Seismic data noise intelligent suppression method and system

Abstract

The invention relates to the technical field of geoscience exploration seismic data processing, in particular to a seismic data noise intelligent suppression method and system, and the method comprises the following steps: constructing a first seismic data noise suppression data set according to a seismic effective signal and random noise; constructing a primary noise suppression model based on the first seismic data noise suppression data set, and further constructing a second seismic data noise suppression data set; according to the second seismic data noise suppression data set, using a complementary set empirical mode decomposition method and a noise reduction automatic encoder to construct a secondary noise suppression model; and carrying out noise reduction on the seismic data by using the primary noise suppression model and the secondary noise suppression model, and carrying out data reconstruction to obtain the seismic data after noise suppression. According to the method, multistage noise reduction is carried out on the seismic data by constructing the first-stage noise suppression model and the second-stage noise suppression model, the continuity and high-frequency characteristics of the event of the seismic data are kept, and the noise suppression effect on the seismic data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of seismic data processing for geological exploration, and in particular to a method and system for intelligently suppressing noise in seismic data. Background Art

[0002] As a key means of oil and gas resource exploration, seismic exploration is based on accurately extracting valuable geological information from seismic data. However, in actual operation, seismic data will inevitably be interfered by various noise sources such as surface environment, instrument errors and underground medium heterogeneity. These noises not only seriously reduce the signal-to-noise ratio of seismic data, but also may cause the continuity of the phase axis to be damaged, thus bringing considerable challenges to the subsequent geological interpretation and oil and gas resource assessment.

[0003] Traditional seismic data noise suppression methods, such as filtering and denoising algorithms, have achieved certain results in reducing noise, but their effects are often limited when faced with complex and changing noise environments. Especially when the signal and noise spectra overlap, it is difficult for traditional methods to effectively remove noise while maintaining signal integrity, which often results in the high-frequency characteristics of the signal being accidentally damaged, while low-frequency noise may stubbornly remain, which adds a lot of difficulties to the analysis and interpretation of seismic data.

[0004] In recent years, with the rapid development of machine learning technology, the field of seismic data noise suppression has ushered in a new dawn. Among them, the application of advanced technologies such as generative adversarial networks (GAN) and deep convolutional neural networks (DnCNN) is particularly eye-catching. However, while pursuing higher noise suppression effects, how to ensure that the continuity of the event axis of the seismic data is not affected, and how to prevent the loss of high-frequency features of the seismic data are still urgent problems to be solved in the current field of seismic data noise suppression. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a method and system for intelligently suppressing noise in seismic data.

[0006] In order to achieve the above-mentioned purpose, in the first aspect, the present invention provides a method for intelligently suppressing noise in seismic data, the method comprising the following steps: constructing a first seismic data noise suppression data set for model training based on seismic effective signals and random noise; constructing a first-level noise suppression model based on the first seismic data noise suppression data set, and then constructing a second seismic data noise suppression data set for model training; constructing a second-level noise suppression model based on the second seismic data noise suppression data set using a complementary set empirical mode decomposition method and a noise reduction autoencoder; using the first-level noise suppression model and the second-level noise suppression model to reduce noise on seismic data, and obtaining noise-suppressed seismic data through data reconstruction. The present invention performs multi-level noise reduction on seismic data by constructing a first-level noise suppression model and a second-level noise suppression model, thereby maintaining the continuity and high-frequency characteristics of the event axis of the seismic data and improving the noise suppression effect on the seismic data.

[0007] Optionally, constructing a first seismic data noise suppression data set for model training based on seismic effective signals and random noise comprises the following steps: Determine the effective seismic signal, and superimpose different random noises on the effective seismic signal to obtain multiple different channels of earthquake measured simulation signals; The measured seismic simulation signal is cut into a plurality of segment signals, and the first seismic data noise suppression data set is constructed using the seismic effective signal and the segment signals.

