Seismic data quality determination method and device and storage medium

Abstract

The invention discloses a seismic data quality determination method and device and a storage medium, and belongs to the field of seismic data acquisition. The method comprises the following steps: generating quality control images of quality control parameters corresponding to a plurality of node devices, and inputting the quality control image corresponding to each node device into a preset quality control model to obtain a quality control prediction result of the quality control parameter corresponding to each node device, therefore, a worker can obtain whether the quality control parameters of the node equipment are abnormal or not based on the quality control prediction result, quality monitoring does not need to be performed on the acquired seismic data manually, the burden of the worker is reduced, and the efficiency of performing quality control on the seismic data is improved.

Description

Technical Field

[0001] This application relates to the field of seismic data acquisition technology, and in particular to a method, apparatus, and storage medium for determining seismic data quality. Background Technology

[0002] With the development of seismic exploration technology, the use of nodal devices to acquire seismic data is becoming increasingly common. To meet the quality requirements of seismic data acquired through nodal data acquisition, quality control of the acquired seismic data is typically necessary.

[0003] In related technologies, after all node devices are recovered, the seismic data collected by all acquisition devices is downloaded. Then, technicians use the seismic data collected by the node devices to identify abnormal seismic data corresponding to each node device. By identifying these abnormal seismic data, they can pinpoint problems with the data or locate malfunctioning acquisition devices, thereby ensuring the quality of the seismic data collected by the node devices.

[0004] However, the judgment and identification of abnormal seismic data often rely on technical personnel, who need to analyze the seismic data collected at each node one by one. This often results in the inability to obtain abnormal seismic data in a short period of time, leading to low efficiency in seismic data quality control. Summary of the Invention

[0005] This application provides a method, apparatus, and storage medium for determining the quality of seismic data, which can improve the efficiency of quality control of seismic data. The technical solution is as follows:

[0006] On the one hand, embodiments of this application provide a method for determining the quality of seismic data, the method comprising:

[0007] Obtain the quality control parameters corresponding to each node device. The quality control parameters are used to indicate whether the device status of the node device meets the requirements for acquiring seismic data.

[0008] Generate quality control images corresponding to the quality control parameters;

[0009] The quality control image corresponding to each node device is input into a preset quality control model to obtain the quality control prediction result of the quality control parameters corresponding to each node device. The quality control model is used to predict whether the quality control parameters of the node device are abnormal.

[0010] Optionally, the method further includes:

[0011] Based on the quality control image and the quality control prediction result for each of the multiple node devices, a quality control report is generated for each of the multiple node devices. The quality control report is used to indicate the abnormal information of the node devices that do not meet the collection requirements.

[0012] Optionally, the quality control parameters include: the root mean square of the amplitude of the seismic data acquired by the node device, the attitude angle of the node device, the polarity of the node device, the coupling of the node device, and at least one of the seismic auxiliary data. The polarity is used to indicate whether there is a situation where the signals received by the detectors of different components in the node device are reversed at the initial arrival. The coupling is used to indicate whether the node device is suspended, whether node displacement or dragging occurs during the acquisition process.

[0013] Optionally, the quality control prediction result includes: a classification result corresponding to each quality control image, wherein the classification result includes at least one of: normal result, abnormal result, and uncertain result.

[0014] Optionally, the method further includes:

[0015] If the classification result includes the uncertain result, the uncertain result is corrected based on the manual judgment result to obtain the corrected classification result, which is either the normal result or the abnormal result.

[0016] Optionally, the method further includes:

[0017] The sample data is input into the initial model, and the initial model is trained to obtain the quality control model. The sample data includes the sample quality control image corresponding to the node device and the quality control classification label corresponding to the sample quality control image.

[0018] Optionally, before inputting the sample data into the initial model, the method further includes:

[0019] Obtain the initial sample quality control image corresponding to the node device;

[0020] The initial sample quality control image is denoised and resized to obtain the sample quality control image.

[0021] On one hand, embodiments of this application provide an apparatus for determining the quality of seismic data, the apparatus comprising:

[0022] The first acquisition module is used to acquire the quality control parameters corresponding to each node device. The quality control parameters are used to indicate whether the device status of the node device meets the requirements for acquiring seismic data.

