Seismic Data Denoising Research Articles

Application of 2D Variational Mode Decomposition Method in Seismic Signal Denoising

Seismic data are typical nonlinear and nonstationary data. In the acquisition and processing of seismic data, many factors interfere with it. Seismic data contain both effective waves and random noises, seriously affecting the quality of seismic data and not conducive to the goal of fine interpretation of subsequent seismic data. Therefore, studying new seismic data denoising methods is beneficial for improving the quality of seismic data and plays a very important role in subsequent seismic data interpretation. In this paper, the principle of variational mode decomposition (VMD) and 2D-VMD is introduced in detail, and the seismic profile with a simple signal and fault model is denoised. Compared to traditional empirical mode decomposition (EMD), the 2D-VMD method has the best seismic data denoising effect. The test results of the synthesised signal show that the 2D-VMD method has a signal-to-noise ratio of 47.14 dB after denoising, which is higher than the signal-to-noise ratio after EMD and VMD denoising, indicating that it has a better denoising effect. The VMD and 2D-VMD methods are applied to the denoising of actual seismic data. The application results show that the 2D-VMD method can effectively improve the quality of the seismic data, enhance the continuity and reliability of the seismic data, and is conducive to the fine interpretation of subsequent seismic data.

Seismic data denoising with two-step prediction strategy based on Neural Network

Seismic data denoising (SDD) plays an important role in obtaining high-quality data for subsequent seismic imaging and inversion. However, traditional SDD methods still present several disadvantages such as parameter selection difficulties, high computational costs, and a strong dependence on the experience of processing personnel. Deep learning (DL)-based SDD methods can overcome these issues to a certain extent, having the advantages of high computational efficiency and negligible dependency on the experience of processing personnel. However, existing DL-based SDD methods typically adopt a specific single-network architecture, which can be further improved in terms of training efficiency and denoising quality. In this paper, we propose a two-step prediction denoising method based on the combination of two identical or different network architectures for improving the accuracy and efficiency of DL-based SDD methods. Compared with existing SDD methods, the two-step prediction denoising method is more capable of extracting feature information at multiple scales because multiple network architectures are combined in a single denoising task, thus improving the training efficiency and denoising accuracy. In this study, we implemented the two-step prediction denoising method using an improved denoising convolutional neural network (DnCNN) and a nested U-shaped fully convolutional network (U-Net++). Several synthetic numerical examples based on three different types of noise were denoised, with the results indicating that the proposed method effectively improves the accuracy and efficiency of the DL-based SDD method. Finally, a test using field data was performed to demonstrate the real-world applicability of the novel two-step prediction denoising method.

Simultaneous denoising and reconstruction of distributed acoustic sensing seismic data via a multicascade deep-learning method

Distributed acoustic sensing (DAS) has been moderately used in seismic exploration as a consequence of its advantages, such as low cost, high resolution, high sensitivity, and strong resistance to high temperatures. Nonetheless, seismic data recorded by the DAS system often are seriously contaminated by a massive amount of background noise and recording gaps, which also decrease the quality of DAS seismic data. Building on its success in numerous fields of data processing, convolutional neural networks (CNNs) also have been applied to seismic data denoising as well as reconstruction and achieved good performance compared with traditional methods. However, relatively few CNN-based studies have been done on the simultaneous denoising and reconstruction of seismic data, especially for the complex DAS seismic data with a low signal-to-noise ratio. In this study, we have developed a multicascade network structure in combination with a channel attention mechanism (MCA-Net) to achieve the simultaneous denoising and reconstruction of DAS seismic data by only using a unified trained model. Particularly, our MCA-Net consists of three branches of cascade networks that can extract abundant features from DAS seismic data with different resolutions. Furthermore, we deploy some channel attention modules and aggressive blocks to MCA-Net to fuse these aforementioned multiresolution features and thus improving the feature extraction ability of the whole network. Meanwhile, a high-quality training data set composed of paired clean complete and noisy incomplete patches is used to train MCA-Net in a supervised fashion. Some synthetic and real DAS seismic data are used to demonstrate the effectiveness of MCA-Net, and our method exhibits better denoising and reconstruction performance than some traditional methods and two existing CNN architectures.

