Quality control in deep learning and confidence quantification: Seismic velocity regression through classification

J Simon, G Fabien-Ouellet, E Gloaguen - Computers & Geosciences, 2024 - Elsevier
Deep learning methods are increasingly used in seismic, but the black-box nature of neural
networks hinders the confidence users may have in their outputs. Moreover, conventional …

First-Arrival Picking for Out-of-Distribution Noisy Data: A Cost-Effective Transfer Learning Method with Tens of Samples

H Li, X Li, Y Sun, H Dong, G Xu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Data-driven methods for picking the first-arrival of seismic waves can encounter challenges
with generalization when they are faced with out-of-distribution data that falls outside their …

Automatic velocity analysis using interpretable multimode neural networks

H Zhang, S Yuan, H Zeng, H Yuan… - Geophysical Journal …, 2023 - academic.oup.com
Seismic velocity analysis is the basis for seismic imaging and understanding complex
subsurface geological structures. Although the performance of automatic velocity analysis …

Transfer learning-based hybrid deep learning method for gas-bearing distribution prediction with insufficient training samples and uncertainty analysis

J Yang, N Lin, K Zhang, C Fu, C Zhang - Energy, 2024 - Elsevier
The availability of sample data, required for seismicity-based reservoir prediction using deep
learning (DL), is often limited by well availability. To alleviate this problem, this study …

A fine‐tuning workflow for automatic first‐break picking with deep learning

A Mardan, M Blouin, G Fabien‐Ouellet… - Near Surface …, 2024 - Wiley Online Library
First‐break picking is an essential step in seismic data processing. For reliable results, first
arrivals should be picked by an expert. This is a time‐consuming procedure and subjective …

Vector Decomposition of Elastic Seismic Wavefields Using Self-Attention Deep Convolutional Generative Adversarial Networks

W Liu, J Cao, J You, H Wang - Applied Sciences, 2023 - mdpi.com
Vector decomposition of P-and S-wave modes from elastic seismic wavefields is a key step
in elastic reverse-time migration (ERTM) to effectively improve the multi-wave imaging …

[HTML][HTML] Deep-learning velocity model building by jointly using seismic first arrivals and early-arrival waveforms

X XU, ZH ZOU, ML HAN, DS JIA, HW ZHOU… - Chinese Journal of …, 2023 - en.dzkx.org
Seismic first arrivals and early-arrival waveform data contain rich velocity structure
information and are widely used in velocity model building. Such methods based on first …

InverMulT-STP: Closed-loop Transformer Seismic AVA Inversion with Synthetic Data Style Transfer Pretraining

X Liu, B Wu, C Wei, X Yan - IEEE Transactions on Geoscience …, 2024 - ieeexplore.ieee.org
Prestack seismic data amplitude variation with angle (AVA) inversion is critical in identifying
oil and gas reservoirs. Recently, deep learning (DL) has gained significant popularity in AVA …

Transfer learning model for estimating site amplification factors from limited microtremor H/V spectral ratios

D Pan, H Miura, C Kwan - Geophysical Journal International, 2024 - academic.oup.com
Site amplification factors (SAFs) of seismic ground motions are essential in evaluating and
estimating seismic hazards. In our previous study, the authors proposed a simple and cost …

Deep-learning viscoelastic seismic inversion for map** subsea permafrost

J Bustamante, G Fabien-Ouellet, MJ Duchesne… - Geophysics, 2024 - library.seg.org
Marine seismic surveys can be used to map ice-bearing subsea permafrost on a large scale.
However, current seismic processing technologies have limited capacity to image …