[0023] The first determining module is used to generate quality control images corresponding to the quality control parameters;

[0024] The second determining module is used to input the quality control image corresponding to each node device into a preset quality control model to obtain the quality control prediction result of the quality control parameters corresponding to each node device. The quality control model is used to predict whether the quality control parameters of the node device are abnormal.

[0025] Optionally, the device further includes:

[0026] The generation module is used to generate a quality control report for each of the multiple node devices based on the quality control image and the quality control prediction result for each node device. The quality control report is used to represent the abnormal information of the node devices that do not meet the collection requirements.

[0027] Optionally, the quality control parameters include: the root mean square of the amplitude of the seismic data acquired by the node device, the attitude angle of the node device, the polarity of the node device, the coupling of the node device, and at least one of the seismic auxiliary data. The polarity is used to indicate whether there is a situation where the signals received by the detectors of different components in the node device are reversed at the initial arrival. The coupling is used to indicate whether the node device is suspended, whether node displacement or dragging occurs during the acquisition process.

[0028] Optionally, the quality control prediction result includes: a classification result corresponding to each quality control image, wherein the classification result includes at least one of: normal result, abnormal result, and uncertain result.

[0029] Optionally, the device further includes:

[0030] The correction module is used to correct the uncertain result based on the manual judgment result if the classification result includes the uncertain result, so as to obtain the corrected classification result, wherein the corrected classification result is the normal result or the abnormal result.

[0031] Optionally, the device further includes:

[0032] The training module is used to input sample data into the initial model, train the initial model to obtain the quality control model, and the sample data includes sample quality control images corresponding to the node devices and quality control classification labels corresponding to the sample quality control images.

[0033] Optionally, the device further includes:

[0034] The second acquisition module is used to acquire the initial sample quality control image corresponding to the node device;

[0035] The adjustment module is used to denoise and resize the initial sample quality control image to obtain the sample quality control image.

[0036] On one hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one instruction, the instruction being loaded and executed by the one or more processors to perform the operation performed by the method for determining the quality of seismic data.

[0037] On one hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the computer-readable storage medium, the instruction being loaded and executed by a processor to implement the operation performed by the method for determining the quality of seismic data.

[0038] The beneficial effects of the technical solutions provided in this application include at least the following:

[0039] The method for determining the quality of seismic data provided in this application generates quality control images of quality control parameters corresponding to multiple node devices. The quality control image corresponding to each node device is input into a preset quality control model to obtain the quality control prediction results of the quality control parameters corresponding to each node device. Thus, staff can determine whether the quality control parameters of the node devices are abnormal based on the quality control prediction results, eliminating the need for manual quality monitoring of the acquired seismic data, reducing the burden on staff, and improving the efficiency of quality control of seismic data. Attached Figure Description

[0040] 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.

[0041] Figure 1 This is a flowchart of a method for determining seismic data quality provided in an embodiment of this application:

[0042] Figure 2 This is a flowchart of another method for determining seismic data quality provided in an embodiment of this application;

[0043] Figure 3 This is a schematic diagram of a seismic data quality determination device provided in an embodiment of this application. Detailed Implementation

[0044] 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.

[0045] Before providing a detailed explanation of the embodiments of this application, let's first introduce the application scenarios involved in the embodiments of this application.

[0046] Currently, when conducting seismic exploration of terrestrial or seabed strata, multiple survey lines can be deployed on the corresponding surface, with multiple nodal devices evenly spaced along each line. These nodal devices collect seismic waves generated at specific locations on the surface, thus obtaining seismic data. Since nodal devices cannot analyze and judge their own recorded seismic data in real time, typically, after collecting seismic data for a certain period, technicians retrieve all the nodal devices. After all nodal devices are retrieved, the seismic data collected by all nodal devices is downloaded. Then, technicians use this data to identify anomalous seismic data corresponding to each nodal device. By identifying these anomalous seismic data, they can pinpoint problems with the data or locate abnormal acquisition devices, thereby ensuring the quality of the seismic data collected by the nodal devices.

[0047] However, with the increased efficiency of seismic acquisition at sea and on land, the retrieval and download of node data are becoming more frequent, leading to a significant increase in the amount of data that needs to be processed from the node devices. This results in a large computational burden in the process of separating and processing seismic data from all node devices, greatly increasing the workload and processing time for on-site technicians. Consequently, abnormal seismic data often cannot be obtained in a short period of time, resulting in low efficiency in seismic data quality control. Therefore, this application provides a seismic data processing method that can improve the efficiency of seismic data quality control, thereby ensuring the quality of seismic data.

