A Self-Supervised Deep Learning Method for Seismic Data Deblending Using a Blind-Trace Network

Wang, Shirui; Hu, Wenyi; Yuan, Pengyu; Wu, Xuqing; Zhang, Qunshan; Nadukandi, Prashanth; Botero, German Ocampo; Chen, Jiefu

doi:10.1109/tnnls.2022.3188915

Cited by 18 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of replacing parts of the data with noise before feeding the data to a DNN is called ‘masking’. In its seismic adaption (Wang, Hu, et al., 2022; S. Liu et al., 2022; Abedi et al., 2023), randomly selected traces in the input data are masked and then a DNN is trained to reconstruct them. Since the network is blinded to a trace in the data, the method is called ‘blind‐trace denoising’.…”

Section: Blind‐trace Denoisingmentioning

confidence: 99%

“…In seismic studies, adaptations of these methods are used for the attenuation of random noise (Meng et al, 2021;Birnie et al, 2021), trace-wise coherent noise (Birnie & Alkhalifah, 2022;S. Liu et al, 2022;Abedi et al, 2023) and deblending (Wang, Hu, et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…An extension of this method (named structured noise to void) aims to attenuate noise along extended blind masks (Broaddus et al., 2020), in which the noise is deemed coherent. In seismic studies, adaptations of these methods are used for the attenuation of random noise (Meng et al., 2021; Birnie et al., 2021), trace‐wise coherent noise (Birnie & Alkhalifah, 2022; S. Liu et al., 2022; Abedi et al., 2023) and deblending (Wang, Hu, et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Semi‐blind‐trace algorithm for self‐supervised attenuation of trace‐wise coherent noise

Abedi,

Pardo,

Alkhalifah

2023

Geophysical Prospecting

View full text Add to dashboard Cite

Trace‐wise noise is a type of noise often seen in seismic data, which is characterized by vertical coherency and horizontal incoherency. Using self‐supervised deep learning to attenuate this type of noise, the conventional blind‐trace deep learning trains a network to blindly reconstruct each trace in the data from its surrounding traces; it attenuates isolated trace‐wise noise but causes signal leakage in clean and noisy traces and reconstruction errors next to each noisy trace. To reduce signal leakage and improve denoising, we propose a new loss function and masking procedure in a semi‐blind‐trace deep learning framework. Our hybrid loss function has weighted active zones that cover masked and non‐masked traces. Therefore, the network is not blinded to clean traces during their reconstruction. During training, we dynamically change the masks' characteristics. The goal is to train the network to learn the characteristics of the signal instead of noise. The proposed algorithm enables the designed U‐net to detect and attenuate trace‐wise noise without having prior information about the noise. A new hyperparameter of our method is the relative weight between the masked and non‐masked traces' contribution to the loss function. Numerical experiments show that selecting a small value for this parameter is enough to significantly decrease signal leakage. The proposed algorithm is tested on synthetic and real off‐shore and land datasets with different noises. The results show the superb ability of the method to attenuate trace‐wise noise while preserving other events. An implementation of the proposed algorithm as a Python code is also made available.This article is protected by copyright. All rights reserved

show abstract

Section: Blind‐trace Denoisingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi‐blind‐trace algorithm for self‐supervised attenuation of trace‐wise coherent noise

Abedi,

Pardo,

Alkhalifah

2023

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…Semi-supervised learning based on contrastive learning emphasizes more on consistency in feature space [37]- [40], while general semisupervised uses more consistency in label space [41]- [44]. These methods have achieved promising results in both natural and medical images, but they have not been widely promoted and applied in the geophysical field [2], and even less work has been done to combine them with acoustic impedance inversion.…”

Section: Introductionmentioning

confidence: 99%

ContrasInver: Voxel-wise Contrastive Semi-supervised Learning for Seismic Inversion

