to the geological body category in the target stratigraphic region. The target seismic data volume is obtained based on the exploration of the target stratigraphic region.

[0011] In some embodiments, adjusting the plurality of reflection coefficients based on geological body categories to obtain a reflection data volume includes:

[0012] The multiple reflection coefficients are folded and deformed to obtain an intermediate data volume, which is used to simulate the reflection characteristics of real geological structures.

[0013] Based on the geological body category, multiple target reflection coefficients in the intermediate data volume are adjusted to obtain the reflection data volume, and the position of the target reflection coefficient is used to indicate the position of the geological body belonging to the geological body category.

[0014] In some embodiments, adjusting the reflection coefficients of multiple targets in the intermediate data volume based on the geological body category to obtain the reflection data volume includes:

[0015] When the geological body type is a karst cave, multiple first target reflectance coefficients and multiple second target reflectance coefficients are obtained. The positions of the first target reflectance coefficients are used to represent the edges of the karst cave, and the positions of the second target reflectance coefficients are used to represent the interior of the karst cave. The multiple first target reflectance coefficients surround the multiple second target reflectance coefficients.

[0016] The reflection coefficients of the plurality of first targets are adjusted such that the value of any one of the adjusted first target reflection coefficients is different from the values ​​of other reflection coefficients in the same stratum.

[0017] Adjust the values ​​of the reflection coefficients of the plurality of second targets to zero;

[0018] The reflection data volume is obtained based on the adjusted reflection coefficients of the plurality of first targets and the plurality of second targets.

[0019] In some embodiments, adjusting the reflection coefficients of multiple targets in the intermediate data volume based on the geological body category to obtain the reflection data volume includes:

[0020] In the case where the geological body category is collapse, multiple third target reflection coefficients are obtained, and the positions of the third target reflection coefficients are used to represent the edges of the collapse.

[0021] The positions of the reflection coefficients of the plurality of third targets are adjusted downward by a preset distance to obtain the reflection data volume, and the preset distance is used to represent the depth of the collapse.

[0022] In some embodiments, processing the reflection data volume based on a three-dimensional point spread function to obtain a sample seismic data volume includes:

[0023] The three-dimensional point diffusion function is determined based on aperture parameters and frequency parameters. The aperture parameters and frequency parameters are used to reflect the exploration effect of the three-dimensional point diffusion function at various locations in the formation.

[0024] The sample seismic data volume is obtained by convolving the reflection data volume based on the three-dimensional point spread function.

[0025] In some embodiments, the method further includes:

[0026] By adjusting at least one of the aperture parameter and the frequency parameter, a new three-dimensional point spread function is obtained;

[0027] The reflection data volume is convolved based on the new three-dimensional point spread function to obtain the new sample seismic data volume.

[0028] In some embodiments, training the geological body identification model based on the sample seismic data volume includes:

[0029] The sample seismic data volume is input into the geological body identification model to obtain seismic data features;

[0030] Based on the seismic data characteristics, the locations of geological bodies belonging to the geological body category within the sample seismic data volume are identified;

[0031] The geological body identification model is trained based on the difference between the location of the identified geological body and the labeled location of the sample seismic data volume, wherein the labeled location is determined based on the adjusted reflection coefficient.

[0032] On the other hand, a geological body identification device is provided, the device comprising:

[0033] The acquisition module is used to acquire multiple reflection coefficients, which are used to simulate the properties of reflected seismic wavelets at multiple locations in multiple strata in three-dimensional space;

[0034] The first adjustment module is used to adjust the multiple reflection coefficients based on the geological body category to obtain a reflection data volume, which is used to simulate the reflection characteristics of geological bodies belonging to the geological body category.

[0035] The processing module is used to process the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume. The three-dimensional point spread function is used to represent the propagation properties of the seismic wavelet in time and space. The sample seismic data volume is used to simulate the characteristics of geological bodies belonging to the geological body category.

[0036] The training module is used to train the geological body identification model based on the sample seismic data volume. The trained geological body identification model is used to identify the location of geological bodies belonging to the geological body category in the strata.

[0037] The prediction module is used to predict the target seismic data volume based on the trained geological body identification model, and to obtain the location of geological bodies belonging to the geological body category in the target stratigraphic region, wherein the target seismic data volume is obtained based on the exploration of the target stratigraphic region.

[0038] In some embodiments, the first adjustment module includes:

[0039] A deformation unit is used to fold and deform the multiple reflection coefficients to obtain an intermediate data volume, which is used to simulate the reflection characteristics of a real geological structure.

[0040] An adjustment unit is used to adjust multiple target reflection coefficients in the intermediate data volume based on the geological body category to obtain the reflection data volume, wherein the position of the target reflection coefficient is used to indicate the position of the geological body belonging to the geological body category.

[0041] In some embodiments, the adjustment unit is configured to, when the geological body type is a karst cave, acquire a plurality of first target reflection coefficients and a plurality of second target reflection coefficients, wherein the positions of the first target reflection coefficients are used to represent the edges of the karst cave, and the positions of the second target reflection coefficients are used to represent the interior of the karst cave, and the plurality of first target reflection coefficients surround the plurality of second target reflection coefficients; adjust the plurality of first target reflection coefficients such that the value of any adjusted first target reflection coefficient is different from the values ​​of other reflection coefficients in the same stratum; adjust the values ​​of the plurality of second target reflection coefficients to zero; and obtain the reflection data volume based on the adjusted plurality of first target reflection coefficients and the plurality of second target reflection coefficients.

[0042] In some embodiments, the adjustment unit is configured to, when the geological body category is collapse, acquire multiple third target reflection coefficients, the positions of which are used to represent the edge of the collapse; and adjust the positions of the multiple third target reflection coefficients downward by a preset distance to obtain the reflection data volume, the preset distance being used to represent the depth of the collapse.

