A method and apparatus for evaluating ocean near-field wavelets

Abstract

The present application provides a kind of marine near-field subwave evaluation method, the method comprises: obtaining the near-field subwave data of marine actual work area, constructs monitoring data set, the monitoring data set includes training data set, test data set and verification data set;The monitoring data set is preprocessed, and effective seismic source data is obtained;Based on the effective seismic source data, the attribute relative error of standard subwave and monitoring subwave is calculated, and near-field subwave attribute sample error data set is constructed;Near-field subwave data evaluation network model is constructed;The training and test of the evaluation network model are carried out based on the near-field subwave attribute sample error data set.The method of the present application can more efficiently and accurately evaluate marine near-field subwave, and has important significance for seismic source state monitoring and improving construction efficiency.

Description

Technical Field

[0001] This invention relates to the field of marine seismic exploration, specifically to a method and apparatus for evaluating near-field wavelets in the ocean. Background Technology

[0002] In marine seismic exploration, air guns are the primary excitation source, and the monitoring results of the source state directly affect the quality of seismic data and the construction efficiency of the entire exploration project. Real-time monitoring of the near-field wavelet state received by hydrophones is an effective means of source state monitoring. Typically, quality control personnel monitor the near-field wavelet state by observing its waveform. However, with the continuous innovation and leaps in marine seismic exploration technology, expectations for construction efficiency and quality are also increasing. This manual qualitative observation and monitoring method of the near-field wavelet waveform is highly subjective and inefficient, and can no longer adequately meet the needs of on-site construction. Therefore, how to automatically evaluate the near-field wavelet with high precision and efficiency is the problem that this invention aims to solve. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a method for evaluating near-field wavelet waves in the ocean, the method comprising:

[0004] Near-field wavelet data from actual marine work areas are acquired, and a monitoring dataset is constructed, which includes a training dataset, a test dataset, and a validation dataset.

[0005] The monitoring dataset is preprocessed to obtain valid seismic source data;

[0006] Based on the effective source data, the relative error of the properties of the standard wavelet and the monitoring wavelet is calculated, and a near-field wavelet property sample error dataset is constructed.

[0007] Construct a network model for evaluating near-field wavelet data;

[0008] The evaluation network model is trained and tested based on the near-field wavelet attribute sample error dataset.

[0009] In one embodiment, obtaining valid seismic source information includes:

[0010] The absolute values ​​of the amplitudes of the wavelet sampling points with the same source number in each near-field wavelet file are summed.

[0011] Compare the accumulated results and set the source number corresponding to the maximum value as the valid source number of the current file;

[0012] Obtain valid source data including the valid source number.

[0013] In one embodiment, constructing the near-field wavelet property sample error dataset includes:

[0014] Based on the effective source data, the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​are calculated.

[0015] Calculate the relative error of the properties of the standard wavelet and the monitoring wavelet;

[0016] The training dataset, test dataset, and validation dataset of the near-field wavelet property sample error dataset are formed based on the training dataset, test dataset, and validation dataset of the monitoring dataset.

[0017] In one embodiment, constructing the near-field wavelet data evaluation network model includes:

[0018] A fully connected network model was constructed to divide the near-field wavelet into anomaly near-field wavelet and normal near-field wavelet.

[0019] In one embodiment, training and testing the evaluation network model includes:

[0020] The parameters of the network model are learned using the training and validation datasets to minimize the network loss.

[0021] Assuming the network is neither overfitting nor underfitting, the model with the minimum network loss is selected as the evaluation network model.

[0022] The near-field wavelet property difference data is input into the evaluation network model to obtain the evaluation results of the near-field wavelet.

[0023] This invention provides a near-field wavelet evaluation device for the ocean, the device comprising:

[0024] The monitoring dataset construction module is used to acquire near-field wavelet data from actual marine work areas and construct a monitoring dataset, which includes a training dataset, a test dataset, and a validation dataset.

[0025] The preprocessing module is used to preprocess the monitoring dataset to obtain valid seismic source data;

[0026] An error dataset construction module is used to calculate the relative errors of the properties of the standard wavelet and the monitoring wavelet based on the effective source data, and to construct a near-field wavelet property sample error dataset.

[0027] The network model building module is used to build network models for evaluating near-field wavelet data.

