AutoEncoder Neural Network Application for Coherent Noise Attenuation in High Frequency Shallow Marine Seismic Data

Hamidi, Rosita; Latif, Abdul Halim Abdul; Lee, Wei Yi

doi:10.4043/30207-ms

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assuming the seismic signal of interest is the dominant component in the data, and a suitably small latent space is used, AEs have been shown to successfully suppress random noise in seismic data (Saad & Chen, 2020). Similarly, AEs can be used to attenuate coherent noise, such as high-frequency noise components in marine seismic data (Hamidi et al, 2020) or diffractions from stacked data (Markovic et al, 2022). Blind-spot networks represent another family of self-supervised methods recently introduced in computer vision: to counter the challenge of sourcing noisy-clean training pairs, Krull et al (2019) proposed a pre-processing methodology to 'blind' a central pixel from the network's input, which they termed Noise2Void (N2V).…”

Section: Introductionmentioning

confidence: 99%

Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising

Birnie,

Ravasi

2024

Geophysical Prospecting

View full text Add to dashboard Cite

The presence of coherent noise in seismic data leads to errors and uncertainties, and as such it is paramount to suppress noise as early and efficiently as possible. Self‐supervised denoising circumvents the common requirement of deep learning procedures of having noisy‐clean training pairs. However, self‐supervised coherent noise suppression methods require extensive knowledge of the noise statistics. We propose the use of explainable artificial intelligence approaches to ‘see inside the black box’ that is the denoising network and use the gained knowledge to replace the need for any prior knowledge of the noise itself. This is achieved in practice by leveraging bias‐free networks and the direct linear link between input and output provided by the associated Jacobian matrix; we show that a simple averaging of the Jacobian contributions over a number of randomly selected input pixels provides an indication of the most effective mask to suppress noise present in the data. The proposed method, therefore, becomes a fully automated denoising procedure requiring no clean training labels or prior knowledge. Realistic synthetic examples with noise signals of varying complexities, ranging from simple time‐correlated noise to complex pseudo‐rig noise propagating at the velocity of the ocean, are used to validate the proposed approach. Its automated nature is highlighted further by an application to two field data sets. Without any substantial pre‐processing or any knowledge of the acquisition environment, the automatically identified blind masks are shown to perform well in suppressing both trace‐wise noise in common shot gathers from the Volve marine data set and coloured noise in post‐stack seismic images from a land seismic survey.

show abstract

Section: Introductionmentioning

confidence: 99%

Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising

Birnie,

Ravasi

2024

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…Different from supervised learning techniques that require labeled data for training, AutoEncoders (AEs) have the ability to automatically learn and store features of the unlabeled, noisy data in an unsupervised learning manner. Working similarly to traditional decomposition-based procedures, the denoising ability of AEs are exploited for both random [9,34] and coherent noise suppression [17]. However, the learned features by AEs are not sufficient to fully represent seismic data [44].…”

Section: Introductionmentioning

confidence: 99%

Coherent noise suppression via a self-supervised blind-trace deep learning scheme

Liu¹,

Birnie²,

Alkhalifah³

2022

Preprint

View full text Add to dashboard Cite

Coherent noise regularly plagues seismic recordings, causing artefacts and uncertainties in products derived from down-the-line processing and imaging tasks. The outstanding capabilities of deep learning in denoising of natural and medical images have recently spur a number of applications of neural networks in the context of seismic data denoising. A limitation of the majority of such methods is that the deep learning procedure is supervised and requires clean (noise-free) data as a target for training the network. Blindspot networks were recently proposed to overcome this requirement, allowing training to be performed directly on the noisy field data as a powerful suppressor of random noise. A careful adaptation of the blind-spot methodology allows for an extension to coherent noise suppression. In this work, we expand the methodology of blind-spot networks to create a blind-trace network that successfully removes trace-wise coherent noise. Through an extensive synthetic analysis, we illustrate the denoising procedure's robustness to varying noise levels, as well as varying numbers of noisy traces within shot gathers. It is shown that the network can accurately learn to suppress the noise when up to 60% of the original traces are noisy. Furthermore, the proposed procedure is implemented on the Stratton 3D field dataset and is shown to restore the previously corrupted direct arrivals. Our adaptation of the blind-spot network for self-supervised, trace-wise noise suppression could lead to other use-cases such as the suppression of coherent noise arising from wellsite activity, passing vessels or nearby industrial activity.Preprint. Under review.

show abstract

Trace-wise coherent noise suppression via a self-supervised blind-trace deep-learning scheme

Liu,

Birnie,

Alkhalifah

2023

GEOPHYSICS

View full text Add to dashboard Cite

Seismic data denoising via supervised deep learning is effective and popular but requires noise-free labels, which are rarely available. Blind-spot networks circumvent this requirement by training directly on noisy data and have been shown to be a powerful suppressor of random noise. In this work, we expand the methodology of blind-spot networks to create a blind-trace network that successfully removes trace-wise coherent noise. An extensive synthetic analysis illustrates the denoising procedures robustness to varying noise levels and varying numbers of noisy traces within shot gathers. It is shown that the network can accurately learn to suppress the noise when up to 60% of the original traces are noisy. Furthermore, the proposed procedure is implemented on the Stratton 3D field dataset and is shown to restore the previously corrupted direct arrivals. In addition to trace-wise noise suppression, we adapted the blind-spot networks to the successful suppression of colored Gaussian noise, which exhibits varying coherent properties in both time and spatial axes. The proposed adaptation of the blind-spot networks paves the way for its use in other applications, such as the suppression of coherent noise arising from wellsite activity, passing vessels, or nearby industrial activity.

show abstract

AutoEncoder Neural Network Application for Coherent Noise Attenuation in High Frequency Shallow Marine Seismic Data

Cited by 3 publications

References 9 publications

Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising

Explainable artificial intelligence‐driven mask design for self‐supervised seismic denoising

Coherent noise suppression via a self-supervised blind-trace deep learning scheme

Trace-wise coherent noise suppression via a self-supervised blind-trace deep-learning scheme

Contact Info

Product

Resources

About