2020
DOI: 10.1190/geo2019-0437.1
|View full text |Cite
|
Sign up to set email alerts
|

A robust first-arrival picking workflow using convolutional and recurrent neural networks

Abstract: A deep-learning-based workflow is proposed in this paper to solve the first-arrival picking problem for near-surface velocity model building. The traditional method such as STA/LTA method performs poorly when signal-to-noise ratio (SNR) is low or near-surface geological structures are complex. This challenging task is formulated as a segmentation problem accompanied by a novel post-processing approach to identify pickings along the segmentation boundary. The workflow includes three parts: a deep U-net for segm… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
10
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 42 publications
(10 citation statements)
references
References 21 publications
0
10
0
Order By: Relevance
“…This method works well for noisy situations and field datasets. After the segmentation image is obtained, a more advanced picking algorithm, such as an RNN, can be applied to take advantage of the global information (Yuan et al, 2020).…”
Section: Seismic Data Processingmentioning
confidence: 99%
“…This method works well for noisy situations and field datasets. After the segmentation image is obtained, a more advanced picking algorithm, such as an RNN, can be applied to take advantage of the global information (Yuan et al, 2020).…”
Section: Seismic Data Processingmentioning
confidence: 99%
“…They deployed seven-layered U-Net architecture with skip connection. In [28], U-Net was used for segmentation of seismic image and Recurrent Neural Network (RNN), for arrival picking. Additionally, the authors proposed a simple weight adaptation method for generalization of the model in unseen data.…”
Section: Related Workmentioning
confidence: 99%
“…In addition to these popular conventional methods, machine‐learning methods are also important and popular ways to identify the locations of arrivals and have been developed by many researchers in recent years (Glinsky et al ., 2001; Reynen and Audet, 2017; Chen, 2018; Zheng et al ., 2018; Chen et al ., 2019; Dokht et al ., 2019; Wang et al ., 2019; Woollam et al ., 2019; Wu et al ., 2019; Chen, 2020; Duan and Zhang, 2020; Qu et al ., 2020; Yuan et al ., 2020; Saad et al ., 2021). McCormack et al .…”
Section: Introductionmentioning
confidence: 99%