[0048] The seismic data processing method provided in this application embodiment can be executed by a computing device, which may have data processing capabilities. Optionally, the computing device may also have a data display function, such as displaying seismic data acquired by the acquisition device, the processing results of the seismic data, and detected abnormal acquisition information. Exemplarily, the computing device may be a terminal device such as a personal computer, tablet computer, or smartphone; of course, it may also be a backend server, which is not limited in this application embodiment.

[0049] Figure 1 This application provides a method for determining the quality of seismic data. For example... Figure 1 As shown, the method includes the following steps:

[0050] Step 101: Obtain the quality control parameters corresponding to each node device. The quality control parameters are used to indicate whether the device status of the node device meets the requirements for acquiring seismic data.

[0051] Step 102: Generate the quality control images corresponding to the quality control parameters.

[0052] Step 103: Input the quality control image corresponding to each node device into the preset quality control model to determine the quality control prediction result of the quality control parameters corresponding to each node device. The quality control model is used to predict whether the quality control parameters of the node device are abnormal.

[0053] The method for determining the quality of seismic data provided in this application generates quality control images of quality control parameters corresponding to multiple node devices. The quality control image corresponding to each node device is input into a preset quality control model to obtain the quality control prediction results of the quality control parameters corresponding to each node device. Thus, staff can determine whether the quality control parameters of the node devices are abnormal based on the quality control prediction results, eliminating the need for manual quality monitoring of the acquired seismic data, reducing the burden on staff, and improving the efficiency of quality control of seismic data.

[0054] Figure 2 This is a flowchart of another method for determining seismic data quality provided in an embodiment of this application. See also... Figure 2 The methods include:

[0055] Step 201: Obtain the quality control parameters corresponding to each node device.

[0056] It should be noted that during seismic exploration of strata, multiple node devices can be deployed on the corresponding surface to collect seismic data. These node devices are capable of both acquiring and storing seismic data.

[0057] In this embodiment, the quality control parameters corresponding to each node device are acquired according to a preset acquisition cycle. The preset acquisition cycle can be one day or multiple days, and this embodiment does not limit this.

[0058] Among them, the quality control parameters are used to indicate whether the equipment status of the node equipment meets the requirements for acquiring seismic data.

[0059] It should be noted that if the equipment status of a node device does not meet the requirements for acquiring seismic data, the corresponding quality control parameters of that node device will be abnormal. Therefore, the quality control parameters can be used to determine whether the equipment status of a node device meets the requirements for acquiring seismic data, thereby ensuring the quality of the seismic data obtained through that node device.

[0060] In one embodiment of this application, the quality control parameters include at least one of the following: the root mean square of the amplitude of the seismic data acquired by the node device, the attitude angle of the node device, the polarity of the node device, the coupling of the node device, and the seismic auxiliary data.

[0061] The root mean square of the earthquake data amplitude is used to measure the average intensity of the earthquake data amplitude. It is calculated by taking the square root of the square of the square of the earthquake data amplitude.

[0062] The attitude angle of a node device refers to the attitude angle of the node device when it is in contact with the ground surface, such as the attitude angle when it is in contact with the seabed or the attitude angle when it is in contact with the land surface. The attitude angle can be three angles: pitch angle, roll angle and attitude azimuth angle. The attitude angle can be obtained by an angle sensor.

[0063] The polarity of a node device is used to indicate whether there is a reversal of the initial arrival signal among the signals received by the detectors of different components within the node device. In this embodiment, the polarity of the node device is determined based on the orientation of the wave peak corresponding to the energy curve of the seismic data. Specifically, if the orientation of the determined wave peak is consistent with the orientation of the wave peak corresponding to a preset standard polarity, the polarity of the node device is considered normal; if the orientations are inconsistent, the polarity is considered abnormal.

[0064] The coupling of the node device is used to indicate whether the node device is suspended, whether node displacement or dragging occurs during the acquisition process.

[0065] Seismic auxiliary data may include: shot-receiver files, relationship files, and time files of the acquired data. The relationship file describes the shot points, receiver points, and the relationships between them in the seismic data; the shot-receiver file describes the location of the receiver points and the location of the excitation points.

[0066] Step 202: Generate a quality control image of the quality control parameters corresponding to each node device.