[0028] The training and testing module is used to train and test the evaluation network model based on the near-field wavelet attribute sample error dataset.

[0029] In one embodiment, the preprocessing module is further configured to:

[0030] The absolute values ​​of the amplitudes of the wavelet sampling points with the same source number in each near-field wavelet file are summed.

[0031] Compare the accumulated results and set the source number corresponding to the maximum value as the valid source number of the current file;

[0032] Obtain valid source data including the valid source number.

[0033] In one embodiment, the error dataset construction module is further configured to,

[0034] Based on the effective source data, the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​are calculated.

[0035] Calculate the relative error of the properties of the standard wavelet and the monitoring wavelet;

[0036] The training dataset, test dataset, and validation dataset of the near-field wavelet property sample error dataset are formed based on the training dataset, test dataset, and validation dataset of the monitoring dataset.

[0037] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the ocean near-field wavelet evaluation method as described above.

[0038] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the ocean near-field wavelet evaluation method as described above.

[0039] The above technical solution has the following beneficial effects:

[0040] First, near-field wavelet data from actual marine work areas are collected to construct a marine near-field wavelet monitoring dataset. The raw near-field wavelet data is preprocessed using bandpass filtering to remove environmental noise and low- and high-frequency noise components from the measuring equipment. A near-field wavelet attribute sample error dataset is constructed, extracting pulse amplitude, band energy, wavelet bubble period, wavelet dominant frequency, and cross-correlation attribute parameters for each near-field wavelet data channel from the monitoring gun, and calculating errors with a standard gun. Deep learning technology is introduced, using the calculated wavelet attribute error results as input to the model to extract potential patterns, thereby automatically evaluating the near-field wavelets of marine airguns. This invention enables more efficient and accurate evaluation of marine near-field wavelets, which is of great significance for monitoring seismic source conditions and improving construction efficiency.

[0041] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0042] Figure 1 This is a flowchart of the near-field wavelet evaluation method for the ocean according to Embodiment 1 of the present invention;

[0043] Figure 2 This is a normal ocean near-field wavelet waveform diagram according to Embodiment 1 of the present invention;

[0044] Figure 3 This is a waveform diagram of an abnormal ocean near-field wavelet from Embodiment 1 of the present invention;

[0045] Figure 4 This is a list of standard near-field wavelet attribute values ​​for source 1 in Embodiment 1 of the present invention;

[0046] Figure 5 This is a list of standard shot near-field wavelet attribute values ​​for source 2 in Embodiment 1 of the present invention;

[0047] Figure 6 This is a list of attribute values ​​for the near-field wavelet (normal single shot) of the monitoring shot of source 1 in Embodiment 1 of the present invention.

[0048] Figure 7 This is a list of attribute values ​​for the near-field wavelet (normal single shot) of the monitoring shot of source 2 in Embodiment 1 of the present invention;

[0049] Figure 8 This is a schematic diagram of the marine near-field wavelet evaluation device according to Embodiment 3 of the present invention;

[0050] Figure 9 This is a functional block diagram of a computer device according to Embodiment 5 of the present invention. Detailed Implementation

[0051] The present invention will be further described below with reference to the embodiments. However, the embodiments of the present invention are merely illustrative examples and should not be construed as limiting the present invention under any circumstances.

[0052] Example 1

[0053] Embodiments of the present invention provide a method for evaluating near-field wavelet in the ocean, such as... Figure 1 As shown, the method includes:

[0054] Step S1: Obtain near-field wavelet data from the actual marine work area and construct a monitoring dataset, which includes a training dataset, a test dataset, and a validation dataset.

[0055] Step S2: Preprocess the monitoring dataset to obtain valid seismic source data;

[0056] Step S3: Calculate the relative error of the properties of the standard wavelet and the monitoring wavelet based on the effective source data, and construct a near-field wavelet property sample error dataset;

[0057] Step S4: Construct a near-field wavelet data evaluation network model;

[0058] Step S5: Train and test the evaluation network model based on the near-field wavelet attribute sample error dataset.

