Fault prediction method, device, equipment and storage medium

Abstract

The application discloses a fault prediction method and device, equipment and a storage medium, and belongs to the technical field of seismic exploration. The fault prediction method provided by the application carries out model training based on a fault energy body and seismic data, obtains a fault prediction model, and predicts the faults in the work area through the fault prediction model. The energy value of the known fault in the fault energy body is obtained based on a geological interpretation mode. The method involves the geological interpretation mode in the model training, forms a fault prediction model driven by the geological interpretation mode and the seismic data, makes the prediction result more consistent with the actual geological development mode of the work area, and thus improves the accuracy of fault prediction. Moreover, the method matches the predicted fault with the known fault, determines the accuracy of the prediction result according to the matching degree of the two, so that the prediction result is controlled by the interpretation scheme of the known fault and is more consistent with the actual geological mode of the region, and thus the accuracy of fault prediction is further improved.

Description

Technical Field

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

[0002] Fault identification and interpretation are important components of seismic interpretation. Accurate and reasonable fault identification is an important guarantee for precise geological structural interpretation, and faults play a crucial role in oil and gas exploration and development.

[0003] In related technologies, fault prediction is mainly based on the experience of staff. However, different regions have different fault types and geological conditions. Therefore, relying solely on experience cannot accurately predict faults, resulting in a low accuracy rate for fault prediction. Summary of the Invention

[0004] This application provides a fault prediction method, apparatus, device, and storage medium, which can improve the accuracy of fault prediction. The technical solution is as follows:

[0005] On the one hand, a fault prediction method is provided, the method comprising:

[0006] Acquire seismic and geological data for the target work area;

[0007] Based on the geological data and the seismic data, a geological interpretation model for the target work area is determined, and the geological interpretation model includes the fault type and fault morphology of the target work area;

[0008] Within the same spatial range as the seismic data, a first fault energy body is generated based on the geological interpretation model and the seismic data. The first fault energy body is marked with the energy values ​​corresponding to known faults in the target work area.

[0009] Based on the earthquake data and the energy body of the first fault, a fault prediction model is obtained through model training.

[0010] Based on the fault prediction model and the seismic data, the unknown faults in the target work area are predicted;

[0011] Determine the matching degree between the predicted fault and the known fault, wherein the predicted fault is the fault predicted by the fault prediction model at the target location, and the target location is the location of the known fault;

[0012] The accuracy of the prediction result is determined based on the relationship between the matching degree and the preset matching degree threshold.

[0013] In one possible implementation, generating a first fault energy body within the same spatial range as the seismic data, based on the geological interpretation model and the seismic data, includes:

[0014] Based on the geological interpretation model and the seismic data, fault labels for the known faults are determined, and the fault labels are used to represent the characteristics of the known faults.

[0015] Within the same spatial range as the seismic data, a first fault energy body corresponding to the fault label is generated.

[0016] In another possible implementation, generating a first fault energy body corresponding to the fault label within the same spatial range as the seismic data includes:

[0017] An initial energy body is generated within the same spatial range as the seismic data;

[0018] Determine the spatial location of the known fault in the seismic data;

[0019] The energy value at the position corresponding to the spatial location in the initial energy body is set to a first preset value, and the energy values ​​at the remaining positions are set to a second preset value to obtain the first fault energy body.

[0020] In another possible implementation, the prediction of unknown faults in the target work area based on the fault prediction model and the seismic data includes:

[0021] The earthquake data is input into the fault prediction model to obtain the second fault energy body;

[0022] Based on the energy values ​​marked in the second fault energy body, the unknown faults in the target work area are determined.

[0023] In another possible implementation, determining the degree of matching between the predicted fault and the known fault includes:

[0024] The fault labels of the known faults are overlaid and displayed in the second fault energy body;

[0025] Based on the overlay display results, the matching degree between the predicted fault and the known fault is determined.

[0026] In another possible implementation, determining the accuracy of the prediction result based on the relationship between the matching degree and a preset matching degree threshold includes:

[0027] If the matching degree is greater than the preset matching degree threshold, it is determined that the accuracy of the prediction result meets the requirements;

[0028] If the matching degree is not greater than the preset matching degree threshold, it is determined that the accuracy of the prediction result does not meet the requirements.

[0029] On the other hand, a fault prediction device is provided, the device comprising:

[0030] The acquisition module is used to acquire seismic and geological data of the target work area;

[0031] The first determining module is used to determine the geological interpretation mode of the target work area based on the geological data and the seismic data, wherein the geological interpretation mode includes the fault type and fault morphology of the target work area;

[0032] The generation module is used to generate a first fault energy body based on the geological interpretation model and the seismic data within the same spatial range as the seismic data. The first fault energy body is marked with the energy values ​​corresponding to known faults in the target work area.

[0033] The training module is used to train the model based on the earthquake data and the first fault energy body to obtain the fault prediction model.

[0034] The prediction module is used to predict unknown faults in the target work area based on the fault prediction model and the seismic data.