[0043] In some embodiments, the processing module is configured to determine the three-dimensional point spread function based on aperture parameters and frequency parameters, wherein the aperture parameters and frequency parameters are used to reflect the exploration effect of the three-dimensional point spread function at various locations in the strata; and to perform convolution on the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume.

[0044] In some embodiments, the apparatus further includes:

[0045] The second adjustment module is used to adjust at least one of the aperture parameter and the frequency parameter to obtain a new three-dimensional point diffusion function.

[0046] The processing module is also used to convolve the reflection data volume based on the new three-dimensional point spread function to obtain a new sample seismic data volume.

[0047] In some embodiments, the training module is configured to input the sample seismic data volume into the geological body identification model to obtain seismic data features; based on the seismic data features, identify the locations of geological bodies belonging to the geological body category in the sample seismic data volume; and train the geological body identification model based on the difference between the identified geological body locations and the labeled locations of the sample seismic data volume, wherein the labeled locations are determined based on the adjusted reflection coefficients.

[0048] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded and executed by the processor to implement the geological body identification method in the embodiments of this application.

[0049] On the other hand, a computer-readable storage medium is provided, wherein at least one computer program is stored in the computer-readable storage medium, the at least one computer program being loaded and executed by a processor to implement the geological body identification method as described in the embodiments of this application.

[0050] On the other hand, a computer program is provided, including a computer program that, when executed by a processor, implements the geological body identification method as described in the embodiments of this application.

[0051] This application provides a method for identifying geological bodies. By adjusting multiple reflection coefficients according to the category of the geological body to be identified, the resulting reflection data volume accurately reflects the reflection characteristics of the geological body in three-dimensional space. Then, the reflection data volume is processed using a three-dimensional point spread function, enabling the resulting sample seismic data volume to accurately reflect the characteristics of the geological body in three-dimensional space. In other words, it can more accurately simulate the data of the geological body in three-dimensional space, resulting in higher realism. The geological body identification model is then trained using the sample seismic data volume, allowing the model to fully learn the characteristics of the geological body, thereby improving its recognition performance. Furthermore, when predicting the location of a target seismic data volume obtained from exploration based on the trained geological body identification model, the location of the geological body can be identified more accurately. Moreover, compared to manual interpretation, identifying the location of a geological body using a trained geological body identification model is more efficient. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart of a method for identifying geological bodies according to an embodiment of this application;

[0054] Figure 2 This is a schematic diagram of a wrinkle deformation according to an embodiment of this application;

[0055] Figure 3 This is a schematic diagram of a reflective data volume for simulating a cavern, according to an embodiment of this application;

[0056] Figure 4 This is a diagram illustrating the effect of processing data using a one-dimensional point spread function and a three-dimensional point spread function, according to an embodiment of this application.

[0057] Figure 5 This is an imaging effect diagram of different three-dimensional point spread functions provided according to an embodiment of this application;

[0058] Figure 6 This is a sample seismic data volume of a collapse provided according to an embodiment of this application;

[0059] Figure 7 This is a schematic diagram of a seismic data feature provided according to an embodiment of this application;

[0060] Figure 8This is a schematic diagram of a geological body identification model provided according to an embodiment of this application;

[0061] Figure 9 This is a schematic diagram of a residual layer according to an embodiment of this application;

[0062] Figure 10 This is a diagram illustrating the effect of cave identification according to an embodiment of this application;

[0063] Figure 11 This is a collapse recognition effect diagram provided according to an embodiment of this application;

[0064] Figure 12 This is a schematic diagram of the structure of a geological body identification device according to an embodiment of this application;

[0065] Figure 13 This is a schematic diagram of the structure of another geological body identification device provided according to an embodiment of this application;

[0066] Figure 14 This is a structural block diagram of a terminal provided according to an embodiment of this application;

[0067] Figure 15 This is a structural block diagram of a server provided according to an embodiment of this application. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0069] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.

[0070] In this application, the term "at least one" means one or more, and "multiple" means two or more.

[0071] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the target seismic data volumes involved in this application were all obtained under full authorization.

[0072] Figure 1 This is a flowchart of a method for identifying geological bodies according to an embodiment of this application. See also... Figure 1 In this embodiment, the method for identifying geological bodies is described using an example executed by a terminal. The method includes the following steps:

[0073] 101. The terminal acquires multiple reflection coefficients, which are used to simulate the properties of reflected seismic wavelets at multiple locations in multiple strata in three-dimensional space.

[0074] In this embodiment, the reflection coefficient refers to the amplitude ratio between the incident seismic wavelet and the reflected seismic wavelet. A seismic wavelet is a signal with a definite start time, finite energy, and a certain duration; it is the basic unit in seismic data. A seismic wavelet can be defined by its amplitude spectrum and phase spectrum. Multiple reflection coefficients include the reflection coefficients of multiple strata. The reflection coefficient of each stratum is composed of reflection coefficients at multiple locations within that stratum. Therefore, the multiple reflection coefficients in this embodiment are used to simulate the reflection coefficients at various locations in three-dimensional space, and not just the reflection coefficients in a single stratum or a single stratigraphic profile. In a three-dimensional stratum, the reflection coefficients at different locations can be the same or different; this embodiment does not impose any limitations on this.

[0075] In some embodiments, the geological composition of the same stratum is roughly the same, while the geological composition of different strata is basically different. For example, some strata are dominated by limestone, while others are dominated by dolomite. Different geological compositions reflect seismic wavelets with different properties. Optionally, in the process of acquiring multiple reflection coefficients, the terminal is set to simulate the same reflection coefficient at different locations within the same stratum and to simulate different reflection coefficients at different locations within different strata. The solution provided in this application, by setting the reflection coefficient to be the same within the same stratum and different within different strata, is not only simple to operate but also can more accurately reflect the reflection characteristics of different strata, which is beneficial for subsequently simulating more accurate seismic data.