[0067] In some embodiments of this application, the quality control image of the quality control parameter is obtained by graphically quantizing the quality control parameter. For example, if the quality control parameter is the root mean square of the seismic data amplitude, then the quality control image is the root mean square plot of the seismic data amplitude, used to represent the average intensity of the seismic data amplitude; if the quality control parameter is the attitude angle of the node device, then the quality control image is an image used to represent the pitch angle, roll angle, and attitude azimuth angle of the node device, using different colors to correspond to different angle ranges, thereby enabling the change of angle to be reflected through the color of the image. If the quality control parameter is the polarity of the node device, then the quality control image is an energy curve representing the seismic data. The polarity of the node device is determined by the orientation of the peaks corresponding to the energy curve of the seismic data. The polarity is used to indicate whether there is a situation where the signals received by the detectors of different components in the node device are reversed at the initial arrival. If the quality control parameter is the coupling of the node device, then the quality control image is used to indicate whether the node device is suspended, whether node displacement or dragging occurs during the acquisition process. If the quality control parameter is seismic auxiliary data, then the quality control image may include at least one of an image representing the time of data acquisition and an image of the water depth corresponding to the shot location. This allows for comparison and identification of the time parameters of other nodes to determine whether there are any abnormalities in the time of data acquisition and whether there are any abnormalities in the image of the water depth corresponding to the color.

[0068] Step 203: Input the quality control image corresponding to each node device into the preset quality control model to obtain the quality control prediction result of the quality control parameters corresponding to each node device.

[0069] The quality control prediction results include: the classification result corresponding to each quality control image, which includes at least one of the following: normal result, abnormal result, and uncertain result. A normal result indicates that the quality control parameter is normal, an abnormal result indicates that the quality control parameter is abnormal, and an uncertain result indicates that it cannot be accurately determined whether the quality control parameter is abnormal.

[0070] It should be noted that when there are multiple quality control parameters, a quality control image will be obtained for each of the multiple quality control parameters. The corresponding quality control prediction result is the classification result for each quality control image. For example, when there are 5 quality control parameters, 5 classification results will be obtained.

[0071] The quality control model is used to predict whether the quality control parameters of the node devices are abnormal. These abnormalities reflect whether the device status meets the requirements for acquiring seismic data. If the quality control parameters are abnormal, the abnormal device status and its cause can be further determined based on these abnormal parameters. For example, for adjacent node devices, if their attitude angles are consistent and their device status meets the acquisition specifications, the root mean square (RMS) image morphology of the seismic data amplitude from each node will be roughly the same. If significant anomalies are found in the RMS of individual node devices through image analysis, it can be determined that the shot point excitation is abnormal or the receiving performance of the node device is abnormal.

[0072] In this embodiment, the quality control model can be a machine learning model, such as a deep neural network model. Based on training with a large number of samples, it is possible to determine whether the quality control parameters of the node device are abnormal.

[0073] The training process of the quality control model provided in this application embodiment is described below. The specific training process of the model is as follows:

[0074] The sample data includes sample quality control images corresponding to the node devices and quality control classification labels corresponding to the sample quality control images. In this embodiment, a large number of sample quality control images corresponding to the node devices and their corresponding quality control classification labels can be obtained as sample data. The quality control classification label is used to represent the classification result corresponding to the sample quality control image, and the classification result includes: normal result, abnormal result, and uncertain result.

[0075] In some embodiments of this application, during the sample data preparation process, an initial sample quality control image corresponding to the node device can be obtained; the initial sample quality control image is then denoised and resized to obtain a sample quality control image. This removes useless information from the sample quality control image and standardizes the image size, thereby improving the model training effect.

[0076] During model training, sample data is input into the initial model to train it, resulting in a quality control model. Specifically, sample data is input into the initial model, whose parameters can be preset initial values. Then, the quality control prediction results corresponding to the sample quality control images output by the initial model are obtained, and the difference information between the quality control prediction result corresponding to each sample quality control image and the quality control classification label corresponding to each sample quality control image is determined. Based on the difference information and the preset training algorithm, the adjustment values ​​of the initial model parameters are determined, and the initial model parameters are numerically adjusted to complete one training iteration. Then, other sample data are acquired, and the above process is repeated until the initial model meets the iteration cutoff condition. This initial model is then used as the quality control model. The cutoff condition can be that the loss function value of the initial model reaches the target function value or the number of iterations reaches the target number. Thus, through training with a large number of samples, the final quality control model is obtained.