[0035] The second determining module is used to determine the matching degree between the predicted fault and the known fault, wherein the predicted fault is the fault predicted by the fault prediction model at the target location, and the target location is the location of the known fault;

[0036] The third determining module is used to determine the accuracy of the prediction result based on the relationship between the matching degree and the preset matching degree threshold.

[0037] In one possible implementation, the generation module is configured to determine fault labels for the known faults based on the geological interpretation model and the seismic data, the fault labels representing the characteristics of the known faults; and generate a first fault energy body corresponding to the fault labels within the same spatial range as the seismic data.

[0038] In another possible implementation, the generation module is used to generate an initial energy body within the same spatial range as the seismic data; determine the spatial location of the known fault in the seismic data; set the energy value of the position corresponding to the spatial location in the initial energy body to a first preset value, and set the energy values ​​of the remaining positions to a second preset value, thereby obtaining the first fault energy body.

[0039] In another possible implementation, the prediction module is used to input the seismic data into the fault prediction model to obtain a second fault energy body; and to determine the unknown faults in the target work area based on the energy values ​​marked in the second fault energy body.

[0040] In another possible implementation, the second determining module is used to overlay and display the fault labels of the known faults in the second fault energy body; and based on the overlay display results, determine the matching degree between the predicted fault and the known faults.

[0041] In another possible implementation, the third determining module is used to determine that the accuracy of the prediction result meets the requirements if the matching degree is greater than the preset matching degree threshold; and to determine that the accuracy of the prediction result does not meet the requirements if the matching degree is not greater than the preset matching degree threshold.

[0042] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one piece of program code, which is loaded and executed by the processor to implement the fault prediction method described in any of the preceding claims.

[0043] On the other hand, a computer-readable storage medium is provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to implement the fault prediction method described in any of the preceding claims.

[0044] On the other hand, a computer program product is provided, wherein at least one piece of program code is stored in the computer program product, the at least one piece of program code being loaded and executed by a processor to implement the fault prediction method described in any of the above claims.

[0045] This application provides a fault prediction method. This method trains a model based on fault energy volumes and seismic data to obtain a fault prediction model, which is then used to predict faults in the work area. The energy values ​​of known faults in the fault energy volumes are obtained based on a geological interpretation model. Therefore, this method incorporates the geological interpretation model into the model training, forming a fault prediction model driven by both the geological interpretation model and seismic data. This makes the prediction results more consistent with the actual geological development pattern of the work area, thereby improving the accuracy of fault prediction. Furthermore, this method matches the predicted faults with known faults. The accuracy of the prediction result is determined based on the relationship between the matching degree and a preset matching degree threshold. In other words, the predicted faults are quality-controlled using known faults, ensuring that the prediction results are controlled by the interpretation scheme of known faults. This better reflects the actual geological pattern of the region, further improving the accuracy of fault prediction.

[0046] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this disclosure. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the implementation environment of a fault prediction method provided in an embodiment of this application;

[0048] Figure 2 This is a flowchart of a fault prediction method provided in an embodiment of this application;

[0049] Figure 3 This is a comparison image of seismic profiles before and after smoothing filtering, provided in an embodiment of this application.

[0050] Figure 4 This is a schematic diagram of picking up fault lines according to an embodiment of this application;

[0051] Figure 5 This is a schematic diagram of a first fault energy body cross-section provided in an embodiment of this application;

[0052] Figure 6 This is a schematic diagram of a second fault energy body profile provided in an embodiment of this application;

[0053] Figure 7 This is a schematic diagram of an embodiment of the present application providing a method for overlaying and displaying fault labels of known faults in a second fault energy body;

[0054] Figure 8 This is a schematic diagram of an interactive training tomography prediction model provided in an embodiment of this application;

[0055] Figure 9 This is a schematic diagram of the structure of a fault prediction device provided in an embodiment of this application;

[0056] Figure 10 This is a structural block diagram of a terminal provided in an embodiment of this application;

[0057] Figure 11 This is a structural block diagram of a server provided in an embodiment of this application. Detailed Implementation

[0058] To make the technical solution and advantages of this application clearer, the embodiments of this application will be described in further detail below.

[0059] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0060] 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 earthquake data and geological data involved in this application were obtained with full authorization.

[0061] Figure 1 This is a schematic diagram of the implementation environment of a fault prediction method provided in an embodiment of this application. Figure 1 The implementation environment includes an electronic device, which can be provided as terminal 101, or as a combination of terminal 101 and server 102. If the electronic device is provided as terminal 101 and server 102, terminal 101 and server 102 can be connected via a wireless or wired network. In this embodiment, the electronic device is not specifically limited.

[0062] If the electronic device is provided as terminal 101, then terminal 101 performs model training to obtain a fault prediction model. This fault prediction model can be deployed in terminal 101, so that terminal 101 can use the fault prediction model to predict unknown faults in the target work area.