[0076] In some embodiments, the multiple reflection coefficients can be randomly generated or generated from the actual formations to be explored as needed. Accordingly, the terminal can perform sonic logging on the actual formations to be explored. Then, the terminal calculates the multiple reflection coefficients based on the sonic and density logging curves. The solution provided in this application, by obtaining reflection coefficients through exploration of actual formations, enables multiple reflection coefficients to more accurately reflect the reflection characteristics of the formations, facilitating the subsequent simulation of more accurate seismic data.

[0077] 102. The terminal adjusts multiple reflection coefficients based on the geological body category to obtain a reflection data volume, which is used to simulate the reflection characteristics of geological bodies belonging to the geological body category.

[0078] In this embodiment, geological bodies can be categorized into types such as karst caves and collapses, and this embodiment does not impose any limitations on this. Different geological bodies have different reflection characteristics. The terminal can adjust multiple previously generated reflection coefficients according to the geological body category to generate a reflection data volume that can simulate the corresponding category of geological body, preparing for subsequent generation of data for training the geological body recognition model. Here, the reflection data volume refers to data used to describe the reflection characteristics at multiple locations within the strata in three-dimensional space.

[0079] Because real geological strata are generally horizontal during formation, and they bend under tectonic forces, a single bend can be called a fold, while a series of wavy bending deformations can be called a fold. Therefore, real geological strata are generally not flat, but rather folded. That is, the positions of multiple reflection coefficients corresponding to the same stratum are not perfectly aligned. Accordingly, to more accurately simulate geological bodies within the strata, the terminal can first fold and deform the previously generated multiple reflection coefficients, and then adjust them according to the geological body category. The process of the terminal adjusting multiple reflection coefficients based on the geological body category to obtain the reflection data volume includes: the terminal folds and deforms multiple reflection coefficients to obtain an intermediate data volume. Then, the terminal adjusts multiple target reflection coefficients in the intermediate data volume based on the geological body category to obtain the reflection data volume. The intermediate data volume is used to simulate the reflection characteristics of the real geological structure. The positions of the target reflection coefficients represent the positions of geological bodies belonging to the same geological body category. The location of the target reflectance coefficient can be determined randomly or based on the correlation between geological body type and stratigraphic structure. For example, some geological bodies tend to appear in areas of stratigraphic folding and deformation, while others tend to appear in areas of flat strata. This application does not impose such limitations. The solution provided in this application deforms multiple reflectance coefficients to more accurately simulate the structure of real strata. Then, based on the geological body type, the target reflectance coefficient among the multiple reflectance coefficients is adjusted, so that the obtained reflectance data volume can more accurately simulate the reflectance characteristics of the geological body, which is beneficial for subsequent training of a geological body recognition model with better recognition performance.

[0080] For example, Figure 2 This is a schematic diagram of a wrinkle deformation according to an embodiment of this application. See also... Figure 2 , Figure 2 (a) exemplarily shows the initial reflection data volume, i.e., the multiple reflection coefficients before adjustment. The multiple reflection coefficients in each layer are positioned horizontally. The terminal can then perform folding deformation on the initial reflection data volume shown in (a) to obtain an intermediate data volume; see [link to relevant documentation]. Figure 2(b) In the intermediate data volume, the reflection coefficients of the same layer are not horizontal, but rather exhibit folding and deformation, which better reflects the structure of real strata. The terminal can also simulate at least one of tilting structures and fault structures based on the intermediate data volume, making the intermediate data volume more accurately simulate the structure of real strata.

[0081] In the process of adjusting the reflection coefficients of multiple targets in an intermediate data volume based on the geological body category to obtain a reflection data volume, the process of adjusting the reflection coefficients of multiple targets at the terminal differs for different geological body categories.

[0082] In some embodiments, the geological body category is a cave. Accordingly, the process by which the terminal adjusts multiple target reflection coefficients in the intermediate data volume based on the geological body category to obtain a reflection data volume includes: when the geological body category is a cave, the terminal acquires multiple first target reflection coefficients and multiple second target reflection coefficients. Then, the terminal adjusts the multiple first target reflection coefficients, such that the value of any adjusted first target reflection coefficient is different from the values ​​of other reflection coefficients in the same stratum. Then, the terminal adjusts the values ​​of the multiple second target reflection coefficients to zero. Then, the terminal obtains the reflection data volume based on the adjusted multiple first target reflection coefficients and multiple second target reflection coefficients. The positions of the first target reflection coefficients represent the edges of the cave. The positions of the second target reflection coefficients represent the interior of the cave, with multiple first target reflection coefficients surrounding multiple second target reflection coefficients. The solution provided in this application adjusts the reflection coefficients in the intermediate data volume according to the structure and reflective properties of the cave, enabling the obtained reflection data volume to more accurately simulate the reflection characteristics of the cave, which is beneficial for subsequent training of a model that can more accurately identify caves.

[0083] The positions of multiple first target reflection coefficients used to simulate the same cave can be enclosed by an ellipsoid, and the reflection coefficients of multiple second targets enclosed by this ellipsoid are zero. That is, this ellipsoid is the simulated cave. This application embodiment does not limit the specific location of the cave, that is, it does not limit the positions of the multiple first target reflection coefficients. Specifically, the terminal can add irregular ellipsoids with randomly spatially distributed abnormal amplitudes to the intermediate data volume to simulate the cave structure. Abnormal amplitudes refer to reflection coefficients that are different from other reflection coefficients in the same layer, or reflection coefficients that differ significantly from other reflection coefficients in the same layer; this application embodiment does not impose restrictions on this.

[0084] For example, Figure 3 This is a schematic diagram of a reflective data volume for simulating a cavern, according to an embodiment of this application. See also... Figure 3 , Figure 3 An example is shown of a cavity in a volume of reflective data. For example, section 301.