Deep learning for noise attenuation from the ocean bottom node 4C data

AbstractThe source vessel noise is a very common noise type in offshore seismic surveys. The state‐of‐art deep learning‐based methods provide an end‐to‐end framework for seismic data denoising. The denoising performance of a pretrained network is, however, highly dependent on the completeness of the training set. When training a denoising network with only field data, especially for attenuating erratic noise, it is hard to obtain a noise‐free data as the training target for the network. Transfer learning, by combining the synthetic and field data, is an alternative solution for improving the generalization capabilities of the network, although being able to model such erratic noise represents also a challenge. Although the denoising results by traditional methods are not accurate enough for creating a complete training set, the features in residual noise by subtracting the denoised data from noisy data are enough for the network to learn. Considering the aforementioned factors, we develop a deep learning‐based workflow for the attenuation of the erratic source vessel noise from ocean bottom node 4C data. Instead of using denoising results directly, we use the conventional methods to extract noise and add them to the high signal‐to‐ratio region of the field data. The created noisy dataset is different from the original noisy data in noise regions; thus, the pretrained network can also be used for predicting the same original data. The denoising results of synthetic and field data all show that even the network is trained on a noisy labelled dataset, we still can obtain high signal‐to‐noise ratio denoising result. Besides, when compare with the results by filtering‐based methods, our proposed method can attenuate the vessel noise more effectively and preserve the near offsets reflections.

SeisDeNet: an intelligent seismic data Denoising network for the internet of things

Deep learning (DL) has attracted tremendous interest in various fields in last few years. Convolutional neural networks (CNNs) based DL architectures have been successfully applied in computer vision, medical image processing, remote sensing, and many other fields. A recent work has proved that CNNs based models can also be used to handle geophysical problems. Due to noises in seismic signals acquired by geophone equipment this kind of important multimedia resources cannot be effectively utilized in practice. To this end, from the perspective of seismic exploration informatization, this paper takes informatization data in seismic signal acquisition and energy exploration field using cutting-edge technologies such as Internet of things and cloud computing as the research object, presenting a novel CNNs based seismic data denoising (SeisDeNet) architecture is suggested. Firstly, a multi-scale residual dense (MSRD) block is built to leverage the characteristics of seismic data. Then, a deep MSRD network (MSRDN) is proposed to restore the noisy seismic data in a coarse-to-fine manner by using cascading MSRDs. Additionally, the denoising problem is formulated into predicting transform-domain coefficients, by which noises can be further removed by MSRDNs while richer structure details are preserved comparing with the results in spatial domain. By using synthetic seismic records, public SEG and EAGE salt and overthrust seismic model and real field seismic data, the proposed method is qualitatively and quantitatively compared with other leading edge schemes to evaluate it performance, and some results shows that the proposed scheme can produce data with higher quality evaluation while maintaining far more useful data comparing with other schemes. The feasibility of this approach is confirmed by the denoising results, and this approach is shown to be promising in suppressing the seismic noise automatically.

Self-adaptive seismic data reconstruction and denoising using dictionary learning based on morphological component analysis

Data reconstruction and data denoising are two critical preliminary steps in seismic data processing. Compressed Sensing states that a signal can be recovered by a series of solving algorithms if it is sparse in a transform domain, and has been well applied in the field of reconstruction, when, sparse representation of seismic data is the key point. Considering the complexity and diversity of seismic data, a single mathematical transformation will lead to incomplete sparse expression and bad restoration effects. Morphological Component Analysis (MCA) decomposes a signal into several components with outstanding morphological features to approximate the complex internal data structure. However, the representation ability of combined dictionaries is constrained by the number of dictionaries, and cannot be self-adaptively matched with the data features. Dictionary learning overcomes the limitation of fixed base function by training dictionaries that are fully suitable for processed data, but requires huge amount of time and considerable hardware cost. To solve the above problems, a new dictionary library (K-Singluar Value Decomposition learning dictionary and Discrete Cosine Transform dictionary) is hereby proposed based on the efficiency of fixed base dictionary and the high precision of learning dictionary. The self-adaptive sparse representation is achieved under the Morphological Component Analysis framework and is successfully applied to the reconstruction and denoising of seismic data. Real data tests have proved that the proposed method performs better than single mathematical transformation and other combined dictionaries.

