Reviving Legacy Seismic Data via Machine Learning Technique-Part 2: Estimating 3-D Seismic Volumes From 2-D Seismic Lines With VQ-VAE

We propose a machine learning-based method that estimates a 3-D seismic volume from irregularly placed 2-D seismic lines, addressing the challenges regarding the local disturbances contained within 2-D lines (e.g., seismic misties and discrepant seismic characteristics across lines). To overcome the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on geoscience and remote sensing Ročník 63; s. 1 - 21
Hlavní autori: Lee, Jun-Woo, Je Lee, Min, Min, Dong-Joo, Cho, Yongchae
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
2-D line interpolation
2-D/3-D seismic data
3-D volume data augmentation
3-D volume estimation
Convolution
D lines
Data augmentation
Disturbances
Estimation
Filters
Geological structures
Geology
Interpolation
Intervals
Learning algorithms
Machine learning
Neural networks
Random signals
Seismic data
Surveys
Three-dimensional displays
Training
Two-dimensional displays
vector-quantized variational autoencoder (VQ-VAE)
Volume measurement
ISSN:0196-2892, 1558-0644
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We propose a machine learning-based method that estimates a 3-D seismic volume from irregularly placed 2-D seismic lines, addressing the challenges regarding the local disturbances contained within 2-D lines (e.g., seismic misties and discrepant seismic characteristics across lines). To overcome these challenges, we employ the vector-quantized variational autoencoder (VQ-VAE) framework, which effectively captures global structures in data. Through appropriate data augmentation processes, the network is trained with diverse samples despite the limited availability of seismic volumes, enhancing its generality for estimating 3-D structures. Specifically, numerous training samples are generated from five seismic volumes with various augmentation methods, including perspective transform along the horizontal axes, horizontal flipping, polarity reversal, and random signal-level perturbations (e.g., smooth gain functions and convolution filters). In addition, a two-stage training process, into which randomly generated convolution filters are incorporated, further strengthens the robustness to local disturbances. We validate and evaluate the trained network on unseen 3-D volumes using <inline-formula> <tex-math notation="LaTeX">L_{1} </tex-math></inline-formula> and 3-D structural similarity index measure (3D-SSIM) metrics, demonstrated with numerical examples. The validation confirms that: 1) the proposed method successfully reconstructs subsurface geological structures from 2-D lines and 2) random filtering enhances performance for inconsistent (IC) lines. In addition, we test the applicability of the proposed method with actual 2-D lines acquired from the Jeju Basin, which have various line intervals ranging from 0.5 to 4 km. The testing results show that the network effectively manages intervals up to 2 km but struggles to estimate structures beyond straightforward horizontal layers at intervals of 4 km.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2025.3567596