中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地质与地球物理研究所
  3. 中国科学院地质与地球物理研究所
  4. 中国科学院油气资源研究重点实验室
Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN

文献类型：期刊论文

作者Li, Wenda1,2; Wu, Tianqi1; Liu, Hong1,2
刊名REMOTE SENSING
出版日期2022-10-01
卷号14期号:20页码:15
关键词random noise attention noise level structure-preserving denoising
DOI10.3390/rs14205240
英文摘要The noise attenuation of seismic data is an indispensable part of seismic data processing, directly impacting the following inversion and imaging. This paper focuses on two bottlenecks in the AI-based denoising method of seismic data: the destruction of structural information of seismic data and the inferior generalizability. We propose a flexible attention-CNN (FACNN) and realized the denoising work of seismic data. This paper's main work and advantages were concentrated on the following three aspects: (i) We propose attention gates (AGs), which progressively suppressed features in irrelevant background parts and improved the denoising performance. (ii) We added a noise level map M as an additional channel, making a single CNN model expected to inherit the flexibility of handling noise models with different parameters, even spatially variant noises. (iii) We propose a mixed loss function based on MS_SSIM to improve the performance of FACNN further. Adding the noise level map can improve the network's generalization ability, and adding the attention structure with the mixed loss function can better protect the structural information of the seismic data. The numerical tests showed that our method has better generalization and can better protect the details of seismic events.
WOS关键词LOW-FREQUENCY NOISE ; TRANSFORM ; SUPPRESSION ; RECONSTRUCTION ; PREDICTION ; REDUCTION
资助项目National Engineering Laboratory for Offshore Oil Exploration Opening Funds
WOS研究方向Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000873498800001
出版者MDPI
资助机构National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds ; National Engineering Laboratory for Offshore Oil Exploration Opening Funds
源URL[http://ir.iggcas.ac.cn/handle/132A11/107756]  
专题地质与地球物理研究所_中国科学院油气资源研究重点实验室
通讯作者Wu, Tianqi
作者单位1.Chinese Acad Sci, Inst Geol & Geophys, Beijing 100864, Peoples R China
2.Univ Chinese Acad Sci, Natl Engn Lab Offshore Oil Explorat, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Li, Wenda,Wu, Tianqi,Liu, Hong. Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN[J]. REMOTE SENSING,2022,14(20):15.
APA Li, Wenda,Wu, Tianqi,&Liu, Hong.(2022).Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN.REMOTE SENSING,14(20),15.
MLA Li, Wenda,et al."Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN".REMOTE SENSING 14.20(2022):15.

入库方式： OAI收割

来源：地质与地球物理研究所

浏览0
下载0
收藏0
其他版本

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。