[0059] In step S1, the ocean near-field wavelet monitoring dataset is constructed. The specific steps are as follows: acquire near-field wavelet data of a certain actual work area in the ocean. The acquired near-field wavelet data is usually in the standard segd or segy format, and each file contains near-field wavelet data of a single shot. The actual work area includes multiple sources, and a standard shot record is selected for each source. The collected near-field wavelet data (excluding standard shot) is divided into training dataset, test dataset and validation dataset in an 8:1:1 ratio.

[0060] In a preferred embodiment, the specific steps are as follows:

[0061] Step S11: Obtain near-field wavelet data from a specific marine work area, including normal and anomalous wavelet data, such as... Figure 2 This is a normal ocean near-field wavelet waveform diagram of the present invention. Figure 3 This is a waveform diagram of anomaly-induced near-field wavelet data from an embodiment of this invention. The acquired near-field wavelet data is in standard Segy format, with each file containing near-field wavelet data from a single shot, totaling 24 wavelets.

[0062] Step S12: The construction work in the actual work area includes two sources, and a standard shot record is selected for each source.

[0063] Step S13: The collected near-field wavelet data (excluding standard shot) is divided into training dataset, test dataset and validation dataset in a ratio of 8:1:1.

[0064] Step S2 involves preprocessing the monitoring dataset to obtain valid source data. Specifically, this includes: accumulating the absolute values ​​of the amplitudes of wavelet sampling points with the same source number in each near-field wavelet file; comparing the accumulation results and setting the source number corresponding to the maximum value as the valid source number of the current file; and obtaining valid source data including the valid source number.

[0065] In a preferred embodiment, the specific steps are as follows:

[0066] Step S21: First, parse the near-field wavelet data file and extract the trace head information of each near-field wavelet, including the source number, line number, and point number, etc.

[0067] Step S22: Since low-frequency and high-frequency noise components may appear during marine seismic exploration and acquisition due to environmental noise and inherent noise of measuring equipment, the effective channel data of the original near-field wavelet is bandpass filtered.

[0068] Step S23: Accumulate the absolute values ​​of the amplitudes of the wavelet sampling points with the same source number in each near-field wavelet file, compare the accumulation results, and the source number corresponding to the maximum value is the valid source number of the current file. Save the source number, corresponding start trace number and end trace number information of the valid source.

[0069] Step S3, which involves constructing a near-field wavelet attribute sample error dataset, includes: calculating the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​based on the effective source data; calculating the relative errors of the attributes of the standard wavelet and the monitored wavelet; and forming the training dataset, test dataset, and verification dataset of the near-field wavelet attribute sample error dataset based on the training dataset, test dataset, and verification dataset of the monitored dataset.

[0070] In a preferred embodiment, the detailed steps include:

[0071] Step S31: First, calculate the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​for the preprocessed near-field wavelet data.

[0072] Step S32: Calculate the relative error of the properties of the standard wavelet and the monitoring wavelet. The calculation formula is as follows:

[0073]

[0074] Where E represents the attribute error ratio between the monitoring wavelet and the standard wavelet, and A represents the attribute value of the monitoring wavelet. s The attribute value representing the standard wavelet.

[0075] Step S33: Based on the training dataset, test dataset, and validation dataset formed in step S13, a training dataset, test dataset, and validation dataset for the near-field wavelet property sample error dataset are formed.

[0076] Step S4 includes building a fully connected network model to divide the near-field wavelet into abnormal near-field wavelet and normal near-field wavelet.

[0077] In a preferred embodiment, the detailed process of constructing a near-field wavelet data evaluation network model includes:

[0078] Step S41 sets the size of each sample data to 1×5, and the final task is to classify the near-field wavelet into abnormal and normal near-field wavelets, which is a binary classification problem. Therefore, a 3-layer fully connected convolutional neural network is built as the basic network model for evaluating the near-field wavelet.

[0079] Step S42: Design the detailed structure of the model. The first layer is the input layer with 5 input nodes and 16 hidden nodes. The second layer also has 16 hidden nodes. The third layer is the output layer for binary classification with 1 output node. The model is trained using the sigmoid activation function, the Adam optimizer, and the binary cross-entropy loss function.

