题名 | Unsupervised Seismic Data Random Noise Attenuation Method Based on Improved Blind Spot Strategy |
作者 | |
DOI | |
发表日期 | 2023
|
会议名称 | IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
|
ISSN | 2153-6996
|
ISBN | 979-8-3503-3174-5
|
会议录名称 | |
卷号 | 2023-July
|
页码 | 6073-6076
|
会议日期 | 16-21 July 2023
|
会议地点 | Pasadena, CA, USA
|
出版地 | 345 E 47TH ST, NEW YORK, NY 10017 USA
|
出版者 | |
摘要 | Noise suppression is crucial for seismic data processing and interpretation. Both the supervised and self-supervised methods need to construct training data pairs, which is challenging for practical implementations. In this research, we propose an unsupervised denoising framework based on improved blind spot strategy, which operates directly on single noisy seismic data. Firstly, a global masker is introduced to mask the noisy data to obtain two masked data and input them into the denoising network, and then utilize the mask mapper to integrate all blind spots onto the same channel. Secondly, original noisy data is incorporated into the network training process to avoid information loss. Finally, a hybrid loss function with orthogonal convolution regularization constraint is adopted to further improve the performance of the network. Synthetic and field seismic data experiments show that the proposed method can make good balance between noise suppression and valid signals preservation. |
关键词 | |
学校署名 | 其他
|
语种 | 英语
|
相关链接 | [IEEE记录] |
收录类别 | |
资助项目 | Natural Science Basic Research Program of Shaanxi[2023-JC-YB-269]
|
WOS研究方向 | Geology
; Instruments & Instrumentation
; Remote Sensing
|
WOS类目 | Geosciences, Multidisciplinary
; Instruments & Instrumentation
; Remote Sensing
|
WOS记录号 | WOS:001098971606044
|
EI入藏号 | 20234915141789
|
来源库 | IEEE
|
全文链接 | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10283322 |
引用统计 | |
成果类型 | 会议论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/609956 |
专题 | 南方科技大学 |
作者单位 | 1.School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China 2.Guangdong Provincial Key Laboratory of Geophysical High-Resolution Imaging Technology, Southern University of Science and Technology, Shenzhen, China |
推荐引用方式 GB/T 7714 |
Jing Wang,Bangyu Wu,Hui Yang. Unsupervised Seismic Data Random Noise Attenuation Method Based on Improved Blind Spot Strategy[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023:6073-6076.
|
条目包含的文件 | 条目无相关文件。 |
|
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论