[0008] Optionally, constructing a primary noise suppression model based on the first seismic data noise suppression data set, and then constructing a second seismic data noise suppression data set for model training comprises the following steps: Constructing a primary noise suppression model, and using the first seismic data noise suppression data set to complete the training and verification of the primary noise suppression model, thereby obtaining the first-level noise suppression model; Using the first-level noise suppression model, performing first-level noise reduction on each of the segment signals in the first seismic data noise suppression data set to obtain corresponding first-level noise reduction data; The second seismic data noise suppression data set for model training is constructed using the seismic effective signal and the first-level noise reduction data.

[0009] Optionally, the constructing of the primary noise suppression model and using the first seismic data noise suppression data set to complete the training and verification of the primary noise suppression model, thereby obtaining the primary noise suppression model comprises the following steps: Construct the feature extraction and enhancement module, the feature multi-scale integration module and the feature fusion output module in sequence; The output of the feature extraction and enhancement module is downsampled as the input of the feature multi-scale integration module, the output of the feature extraction and enhancement module is used as the first input of the feature fusion output module, and the output of the feature multi-scale integration module is upsampled as the second input of the feature fusion output module to obtain the primary noise suppression model; The first seismic data noise suppression data set is divided into a training set and a verification set, thereby completing the training and verification of the primary noise suppression model, and finally obtaining the first-level noise suppression model.

[0010] Optionally, the feature extraction and enhancement module satisfies the following relationship: , Wherein, F is the input of the feature extraction and enhancement module, is the output of the feature extraction and enhancement module, Indicates that the first type of convolutional layer is used for convolution operation. , , and These are all reference symbols set up for the convenience of writing. Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling.

[0011] Optionally, the feature multi-scale integration module satisfies the following relationship: , in, is the output of the feature multi-scale integration module, The i-th reference symbol is set for the convenience of writing. , Indicates that the second type of convolutional layer is used for convolution operation. Indicates that the third type of convolutional layer is used for convolution operation. Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling. Indicates downsampling. Indicates upsampling. is the output of the feature extraction and enhancement module, Indicates that and Perform channel splicing.

[0012] Optionally, the feature fusion output module satisfies the following relationship: , in, is the output of the feature fusion output module, Indicates the use of hyperbolic tangent activation function, Indicates that the first type of convolutional layer is used for convolution operation. The jth reference symbol is set for the convenience of writing. , Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling. Indicates upsampling. is the output of the feature extraction and enhancement module, is the output of the feature multi-scale integration module, Indicates that and Perform channel splicing.

[0013] Optionally, according to the second seismic data noise suppression data set, constructing a secondary noise suppression model using a complementary set empirical mode decomposition method and a noise reduction autoencoder comprises the following steps: Using the multiple IMF components of the primary denoised data obtained by the complementary set empirical mode decomposition method as input of the denoising autoencoder to obtain an original secondary noise suppression model; The second seismic data noise suppression data set is divided into a training set and a verification set, thereby completing the training and verification of the original secondary noise suppression model to obtain the secondary noise suppression model.

[0014] Optionally, the step of using the primary noise suppression model and the secondary noise suppression model to reduce noise on seismic data and obtaining noise-suppressed seismic data through data reconstruction comprises the following steps: Using the first-level noise suppression model to perform first-level noise reduction on the seismic data to obtain first-level noise reduction data; Performing secondary noise reduction on seismic data using the secondary noise suppression model to obtain a set of noise-reduced IMF components; The obtained denoised IMF components are used to perform data reconstruction to obtain noise-suppressed seismic data.

[0015] In a second aspect, the present invention provides a system for intelligently suppressing noise from seismic data, the system comprising: a data acquisition device, a data output device, a processor and a storage device, the storage device comprising a computer-readable storage medium, the computer-readable storage medium storing a computer program, the computer program comprising program instructions, and when the program instructions are executed by the processor, the processor implements a method for intelligently suppressing noise from seismic data of the present invention.