[0077] The following explains the specific construction process of the initial model: The topology of the deep neural network model can be constructed using a neural network with input layers, hidden layers, and output layers. The number of nodes in the input layer and the number of nodes in the output layer correspond to the number of quality control images. The loss function in the initial model can include either the cross-entropy loss function or the mean squared error loss function.

[0078] It should be noted that after determining the quality control parameters using the quality control model, if the classification result includes uncertain results, the classification result can be corrected based on step 204. The corrected classification result updates the quality control prediction result. Alternatively, the classification result can be left uncorrected.

[0079] Step 204: If the classification result includes uncertain results, the uncertain results are corrected based on the manual judgment result to obtain the corrected classification result, and the corrected classification result is used to update the quality control prediction result.

[0080] The corrected classification results are either normal or abnormal.

[0081] Step 205: Based on the quality control image and the quality control prediction result corresponding to each of the multiple node devices, generate a quality control report corresponding to the multiple node devices.

[0082] The quality control report is used to indicate abnormal information corresponding to node devices that do not meet the data collection requirements among multiple node devices. The quality control report can be the quality control report for relevant node devices for a certain time period, a certain firing line, or a certain work area, thereby providing statistical report information for field production.

[0083] In this embodiment of the application, the abnormal information may include at least one of the following: the device identifier of the node device that does not meet the acquisition requirements, the abnormal quality control parameter corresponding to the abnormal node device, the quality control image corresponding to the abnormal quality control parameter, the number of abnormal node devices, the number of node devices corresponding to each abnormal quality control parameter, and the time corresponding to the abnormal quality control parameter.

[0084] The method for determining the quality of seismic data provided in this application generates quality control images of quality control parameters corresponding to multiple node devices. The quality control image corresponding to each node device is input into a preset quality control model to obtain the quality control prediction results of the quality control parameters corresponding to each node device. Thus, staff can determine whether the quality control parameters of the node devices are abnormal based on the quality control prediction results, eliminating the need for manual quality monitoring of the acquired seismic data, reducing the burden on staff, and improving the efficiency of quality control of seismic data.

[0085] Furthermore, the batch execution of quality control parameters for each node device uses the same execution entry point. After setting and executing the quality control parameters, the corresponding quality control images are output. Based on the quality control images corresponding to each node device, the quality control prediction results of the quality control parameters corresponding to each node device are determined through the preset quality control model. Each quality control image is then classified, thereby improving the accuracy of quality control.

[0086] Figure 3 This is a schematic diagram of a seismic data quality determination device provided in an embodiment of this application. The device includes: a first acquisition module 301, a first determination module 302, and a second determination module 303.

[0087] The first acquisition module 301 is used to acquire the quality control parameters corresponding to each node device. The quality control parameters are used to indicate whether the device status of the node device meets the requirements for acquiring seismic data.

[0088] The first determining module 302 is used to generate quality control images corresponding to the quality control parameters;

[0089] The second determining module 303 is used to input the quality control image corresponding to each node device into the preset quality control model, and determine the quality control prediction result of the quality control parameters corresponding to each node device. The quality control model is used to predict whether the quality control parameters of the node device are abnormal.

[0090] Optionally, the device also includes:

[0091] The generation module is used to generate quality control reports for multiple node devices based on the quality control images and state prediction results for each node device. The quality control reports are used to represent the abnormal information of the node devices that do not meet the acquisition requirements.

[0092] Optionally, the quality control parameters include: the root mean square of the amplitude of the seismic data acquired by the node device, the attitude angle of the node device, the polarity of the node device, the coupling of the node device, and at least one of the seismic auxiliary data. The polarity is used to indicate whether there is a situation where the signals received by the detectors of different components in the node device are reversed at the initial arrival. The coupling is used to indicate whether the node device is suspended, whether node displacement or dragging occurs during the acquisition process.

[0093] Optionally, the quality control prediction results include: the classification results corresponding to each quality control image, and the classification results include at least one of the following: normal results, abnormal results, and uncertain results.

[0094] Optionally, the device also includes:

[0095] The correction module is used to correct uncertain results based on manual judgment if the classification results include uncertain results, so as to obtain corrected classification results, which are either normal results or abnormal results.