[0085] In some embodiments, the geological body category is collapse. Accordingly, the process by which the terminal adjusts multiple target reflection coefficients in the intermediate data volume based on the geological body category to obtain a reflection data volume includes: when the geological body category is collapse, the terminal acquires multiple third target reflection coefficients. Then, the terminal adjusts the positions of the multiple third target reflection coefficients downwards by a preset distance to obtain the reflection data volume. The positions of the third target reflection coefficients represent the edges of the collapse. The preset distance represents the depth of the collapse. That is, the terminal can simulate a collapse structure by randomly indenting reflection coefficients to a certain depth based on the intermediate data volume. This application embodiment does not limit the specific location of the collapse, that is, it does not limit the positions of the multiple third target reflection coefficients. The solution provided in this application embodiment adjusts the reflection coefficients in the intermediate data volume according to the structure and reflection properties of the collapse, so that the obtained reflection data volume can more accurately simulate the reflection characteristics of the collapse, which is beneficial for subsequent training of a model that can more accurately identify collapses.

[0086] 103. The terminal processes the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume. The three-dimensional point spread function is used to represent the propagation properties of the seismic wavelet in time and space. The sample seismic data volume is used to simulate the characteristics of geological bodies belonging to the geological body category.

[0087] In this application embodiment, the point spread function (PSF) is used to evaluate the minimum spatial resolution of an imaging system. Point spread refers to the dispersion of light energy after imaging from a point source. Assuming we consider an object as being composed entirely of a single point, then the image of that object is at least the width of a single image point. However, typically, the image of an object is composed of a patch of many image points, with the central part of the patch being the brightest and the brightness decreasing towards the periphery. Obviously, the more concentrated the patch, the better the imaging effect. In the field of seismic exploration, the point spread function refers to the seismic imaging response of a single diffraction point underground, and is the basis for seismic imaging data. When exploring a point (location) in the strata, the terminal can use the point spread function to calculate and obtain the seismic data for that point.

[0088] Point spread functions (PSFs) can be divided into one-dimensional (1D) and three-dimensional (3D) PSFs. A one-dimensional PSF primarily represents the properties of a seismic wavelet propagating through the strata in the time direction. The time direction refers to the direction perpendicular to the strata and downwards. A three-dimensional PSF primarily represents the properties of a seismic wavelet propagating through the strata in both the time and spatial directions. The spatial direction refers to the direction parallel to the strata. Because seismic wavelets propagate through the strata not only perpendicularly downwards but also horizontally, this application's embodiment uses a three-dimensional PSF to process the reflection data volume. This allows the obtained sample seismic data volume to more accurately reflect the properties of geological bodies in three-dimensional space, thus facilitating the subsequent training of a geological body recognition model with better recognition performance.

[0089] For example, Figure 4 This is a diagram illustrating the effects of processing data using a one-dimensional point spread function and a three-dimensional point spread function, according to embodiments of this application. See also... Figure 4 , Figure 4 Figure (a) exemplifies the sample seismic data obtained by processing the reflection data volume using a one-dimensional point spread function. 401 in Figure (a) represents the cave structure obtained by processing with the one-dimensional point spread function. Figure 4 Figure (b) exemplifies the sample seismic data volume obtained by processing the reflection data volume using a three-dimensional point spread function. 402 in Figure (b) represents the cave structure obtained after processing with the three-dimensional point spread function. It is evident that processing with the three-dimensional point spread function yields a smaller range of cave structures, meaning the location of the caves is more precise.

[0090] In some embodiments, the three-dimensional point spread function includes aperture parameters and frequency parameters. Aperture and frequency parameters can affect the imaging effect of the three-dimensional point spread function, that is, they can affect the exploration effect of the geological body. The terminal can determine the three-dimensional point spread function based on the aperture and frequency parameters to simulate the seismic data volume of the geological body. Accordingly, the process of the terminal processing the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume includes: the terminal determining the three-dimensional point spread function based on the aperture and frequency parameters; then, the terminal convolving the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume. The aperture and frequency parameters are used to reflect the exploration effect of the three-dimensional point spread function at various locations in the strata. The aperture and frequency parameters can be randomly generated, empirical parameters, or determined according to the geological body type; this embodiment does not impose such limitations. The solution provided in this application determines the three-dimensional point spread function by using aperture parameters and frequency parameters, and then convolves the reflection data volume using the three-dimensional point spread function, so that the obtained sample seismic data volume can more accurately reflect the properties of geological bodies in three-dimensional space, thereby facilitating the subsequent training of a geological body recognition model with better recognition performance.

[0091] In some embodiments, the terminal can also adjust the aperture parameter or frequency parameter to obtain different three-dimensional point spread functions, thereby simulating different sample seismic data volumes. Accordingly, the terminal adjusts at least one of the aperture parameter and frequency parameter to obtain a new three-dimensional point spread function. Then, the terminal convolves the reflection data volume based on the new three-dimensional point spread function to obtain a new sample seismic data volume. The solution provided in this application embodiment, by adjusting at least one of the aperture parameter and frequency parameter, can obtain different three-dimensional point spread functions, thereby simulating different sample seismic data volumes. This provides rich training data for subsequent training of the geological body recognition model, which is beneficial to further improving the generalization ability of the geological body recognition model, enabling the geological body recognition model to adapt to seismic data under different conditions and complex geological situations.

