Deep Nonlocal Regularizer: A Self-Supervised Learning Method for 3-D Seismic Denoising

Xu, Zitai; Luo, Yisi; Wu, Bangyu; Meng, Deyu; Chen, Yangkang

doi:10.1109/tgrs.2023.3329303

Cited by 6 publications

(1 citation statement)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seismic data processing tasks are now increasingly utilizing self-supervised learning techniques, such as seismic velocity inversion, stratigraphic phase semantic segmentation, seismic data denoising, etc. [30][31][32], which demonstrates the applicability of self-supervised pre-training methods in seismic data feature extraction. However, only a few studies apply the Transformer framework to fault recognition tasks.…”

Section: Related Workmentioning

confidence: 77%

Improving Seismic Fault Recognition with Self-Supervised Pre-Training: A Study of 3D Transformer-Based with Multi-Scale Decoding and Fusion

Zhang,

Chen,

2024

Remote Sensing

View full text Add to dashboard Cite

Seismic fault interpretation holds great significance in the fields of geophysics and geology. However, conventional methods of seismic fault recognition encounter various issues. For example, models trained on synthetic data often exhibit inadequate generalization when applied to field seismic data, and supervised learning is heavily dependent on the quantity and quality of annotated data, being susceptible to the subjectivity of interpreters. To address these challenges, we propose applying self-supervised pre-training methods to seismic fault recognition, exploring the transfer of 3D Transformer-based backbone networks and different pre-training methods on fault recognition tasks, thereby enabling the model to learn more powerful feature representations from extensive unlabeled datasets. Additionally, we propose an innovative pre-training strategy for the entire segmentation network based on the characteristics of seismic data and introduce a multi-scale decoding and fusion module that significantly improves recognition accuracy. Specifically, during the pre-training stage, we compare various self-supervision methods, like MAE, SimMIM, SimCLR, and a joint self-supervised learning approach. We adopt multi-scale decoding step-by-step fitting expansion targets during the fine-tuning stage. Ultimately merging features to refine fault edges, the model displays superior adaptability when handling narrow, elongated, and unevenly distributed fault annotations. Experiments demonstrate that our proposed method achieves state-of-the-art performance on Thebe, the currently largest publicly annotated dataset in this field.

show abstract

Section: Related Workmentioning

confidence: 77%

Improving Seismic Fault Recognition with Self-Supervised Pre-Training: A Study of 3D Transformer-Based with Multi-Scale Decoding and Fusion

Zhang,

Chen,

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

Seismic random noise attenuation using edge preserving variational mode decomposition

Banjade,

Zhou,

Chen

et al. 2024

Digital Signal Processing

View full text Add to dashboard Cite

Unsupervised Coherent Noise Removal From Seismological Distributed Acoustic Sensing Data

Konietzny,

Lai,

Miller

et al. 2024

Journal of Geophysical Research: Machine Learning and Computati

View full text Add to dashboard Cite

Recent advances in sensing technologies, particularly Distributed Acoustic Sensing (DAS), have significantly improved the collection and analysis of seismological data. DAS is a powerful method for detecting vibrations from various sources, including earthquakes. However, the vast amount of data produced by DAS requires sophisticated analytical methods to differentiate between signals of interest and noise, such as traffic signals. We introduce an innovative approach by extending the Noise2Self framework to effectively remove unwanted, structured coherent noise from DAS data. By creating masks based on the characteristics of traffic signals, we isolate and preserve earthquake signals while maintaining the denoising performance of the original Noise2Self approach, which reduces noise without requiring clean reference data. To evaluate our method, we used synthetic data generated from seismic recordings of closely spaced seismometers and then applied our approach to data from a DAS array crossing the Alpine Fault near Haast, New Zealand. Our results demonstrate that our model successfully removes traffic noise and other non‐coherent noise while preserving seismic signals, leading to improvements in both Signal‐to‐Noise Ratio (SNR) and waveform coherence. Evaluations on real‐world DAS data further confirm the robustness of our method, positioning it as a valuable tool for analyzing large‐scale DAS data sets in various geoscientific contexts. This approach, which we refer to as “CoherentNoise2Self” to emphasize the extension of Noise2Self to coherent noise, advances the capabilities for near real‐time monitoring and analysis of seismic DAS data.

show abstract

Deep Nonlocal Regularizer: A Self-Supervised Learning Method for 3-D Seismic Denoising

Cited by 6 publications

References 97 publications

Improving Seismic Fault Recognition with Self-Supervised Pre-Training: A Study of 3D Transformer-Based with Multi-Scale Decoding and Fusion

Improving Seismic Fault Recognition with Self-Supervised Pre-Training: A Study of 3D Transformer-Based with Multi-Scale Decoding and Fusion

Seismic random noise attenuation using edge preserving variational mode decomposition

Unsupervised Coherent Noise Removal From Seismological Distributed Acoustic Sensing Data

Contact Info

Product

Resources

About