A multi-scale dense-connection denoising network for DAS-VSP records

Due to high spatial resolution, low cost, and wide bandwidth, distributed optical fiber acoustic sensing (DAS) is regarded as a potential tool for data acquisition in vertical seismic profile (VSP) surveys. However, in real DAS-VSP records, desired signals are often seriously plagued by various noise, which does not appear in the conventional seismic data received by electronic geophones. Exploring a high-performing attenuation method for the background noise can significantly improve the quality of DAS-VSP records and has essential impacts on the following imaging and interpretation. Deep-learning-based methods, especially convolutional neural network (CNN), have shown remarkable performance in seismic data denoising. However, the conventional CNN-based methods may degrade when dealing with DAS-VSP records in low signal-to-noise ratio. In this study, we propose a novel multi-scale dense-connection denoising network (MDD-Net) to achieve high-accuracy processing of the complex DAS background noise. Unlike conventional multi-scale networks, MDD-Net utilizes widen convolution block to capture the multi-scale features of the analyzed data. On this basis, dense connection operations are employed to fuse the features and improve the network efficiency. Meanwhile, an enhanced spatial attention (ESA) block is designed to reinforce the features, which are helpful for noise suppression and weak signal recovery. Both synthetic and field DAS-VSP records are processed to verify the effectiveness of MDD-Net. Meanwhile, we also compare the denoising results with other competing methods. The experimental results demonstrate that MDD-Net can significantly attenuate the complex DAS background noise and restore the desired signals, even for the weak upgoing signals.

Ensemble empirical mode decomposition and stacking model for filtering borehole distributed acoustic sensing records

We have evaluated the ensemble empirical mode decomposition (EEMD) and stacking model for borehole seismic-data denoising. The borehole records collected by distributed acoustic sensing (DAS) technology have multitype noise contamination, and it is difficult to attenuate these noises while recovering the seismic waves well. We first perform EEMD on the seismic data to obtain the signal-to-noise modal components, then extract the time and frequency information of the decomposed modes using six feature factors, and finally introduce an ensemble learning method to classify the acquired modal features effectively. Stacking is the ensemble learning technique we used in our study. This technique integrates several diverse basic ensemble models using the meta-learning strategy and constructs a highly integrated framework with superior performance and good generalization. In addition, the basic ensemble models consist of many decision tree classifiers following two different ideas of parallelization and serialization. The feature extraction process provides sufficient DAS feature data for the training process of the framework. Synthetic and real experimental results demonstrate that the stacking integration framework effectively separates the signal-to-noise modal features of the borehole DAS records. Furthermore, the EEMD-stacking method performs better than wavelet transform, intrinsic time-scale decomposition, robust principal component analysis, k-means singular value decomposition, and median filtering on the denoising task.

A Denoising Method for Seismic Data Based on SVD and Deep Learning

When reconstructing seismic data, the traditional singular value decomposition (SVD) denoising method has the challenge of difficult rank selection. Therefore, we propose a seismic data denoising method that combines SVD and deep learning. In this method, seismic data with different signal-to-noise ratios (SNRs) are processed by SVD. Data sets are created from the decomposed right singular vectors and data sets divided into two categories: effective signal and noise. The lightweight MobileNetV2 network was chosen for training because of its quick response speed and great accuracy. We forecasted and categorized the right singular vectors by SVD using the trained MobileNetV2 network. The right singular vector (RSV) corresponding to the noise in the seismic data was removed during reconstruction, but the effective signal was kept. The effective signal was projected to smooth the RSV. Finally, the goal of low SNR denoising of two-dimensional seismic data was accomplished. This approach addresses issues with deep learning in seismic data processing, including the challenge of gathering sample data and the weak generalizability of the training model. Compared with the traditional denoising method, the improved denoising method performs well at removing Gaussian and irregular noise with strong amplitudes.

Research on Sparse Denoising of Strong Earthquakes Early Warning Based on MEMS Accelerometers.