[0063] If the electronic device is provided as server 102, then server 102 performs model training to obtain a fault prediction model, which can be deployed to terminal 101. Accordingly, the implementation environment also includes terminal 101, which can be connected to server 102 via a wireless or wired network. Terminal 101 uses the fault prediction model to predict unknown faults in the target work area.

[0064] If the electronic device is provided as terminal 101 and server 102, then server 102 performs model training to obtain a fault prediction model, and then the fault prediction model is deployed to terminal 101, so that terminal 101 can use the fault prediction model to predict unknown faults in the target work area.

[0065] The terminal 101 can be at least one of the following: tablet computer, desktop computer, PC (Personal Computer) device, intelligent voice interaction device, etc. The server 102 can be at least one of the following: a single server, a server cluster consisting of multiple servers, a cloud server, a cloud computing platform, and a virtualization center.

[0066] Figure 2 This is a flowchart of a fault prediction method provided in an embodiment of this application, executed by an electronic device. See also... Figure 2 The method includes:

[0067] Step 201: Electronic equipment acquires seismic and geological data of the target work area.

[0068] The target work area is the earthquake research area.

[0069] Geological data may include stratigraphic data, stratigraphic data, geological lithology data, and other relevant geological data for the target work area.

[0070] Electronic devices can acquire locally stored seismic data, as well as seismic data transmitted by other electronic devices; there is no specific limitation in this regard. Similarly, electronic devices can acquire locally stored geological data, as well as geological data transmitted by other electronic devices; there is no specific limitation in this regard.

[0071] Step 202: The electronic equipment determines the geological interpretation model of the target work area based on geological and seismic data.

[0072] The geological interpretation model includes the fault type and fault morphology of the target work area. Fault type can include normal faults, reverse faults, strike-slip faults, and other types of faults, without specific limitations. Fault morphology can include planar faults, shovel faults, backhoe faults, step faults, and other morphologies, without specific limitations.

[0073] Electronic equipment can display seismic data from multiple perspectives, including main seismic line profiles, tie line profiles, and horizontal slices, at intervals of 1–10 lines, 1–10 lines, and 1–10 milliseconds or meters, respectively. This allows for the preliminary acquisition of the amplitude, phase, and frequency ranges of various parts of the seismic data, as well as the location and structural type of seismic phase axes. Combined with geological data, a geological interpretation model can be determined. The structural types of seismic phase axes include parallel, sub-parallel, and non-parallel.

[0074] Step 203: The electronic device generates the first fault energy body based on the geological interpretation model and the seismic data within the same spatial range as the seismic data.

[0075] The energy volume of the first fault is marked with the energy values ​​corresponding to the known faults in the target work area.

[0076] This step can be achieved through the following steps (1) to (2), including:

[0077] (1) Electronic devices determine the fault labels of known faults based on geological interpretation models and seismic data.

[0078] Fault labels are used to indicate the characteristics of known faults. These characteristics include the location of the known fault on the seismic profile, and may also include at least one of length, shape, and dip angle. The length of a known fault can range from 10 to 3000 meters, the shape can be a straight line, a broken line, or a curve, and the dip angle can range from 0 to 90°.

[0079] Step (1) can be achieved through the following steps (1-1) to (1-2), including:

[0080] (1-1) Electronic equipment performs smoothing filtering on seismic data to obtain processed seismic data.

[0081] Electronic equipment can extract the dip angle / slope and fault information of seismic data, and then use fault scanning to enhance and refine the faults. Under the constraints of the refined fault and stratigraphic data, the seismic data is smoothed and filtered to obtain the processed seismic data.

[0082] In the embodiments of this application, smoothing filtering of seismic data can improve the signal-to-noise ratio of seismic data, making the signal-to-noise ratio of seismic data greater than 3, while also doubling the number of disconnected seismic phase axes.

[0083] See Figure 3 (a) and (b), Figure 3 (a) is the seismic profile before smoothing filtering. Figure 3 (b) shows the seismic profile after smoothing filtering. Smoothing filtering can improve the signal-to-noise ratio of seismic data to 3.5. It can be seen that after smoothing filtering, the location of the seismic phase axis misalignment is clearer and more distinct, and the continuous parts are more continuous.

[0084] (1-2) Electronic devices determine the fault labels of known faults based on processed seismic data and geological interpretation models.

[0085] The electronic equipment can acquire interpreted fault data of the target work area and, based on this data, count the number, length (10–3000 meters), shape (straight line, broken line, or curve), and dip angle (0–90°) of existing faults. This interpreted fault data can be obtained through human interpretation, and the electronic equipment can acquire the input interpreted fault data.

[0086] Electronic equipment performs profile fault interpretation on the processed seismic data. Based on the geological interpretation model and the location of the seismic phase axis misalignment, it picks the above-mentioned statistical fault segments as known faults and determines the location of the fault segments on the seismic profile. At the same time, it can also determine at least one of the length, shape and dip angle of the fault segments, thereby obtaining the fault label of the known faults.

