Seismic Interference Noise Research Articles

Deep neural network-based workflow for attenuating seismic interference noise and its application to marine towed-streamer data from the northern Viking Graben

To separate seismic interference (SI) noise while ensuring high signal fidelity, we have developed a deep neural network (DNN)-based workflow applied to common-shot gathers (CSGs). In our design, a small subset of the entire to-be-processed data set is first processed by a conventional algorithm to obtain an estimate of the SI noise (from now on called the SI noise model). By manually blending the SI noise model with SI-free CSGs and a set of simulated random noise, we obtain training inputs for the DNN. The SI-free CSGs can be either real SI-free CSGs from the survey or SI-attenuated CSGs produced in parallel with the SI noise model from the conventional algorithm depending on the specific project. To enhance the DNN’s output signal fidelity, adjacent shots on both sides of the to-be-processed shot are used as additional channels of the input. We train the DNN to output the SI noise into one channel and the SI-free shot along with the intact random noise into another. Once trained, the DNN can be applied to the entire data set contaminated by the same types of SI in the training process, producing results efficiently. For demonstration, we applied our DNN-based workflow to 3D seismic field data acquired from the northern Viking Graben of the North Sea and compared it with a conventional algorithm. The studied area has a challenging SI contamination problem with no sail lines free from SI noise during the acquisition. The comparison finds that our DNN-based workflow outperformed the conventional algorithm in processing quality with less noise residual and better signal preservation. This validates its feasibility and value for real processing projects.

Improving signal fidelity for deep learning‐based seismic interference noise attenuation

AbstractDeep learning has shown a considerable potential to significantly improve processing efficiency but has not yet been widely deployed to production projects of seismic signal separation such as seismic interference attenuation. The main reasons are: First, the industry has high standards for signal fidelity, which are critical for the success of subsequent seismic imaging, and deep neural network methods have not yet matched the required level; second, the network's interpretability issue has affected many geophysicists and sponsors’ trust in the deep learning technique. To develop deep neural network methods towards the end of benefiting real‐world production, we first attempt to better understand their performance, especially in how they make use of local and global features of the data. A novel quantitative research of the overall network model behaviour on synthetic data is conducted. We simulate three types of coherent seismic data components in the shot domain, blend them together and then train a network to separate them. In this process, random noise, a component having only learnable local features, is selectively injected into the network's training pairs. Three network models sharing the same architecture are trained individually, and they show distinctive behaviours when applied to the same test data. Step‐by‐step analysis of each of them reveals that training the network with additional random noise injected into both the input and the output channel of the desired signal can lead to a decent prediction of the coherent noise based on good learning of the global features and, in the meantime, preserve almost all the data information from being lost. We propose this key lesson we learnt as a new method to improve the network's signal fidelity for shot‐domain seismic interference attenuation, which is essentially a signal separation task. Its effectiveness is demonstrated on field data from Africa with a comparison to a conventional physics‐based seismic interference attenuation method used in production.

A Method for Denoising Seismic Signals With a CNN Based on an Attention Mechanism

Suppressing random noise in seismic data is a significant problem in seismic data processing. Often, there is serious aliasing between the effective signal and random noise, affecting the identification of weak signals, and even resulting in great difficulties in the suppression of conventional seismic signals. We propose an improved attention-guided convolutional neural network (ADNet) to eliminate seismic interference noise. After a sufficient amount of training, the network removes noise by transferring seismic data features learned from a synthetic dataset to tests with complex field data. Our workflow consists of four parts. First, in the model, we improve the feature enhancement module (FEM) and attention module (AM), increase the convergence speed, and enhance the expressive ability. Second, we use 2-D synthetic data to verify the ability of the model to suppress noise in seismic records. Third, we use 2-D real seismic data to further verify the denoising effect of the improved ADNet. Fourth, we convert the 3-D simulated seismic data and field data into 2-D data for processing and reorganize the 2-D denoising results into 3-D data. By comparing the noise suppression outcomes of several classic denoising methods, simulations and actual experiments show that the improved ADNet effectively maintains the signal amplitude, reduces the network depth, and better suppresses seismic noise. Hence, we believe that our model can be widely applied in the field of seismic data processing.