In view of the fact that the noise in the same frequency band as the useful signal in the MEMS acceleration sensor observation data cannot be effectively removed by traditional filtering methods, a denoising method for strong earthquake signals based on the theory of sparse representation and compressive sensing is proposed in this paper. This skillfully realized the separation of strong earthquake signals from noise by adopting a fixed dictionary and utilizing sparse characteristics. Furthermore, considering the weakness of the sparse denoising method based on the fixed dictionary in the high signal-to-noise ratio, a spare denoising method based on learning an over-complete dictionary is proposed. Through the initial given seismic data, the ideal over-complete dictionary is trained to achieve seismic data denoising. In addition, for the interference waves of non-seismic events, this paper proposes an idea based on sparse representation classification to remove such non-seismic interference directly. Combining the ideas of noise reduction and non-seismic event elimination, we can obtain a standard sparse anti-interference denoising model for earthquake early warning. It's innovative that this model implements the sparse theory into the field of earthquake early warning. According to the experimental results, in the case of heavy noise, the denoising model based on sparse representation can reach average SNR of 8.73 and an average MSE of 29.53, and the denoising model based on compression perception can reach average SNR of 7.29 and an average MSE 41.34, and the denoising model based on learning dictionary can reach average SNR 11.07 and average MSE 17.32. The performance of these models is better than the traditional FIR filtering method (average SNR -0.73 and average MSE 260.37) or IIR filtering method (average SNR 4.73 and average MSE 73.95). On the other hand, the anti-interference method of the sparse classification proposed in this paper can accurately distinguish non-seismic interference events from natural earthquakes. The classification accuracy of the method based on the noise category of the selected test data set reaches 100% and achieves good results.

Random noise attenuation with weak feature preservation via total variation regularization

Dictionary learning (DL) methods have been successfully applied to seismic data denoising. However, when the noise is strong, weak signals cannot be well preserved. Considering the characteristics of seismic data in the spatial-time domain, we propose a dictionary learning method with total variation regularization (DLTV). The DLTV method consists of two steps. The first step is to learn the dictionary; it uses the sparse feature of the data in the dictionary domain and the learned dictionary contains data features. The second step is to use the augmented Lagrange multiplier method to restore the data, and total variation regularization to preserve the weak signal by sampling data information around it. An example with seismic data shows that the proposed method retains the weak features better than the traditional F-X deconvolution (FX-Decon) method and the data-driven tight frame method (DDTF).

Seismic random noise suppression by using deep residual U-Net

Pre-stack seismic denoising is one of most important processing steps in seismic exploration, which can significantly enhance the signal-to-noise ratio (SNR) and resolution of real seismic data. Seismic random noise often presents some complicated characteristics (non-gaussian, non-stationary, non-linear) and may overlap with desired signals in frequency domain. Thus, we need to explore the corresponding approach to attenuate the unwanted random noise and simultaneously recover the signals. Recently, some methods based on convolutional neural network (CNN) have shown excellent performance in seismic data denoising. These CNN-based denoising methods can learn the potential features of labeled data, thereby establishing the mapping relationship between noisy seismic data and signals. However, these existing CNN-based methods only consider the single-scale potential features and neglect some useful multiscale features, leading to their performance degradation when processing some seismic data with low SNR. In view of above drawback, we propose a novel CNN by introducing the residual theory and reconstruction block into the conventional U-Net, called deep residual U-Net (DRUN). In DRUN, some residual blocks are utilized to obtain the multiscale features of noisy seismic data and the followed reconstruction block can incorporate features of different scales, thereby distinguishing signals and random noise. Both the synthetic and field seismic data are processed to verify the effectiveness of DRUN. Compared with the original U-Net, the experimental results demonstrate that the proposed DRUN has superiority in noise attenuation and signal preservation.

A Convolutional Autoencoder Method for Simultaneous Seismic Data Reconstruction and Denoising

Petroleum geophysical exploration is based on seismic data and has been widely affected by deep learning technology in recent years. As a consequence of the high efficiency and nonlinear fitting ability of deep learning models, we propose an improved convolutional autoencoder (CAE) method to achieve simultaneous reconstruction and denoising of seismic data. The architecture of the improved CAE is based on group convolution and inception structures, which have powerful feature extraction capabilities for seismic data. The CAE method regards the reconstruction and denoising of seismic data as a feature extraction process of the target seismic signals; this enables the method to simultaneously reconstruct the seismic signal accurately and suppress the random noise mixed in the seismic data. During the training of the CAE, the mean absolute error (MAE) loss function and Adam optimization algorithm were used. Because this is a data-driven method and does not require the threshold to be input manually, it can process a large amount of seismic data quickly and intelligently. Synthetic and field data examples demonstrate the effectiveness of the CAE method.