[0087] For example, electronic equipment picks up fault segments as known faults based on the location of phase axis misalignment on three seismic profiles. See also Figure 4 , Figure 4 The fault segments marked in the image are obtained by picking fault segments from a certain seismic profile.

[0088] It should be noted that if the number of known faults is small, for example less than the preset number, the electronic device can perform random simulation based on at least one of the length, dip angle, and morphology of the known faults to generate simulated faults, and use the simulated faults as known faults.

[0089] For example, if the dip angle of a known fault is the first dip angle, the electronic device can rotate the known fault by a preset angle to obtain a simulated fault with the second dip angle, and use the simulated fault with the second dip angle as the known fault.

[0090] Another point to note is that by controlling the fault labels (at least one of length, shape, and dip), the fault prediction model can make selective predictions. For example, if the fault label only includes one of length, shape, and dip, such as a fault label that only includes length and has a length of 100 meters, then the trained fault prediction model can only predict faults with a length of 100 meters, thus achieving the prediction of only one type of fault. Alternatively, if the fault label includes multiple factors such as length, shape, and dip, such as fault labels that include length (10–3000 meters) and shape (straight line, broken line, curve), then the fault prediction model can predict faults with a length between 10 and 3000 meters or with a shape that is straight, broken, or curved, thus achieving the prediction of multiple types of faults.

[0091] (2) Within the same spatial range as the seismic data, the electronic device generates the first fault energy body corresponding to the fault label.

[0092] The electronic device first generates an initial energy volume within the same spatial range as the seismic data; then it determines the spatial location of the known fault in the seismic data; then it sets the energy value of the location corresponding to the spatial location in the initial energy volume to a first preset value, and sets the energy values ​​of the remaining locations to a second preset value, thus obtaining the first fault energy volume.

[0093] The initial energy body generated by the electronic device can have an energy value set, or it can be left unset. If an energy value is set, the energy value at each location will be the same, either the default value or the second preset value.

[0094] Electronic equipment can determine the spatial location of a known fault in seismic data by identifying its line number, trace number, X coordinate, Y coordinate, and depth value.

[0095] If the energy value at each position in the initial energy body is the default value, the electronic device will adjust the energy value at the position corresponding to that spatial position in the initial energy body from the default value to the first preset value, and adjust the energy value at the remaining positions from the default value to the second preset value, thus obtaining the first fault energy body.

[0096] If the energy value at each position in the initial energy body is the second preset value, the electronic device will adjust the energy value at the position corresponding to that spatial position in the initial energy body from the second preset value to the first preset value, while keeping the energy values ​​at the other positions unchanged, thus obtaining the first fault energy body.

[0097] If no energy value is set in the initial energy body, the electronic device modifies the energy value at the position corresponding to the spatial location in the initial energy body to the first preset value, and modifies the energy values ​​at the other positions to the second preset value, thus obtaining the first fault energy body.

[0098] The first and second preset values ​​can be set and changed as needed, and are not specifically limited thereto. For example, the first preset value can be 100, and the second preset value can be 0. In this embodiment, only the example of a first preset value of 100 and a second preset value of 0 is used for illustration.

[0099] For example, the electronic device generates fault energy volumes corresponding to fault labels of known faults in three seismic profiles. See also Figure 5 , Figure 5 This is a schematic diagram of the energy body profile of the first fault. The white line in the diagram indicates the location of the known fault. The energy value corresponding to the white line is 100, and the energy value at other locations is 0.

[0100] In this embodiment of the application, the first fault energy body is an energy body containing known fault information. Inside it, the energy value at the location of the fault label is 100, and the energy value at other locations is 0.

[0101] In the embodiments of this application, after the electronic device generates the first fault energy body, it can directly perform model training, or it can first store the smoothed and filtered seismic data and the first fault energy body in the sample label library, and then obtain the seismic data and the corresponding first fault energy body from the sample label library during subsequent training. No specific limitation is made in this regard.

[0102] Step 204: The electronic device trains the model based on the seismic data and the energy body of the first fault to obtain the fault prediction model.

[0103] In this step, the electronic device trains a model using a neural network based on the smoothed and filtered seismic data and the energy volume of the first fault. This neural network is a two-dimensional U-shaped encoder-decoder structure, which saves computational resources while learning nonlinear features at different scales. By minimizing the loss function, the nonlinear features between the seismic data and the fault labels are established, as shown in Equation 1 below:

[0104]

[0105] Where L(Θ) represents the loss function, y i Indicates the true label of a known fault. This represents the predicted fault, and N represents the number of pixels corresponding to the fault line segment of the known fault.

[0106] Electronic devices use neural network models for iterative training. When the number of iterations reaches the preset number of iterations, or the difference between the loss values ​​of the two generations of training is less than the preset threshold, it is determined that the convergence condition is met, and the model that meets the convergence condition is determined as the fault prediction model.