[0016] The present invention has at least the following beneficial effects: 1. In the feature extraction and enhancement module, feature multi-scale integration module and feature fusion output module constructed by this method, the integrity of the input information is maintained by directly transferring the shallow feature information to a deeper level through identity mapping, and the residual between the input and output is effectively minimized, thereby ensuring the stability and continuity of the information during deep transmission, which helps to accurately extract the multi-scale features of seismic data and thus improve the noise suppression effect on seismic data.

[0017] 2. This method first performs preliminary feature extraction and feature enhancement on seismic data through the feature extraction and enhancement module, so that more abundant feature information can be extracted later; secondly, this method uses the feature multi-scale integration module to further extract the multi-scale features of seismic data, realize the deep extraction of feature information, enrich the feature level, and preliminarily integrate the extracted feature information to obtain feature information of the next level compared with the feature map extracted by the feature extraction and enhancement module; finally, this method uses the feature fusion output module to finally fuse the feature information extracted by the first two modules to obtain the first-level denoised data, thereby retaining the effective signal in the earthquake to the greatest extent, thereby improving the signal-to-noise ratio and event continuity of the seismic data.

[0018] 3. After obtaining the first-level denoised data, this method further constructs a second-level noise suppression model to perform second-level denoising on the first-level denoised data, so as to solve the problem of stubborn residual low-frequency noise and loss of high-frequency features when the seismic signal overlaps with the noise spectrum in the first-level denoised data, thereby further improving the noise suppression effect on seismic data.

[0019] 4. The present invention provides a system compatible with the present method, which can stably operate the present method, improve the efficiency of noise suppression on seismic data, and improve the practicability of the present method. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a flow chart of a method for intelligently suppressing noise in seismic data according to an embodiment of the present invention; Figure 2 A simplified structural diagram of a primary noise suppression model according to an embodiment of the present invention; Figure 3 A simplified structural diagram of a feature extraction and enhancement module according to an embodiment of the present invention; Figure 4 A simplified structural diagram of a feature multi-scale integration module according to an embodiment of the present invention; Figure 5 A simplified structural diagram of a feature fusion output module according to an embodiment of the present invention; Figure 6 The figure is a schematic diagram of the framework of a seismic data noise intelligent suppression system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0023] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0024] It should be noted in advance that, in an optional embodiment, except for independent explanations, the same symbols or letters appearing in all formulas have the same meanings and values.

[0025] In an alternative embodiment, see Figure 1 The present invention provides a method for intelligently suppressing noise in seismic data, the method comprising the following steps: S1. Constructing a first seismic data noise suppression dataset for model training based on seismic effective signals and random noise.

[0026] The seismic data referred to in this embodiment refers to the seismic measured signals collected by sensors. Step S1 specifically includes the following steps: S11, determining the effective seismic signal, and superimposing different random noises on the effective seismic signal to obtain a plurality of different channels of actual seismic simulation signals.

[0027] Specifically, in this embodiment, the Ricker wavelet is used as a clean signal without noise, that is, an effective seismic signal. Then, different random noises are superimposed on the effective seismic signal to obtain multiple different channels of seismic measured simulation signals, that is, seismic measured simulation signals collected by sensors at different positions.

[0028] S12. Cut the measured earthquake simulation signal into a plurality of segment signals, and use the earthquake effective signal and the segment signals to construct the first seismic data noise suppression data set.

[0029] Specifically, in this embodiment, after obtaining the measured earthquake simulation signal, each measured earthquake simulation signal can be cut into multiple segment signals according to the set window size, and a segment signal and the earthquake effective signal corresponding to the segment signal are used as a set of seismic signal data, and then multiple sets of seismic signal data are used to construct the first seismic data noise suppression data set.

[0030] S2. Constructing a primary noise suppression model based on the first seismic data noise suppression data set, and then constructing a second seismic data noise suppression data set for model training.

[0031] Wherein, step S2 specifically includes the following steps: S21. Construct a primary noise suppression model, and use the first seismic data noise suppression data set to complete the training and verification of the primary noise suppression model, thereby obtaining the first-level noise suppression model.

