Self-Attention Deep Image Prior Network for Unsupervised 3-D Seismic Data Enhancement

Saad, Omar M.; Oboué, Yapo Abolé Serge Innocent; Samy, Lotfy; Yang, Liuqing; Chen, Yangkang

doi:10.1109/tgrs.2021.3108515

Cited by 49 publications

(2 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the numerous benefits, DAS data can still be contaminated by various types of noise from the ambient environment and the optical instruments. Supervised ML techniques were applied to target specific noise types to improve the SNR and denoising (noise reduction) of DAS data [73]. Recent research implemented supervised ML method DAS-N2N (Noise2Noise) to denoise DAS data without clean data [74].…”

Section: Application In Smf Processingmentioning

confidence: 99%

Application of Distributed Acoustic Sensing in Geophysics Exploration: Comparative Review of Single-Mode and Multi-Mode Fiber Optic Cables

Rafi,

Mohd Noh,

Abdul Latiff

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The advent of fiber optic technology in geophysics exploration has grown in its use in the exploration, production, and monitoring of subsurface environments, revolutionizing the way data are gathered and interpreted critically to speed up decision-making and reduce expense and time. Distributed Acoustic Sensing (DAS) has been increasingly utilized to build relationships in complex geophysics environments by utilizing continuous measurement along fiber optic cables with high spatial resolution and a frequency response of up to 10 KHz. DAS, as fiber optic technology examining backscattered light from a laser emitted inside the fiber and measuring strain changes, enables the performance of subsurface imaging in terms of real-time monitoring for Vertical Seismic Profiling (VSP), reservoir monitoring, and microseismic event detection. This review examines the most widely used fiber optic cables employed for DAS acquisition, namely Single-Mode Fiber (SMF) and Multi-Mode Fiber (MMF), with the different deployments and scopes of data used in geophysics exploration. Over the years, SMF has emerged as a preferred type of fiber optic cable utilized for DAS acquisition and, in most applications examined in this review, outperformed MMF. On the other side, MMF has proven to be preferable when used to measure distributed temperature. Finally, the fiber optic cable deployment technique and acquisition parameters constitute a pivotal preliminary step in DAS data preprocessing, offering a pathway to improve imaging resolution based on DAS measurement as a future scope of work.

show abstract

Section: Application In Smf Processingmentioning

confidence: 99%

Application of Distributed Acoustic Sensing in Geophysics Exploration: Comparative Review of Single-Mode and Multi-Mode Fiber Optic Cables

Rafi,

Mohd Noh,

Abdul Latiff

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning is widely used in the field of seismology, including earthquake detection and picking (Mousavi et al., 2020; Saad & Chen, 2021; Saad, Huang, et al., 2021; Zhu & Beroza, 2018), seismic data denoising (Saad & Chen, 2020; Saad, Oboué, et al., 2021; Yang et al., 2021; Zhang et al., 2019), estimation of earthquake location (Mousavi & Beroza, 2019; Münchmeyer et al., 2021), and seismic data inversion (Li et al., 2019; Liu et al., 2021; Ren et al., 2020; Zhang et al., 2021). The convolutional neural network (CNN) is a commonly used architecture due to its ability to extract significant features from the input data.…”

Section: Introductionmentioning

confidence: 99%

Real‐Time Earthquake Detection and Magnitude Estimation Using Vision Transformer

et al. 2022

Self Cite

View full text Add to dashboard Cite

Earthquake magnitude estimation is one of the fundamental processes for earthquake monitoring systems. The earthquake magnitude denotes the energy released during the shock, which is one of the main concerns for scientific research and the public. Richter magnitude (local magnitude) is one of the most widely used scales to inform the public of the earthquake size (Richter, 1935). Empirically, Richter magnitude (M L ) is obtained for every single station (each trace) by estimating the maximum amplitude among certain periods and takes the average magnitude over multiple stations (Havskov & Ottemoller, 2010). However, measuring the maximum amplitude of the seismic stations can be affected by unwanted signals of, for example, industrial activities, interfering noise, random noise, or other sources of interference, which leads to inaccurate magnitude estimation (Yamada & Mori, 2009). There are two strategies for magnitude estimation, that is, on-site (single station) approach (Wu et al., 2006) and network approach (Kuang et al., 2021). One single station is used in the on-site approach,

show abstract

Research on Image Denoising Algorithm Based on Spectrum Information

Huang

2024

2024 International Conference on Intelligent Computing and Data Mining (ICDM)

View full text Add to dashboard Cite

Self-Attention Deep Image Prior Network for Unsupervised 3-D Seismic Data Enhancement

Cited by 49 publications

References 66 publications

Application of Distributed Acoustic Sensing in Geophysics Exploration: Comparative Review of Single-Mode and Multi-Mode Fiber Optic Cables

Application of Distributed Acoustic Sensing in Geophysics Exploration: Comparative Review of Single-Mode and Multi-Mode Fiber Optic Cables

Real‐Time Earthquake Detection and Magnitude Estimation Using Vision Transformer

Research on Image Denoising Algorithm Based on Spectrum Information

Contact Info

Product

Resources

About