[0107] The preset number of iterations and the preset threshold can be set and changed as needed, without any specific limitations.

[0108] Step 205: The electronic equipment predicts unknown faults in the target work area based on the fault prediction model and seismic data.

[0109] The electronic equipment inputs the smoothed and filtered seismic data into the fault prediction model to obtain the second fault energy volume; based on the energy values ​​marked in the second fault energy volume, the unknown faults in the target work area are determined.

[0110] In this implementation, the electronic device determines the location of the unknown fault as the position marked with the first preset value in the second fault energy body, and determines the length, dip angle and shape of the unknown fault based on at least one of the length, dip angle and shape of the position.

[0111] See Figure 6 , Figure 6 This is a schematic diagram of the energy body profile of the second fault. Figure 6 The black line in the image indicates the predicted location of the fault.

[0112] In this embodiment of the application, the electronic device predicts unknown faults in the target work area through a fault prediction model, thereby depicting the possible fault locations within the spatial range of the seismic data and assisting in the fault interpretation of the seismic data.

[0113] Step 206: Electronic equipment determines the degree of matching between the predicted fault and the known fault.

[0114] The electronic device overlays the fault labels of known faults onto a second fault energy body. Based on the overlay display results, it determines the matching degree between the predicted fault and the known fault. Here, the predicted fault is the fault predicted by the fault prediction model at the target location, and the target location is the location of the known fault.

[0115] In this implementation, the electronic device can overlay and display the fault labels of the known faults in the second fault energy volume based on the spatial location of the known faults in the seismic data, and then determine the matching degree between the fault labels of the predicted faults and the fault labels of the known faults based on the overlay display results.

[0116] If the fault label includes at least one of length, shape, and dip, the electronic device can determine the degree of matching between at least one of the length, shape, and dip of the predicted fault and at least one of the length, shape, and dip of a known fault.

[0117] Step 207: The electronic device determines the accuracy of the prediction result based on the relationship between the matching degree and the preset matching degree threshold.

[0118] If the matching degree is greater than the preset matching degree threshold, the accuracy of the prediction result is determined to meet the requirements; if the matching degree is not greater than the preset matching degree threshold, the accuracy of the prediction result is determined to not meet the requirements.

[0119] In one possible implementation, the fault label includes length, so the electronic device can determine the degree of matching between the length of the predicted fault and the length of the known fault.

[0120] The electronic device can determine the ratio of the total length of the predicted fault segments to the total length of the known fault segments, and define this ratio as the matching degree. If the matching degree is greater than a preset matching degree threshold, the accuracy of the prediction result is determined to meet the requirements; if the matching degree is not greater than the preset matching degree threshold, the accuracy of the prediction result is determined to not meet the requirements.

[0121] For example, if the preset matching threshold is 80%, the total length of the predicted fault segment is 5800m, and the total length of the known fault segment is 6600m, then the ratio of the two is 87.88%. Since 87.88% > 80%, the accuracy of the prediction result is determined to meet the requirements.

[0122] See Figure 7 , Figure 7 This is a schematic diagram showing the overlay display of fault labels of known faults in a second fault energy body. Figure 7The black line represents the predicted location of the fault, while the gray line represents the location of the known fault.

[0123] In one possible implementation, the fault label includes morphology, so the electronic device can determine the degree of matching between the morphology of the predicted fault and the morphology of a known fault.

[0124] For example, if the predicted fault is a straight line and the known fault is also a straight line, then they are determined to be consistent. In this case, the electronic device determines that the matching degree is greater than a preset matching degree threshold, thus determining that the accuracy of the prediction result meets the requirements. Conversely, if the predicted fault is a curve and the known fault is a straight line, then they are determined to be inconsistent. In this case, the electronic device determines that the matching degree is not greater than a preset matching degree threshold, thus determining that the accuracy of the prediction result does not meet the requirements.

[0125] In one possible implementation, the fault label includes dip angle, so the electronic device can determine the degree of matching between the dip angle of the predicted fault and the dip angle of the known fault.

[0126] The electronic device determines the angle difference between the dip angle of the predicted fault and the dip angle of the known fault, and uses this angle difference as the matching degree. If the angle difference is less than a preset angle difference, the matching degree is determined to be greater than a preset matching degree threshold, and thus the accuracy of the prediction result is determined to meet the requirements; if the angle difference is not less than the preset angle difference, the matching degree is determined to be less than the preset matching degree threshold, and thus the accuracy of the prediction result is determined to not meet the requirements.

[0127] For example, if the predicted fault dip angle is 10° and the known fault dip angle is 15°, the angle difference between the two is 5°, which is less than the preset angle difference of 10°. In this case, the electronic device determines that the matching degree is greater than the preset matching degree threshold, and thus determines that the accuracy of the prediction result meets the requirements. If the angle difference between the two is 20°, which is greater than the preset angle difference of 10°, the electronic device determines that the matching degree is not greater than the preset matching degree threshold, and thus determines that the accuracy of the prediction result does not meet the requirements.