[0032] Among them, see Figure 2 , Figure 3 , Figure 4 and Figure 5 , step S21 specifically includes the following steps: S211, construct a feature extraction and enhancement module, a feature multi-scale integration module and a feature fusion output module in sequence.

[0033] Specifically, in this embodiment, a feature extraction and enhancement module is constructed. In the feature extraction and enhancement module, a first-class convolutional layer and a ReLU activation function are first used to extract the local features of the input seismic data in a relatively detailed manner, and then a first feature enhancement network FES1 similar to the residual structure is used to enhance the extracted local features to obtain enhanced local features, thereby laying a solid foundation for primary noise suppression. In the first feature enhancement structure FES1, jump connections are used many times, which enables the network to map part of the information to a deeper level when performing deep feature learning, reduce information loss, and alleviate the problem of gradient vanishing or explosion in the deep network training process, thereby ensuring the stability and coherence of information in the deep transmission process, which is conducive to improving the noise suppression effect on seismic data. The function of the feature extraction and enhancement module can be expressed using the following relationship: , Among them, F is the input of the feature extraction and enhancement module, is the output of the feature extraction and enhancement module, Indicates that the first type of convolutional layer is used for convolution operation. , , and These are all reference symbols set up for the convenience of writing. Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling. The first type of convolution layer has 64 convolution kernels, the convolution kernel size is 2×2, the stride is 1, and the padding parameter of the convolution layer is set to 'same', so that the feature map output by the convolution layer has the same size as the input feature map.

[0034] Furthermore, a feature multi-scale integration module is constructed. The output of the feature extraction and enhancement module is downsampled and input into the second feature enhancement structure FES2, and then the output of the second feature enhancement structure FES2 is downsampled and input into the third feature enhancement structure FES3, thereby extracting the multi-scale features of the seismic data, realizing the deep extraction of feature information, and enriching the feature hierarchy. Next, the output of the third feature enhancement structure FES3 is upsampled and channel-joined with the output of the second feature enhancement structure FES2, and a second-class convolutional layer and the second feature enhancement structure FES2 are used to preliminarily integrate the extracted feature information to obtain feature information of a level lower than the feature map extracted by the feature extraction and enhancement module. Among them, the second feature enhancement structure FES2 uses the second-class convolutional layer, the third feature enhancement structure FES3 uses the third-class convolutional layer, and the second feature enhancement structure FES2 and the third feature enhancement structure FES3 have the same network structure as the first feature enhancement structure FES1. The second type of convolution layer has 128 convolution kernels, the convolution kernel size is 2×2, and the step size is 1; the third type of convolution layer has 256 convolution kernels, the convolution kernel size is 2×2, and the step size is 1. The function of the feature multi-scale integration module can be expressed by the following relationship: , in, is the output of the feature multi-scale integration module, The i-th reference symbol is set for the convenience of writing. , Indicates that the second type of convolutional layer is used for convolution operation. Indicates that the third type of convolutional layer is used for convolution operation. Indicates downsampling. Indicates upsampling. Indicates channel splicing.

[0035] Furthermore, a feature fusion output module is constructed. First, the output of the feature multi-scale integration module is upsampled and then channel-joined with the output of the feature extraction and enhancement module; then, a first-class convolutional layer and ReLU activation function are used to reduce the number of channels, and the first feature enhancement network FES1 is further used to refine the feature processing to ensure the effective integration of multi-scale feature information; finally, the first-class convolutional layer and ReLU activation function are used to fuse the feature information, and the first-class convolutional layer and hyperbolic tangent activation function are used to convert the finely processed feature map into first-level noise reduction data, thereby retaining the effective signal in the earthquake to the greatest extent, thereby improving the signal-to-noise ratio and event continuity of the seismic data. The function of the feature fusion output module can be expressed using the following relationship: , in, is the output of the feature fusion output module, Indicates the use of hyperbolic tangent activation function, Indicates that the first type of convolutional layer is used for convolution operation. The jth reference symbol is set for the convenience of writing. .