Noise types and their attenuation in towed marine seismic: A tutorial

The presence of noise in towed marine seismic data is a long-standing problem. The various types of noise present in marine seismic records are never truly random. Instead, seismic noise is more complex and often challenging to attenuate in seismic data processing. Therefore, we have examined a wide range of real data examples contaminated by different types of noise including swell noise, seismic interference noise, strumming noise, passing vessel noise, vertical particle velocity noise, streamer hit and fishing gear noise, snapping shrimp noise, spike-like noise, cross-feed noise, and streamer-mounted device noise. The noise examples investigated focus only on data acquired with analog group forming. Each noise type is classified based on its origin, coherency, and frequency content. We then determine how the noise component can be effectively attenuated through industry-standard seismic processing techniques. In this tutorial, we avoid presenting the finest details of either the physics of the different types of noise themselves or the noise attenuation algorithms applied. Rather, we focus on presenting the noise problems themselves and find out how well the community is able to address such noise. Our aim is that, based on the provided insights, the geophysical community will be able to gain an appreciation of some of the most common types of noise encountered in marine towed seismic, in the hope to inspire more researchers to focus their attention on noise problems with greater potential industry impact.

Seismic Interference Noise Attenuation by Convolutional Neural Network Based on Training Data Generation

External source interference noise (ESIN) is a common kind of noise in marine seismic data acquisition. According to the noise-to-signal ratio (NSR), a shot gather can be divided into a low NSR part and a high NSR part. The existing ESIN attenuation methods work well in high NSR parts of shot gathers. However, because the signals in low NSR parts are much stronger than ESINs, these methods cannot suppress the ESINs in low NSR parts, and they usually damage the signals. In this letter, we propose a deep-learning method to suppress the ESINs in low NSR parts based on a convolutional neural network (CNN). The end-to-end fully convolutional network needs labeled training samples; however, the real data are unlabeled, i.e., the ESINs in low NSR parts are unknown. To obtain the labeled training data, we propose a sample generation method based on real data. The ESINs in high NSR parts extracted by the traditional methods and the signals of the clean shot gathers are added together to synthesize training samples. We then use the synthesized data and its ESINs to train the network. The experiments prove that the proposed method can suppress the ESINs in low NSR parts properly and protect the signals as well.

Attenuation of marine seismic interference noise employing a customized U‐Net

ABSTRACTMarine seismic interference noise occurs when energy from nearby marine seismic source vessels is recorded during a seismic survey. Such noise tends to be well preserved over large distances and causes coherent artefacts in the recorded data. Over the years, the industry has developed various denoising techniques for seismic interference removal, but although well performing, they are still time‐consuming in use. Machine‐learning‐based processing represents an alternative approach, which may significantly improve the computational efficiency. In the case of conventional images, autoencoders are frequently employed for denoising purposes. However, due to the special characteristics of seismic data as well as the noise, autoencoders failed in the case of marine seismic interference noise. We, therefore, propose the use of a customized U‐Net design with element‐wise summation as part of the skip‐connection blocks to handle the vanishing gradient problem and to ensure information fusion between high‐ and low‐level features. To secure a realistic study, only seismic field data were employed, including 25,000 training examples. The customized U‐Net was found to perform well, leaving only minor residuals, except for the case when seismic interference noise comes from the side. We further demonstrate that such noise can be treated by slightly increasing the depth of our network. Although our customized U‐Net does not outperform a standard commercial algorithm in quality, it can (after proper training) read and process one single shot gather in approximately 0.02 s. This is significantly faster than any existing industry denoising algorithm. In addition, the proposed network processes shot gathers in a sequential order, which is an advantage compared with industry algorithms that typically require a multi‐shot input to break the coherency of the noise.

Streamer depth versus vessel and seismic interference noise

For marine seismic surveying, it is commonly assumed that the noise level decreases with depth. In addition, recent advances in broadband seismic have shown that a greater receiver depth is beneficial in preserving low-frequency data. However, in a heavily trafficked ocean, noise from other ships, including seismic interference, is a counteractive process in which the noise actually varies with depth. Normal modes can be used to explain and predict the ship noise and seismic interference noise level. We find that weather noise is dominant below the first mode’s cutoff frequency (approximately 6 Hz), ship noise is dominant from that frequency to the upper end of the useful seismic frequency band (80 Hz). We have used a data set in which the streamer was towed at 8, 45, and 60 m depths in three passes over the same area in the North Sea. The water depth is 135 m on average. We observe that the noise level at 45 and 60 m depth is approximately 1.6 times stronger than that at 8 m. We find that the air-gun energy is up to 46 dB stronger than the noise from the seismic vessel. However, the total noise from all the ships within several hundred kilometers radius can reduce the data quality.