Dou¹,

Li²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent studies have shown that learning theories have been very successful in hydrocarbon exploration. Inversion of seismic into various attributes through the relationship of 1D well-logs and 3D seismic is an essential step in reservoir description, among which, acoustic impedance is one of the most critical attributes, and although current deep learningbased impedance inversion obtains promising results, it relies on a large number of logs (1D labels, typically more than 30 well-logs are required per inversion), which is unacceptable in many practical explorations. In this work, we define acoustic impedance inversion as a regression task for learning sparse 1D labels from 3D volume data and propose a voxel-wise semisupervised contrastive learning framework, ContrasInver, for regression tasks under sparse labels. ConstraInver consists of several key components, including a novel pre-training method for 3D seismic data inversion, a contrastive semi-supervised strategy for diffusing well-log information to the global, and a continuous-value vectorized characterization method for a contrastive learning-based regression task, and also designed the distance TopK sampling method for improving the training efficiency. We performed a complete ablation study on SEAM Phase I synthetic data to verify the effectiveness of each component and compared our approach with the current mainstream methods on this data, and our approach demonstrated very significant advantages. In this data we achieved an SSIM of 0.92 and an MSE of 0.079 with only four well-logs. ConstraInver is the first purely data-driven approach to invert two classic field data, F3 Netherlands (only four well-logs) and Delft (only three well-logs) and achieves very reasonable and reliable results.

show abstract

“…Building on this, Liu et al (2022a,b) proposed to extend the blind-spot property to become a blind-trace, adapting the previously proposed selfsupervised denoiser for the suppression of trace-wise noise. Similarly, both Luiken et al (2022) and Wang et al (2022) proposed blind-trace networks implemented at the architecture level, as opposed to the likes of Krull et al (2019); Birnie et al (2021); Liu et al (2022a) which were implemented as processing steps. Both Liu et al (2022a) and Luiken et al (2022) illustrated successful suppression of tracewise noise, specifically poorly coupled receivers in common shot gathers and blending noise in common channel gathers, respectively.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning for self-supervised, blind-spot seismic denoising

Birnie

Alkhalifah

2022

Front. Earth Sci.

View full text Add to dashboard Cite

Noise is ever present in seismic data and arises from numerous sources and is continually evolving, both spatially and temporally. The use of supervised deep learning procedures for denoising of seismic datasets often results in poor performance: this is due to the lack of noise-free field data to act as training targets and the large difference in characteristics between synthetic and field datasets. Self-supervised, blind-spot networks typically overcome these limitation by training directly on the raw, noisy data. However, such networks often rely on a random noise assumption, and their denoising capabilities quickly decrease in the presence of even minimally-correlated noise. Extending from blind-spots to blind-masks has been shown to efficiently suppress coherent noise along a specific direction, but it cannot adapt to the ever-changing properties of noise. To preempt the network’s ability to predict the signal and reduce its opportunity to learn the noise properties, we propose an initial, supervised training of the network on a frugally-generated synthetic dataset prior to fine-tuning in a self-supervised manner on the field dataset of interest. Considering the change in peak signal-to-noise ratio, as well as the volume of noise reduced and signal leakage observed, using a semi-synthetic example we illustrate the clear benefit in initialising the self-supervised network with the weights from a supervised base-training. This is further supported by a test on a field dataset where the fine-tuned network strikes the best balance between signal preservation and noise reduction. Finally, the use of the unrealistic, frugally-generated synthetic dataset for the supervised base-training includes a number of benefits: minimal prior geological knowledge is required, substantially reduced computational cost for the dataset generation, and a reduced requirement of re-training the network should recording conditions change, to name a few. Such benefits result in a robust denoising procedure suited for long term, passive seismic monitoring.

show abstract

A Self-Supervised Deep Learning Method for Seismic Data Deblending Using a Blind-Trace Network

Cited by 18 publications

References 21 publications

Semi‐blind‐trace algorithm for self‐supervised attenuation of trace‐wise coherent noise

Semi‐blind‐trace algorithm for self‐supervised attenuation of trace‐wise coherent noise

ContrasInver: Voxel-wise Contrastive Semi-supervised Learning for Seismic Inversion

Transfer learning for self-supervised, blind-spot seismic denoising

Contact Info

Product

Resources

About