[0092] For example, Figure 5 This is an imaging effect diagram of different three-dimensional point spread functions provided according to an embodiment of this application. See also Figure 5 , Figure 5 (a) in the figure exemplarily demonstrates the imaging effect of a small-aperture and wide-bandwidth three-dimensional point spread function; Figure 5 (b) in the example demonstrates the imaging effect of a large-aperture and wide-bandwidth three-dimensional point spread function; Figure 5 (c) in the figure exemplarily demonstrates the imaging effect of a three-dimensional point spread function with a large aperture and narrow bandwidth; Figure 5(d) in the diagram exemplifies the imaging effect of a three-dimensional point spread function with a small aperture and narrow bandwidth. It is evident that a three-dimensional point spread function with a larger aperture parameter and a larger bandwidth parameter produces better imaging results; that is, a point (location) can be observed more clearly, and the imaged location is more precise.

[0093] The terminal processes the reflection data volume using a three-dimensional point spread function to obtain the sample seismic data volume. The sample seismic data volume is a three-dimensional tensor. Taking a landslide as an example, the terminal processes the landslide reflection data volume using a three-dimensional point spread function to obtain the landslide sample seismic data volume. See also... Figure 6 , Figure 6 This is a sample seismic data volume of a collapse, provided according to an embodiment of this application. For example... Figure 6 601 in the diagram represents a collapse. The terminal can obtain multiple sample training data using the methods described in steps 101 to 103 to prepare for subsequent model training.

[0094] 104. The terminal trains the geological body identification model based on sample seismic data. The trained geological body identification model is used to identify the location of geological bodies belonging to the geological body category in the strata.

[0095] In this embodiment, the terminal inputs sample seismic data into a geological body recognition model to train the model. Specifically, the process of training the geological body recognition model based on the sample seismic data includes: the terminal inputs the sample seismic data into the geological body recognition model to obtain seismic data features. Each seismic data feature is a three-dimensional tensor. Then, based on the seismic data features, the terminal identifies the locations of geological bodies belonging to the geological body category within the sample seismic data. Then, based on the difference between the identified geological body locations and the labeled locations in the sample seismic data, the terminal trains the geological body recognition model. The labeled locations are determined based on adjusted reflection coefficients. The solution provided in this embodiment trains the geological body recognition model using sample seismic data, enabling the model to fully learn the characteristics of geological bodies, thereby improving its recognition performance. Consequently, when predicting target seismic data obtained from exploration based on the trained geological body recognition model, the location of geological bodies can be identified more accurately. Furthermore, compared to manual interpretation, identifying the location of geological bodies using a trained geological body recognition model is more efficient.

[0096] For example, Figure 7 This is a schematic diagram of a seismic data feature provided according to an embodiment of this application. See also... Figure 7 , Figure 7 Figure (a) exemplarily illustrates the seismic data characteristics of a cave. 701 in Figure (a) exemplarily illustrates a cave. Figure 7 Figure (b) exemplarily illustrates the seismic data characteristics of a collapse. 702 in Figure (b) exemplarily illustrates a collapse.

[0097] This application does not impose any restrictions on the structure of the geological body recognition model. The end-to-end network originates from the encoder-decoder model, which is frequently used for semantic segmentation problems. Cave and collapse detection can be considered as a segmentation problem. Optionally, the geological body recognition model is an end-to-end convolutional neural network.

[0098] For example, Figure 8 This is a schematic diagram of a geological body recognition model provided according to an embodiment of this application. The geological body recognition model includes convolutional layers, activation layers, batch normalization layers, pooling layers, upsampling layers, concatenate layers, and residual layers, etc. See also Figure 8 In the geological body identification model, blocks 1, 3, 5, 7, 10, 12, 14, and 15 are residual blocks, containing convolutional layers, batch normalization layers, and activation layers. Blocks 2, 4, 6, 8, 9, 11, and 13 are convolutional blocks, each containing a convolutional layer. Residual blocks and convolutional blocks can be connected by max-pooling layers, such as between 2 and 3, 4 and 5, and 6 and 7. Convolutional blocks 8 and 9 can be connected by upsampling layers; residual block 10 and convolutional block 11 can be connected by upsampling layers; residual block 12 and convolutional block 13 can be connected by upsampling layers. Convolutional blocks 2 and 13 can be connected by connection layers; convolutional blocks 4 and 11 can be connected by connection layers; and convolutional blocks 6 and 8 can be connected by connection layers.

[0099] To further improve the feature extraction capability of the geological body identification model, this application embodiment can employ multiple residual layers. Residual layers can avoid the gradient vanishing problem; by adding residual layers, the number of layers in the geological body identification model can be significantly increased, thereby improving the model's identification accuracy.

[0100] For example, Figure 9 This is a schematic diagram of a residual layer according to an embodiment of this application. See also... Figure 9 The residual layer includes convolutional layer 1, convolutional layer 2, and convolutional layer 3. The convolutional kernels in convolutional layers 1 and 2 are 3x3 kernels; the convolutional kernel in convolutional layer 3 is a 1x1 kernel. The terminal adds the outputs of convolutional layer 2 and convolutional layer 3 and activates them using an activation function to obtain the output of the residual layer. This activation function can be ReLU (Rectified Linear Unit), and this embodiment does not limit this to a specific function.

[0101] 105. The terminal predicts the target seismic data volume based on the trained geological body identification model, and obtains the location of the geological body belonging to the geological body category in the target stratigraphic region. The target seismic data volume is obtained based on the exploration of the target stratigraphic region.

[0102] In this embodiment, the terminal uses a trained geological body recognition model to predict whether the target seismic data volume contains a cave (or collapse) geological body, thus obtaining a three-dimensional probability volume. The three-dimensional probability volume includes multiple probability values. Each probability value represents the probability that the corresponding location in three-dimensional space is a cave (or collapse) geological body. Multiple probability values ​​can be arranged according to their corresponding locations in three-dimensional space to obtain the three-dimensional probability volume.

[0103] In the case of identifying caves, please refer to Figure 10 , Figure 10 This is a diagram illustrating the effect of cave identification according to an embodiment of this application. Figure 10 (a) in the example demonstrates a three-dimensional probability volume for predicting caves. Darker areas are more likely to contain caves. The terminal can also use 3D display or sculpting functions to process the three-dimensional probability volume of caves to display them, thus enabling interpretation of the caves. See also... Figure 10 In (b), 1001 is the identified cave.