[0080] The beneficial effects of this embodiment are as follows: It acquires near-field wavelet data from actual marine work areas; by preprocessing the raw near-field wavelet data, bandpass filtering is used to remove environmental noise and low-frequency and high-frequency noise components from the measuring equipment, improving the accuracy of subsequent wavelet attribute extraction; pulse amplitude, band energy, wavelet bubble period, wavelet dominant frequency, and cross-correlation attribute parameters are extracted for each near-field wavelet data channel; the relative error between the attributes of a standard single shot and a monitored single shot is calculated, constructing a dataset of attribute differences between the monitored wavelet and the standard wavelet; a convolutional neural network is built, using the extracted wavelet attribute errors as network input to complete the training and testing of the network model, resulting in a near-field wavelet evaluation model. Through the solution of this invention, near-field wavelet evaluation quality control can be completed more efficiently and accurately, which is of great significance for monitoring the source state and improving construction efficiency.

[0081] Example 2

[0082] This embodiment provides a technical solution for training and testing a network model using a near-field ocean wavelet attribute sample error dataset. The detailed steps are as follows:

[0083] Step S51: Network model training. The training and validation sets from step S3, combined with the network loss function, are used to learn the network model's parameters. Based on the training results, hyperparameters such as the learning rate and the number of training iterations are fine-tuned to minimize the network loss. The model with the minimum network loss is selected as the final ocean near-field wavelet evaluation model, provided that the network does not exhibit overfitting or underfitting.

[0084] Step S52: Write network model test code, input the preprocessed near-field wavelet attribute difference data into the trained ocean near-field wavelet intelligent evaluation model, and obtain the near-field wavelet intelligent evaluation results.

[0085] Step S53: Compare and calculate the network model test results with the qualitative evaluation results (labels) from manual observation, using classification accuracy as the evaluation index. The calculation formula is as follows:

[0086]

[0087] In the formula, TP represents ocean near-field wavelet data that is correctly classified as normal, TN represents ocean near-field wavelet data that is correctly classified as abnormal, FP represents ocean near-field wavelet data that is misclassified as normal, and FN represents ocean near-field wavelet data that is misclassified as abnormal.

[0088] This embodiment provides an efficient method for automatically evaluating near-field wavelets in the ocean, used to monitor the quality of near-field wavelet data, determine whether the state of the air gun source is abnormal, effectively help construction workers understand the working status of the data acquisition equipment in detail, and improve the efficiency of data acquisition and construction.

[0089] Example 3

[0090] This embodiment provides a near-field wavelet evaluation device for the ocean. For example... Figure 8 As shown, the device includes:

[0091] The monitoring dataset construction module 201 is used to acquire near-field wavelet data from the actual marine work area and construct a monitoring dataset, which includes a training dataset, a test dataset, and a validation dataset.

[0092] Preprocessing module 202 is used to preprocess the monitoring dataset to obtain valid seismic source data;

[0093] Error dataset construction module 203 is used to calculate the relative error of the properties of the standard wavelet and the monitoring wavelet based on the effective source data, and to construct a near-field wavelet property sample error dataset;

[0094] Network model building module 204 is used to build a network model for evaluating near-field wavelet data.

[0095] The training and testing module 205 is used to train and test the evaluation network model based on the near-field wavelet attribute sample error dataset.

[0096] The preprocessing module 202 is further configured to: accumulate the absolute values ​​of the amplitudes of the wavelet sampling points with the same source number in each near-field wavelet file; compare the accumulation results and set the source number corresponding to the maximum value as the valid source number of the current file; and obtain valid source data including the valid source number.

[0097] The error dataset construction module 203 is further configured to: calculate the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​based on the effective source data; calculate the relative error of the attributes of the standard wavelet and the monitoring wavelet; and form the training dataset, test dataset, and verification dataset of the near-field wavelet attribute sample error dataset based on the training dataset, test dataset, and verification dataset of the monitoring dataset.

[0098] The device provided in this embodiment incorporates deep learning technology, using the calculated wavelet attribute error results as input to the model to extract potential patterns, thereby automatically evaluating near-field wavelets of marine airguns. This embodiment's approach enables more efficient and accurate evaluation of near-field wavelets in the ocean, which is of great significance for monitoring seismic source conditions and improving construction efficiency.

[0099] Example 4

[0100] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements any of the above-described methods for evaluating near-field ocean wavelets.