[0036] S212. Down-sample the output of the feature extraction and enhancement module and use it as the input of the feature multi-scale integration module; use the output of the feature extraction and enhancement module as the first input of the feature fusion output module; and up-sample the output of the feature multi-scale integration module and use it as the second input of the feature fusion output module to obtain the primary noise suppression model.

[0037] S213, dividing the first seismic data noise suppression data set into a training set and a verification set, thereby completing the training and verification of the primary noise suppression model, and finally obtaining the first-level noise suppression model.

[0038] Specifically, in this embodiment, the first seismic data noise suppression data set is divided into a training set and a verification set in a ratio of 7:3, thereby completing the training and verification of the primary noise suppression model to obtain a primary noise suppression model.

[0039] S22. Performing first-level noise reduction on each of the segment signals in the first seismic data noise suppression data set using the first-level noise reduction model to obtain corresponding first-level noise reduction data.

[0040] Specifically, in this embodiment, a first-level noise suppression model is used to perform first-level noise reduction on each segment signal to obtain corresponding first-level noise reduction data.

[0041] S23. Use the seismic effective signal and the first-level noise reduction data to construct the second seismic data noise suppression data set for model training.

[0042] Specifically, in this embodiment, the second seismic data noise suppression dataset is constructed in a similar manner to the first seismic data noise suppression dataset. In fact, the second seismic data noise suppression dataset can be obtained by replacing the segment signal in the first seismic data noise suppression dataset with the corresponding first-level noise reduction data.

[0043] S3. According to the second seismic data noise suppression data set, a secondary noise suppression model is constructed using a complementary set empirical mode decomposition method and a noise reduction autoencoder.

[0044] Wherein, step S3 specifically includes the following steps: S31. Using the multiple IMF components of the primary denoised data obtained by the complementary set empirical mode decomposition method as the input of the denoising autoencoder to obtain an original secondary noise suppression model.

[0045] Specifically, in this embodiment, complementary set empirical mode decomposition is a variant of set empirical mode decomposition, which has better stability than set empirical mode decomposition and can process input data adaptively; the denoising autoencoder adds noise to the input data on the basis of the autoencoder to train the entire network, and the ultimate goal is to reconstruct the original data without noise, eliminate the influence of the random destruction process, and retain the high-frequency effective signal after modal decomposition. Therefore, this embodiment combines complementary set empirical mode decomposition and denoising autoencoder to construct a secondary noise suppression model.

[0046] S32, dividing the second seismic data noise suppression data set into a training set and a verification set, thereby completing the training and verification of the original secondary noise suppression model to obtain the secondary noise suppression model.

[0047] Specifically, in this embodiment, the second seismic data noise suppression data set is divided into a training set and a validation set in a ratio of 7:3.

[0048] S4. Use the primary noise suppression model and the secondary noise suppression model to reduce noise on the seismic data, and obtain the noise-suppressed seismic data through data reconstruction.

[0049] Wherein, step S4 specifically includes the following steps: S41. Performing first-level noise reduction on the seismic data using the first-level noise suppression model to obtain first-level noise reduction data.

[0050] Specifically, in this embodiment, a first-level noise suppression model is used to perform first-level noise reduction on the seismic data collected in real time to obtain corresponding first-level noise reduction data, thereby achieving preliminary suppression of noise.

[0051] S42, using the secondary noise suppression model to perform secondary noise reduction on the seismic data to obtain a set of noise-reduced IMF components.

[0052] Specifically, in this embodiment, since the first-level denoised data obtained in step S41 may contain stubborn residual low-frequency noise and loss of high-frequency features due to the overlap of the seismic signal and the noise spectrum, this embodiment uses a secondary noise suppression model to perform secondary denoising on the first-level denoised data obtained in step S41 to obtain a set of denoised IMF components, and then the noise-suppressed seismic data can be obtained through data reconstruction.