[0104] In the case of identifying a collapse, please refer to Figure 11 , Figure 11 This is a collapse recognition effect diagram provided according to an embodiment of this application. Figure 11 (a) in the example shows the target seismic data volume that was explored; Figure 11 (b) in the example demonstrates the identification results of the geological body identification model. 1101 is the identified collapse. Figure 11 (c) in the diagram exemplarily shows a top-down view of the collapsed ground. The arrow points to the location of the collapse.

[0105] This application provides a method for identifying geological bodies. By adjusting multiple reflection coefficients according to the category of the geological body to be identified, the resulting reflection data volume accurately reflects the reflection characteristics of the geological body in three-dimensional space. Then, the reflection data volume is processed using a three-dimensional point spread function, enabling the resulting sample seismic data volume to accurately reflect the characteristics of the geological body in three-dimensional space. In other words, it can more accurately simulate the data of the geological body in three-dimensional space, resulting in higher realism. The geological body identification model is then trained using the sample seismic data volume, allowing the model to fully learn the characteristics of the geological body, thereby improving its recognition performance. Furthermore, when predicting the location of a target seismic data volume obtained from exploration based on the trained geological body identification model, the location of the geological body can be identified more accurately. Moreover, compared to manual interpretation, identifying the location of a geological body using a trained geological body identification model is more efficient.

[0106] Figure 12 This is a schematic diagram of a geological body identification device according to an embodiment of this application. The device is used to perform the steps of the geological body identification method described above, see below. Figure 12 The device includes: an acquisition module 1201, a first adjustment module 1202, a processing module 1203, a training module 1204, and a prediction module 1205.

[0107] The acquisition module 1201 is used to acquire multiple reflection coefficients, which are used to simulate the properties of reflected seismic wavelets at multiple locations in multiple strata in three-dimensional space.

[0108] The first adjustment module 1202 is used to adjust multiple reflection coefficients based on the geological body category to obtain a reflection data volume. The reflection data volume is used to simulate the reflection characteristics of geological bodies belonging to the geological body category.

[0109] Processing module 1203 is used to process the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume. The three-dimensional point spread function is used to represent the propagation properties of the seismic wavelet in time and space, and the sample seismic data volume is used to simulate the characteristics of geological bodies belonging to the geological body category.

[0110] Training module 1204 is used to train the geological body identification model based on sample seismic data. The trained geological body identification model is used to identify the location of geological bodies belonging to the geological body category in the strata.

[0111] The prediction module 1205 is used to predict the target seismic data volume based on the trained geological body identification model, and to obtain the location of geological bodies belonging to the geological body category in the target stratigraphic region. The target seismic data volume is obtained based on the exploration of the target stratigraphic region.

[0112] In some embodiments, Figure 13 This is a schematic diagram of another geological body identification device provided according to an embodiment of this application. See also... Figure 13 The first adjustment module 1202 includes:

[0113] Deformation unit 12021 is used to fold and deform multiple reflection coefficients to obtain intermediate data volume, which is used to simulate the reflection characteristics of real geological structures.

[0114] The adjustment unit 12022 is used to adjust the reflection coefficients of multiple targets in the intermediate data volume based on the geological body category to obtain the reflection data volume. The position of the target reflection coefficient is used to indicate the position of the geological body belonging to the geological body category.

[0115] In some embodiments, see continue to see Figure 13 The adjustment unit 12022 is used to acquire multiple first target reflection coefficients and multiple second target reflection coefficients when the geological body type is a karst cave. The position of the first target reflection coefficient is used to represent the edge of the karst cave, and the position of the second target reflection coefficient is used to represent the interior of the karst cave. The multiple first target reflection coefficients surround the multiple second target reflection coefficients. The multiple first target reflection coefficients are adjusted so that the value of any first target reflection coefficient after adjustment is different from the value of other reflection coefficients in the same stratum. The values ​​of the multiple second target reflection coefficients are adjusted to zero. Based on the adjusted multiple first target reflection coefficients and multiple second target reflection coefficients, a reflection data volume is obtained.

[0116] In some embodiments, see continue to see Figure 13 The adjustment unit 12022 is used to obtain multiple third target reflection coefficients when the geological body type is collapse. The position of the third target reflection coefficients is used to represent the edge of the collapse. The position of the multiple third target reflection coefficients is adjusted downward by a preset distance to obtain the reflection data volume. The preset distance is used to represent the depth of the collapse.

[0117] In some embodiments, see continue to see Figure 13 The processing module 1203 is used to determine the three-dimensional point spread function based on the aperture parameter and frequency parameter. The aperture parameter and frequency parameter are used to reflect the exploration effect of the three-dimensional point spread function at various locations in the strata. Based on the three-dimensional point spread function, the reflection data volume is convolved to obtain the sample seismic data volume.

[0118] In some embodiments, see continue to see Figure 13 The device also includes:

[0119] The second adjustment module 1206 is used to adjust at least one of the aperture parameter and frequency parameter to obtain a new three-dimensional point diffusion function.

[0120] The processing module 1203 is also used to convolve the reflection data volume based on the new three-dimensional point spread function to obtain a new sample seismic data volume.

[0121] In some embodiments, see continue to see Figure 13 The training module 1204 is used to input sample seismic data volumes into the geological body recognition model to obtain seismic data features; based on the seismic data features, it identifies the locations of geological bodies belonging to the geological body category in the sample seismic data volumes; based on the difference between the identified geological body locations and the labeled locations of the sample seismic data volumes, it trains the geological body recognition model, and the labeled locations are determined based on the adjusted reflection coefficients.