Noisy2Noisy: Denoise Pre-Stack Seismic Data Without Paired Training Data With Labels

In recent years, supervised deep learning-based denoising methods have been popularized and developed rapidly in the field of seismic data processing. Supervised training, however, is limited by the quality and quantity of the paired training data (noisy clean or noisy noise). Data labeling is a time-consuming and expensive work. Compared with raw seismic data, only a small amount of seismic data have been correctly labeled, which, to some extent, limits the long-term development of supervised deep learning-based methods in the field of seismic data denoising. In this letter, we propose an improved denoising framework based on an unsupervised deep learning-based denoising method Noise2Noise, which only needs unprocessed raw seismic data to train the denoising model. Moreover, unlike Noise2Noise, the proposed method does not need to repeatedly collect seismic data to obtain a training pair with similar signal, which is more convenient and effective. Specifically, we propose a block random sampler that can generate training pairs using raw seismic data, which satisfies the training assumption of Noise2Noise that the training pair has a similar signal. In addition, our method has no requirements for the network structure and noise distribution prior and is flexible. Both synthetic seismic data and field seismic data denoising results show that our method can effectively suppress the random noise, and the denoising performance is equivalent to that of supervised deep learning-based denoising methods. In addition, our method may provide a certain reference for geophysical-related research.

Research on Application of Deep Learning Algorithm in Earthquake Noise Reduction

For the traditional denoising method, it is necessary to accurately model the signal and noise and optimize and adjust the manual input parameters, which causes the problem that it is difficult to remove the noise of the seismic data. Especially random noise in remote areas has the characteristics of non-stationary, high energy, and serious aliasing of effective signals and random noise in the frequency domain, which brings great difficulty to the recovery of seismic data by conventional denoising methods, but the existence of random noise seriously affects subsequent earthquakes. The processing and interpretation of data makes it difficult to determine the exact location of oil and gas. It is necessary to develop an efficient denoising algorithm, which can retain the complex edge information and rich texture information of the signal as much as possible while removing random noise, so as to restore the seismic data and improve the utilization rate of the seismic data. In this paper, the convolutional neural network is applied to seismic data processing. The algorithm has a good denoising effect in seismic data. While eliminating a large amount of random noise, it retains the texture features in the data, realizes denoising of seismic data, and enhances vision quality.

DenoiseNet: Deep Generator and Discriminator Learning Network With Self-Attention Applied to Ocean Data

Well-organized seismic signals play a significant role in subsequent seismic data processing. The multi-scale learning of characteristic signals of complex structures by deep convolutional neural networks has obvious benefits in reducing random noise in seismic data. However, deep convolutional neural networks also have shortcomings. It cannot discover effective features in seismic data structures or recover highquality seismic signals just using convolution. Therefore, the paper presents a Generative Adversarial Network (GAN) architecture in conjunction with the U-Net network. To produce the mapping connection between clean seismic signals and noisy seismic data, the U-Net network is employed as the G network of GAN. Incorporating a self-attention mechanism to strengthen the correlation between seismic data, with the goal of improving the network’s reconstruction capacity on the continuity of seismic signals. The intelligent denoising of seismic data enabled by DsGAN enhances labor efficiency when compared to traditional approaches. When compared to the optimal state of current models such as DnCNN, DnGAN, the peak signal-to-noise ratio (PSNR) is enhanced by 1.52db of the DsGAN model, according to experimental data from simulated and actual seismic data. Not only that, the network also has the ability to learn complex unknown noise with strong generalization and robustness.

Unsupervised CNN Based on Self-Similarity for Seismic Data Denoising

Convolutional neural network (CNN)-based methods are powerful tools for seismic data denoising. Most methods adopt a supervised learning strategy, which requires noise-free labels to construct an objective function to guide the training of network parameters; however, it is impossible to obtain true noise-free field data. We propose a novel unsupervised random-noise-suppression method that can train a network directly on noisy target data without noise-free labels. The proposed method is inspired by the simple denoising idea of averaging multiple noisy observations, and it requires noise to satisfy two assumptions: it should be zero-mean and independent of the signal. In this method, multiple observations can be used as labels, and the loss function is constructed as the mean square error expected between the network output and these observations. The trained network estimates the expected value of these noise observations (i.e., the clean signal). This unsupervised method theoretically requires multiple noisy observations. Considering the good nonlocal self-similarity of seismic data, we used self-similar blocks to rearrange the data to construct multiple pseudo-observations and finally realize unsupervised training. The proposed method was compared with the traditional <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f-x</i> deconvolution, curvelet, and generator CNN method on synthetic and field data, and the experimental results verified the effectiveness of the proposed method.