[0101] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. Of course, there are other types of readable storage media, such as quantum memories, graphene memories, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0102] Example 5

[0103] This embodiment provides a computer device, for reference... Figure 9 It shows a schematic diagram of the structure of a computer device 800 suitable for implementing embodiments of the present invention.

[0104] Figure 9The computer device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the described near-field ocean wavelet evaluation method.

[0105] like Figure 9 As shown, the computer device 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage section 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the computer system 800. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0106] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0107] In particular, according to the embodiments disclosed in this invention, the processes described in the above main step diagrams can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the main step diagrams. In the above embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit 801, it performs the functions defined in the system of this invention.

[0108] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. The units described in the embodiments of the present invention may be implemented in software or hardware.

[0110] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0111] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, electronic devices, and readable storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0112] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method of evaluating a marine near-field wavelet, characterized by, The method includes: Near-field wavelet data from actual marine work areas are acquired, and a monitoring dataset is constructed, which includes a training dataset, a test dataset, and a validation dataset. The monitoring dataset is preprocessed to obtain valid seismic source data; Based on the effective source data, the relative error of the properties of the standard wavelet and the monitoring wavelet is calculated, and a near-field wavelet property sample error dataset is constructed. Construct a network model for evaluating near-field wavelet data; The evaluation network model is trained and tested based on the near-field wavelet attribute sample error dataset.

2. The method of claim 1, wherein, The acquisition of valid seismic source information includes: The absolute values ​​of the amplitudes of the wavelet sampling points with the same source number in each near-field wavelet file are summed. Compare the accumulated results and set the source number corresponding to the maximum value as the valid source number of the current file; Obtain valid source data including the valid source number.

3. The method of claim 1, wherein, The constructed near-field wavelet property sample error dataset includes: Based on the effective source data, the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​are calculated. Calculate the relative error of the properties of the standard wavelet and the monitoring wavelet; The training dataset, test dataset, and validation dataset of the near-field wavelet property sample error dataset are formed based on the training dataset, test dataset, and validation dataset of the monitoring dataset.

4. The method according to claim 1, characterized in that, The construction of the near-field wavelet data evaluation network model includes: A fully connected network model was constructed to divide the near-field wavelet into anomaly near-field wavelet and normal near-field wavelet.

5. The method according to claim 3, characterized in that, Training and testing the evaluation network model includes: The parameters of the network model are learned using the training and validation datasets to minimize the network loss. Assuming the network is neither overfitting nor underfitting, the model with the minimum network loss is selected as the evaluation network model. The near-field wavelet property difference data is input into the evaluation network model to obtain the evaluation results of the near-field wavelet.

6. A near-field wavelet evaluation device for the ocean, characterized in that, The device includes: The monitoring dataset construction module is used to acquire near-field wavelet data from actual marine work areas and construct a monitoring dataset, which includes a training dataset, a test dataset, and a validation dataset. The preprocessing module is used to preprocess the monitoring dataset to obtain valid seismic source data; An error dataset construction module is used to calculate the relative errors of the properties of the standard wavelet and the monitoring wavelet based on the effective source data, and to construct a near-field wavelet property sample error dataset. The network model building module is used to build network models for evaluating near-field wavelet data. The training and testing module is used to train and test the evaluation network model based on the near-field wavelet attribute sample error dataset.

7. The apparatus according to claim 6, characterized in that, The preprocessing module is also used for: The absolute values ​​of the amplitudes of the wavelet sampling points with the same source number in each near-field wavelet file are summed. Compare the accumulated results and set the source number corresponding to the maximum value as the valid source number of the current file; Obtain valid source data including the valid source number.

8. The apparatus according to claim 6, characterized in that, The error dataset construction module is also used for, Based on the effective source data, the wavelet bubble period, pulse energy, band energy, dominant frequency, and cross-correlation coefficient attribute values ​​are calculated. Calculate the relative error of the properties of the standard wavelet and the monitoring wavelet; The training dataset, test dataset, and validation dataset of the near-field wavelet property sample error dataset are formed based on the training dataset, test dataset, and validation dataset of the monitoring dataset.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the ocean near-field wavelet evaluation method as described in any one of claims 1-5.

10. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and when the processor executes the computer program, it implements the ocean near-field wavelet evaluation method as described in any one of claims 1-5.

Images