[0053] S43, using the obtained denoised IMF component to perform data reconstruction to obtain noise-suppressed seismic data.

[0054] Specifically, in this embodiment, this step is a prior art method and will not be described in detail here.

[0055] It should be noted that, in some cases, the actions described in the specification can be performed in a different order and still achieve the desired results. In this embodiment, the order of steps given is only to make the embodiment appear clearer and easier to explain, rather than to limit it.

[0056] In an alternative embodiment, see Figure 6 The present invention provides a seismic data noise intelligent suppression system, the seismic data noise intelligent suppression system comprises: a data acquisition device A1, a data output device A2, a processor A3 and a storage A4, the storage A4 comprises a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program comprises program instructions, and when the program instructions are executed by the processor A3, the processor A3 executes the contents of steps S1 to S4.

[0057] Specifically, in this embodiment, when the computer program executed by the processor A3 implements the contents described in steps S1-S4, the data acquisition device A1 is used to acquire seismic data, and the data output device A2 is used to output the seismic data after noise suppression.

[0058] In summary, the present invention performs multi-level noise reduction on seismic data by constructing a primary noise suppression model and a secondary noise suppression model, thereby realizing noise suppression of seismic data. Among them, the method performs preliminary feature extraction and feature enhancement on seismic data through a feature extraction and enhancement module, so that more abundant feature information can be extracted later; the multi-scale features of seismic data are further extracted through a feature multi-scale integration module, the deep extraction of feature information is realized, the feature level is enriched, and the extracted feature information is preliminarily integrated to obtain feature information of the next level of the feature map extracted by the feature extraction and enhancement module; the feature information extracted by the first two modules is finally fused through a feature fusion output module to obtain primary noise reduction data, thereby retaining the effective signal in the earthquake to the greatest extent, thereby improving the signal-to-noise ratio and event continuity of the seismic data. After obtaining the primary noise reduction data, the method further constructs a secondary noise suppression model to perform secondary noise reduction on the primary noise reduction data, so as to solve the problem of stubborn residual low-frequency noise and loss of high-frequency features when the seismic signal overlaps with the noise spectrum in the primary noise reduction data, thereby further improving the noise suppression effect on seismic data. In addition, the system can stably run the method, improve the efficiency of noise suppression on seismic data, and improve the practicability of the method.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for intelligently suppressing noise in seismic data, characterized in that: The steps include: Constructing a first seismic data noise suppression dataset for model training based on seismic effective signals and random noise; Building a primary noise suppression model based on the first seismic data noise suppression data set, and then building a second seismic data noise suppression data set for model training; According to the second seismic data noise suppression data set, a secondary noise suppression model is constructed using a complementary set empirical mode decomposition method and a noise reduction autoencoder; The first-level noise suppression model and the second-level noise suppression model are used to reduce noise on seismic data, and the noise-suppressed seismic data are obtained through data reconstruction.

2. The method for intelligently suppressing noise in seismic data according to claim 1, characterized in that: The method of constructing a first seismic data noise suppression data set for model training based on seismic effective signals and random noise comprises the following steps: Determine the effective seismic signal, and superimpose different random noises on the effective seismic signal to obtain multiple different channels of earthquake measured simulation signals; The measured seismic simulation signal is cut into a plurality of segment signals, and the first seismic data noise suppression data set is constructed using the seismic effective signal and the segment signals.

3. The method for intelligently suppressing noise in seismic data according to claim 2, characterized in that: The step of constructing a primary noise suppression model based on the first seismic data noise suppression data set, and then constructing a second seismic data noise suppression data set for model training comprises the following steps: Constructing a primary noise suppression model, and using the first seismic data noise suppression data set to complete the training and verification of the primary noise suppression model, thereby obtaining the first-level noise suppression model; Using the first-level noise suppression model, performing first-level noise reduction on each of the segment signals in the first seismic data noise suppression data set to obtain corresponding first-level noise reduction data; The second seismic data noise suppression data set for model training is constructed using the seismic effective signal and the first-level noise reduction data.