Low-Rank Tensor Minimization Method for Seismic Denoising Based on Variational Mode Decomposition

Seismic data contain a lot of information in both spatial (<i>t-x</i>) and frequency domains. In order to make full use of the effective information in multiple domains, this letter proposes a low-rank tensor minimization method for seismic data denoising. This model first uses variational mode decomposition (VMD) to decompose the seismic data in the frequency domain and constructs a seismic tensor to highlight the frequency information of the seismic data; then to make use of the spatial similarity and frequency correlation of the seismic tensor, a low rank seismic tensor is built through block matching and a low-rank tensor minimization model is established to attenuate the noise. Finally, the denoised seismic tensor is reconstructed into a seismic section. Experimental results show that compared with several denoising methods, the method proposed in this letter can obtain higher signal-to-noise ratio (SNR) and structural similarity (SSIM) and achieve better denoising effects.

Attention-Based Neural Network for Erratic Noise Attenuation From Seismic Data With a Shuffled Noise Training Data Generation Strategy

The supervised neural network-based method provides an effective way for seismic data denoising. The noise level of seismic erratic noise, i.e. outlier, varies from traces, time windows and shot gathers. The networks with popular structures may damage reflections because the network cannot learn the exact location of the noises. In order to accommodate the characteristics of erratic noise, we propose using an attention-based network which focuses more on noisy regions. The network outputs an attention map which shows the spatial distribution probability of erratic noise and a raw-noise which may have leakage reflections. To train the network with two kinds of outputs, we use two different loss function to optimize the network. The erratic noises in the specified area can be extracted by multiplying the attention map and the raw-noise, and the reflections in areas without noise are preserved. For generating the training set, we proposed a shuffled noise strategy which starts from the inaccurate denoised data with conventional method. Only the noisy data is available in the whole denoising workflow. The network can learn the noise features effectively with the shuffle noise strategy and can achieve better denoising effect than that based on conventional method. Besides, the denoising capability of the network can be controlled manually by filtering the attention map with probability, and the denoising effect can be further improved through recovering the leaked signals. Synthetic and field data examples show that the proposed method has potential for field erratic noise attenuation.

Parameter-shared variational auto-encoding adversarial network for desert seismic data denoising in Northwest China

One of the key and difficult points in seismic data processing is seismic data denoising. Under the influence of the acquisition environment, the collected seismic data usually have low signal-to-noise ratio (SNR) and low resolution. In desert region of western China, different from other regions, the random noise there has complex characteristics of non-Gaussian, non-stationary and non-linearity. Its main frequency is quite low and its spectral overlap with those of effective signals. Moreover, large amount of data and intelligent requirements make traditional denoising methods encounter difficulties. In addition, the existing deep learning denoising methods also reveal two problems: first, they can only effectively suppress simple seismic noise such as Gaussian noise. But for the case of desert noise, they usually mistakenly judge noise as effective signals and destroy signal characteristic structure. Second, what is more important, in supervised-based methods paired noisy and pure data are usually used as training set. However, there is no noise-free data in actual desert seismic data, which severely limits the processing performance of supervised-based networks. Thus, a new parameter-shared variational auto-encoding adversarial network (PS-VAAN) is proposed for desert seismic data denoising in this paper. This new method includes two encoders, two generators and two discriminators. It can realize domain conversion from noisy data domain to pure data domain. We construct relatively complete unpaired pure and noisy data training sets for training, and design reconstruction loss function and adversarial loss function to optimize network parameters. Moreover, cycle-consistency loss is introduced to make sure two domains mapping into the same space. Compared with the state-of-art denoising methods on synthetic and actual seismic records, the proposed method not only has superior denoising ability, but also has strong feature extraction and fitting ability to recover effective signals with almost no energy loss.