Unsupervised deep learning with higher-order total-variation regularization for multidimensional seismic data reconstruction

TA Larsen Greiner, JE Lie, O Kolbjørnsen… - Geophysics, 2022 - library.seg.org
In 3D marine seismic acquisition, the seismic wavefield is not sampled uniformly in the
spatial directions. This leads to a seismic wavefield consisting of irregularly and sparsely …

Deblending and recovery of incomplete blended data via MultiResUnet

B Wang, J Li, D Han, J Song - Surveys in Geophysics, 2022 - Springer
Blended acquisition is still open to improve the efficiency of seismic data acquisition.
Deblending is an essential procedure to provide separated gathers for subsequent …

Seismic data reconstruction based on a multicascade self-guided network

X Dong, C Wei, T Zhong, M Cheng, S Dong, F Li - Geophysics, 2024 - library.seg.org
Due to inherent limitations in data acquisition, seismic data reconstruction is an important
procedure to recover missing data or improve observation density. Many conventional …

Radar Attenuation in the Shallow Martian Subsurface: RIMFAX Time‐Frequency Analysis and Constant‐Q Characterization Over Jezero Crater Floor

S Eide, TM Casademont, T Berger… - Geophysical …, 2023 - Wiley Online Library
Attenuation of radar waves in the subsurface can be quantified with a constant‐Q
approximation through time‐frequency analysis. We implement the centroid frequency‐shift …

Deblending of seismic data based on neural network trained in the CSG

K Wang, T Hu - IEEE Transactions on Geoscience and Remote …, 2021 - ieeexplore.ieee.org
The simultaneous source acquisition method, which excites multiple sources in a narrow
time interval, can greatly improve the efficiency of seismic data acquisition and provide good …

An unsupervised learning approach to deblend seismic data from denser shot coverage surveys

K Wang, T Hu, S Wang - Geophysical Journal International, 2022 - academic.oup.com
The simultaneous source data obtained by simultaneous source acquisition contain
crosstalk noise and cannot be directly used in conventional data processing procedures …

Deep learning-based shot-domain seismic deblending

J Sun, S Hou, V Vinje, G Poole, LJ Gelius - Geophysics, 2022 - library.seg.org
To streamline the fast-track processing of large data volumes, we have developed a deep
learning approach to deblend seismic data in the shot domain based on a practical strategy …

[PDF][PDF] 基于扩张卷积的智能化规则缺失炮插值重建方法

王本锋, 韩东, 李家阔 - 地球物理学报, 2022 - dsjyj.com.cn
摘要地震数据采集过程中, 由于采集成本的制约, 炮点间距相对检波点间距大,
导致地震数据一致性弱, 影响自由表面多次波衰减与偏移成像的精度. 较大的炮点间距使得共 …

Missing shots and near-offset reconstruction of marine seismic data with towered streamers via self-supervised deep learning

B Wang, D Han, J Li - IEEE Transactions on Geoscience and …, 2022 - ieeexplore.ieee.org
Marine seismic data with towered streamers have played an important role in marine
exploration. However, the distance between adjacent sources and the distance between …

Near offset reconstruction for marine seismic data using a convolutional neural network

OR Huff, VS Thorkildsen, TL Greiner… - Geophysical …, 2024 - Wiley Online Library
Marine seismic data is often missing near offset information due to separation between the
source and receiver cables. To solve this problem, a convolutional neural network is trained …