Seismic envelope inversion: reduction of local minima and noise resistance

ABSTRACTWaveform inversion met severe challenge in retrieving long‐wavelength background structure. We have proposed to use envelope inversion to recover the large‐scale component of the model. Using the large‐scale background recovered by envelope inversion as new starting model, we can get much better result than the conventional full waveform inversion. By comparing the configurations of the misfit functional between the envelope inversion and the conventional waveform inversion, we show that envelope inversion can greatly reduce the local minimum problem. The combination of envelope inversion and waveform inversion can deliver more faithful and accurate final result with almost no extra computation cost compared to the conventional full waveform inversion. We also tested the noise resistance ability of envelope inversion to Gaussian noise and seismic interference noise. The results showed that envelope inversion is insensitive to Gaussian noise and, to a certain extent, insensitive to seismic interference noise. This indicates the robustness of this method and its potential use for noisy data.

A hybrid method for strong low-frequency noise suppression in prestack seismic data

Abstract Low-frequency components are important portion of seismic data in exploration geophysics, and have great effects on seismic imaging of deep subsurface and full waveform inversion. Unfortunately, seismic data usually suffers from various kinds of noises and has low signal to noise ratio (SNR) in low-frequency band, although this situation has been improved by developments of acquisition technology. In this paper, we propose a low-frequency cascade filter (LFCF) in Fourier domain for strong low-frequency noise suppression in prestack gathers. LFCF includes a 1D adaptive median filter in f–x domain and a 2D notch filter in f–k domain, which is able to process high-amplitude swell noise, random noise, and seismic interference noise. We employ traces rearrangement and spike-detection mechanisms in adaptive f–x median filter, which can handle strong noise specifically, such as wide-spreading swell noise and tug noise. And a notch filter in f–k domain is designed to separate reflection signal and random noise by different apparent velocities. Through these means, our method can effectively attenuate low-frequency random and coherent noise while simultaneously protect the signal. Experiments on synthetic example and field data are conducted, and the results demonstrate that our method is practical and effective and can preserve signal down to 2 Hz.

Time‐frequency seismic data de‐noising

ABSTRACTMarine seismic data are always affected by noise. An effective method to handle a broad range of noise problems is a time‐frequency de‐noising algorithm. In this paper we explain details regarding the implementation of such a method. Special emphasis is given to the choice of threshold values, where several different strategies are investigated. In addition we present a number of processing results where time‐frequency de‐noising has been successfully applied to attenuate noise resulting from swell, cavitation, strumming and seismic interference. Our seismic interference noise removal approach applies time‐frequency de‐noising on slowness gathers (τ−p domain). This processing trick represents a novel approach, which efficiently handles certain types of seismic interference noise that otherwise are difficult to attenuate. We show that time‐frequency de‐noising is an effective, amplitude preserving and robust tool that gives superior results compared to many other conventional de‐noising algorithms (for example frequency filtering, τ−p or fx‐prediction). As a background, some of the physical mechanisms responsible for the different types of noise are also explained. Such physical understanding is important because it can provide guidelines for future survey planning and for the actual processing.

Two different algorithms for seismic interference noise attenuation

This paper illustrates an automatic seismic interference noise attenuation algorithm and suggests studies to determine the propagation mechanism of seismic interference noise to help devise better algorithms. It also introduces another algorithm that relies on the assumption of a simple propagation mechanism to detect interfering source locations to attenuate such noise.

Optimizing the removal of seismic interference noise

Perhaps the most important step in the processing of seismic data is the removal of coherent and incoherent noise. According to the ageless signal-processing mantra “rubbish in, rubbish out;” in other words, however sophisticated your imaging algorithm is, if your signal is lost under a sea of noise, then no useful seismic image will be produced. Of course, as suggested by the quotation above, one processor's noise is another processor's signal, so we may possibly want to reformulate noise removal as simply a separation of signals into those desired for the final image and those which do not contribute useful information.

Mitigating seismic noise with an acoustic blanket—the promise and the challenge

Waterborne seismic noise is a broad category encompassing well-known noises like marine multiples, seismic interference noise, noise emanating from offshore structures and propagating into the marine environment, and even borehole-trapped noise. For several years, we have been studying the potential of bubble curtains for suppressing these types of noises.