[0122] This application provides a geological body identification device. By adjusting multiple reflection coefficients according to the category of the geological body to be identified, the resulting reflection data volume accurately reflects the reflection characteristics of the geological body in three-dimensional space. Then, the reflection data volume is processed using a three-dimensional point spread function, enabling the resulting sample seismic data volume to accurately reflect the characteristics of the geological body in three-dimensional space. In other words, it can more accurately simulate the data of the geological body in three-dimensional space, resulting in higher realism. The geological body identification model is then trained using the sample seismic data volume, allowing the model to fully learn the characteristics of the geological body, thereby improving its identification performance. Furthermore, when predicting the location of a target seismic data volume obtained from exploration based on the trained geological body identification model, the location of the geological body can be identified more accurately. Moreover, compared to manual interpretation, identifying the location of a geological body using a trained geological body identification model is more efficient.

[0123] It should be noted that the geological body identification device provided in the above embodiments is only illustrated by the division of the above functional modules when running the application. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the geological body identification device and the geological body identification method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0124] In the embodiments of this application, the computer device can be configured as a terminal or a server. When the computer device is configured as a terminal, the terminal can act as the execution subject to implement the technical solutions provided in the embodiments of this application. When the computer device is configured as a server, the server can act as the execution subject to implement the technical solutions provided in the embodiments of this application. Alternatively, the technical solutions provided in this application can be implemented through the interaction between the terminal and the server. The embodiments of this application do not limit this.

[0125] Figure 14 This is a structural block diagram of a terminal 1400 provided according to an embodiment of this application. The terminal 1400 can be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 1400 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0126] Typically, terminal 1400 includes a processor 1401 and a memory 1402.

[0127] Processor 1401 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1401 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1401 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1401 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, processor 1401 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0128] The memory 1402 may include one or more computer-readable storage media, which may be non-transitory. The memory 1402 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1402 are used to store at least one computer program, which is executed by the processor 1401 to implement the geological body identification method provided in the method embodiments of this application.

[0129] In some embodiments, the terminal 1400 may also optionally include a peripheral device interface 1403 and at least one peripheral device. The processor 1401, memory 1402, and peripheral device interface 1403 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1403 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 1404, a display screen 1405, a camera assembly 1406, an audio circuit 1407, and a power supply 1408.

[0130] Peripheral device interface 1403 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1401 and memory 1402. In some embodiments, processor 1401, memory 1402 and peripheral device interface 1403 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1401, memory 1402 and peripheral device interface 1403 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0131] The radio frequency (RF) circuit 1404 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1404 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1404 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. In some embodiments, the RF circuit 1404 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1404 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1404 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0132] Display screen 1405 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1405 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1401 for processing. In this case, display screen 1405 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1405, disposed on the front panel of terminal 1400; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1400 or in a folded design; in still other embodiments, display screen 1405 may be a flexible display screen, disposed on a curved or folded surface of terminal 1400. Furthermore, display screen 1405 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1405 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0133] The camera assembly 1406 is used to acquire images or videos. In some embodiments, the camera assembly 1406 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1406 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash is a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0134] The audio circuit 1407 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1401 for processing, or input to the radio frequency circuit 1404 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1400. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1401 or the radio frequency circuit 1404 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1407 may also include a headphone jack.

[0135] Power supply 1408 is used to power the various components in terminal 1400. Power supply 1408 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1408 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0136] In some embodiments, the terminal 1400 further includes one or more sensors 1409. The one or more sensors 1409 include, but are not limited to: an accelerometer 1410, a gyroscope 1411, a pressure sensor 1412, an optical sensor 1413, and a proximity sensor 1414.

[0137] Accelerometer 1410 can detect the magnitude of acceleration along the three axes of a coordinate system established by terminal 1400. For example, accelerometer 1410 can be used to detect the components of gravitational acceleration along the three axes. Processor 1401 can control display screen 1405 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1410. Accelerometer 1410 can also be used for games or for acquiring user motion data.

[0138] The gyroscope sensor 1411 can detect the orientation and rotation angle of the terminal 1400. The gyroscope sensor 1411 can work in conjunction with the accelerometer sensor 1410 to collect the user's 3D movements on the terminal 1400. Based on the data collected by the gyroscope sensor 1411, the processor 1401 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0139] The pressure sensor 1412 can be disposed on the side bezel of the terminal 1400 and / or on the lower layer of the display screen 1405. When the pressure sensor 1412 is disposed on the side bezel of the terminal 1400, it can detect the user's grip signal on the terminal 1400, and the processor 1401 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1412. When the pressure sensor 1412 is disposed on the lower layer of the display screen 1405, the processor 1401 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1405. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0140] Optical sensor 1413 is used to collect ambient light intensity. In one embodiment, processor 1401 can control the display brightness of display screen 1405 based on the ambient light intensity collected by optical sensor 1413. Specifically, when the ambient light intensity is high, the display brightness of display screen 1405 is increased; when the ambient light intensity is low, the display brightness of display screen 1405 is decreased. In another embodiment, processor 1401 can also dynamically adjust the shooting parameters of camera assembly 1406 based on the ambient light intensity collected by optical sensor 1413.

[0141] The proximity sensor 1414, also known as a distance sensor, is typically located on the front panel of the terminal 1400. The proximity sensor 1414 is used to detect the distance between the user and the front of the terminal 1400. In one embodiment, when the proximity sensor 1414 detects that the distance between the user and the front of the terminal 1400 is gradually decreasing, the processor 1401 controls the display screen 1405 to switch from a screen-on state to a screen-off state; when the proximity sensor 1414 detects that the distance between the user and the front of the terminal 1400 is gradually increasing, the processor 1401 controls the display screen 1405 to switch from a screen-off state to a screen-on state.