[0128] In one possible implementation, when the fault label includes multiple factors such as length, shape, and dip, the process for determining the accuracy of the prediction result is the same as the process for determining the accuracy of the prediction result when the fault label includes length, shape, and dip respectively, and will not be repeated here.

[0129] It should be noted that if the electronic device determines that the accuracy of the prediction results does not meet the requirements, it can increase the number of known faults. For example, it can randomly generate a portion of simulated faults based on known faults, thereby increasing the number of known faults, and / or acquire a portion of interpreted fault data, thus increasing the number of known faults. Based on the increased known faults, the first fault energy volume is regenerated. The model is then trained using the regenerated first fault energy volume and smoothed seismic data until the accuracy of the prediction results meets the requirements.

[0130] In this embodiment, the electronic device performs quality control on the predicted fault based on the known fault to determine the accuracy of the prediction results. This makes the prediction results subject to the interpretation scheme of the known fault, which is more in line with the actual geological model of the region and helps to improve the accuracy of fault interpretation work. At the same time, it greatly improves the accuracy and efficiency of fault prediction at different scales and lays the foundation for other seismic interpretation work.

[0131] This application provides a fault prediction method. This method trains a model based on fault energy volumes and seismic data to obtain a fault prediction model, which is then used to predict faults in the work area. The energy values ​​of known faults in the fault energy volumes are obtained based on a geological interpretation model. Therefore, this method incorporates the geological interpretation model into the model training, forming a fault prediction model driven by both the geological interpretation model and seismic data. This makes the prediction results more consistent with the actual geological development pattern of the work area, thereby improving the accuracy of fault prediction. Furthermore, this method matches the predicted faults with known faults. The accuracy of the prediction result is determined based on the relationship between the matching degree and a preset matching degree threshold. In other words, the predicted faults are quality-controlled using known faults, ensuring that the prediction results are controlled by the interpretation scheme of known faults. This better reflects the actual geological pattern of the region, further improving the accuracy of fault prediction.

[0132] Furthermore, the fault prediction model trained in this application starts from the actual work area, incorporating known faults in the area into the model training to establish an end-to-end mapping between known faults and seismic data. The trained fault prediction model is then applied to predict faults in the work area. This interactive training method can further improve the accuracy of fault prediction. See also... Figure 8 , Figure 8 This is a schematic diagram of interactive training of a fault prediction model.

[0133] The method provided in this application was used to test seismic data from the Bohai Bay Basin and Songliao Basin. The results showed that the fault distribution characteristics reflected in other geological data were consistent with those of the method, demonstrating its feasibility and accuracy.

[0134] Figure 9This is a schematic diagram of the structure of a fault prediction device provided in an embodiment of this application. See also... Figure 9 The device includes:

[0135] Module 901 is used to acquire seismic and geological data of the target work area;

[0136] The first determining module 902 is used to determine the geological interpretation model of the target work area based on geological data and seismic data. The geological interpretation model includes the fault type and fault morphology of the target work area.

[0137] The generation module 903 is used to generate a first fault energy body based on the geological interpretation model and the seismic data within the same spatial range as the seismic data. The first fault energy body is marked with the energy values ​​corresponding to the known faults in the target work area.

[0138] Training module 904 is used to train the model based on seismic data and the energy body of the first fault to obtain the fault prediction model.

[0139] Prediction module 905 is used to predict unknown faults in the target work area based on fault prediction models and seismic data;

[0140] The second determining module 906 is used to determine the matching degree between the predicted fault and the known fault, wherein the predicted fault is the fault predicted by the fault prediction model at the target location, and the target location is the location of the known fault.

[0141] The third determining module 907 is used to determine the accuracy of the prediction result based on the relationship between the matching degree and the preset matching degree threshold.

[0142] In one possible implementation, generation module 903 is used to determine fault labels of known faults based on geological interpretation models and seismic data. The fault labels are used to represent the characteristics of known faults. Within the same spatial range as the seismic data, a first fault energy body corresponding to the fault labels is generated.

[0143] In another possible implementation, the generation module 903 is used to generate an initial energy volume within the same spatial range as the seismic data; determine the spatial location of the known fault in the seismic data; set the energy value of the location corresponding to the spatial location in the initial energy volume to a first preset value, and set the energy values ​​of the remaining locations to a second preset value, thereby obtaining a first fault energy volume.

[0144] In another possible implementation, prediction module 905 is used to input seismic data into the fault prediction model to obtain a second fault energy body; based on the energy values ​​marked in the second fault energy body, the unknown faults in the target work area are determined.

[0145] In another possible implementation, the second determining module 906 is used to overlay and display the fault labels of known faults in the second fault energy body; based on the overlay display results, the matching degree between the predicted fault and the known fault is determined.

[0146] In another possible implementation, the third determining module 907 is used to determine that the accuracy of the prediction result meets the requirements if the matching degree is greater than the preset matching degree threshold; and to determine that the accuracy of the prediction result does not meet the requirements if the matching degree is not greater than the preset matching degree threshold.