4. A method for intelligently suppressing noise in seismic data according to claim 3, characterized in that: The step of constructing a primary noise suppression model and using the first seismic data noise suppression data set to complete the training and verification of the primary noise suppression model, thereby obtaining the first-level noise suppression model comprises the following steps: Construct the feature extraction and enhancement module, the feature multi-scale integration module and the feature fusion output module in sequence; The output of the feature extraction and enhancement module is downsampled as the input of the feature multi-scale integration module, the output of the feature extraction and enhancement module is used as the first input of the feature fusion output module, and the output of the feature multi-scale integration module is upsampled as the second input of the feature fusion output module to obtain the primary noise suppression model; The first seismic data noise suppression data set is divided into a training set and a verification set, thereby completing the training and verification of the primary noise suppression model, and finally obtaining the first-level noise suppression model.

5. The method for intelligently suppressing noise in seismic data according to claim 4, characterized in that: The feature extraction and enhancement module satisfies the following relationship: ， Wherein, F is the input of the feature extraction and enhancement module, is the output of the feature extraction and enhancement module, Indicates that the first type of convolutional layer is used for convolution operation. , , and These are all reference symbols set for the convenience of writing. Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling.

6. A method for intelligently suppressing noise in seismic data according to claim 5, characterized in that: The feature multi-scale integration module satisfies the following relationship: ， in, is the output of the feature multi-scale integration module, The i-th reference symbol is set for the convenience of writing. , Indicates that the second type of convolutional layer is used for convolution operation. Indicates that the third type of convolutional layer is used for convolution operation. Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling. Indicates downsampling. Indicates upsampling. is the output of the feature extraction and enhancement module, Indicates channel splicing.

7. A method for intelligently suppressing noise in seismic data according to claim 6, characterized in that: The feature fusion output module satisfies the following relationship: ， in, is the output of the feature fusion output module, Indicates the use of hyperbolic tangent activation function, Indicates that the first type of convolutional layer is used for convolution operation. The jth reference symbol is set for the convenience of writing. , Indicates the use of ReLU activation function, Indicates the use of Sigmoid activation function, Indicates maximum pooling. Indicates average pooling. Indicates upsampling. is the output of the feature extraction and enhancement module, is the output of the feature multi-scale integration module, Indicates channel splicing.

8. The method for intelligently suppressing noise in seismic data according to claim 3, characterized in that: According to the second seismic data noise suppression data set, using the complementary set empirical mode decomposition method and the noise reduction autoencoder to construct a secondary noise suppression model includes the following steps: Using the multiple IMF components of the primary denoised data obtained by the complementary set empirical mode decomposition method as input of the denoising autoencoder to obtain an original secondary noise suppression model; The second seismic data noise suppression data set is divided into a training set and a verification set, thereby completing the training and verification of the original secondary noise suppression model to obtain the secondary noise suppression model.

9. The method for intelligently suppressing noise in seismic data according to claim 3, characterized in that: The method of using the primary noise suppression model and the secondary noise suppression model to reduce noise on seismic data and obtaining noise-suppressed seismic data through data reconstruction comprises the following steps: Using the first-level noise suppression model to perform first-level noise reduction on the seismic data to obtain first-level noise reduction data; Performing secondary noise reduction on seismic data using the secondary noise suppression model to obtain a set of noise-reduced IMF components; The obtained denoised IMF components are used to perform data reconstruction to obtain noise-suppressed seismic data.

10. An intelligent noise suppression system for seismic data, characterized in that: The intelligent noise suppression system for seismic data comprises: a data acquisition device, a data output device, a processor and a storage device, wherein the storage device comprises a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and wherein the computer program comprises program instructions, and when the program instructions are executed by the processor, the processor implements the intelligent noise suppression method for seismic data as described in any one of claims 1 to 9.

Images