[0142] Those skilled in the art will understand that Figure 14 The structure shown does not constitute a limitation on terminal 1400 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0143] Figure 15 This is a structural block diagram of a server according to an embodiment of this application. The server 1500 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1501 and one or more memories 1502. The memory 1502 stores at least one computer program, which is loaded and executed by the processor 1501 to implement the geological body identification method provided in the above-described method embodiments. Of course, the server 1500 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 1500 may also include other components for implementing device functions, which will not be elaborated here.

[0144] This application also provides a computer-readable storage medium storing at least one computer program. This computer program is loaded and executed by a processor of a computer device to implement the operations performed by the computer device in the geological body identification method of the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0145] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program code, causing the computer device to perform the geological body identification method provided in the various optional implementations described above.

[0146] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0147] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for identifying geological bodies, characterized in that, The method includes: Multiple reflection coefficients are obtained, which are used to simulate the properties of reflected seismic wavelets at multiple locations in multiple strata in three-dimensional space. The multiple reflection coefficients are folded and deformed to obtain an intermediate data volume, which is used to simulate the reflection characteristics of real geological structures. When the geological body type is a karst cave, multiple first target reflection coefficients and multiple second target reflection coefficients are obtained from the intermediate data volume. The position of the first target reflection coefficient is used to represent the edge of the karst cave, and the position of the second target reflection coefficient is used to represent the interior of the karst cave. The multiple first target reflection coefficients surround the multiple second target reflection coefficients. The reflection coefficients of the plurality of first targets are adjusted such that the value of any one of the adjusted first target reflection coefficients is different from the values ​​of other reflection coefficients in the same stratum. Adjust the values ​​of the reflection coefficients of the plurality of second targets to zero; Based on the adjusted reflection coefficients of the plurality of first targets and the plurality of second targets, a reflection data volume is obtained, which is used to simulate the reflection characteristics of geological bodies belonging to the geological body category; The reflection data volume is processed based on the three-dimensional point spread function to obtain the sample seismic data volume. The three-dimensional point spread function is used to represent the propagation properties of the seismic wavelet in time and space. The sample seismic data volume is used to simulate the characteristics of geological bodies belonging to the geological body category. Based on the sample seismic data, a geological body identification model is trained, and the trained geological body identification model is used to identify the location of geological bodies belonging to the geological body category in the strata; Based on the trained geological body identification model, the target seismic data volume is predicted to obtain the location of geological bodies belonging to the geological body category in the target stratigraphic region. The target seismic data volume is obtained based on the exploration of the target stratigraphic region.

2. The method according to claim 1, characterized in that, The method further includes: In the case where the geological body category is collapse, multiple third target reflection coefficients are obtained in the intermediate data volume, and the positions of the third target reflection coefficients are used to represent the edges of the collapse. The positions of the reflection coefficients of the plurality of third targets are adjusted downward by a preset distance to obtain the reflection data volume, and the preset distance is used to represent the depth of the collapse.

3. The method according to claim 1, characterized in that, The process of processing the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume includes: The three-dimensional point diffusion function is determined based on aperture parameters and frequency parameters. The aperture parameters and frequency parameters are used to reflect the exploration effect of the three-dimensional point diffusion function at various locations in the formation. The sample seismic data volume is obtained by convolving the reflection data volume based on the three-dimensional point spread function.

4. The method according to claim 3, characterized in that, The method further includes: By adjusting at least one of the aperture parameter and the frequency parameter, a new three-dimensional point spread function is obtained; The reflection data volume is convolved based on the new three-dimensional point spread function to obtain the new sample seismic data volume.

5. The method according to claim 1, characterized in that, The training of the geological body identification model based on the sample seismic data volume includes: The sample seismic data volume is input into the geological body identification model to obtain seismic data features; Based on the seismic data characteristics, the locations of geological bodies belonging to the geological body category within the sample seismic data volume are identified; The geological body identification model is trained based on the difference between the location of the identified geological body and the labeled location of the sample seismic data volume, wherein the labeled location is determined based on the adjusted reflection coefficient.

6. A device for identifying geological bodies, characterized in that, The device includes: The acquisition module is used to acquire multiple reflection coefficients, which are used to simulate the properties of reflected seismic wavelets at multiple locations in multiple strata in three-dimensional space; A first adjustment module is used to fold and deform the multiple reflection coefficients to obtain an intermediate data volume, which is used to simulate the reflection characteristics of a real geological structure. In the case of a karst cave, multiple first target reflection coefficients and multiple second target reflection coefficients are obtained. The positions of the first target reflection coefficients represent the edges of the karst cave, and the positions of the second target reflection coefficients represent the interior of the karst cave. The multiple first target reflection coefficients surround the multiple second target reflection coefficients. The multiple first target reflection coefficients are adjusted such that the value of any adjusted first target reflection coefficient is different from the values ​​of other reflection coefficients in the same stratum. The values ​​of the multiple second target reflection coefficients are adjusted to zero. Based on the adjusted multiple first target reflection coefficients and multiple second target reflection coefficients, a reflection data volume is obtained, which is used to simulate the reflection characteristics of a geological body belonging to the specified geological body category. The processing module is used to process the reflection data volume based on the three-dimensional point spread function to obtain the sample seismic data volume. The three-dimensional point spread function is used to represent the propagation properties of the seismic wavelet in time and space. The sample seismic data volume is used to simulate the characteristics of geological bodies belonging to the geological body category. The training module is used to train the geological body identification model based on the sample seismic data volume. The trained geological body identification model is used to identify the location of geological bodies belonging to the geological body category in the strata. The prediction module is used to predict the target seismic data volume based on the trained geological body identification model, and to obtain the location of geological bodies belonging to the geological body category in the target stratigraphic region, wherein the target seismic data volume is obtained based on the exploration of the target stratigraphic region.

7. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded by the processor and executed as the geological body identification method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store at least one computer program for performing the geological body identification method according to any one of claims 1 to 5.

Images