[0147] This application provides a fault prediction device. This device trains a model based on fault energy volumes and seismic data to obtain a fault prediction model, which is then used to predict faults in the work area. The energy values ​​of known faults in the fault energy volumes are obtained based on a geological interpretation model. Therefore, this device incorporates the geological interpretation model into the model training, forming a fault prediction model driven by both the geological interpretation model and seismic data. This makes the prediction results more consistent with the actual geological development pattern of the work area, thereby improving the accuracy of fault prediction. Furthermore, the device matches the predicted faults with known faults. Based on the relationship between the matching degree and a preset matching degree threshold, the accuracy of the prediction results is determined. In other words, the predicted faults are quality-controlled using known faults, ensuring that the prediction results are controlled by the interpretation scheme of known faults. This better reflects the actual geological pattern of the region, further improving the accuracy of fault prediction.

[0148] In some embodiments, the electronic device is provided as a terminal. (See reference) Figure 10 , Figure 10 This illustration shows a structural block diagram of a terminal 1000 provided in an exemplary embodiment of this application. The terminal 1000 may 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 1000 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0149] Typically, terminal 1000 includes a processor 1001 and a memory 1002.

[0150] Processor 1001 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1001 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 1001 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 1001 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 1001 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0151] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 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 1002 are used to store at least one line of program code, which is executed by the processor 1001 to implement the tomography prediction method provided in the method embodiments of this application.

[0152] In some embodiments, the terminal 1000 may also optionally include a peripheral device interface 1003 and at least one peripheral device. The processor 1001, memory 1002, and peripheral device interface 1003 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1003 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 1004, a display screen 1005, a camera assembly 1006, an audio circuit 1007, and a power supply 1008.

[0153] Peripheral device interface 1003 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1001 and memory 1002. In some embodiments, processor 1001, memory 1002 and peripheral device interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1001, memory 1002 and peripheral device interface 1003 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0154] The radio frequency (RF) circuit 1004 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1004 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1004 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1004 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 1004 can communicate with other terminals via 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 1004 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0155] Display screen 1005 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1005 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 1001 for processing. In this case, display screen 1005 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 1005, disposed on the front panel of terminal 1000; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1000 or in a folded design; in still other embodiments, display screen 1005 may be a flexible display screen, disposed on a curved or folded surface of terminal 1000. Furthermore, display screen 1005 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1005 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0156] The camera assembly 1006 is used to acquire images or videos. Optionally, the camera assembly 1006 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 1006 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 refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0157] The audio circuit 1007 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 1001 for processing, or input to the radio frequency circuit 1004 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 1000. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1001 or the radio frequency circuit 1004 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 1007 may also include a headphone jack.

[0158] The power supply 1008 is used to power the various components in the terminal 1000. The power supply 1008 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When the power supply 1008 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, while 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.

[0159] In some embodiments, the terminal 1000 further includes one or more sensors 1009. The one or more sensors 1009 include, but are not limited to: an acceleration sensor 1010, a gyroscope sensor 1011, a pressure sensor 1012, an optical sensor 1013, and a proximity sensor 1014.

[0160] Accelerometer 1010 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by terminal 1000. For example, accelerometer 1010 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1001 can control display screen 1005 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1010. Accelerometer 1010 can also be used for games or for acquiring user motion data.

[0161] The gyroscope sensor 1011 can detect the orientation and rotation angle of the terminal 1000. The gyroscope sensor 1011 can work in conjunction with the accelerometer sensor 1010 to collect 3D motion data from the user on the terminal 1000. Based on the data collected by the gyroscope sensor 1011, the processor 1001 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.

[0162] The pressure sensor 1012 can be disposed on the side bezel of the terminal 1000 and / or on the lower layer of the display screen 1005. When the pressure sensor 1012 is disposed on the side bezel of the terminal 1000, it can detect the user's grip signal on the terminal 1000, and the processor 1001 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1012. When the pressure sensor 1012 is disposed on the lower layer of the display screen 1005, the processor 1001 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1005. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0163] An optical sensor 1013 is used to collect ambient light intensity. In one embodiment, a processor 1001 can control the display brightness of a display screen 1005 based on the ambient light intensity collected by the optical sensor 1013. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1005 is increased; when the ambient light intensity is low, the display brightness of the display screen 1005 is decreased. In another embodiment, the processor 1001 can also dynamically adjust the shooting parameters of a camera assembly 1006 based on the ambient light intensity collected by the optical sensor 1013.

[0164] The proximity sensor 1014, also known as a distance sensor, is typically installed on the front panel of the terminal 1000. The proximity sensor 1014 is used to detect the distance between the user and the front of the terminal 1000. In one embodiment, when the proximity sensor 1014 detects that the distance between the user and the front of the terminal 1000 is gradually decreasing, the processor 1001 controls the display screen 1005 to switch from a screen-on state to a screen-off state; when the proximity sensor 1014 detects that the distance between the user and the front of the terminal 1000 is gradually increasing, the processor 1001 controls the display screen 1005 to switch from a screen-off state to a screen-on state.