[0096] Optionally, the device also includes:

[0097] The training module is used to input sample data into the initial model, train the initial model to obtain the quality control model, and the sample data includes the sample quality control images corresponding to the node devices and the quality control classification labels corresponding to the sample quality control images.

[0098] Optionally, the device also includes:

[0099] The second acquisition module is used to acquire the initial sample quality control image corresponding to the node device;

[0100] The adjustment module is used to denoise and resize the initial sample quality control image to obtain the sample quality control image.

[0101] The method for determining the quality of seismic data provided in this application generates quality control images of quality control parameters corresponding to multiple node devices. The quality control image corresponding to each node device is input into a preset quality control model to obtain the quality control prediction results of the quality control parameters corresponding to each node device. Thus, staff can determine whether the quality control parameters of the node devices are abnormal based on the quality control prediction results, eliminating the need for manual quality monitoring of the acquired seismic data, reducing the burden on staff, and improving the efficiency of quality control of seismic data.

[0102] It should be noted that the seismic data quality determination device provided in the above embodiments is only illustrated by the division of the above functional modules when acquiring seismic data. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the seismic data quality determination device and the seismic data quality determination 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.

[0103] This application also provides a computer device, which includes one or more processors and one or more memories. The one or more memories store at least one instruction, which is loaded and executed by the one or more processors to perform the operation of the method for determining the quality of seismic data.

[0104] This application also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to perform the operation of the method for determining seismic data quality.

[0105] 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.

[0106] The above are merely optional embodiments of this application and are 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 determining the quality of seismic data, characterized in that, The method includes: Obtain the quality control parameters corresponding to each node device. The quality control parameters are used to indicate whether the device status of the node device meets the requirements for acquiring seismic data. Generate the quality control image corresponding to the quality control parameters; The quality control image corresponding to each node device is input into a preset quality control model to obtain the quality control prediction result of the quality control parameter corresponding to each node device. The quality control model is used to predict whether the quality control parameter of the node device is abnormal.

2. The method according to claim 1, characterized in that, The method further includes: Based on the quality control image and the quality control prediction result for each of the multiple node devices, a quality control report is generated for each of the multiple node devices. The quality control report is used to indicate the abnormal information of the node devices that do not meet the collection requirements.

3. The method according to claim 1, characterized in that, The quality control parameters include at least one of the following: root mean square of the amplitude of the seismic data acquired by the node device, attitude angle of the node device, polarity of the node device, coupling of the node device, and seismic auxiliary data. The polarity is used to indicate whether there is a case of reverse initial arrival signal when the signals received by the detectors of different components in the node device are reversed. The coupling is used to indicate whether the node device is suspended, whether node displacement or dragging occurs during the acquisition process.

4. The method according to claim 1, characterized in that, The quality control prediction results include: the classification results corresponding to each quality control image, and the classification results include at least one of the following: normal results, abnormal results, and uncertain results.

5. The method according to claim 4, characterized in that, The method further includes: If the classification result includes the uncertain result, the uncertain result is corrected based on the manual judgment result to obtain the corrected classification result, which is either the normal result or the abnormal result.

6. The method according to claim 1, characterized in that, The method further includes: The sample data is input into the initial model, and the initial model is trained to obtain the quality control model. The sample data includes the sample quality control image corresponding to the node device and the quality control classification label corresponding to the sample quality control image.

7. The method according to claim 6, characterized in that, Before inputting the sample data into the initial model, the method further includes: Obtain the initial sample quality control image corresponding to the node device; The initial sample quality control image is denoised and resized to obtain the sample quality control image.

8. A device for determining the quality of seismic data, characterized in that, The device includes: The first acquisition module is used to acquire the quality control parameters corresponding to each node device. The quality control parameters are used to indicate whether the device status of the node device meets the requirements for acquiring seismic data. The first determining module is used to generate the quality control image corresponding to the quality control parameters; The second determining module is used to input the quality control image corresponding to each node device into a preset quality control model to obtain the quality control prediction result of the quality control parameter corresponding to each node device. The quality control model is used to predict whether the quality control parameter of the node device is abnormal.

9. A computer device, characterized in that, The computer device includes one or more processors and one or more memories, wherein at least one instruction is stored in the one or more memories, the instruction being loaded and executed by the one or more processors to perform the operation performed by the method for determining the quality of seismic data as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores at least one instruction, which is loaded and executed by a processor to perform the operation of the method for determining seismic data quality as described in any one of claims 1 to 7.

Images