[0165] Those skilled in the art will understand that Figure 10 The structure shown does not constitute a limitation on terminal 1000 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0166] In some embodiments, the electronic device is provided as a server. A structural block diagram of the server can be found... Figure 11The server 1100 can vary considerably depending on its configuration or performance. It may include a processor (CPU) 1101 and a memory 1102, wherein the memory 1102 stores at least one line of program code, which is loaded and executed by the processor 1101 to implement the aforementioned tomography prediction method. Of course, the server 1100 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 1100 may also include other components for implementing device functions, which will not be elaborated here.

[0167] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one piece of program code that is loaded and executed by a processor to implement the tomography prediction method in the above embodiments.

[0168] In an exemplary embodiment, a computer program product is also provided, which stores at least one piece of program code that is loaded and executed by a processor to implement the tomography prediction method in the above embodiments.

[0169] 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.

[0170] The above description is only for the purpose of enabling those skilled in the art to understand the technical solution 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 fault prediction method, characterized in that, The method includes: Acquire seismic and geological data for the target work area; Based on the geological data and the seismic data, a geological interpretation model for the target work area is determined, and the geological interpretation model includes the fault type and fault morphology of the target work area; Within the same spatial range as the seismic data, a first fault energy body is generated based on the geological interpretation model and the seismic data. The first fault energy body is marked with the energy values ​​corresponding to known faults in the target work area. Based on the earthquake data and the energy body of the first fault, a fault prediction model is obtained through model training. Based on the fault prediction model and the seismic data, the unknown faults in the target work area are predicted; Determine the matching degree between the predicted fault and the known fault, wherein the predicted fault is the fault predicted by the fault prediction model at the target location, and the target location is the location of the known fault; The accuracy of the prediction result is determined based on the relationship between the matching degree and the preset matching degree threshold.

2. The method according to claim 1, characterized in that, The process of generating a first fault energy body within the same spatial range as the seismic data, based on the geological interpretation model and the seismic data, includes: Based on the geological interpretation model and the seismic data, fault labels for the known faults are determined, and the fault labels are used to represent the characteristics of the known faults. Within the same spatial range as the seismic data, a first fault energy body corresponding to the fault label is generated.

3. The method according to claim 2, characterized in that, The step of generating a first fault energy body corresponding to the fault label within the same spatial range as the seismic data includes: An initial energy body is generated within the same spatial range as the seismic data; Determine the spatial location of the known fault in the seismic data; The energy value at the position corresponding to the spatial location in the initial energy body is set to a first preset value, and the energy values ​​at the remaining positions are set to a second preset value to obtain the first fault energy body.

4. The method according to claim 1, characterized in that, The prediction of unknown faults in the target work area based on the fault prediction model and the seismic data includes: The earthquake data is input into the fault prediction model to obtain the second fault energy body; Based on the energy values ​​marked in the second fault energy body, the unknown faults in the target work area are determined.

5. The method according to claim 4, characterized in that, Determining the matching degree between the predicted fault and the known fault includes: The fault labels of the known faults are overlaid and displayed in the second fault energy body; Based on the overlay display results, the matching degree between the predicted fault and the known fault is determined.

6. The method according to claim 1, characterized in that, Determining the accuracy of the prediction result based on the relationship between the matching degree and a preset matching degree threshold includes: If the matching degree is greater than the preset matching degree threshold, it is determined that the accuracy of the prediction result meets the requirements; If the matching degree is not greater than the preset matching degree threshold, it is determined that the accuracy of the prediction result does not meet the requirements.

7. A fault prediction device, characterized in that, The device includes: The acquisition module is used to acquire seismic and geological data of the target work area; The first determining module is used to determine the geological interpretation mode of the target work area based on the geological data and the seismic data, wherein the geological interpretation mode includes the fault type and fault morphology of the target work area; The generation module is used to generate a first fault energy body based on the geological interpretation model and the seismic data within the same spatial range as the seismic data. The first fault energy body is marked with the energy values ​​corresponding to known faults in the target work area. The training module is used to train the model based on the earthquake data and the first fault energy body to obtain the fault prediction model. The prediction module is used to predict unknown faults in the target work area based on the fault prediction model and the seismic data. The second determining module is used to determine the matching degree between the predicted fault and the known fault, wherein the predicted fault is the fault predicted by the fault prediction model at the target location, and the target location is the location of the known fault; The third determining module is used to determine the accuracy of the prediction result based on the relationship between the matching degree and the preset matching degree threshold.

8. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one piece of program code, which is loaded and executed by the processor to implement the fault prediction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to implement the fault prediction method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product stores at least one piece of program code, which is loaded and executed by a processor to implement the fault prediction method as described in any one of claims 1 to 6.

Images