Unsupervised seismic random noise attenuation by a recursive deep image prior

计算机科学 噪音(视频) 降噪 趋同(经济学) 算法 阈值 信号(编程语言) 人工智能 模式识别(心理学) 图像(数学) 经济增长 经济 程序设计语言
作者
Yun Zhang,Benfeng Wang
出处
期刊:Geophysics [Society of Exploration Geophysicists]
卷期号:88 (6): V473-V485 被引量:2
标识
DOI:10.1190/geo2022-0612.1
摘要

The presence of random noise in field data significantly reduces the precision of subsequent seismic processing steps. As a result, random noise suppression is essential to improve the quality of field data. Because most traditional algorithms characterize seismic data linearly, the denoising accuracy is still open to be improved. As an unsupervised deep-learning method, the deep image prior (DIP) algorithm can characterize seismic data nonlinearly. The DIP uses randomly generated noise as input and noisy seismic data as desired output for random noise attenuation over several rounds of training epochs. However, determining the optimal training epoch for obtaining the final denoised result of unlabeled noisy data remains a challenge. To terminate the DIP training in time and obtain the denoised result, we design an improved quality control criterion (IQCC) based on adjacent estimations of seismic signal. To further improve the denoising accuracy, a recursive strategy is developed that uses the previous desired output as the new input and the previous denoised result as the new desired output. To obtain the optimal denoised results using the suggested recursive algorithm, a convergence condition also is established. Numerous examples of synthetic prestack and poststack data demonstrate the effectiveness of the designed IQCC and our recursive strategy with a convergence condition in protecting the effective signal, especially when compared with the curvelet thresholding algorithm and the original DIP. Furthermore, the denoising accuracy is on par with that of the supervised learning algorithm, demonstrating the adaptability of our recursive DIP under the convergence condition. Its superiority is further supported by field poststack seismic data processing, which uses the local similarity for performance assessments.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Sherlock完成签到,获得积分10
刚刚
荔枝味完成签到,获得积分20
刚刚
感动如音完成签到 ,获得积分10
1秒前
不想看文献完成签到 ,获得积分10
1秒前
Maestro_S的应助被晚风采纳,获得10
1秒前
Lczhou完成签到,获得积分10
1秒前
3秒前
无情愫的应助被WM采纳,获得10
3秒前
DW的应助被zhouqian采纳,获得10
3秒前
zhenzhen完成签到,获得积分10
4秒前
lilili发布了新的文献求助10
4秒前
一行发布了新的文献求助10
4秒前
Nole的应助被15735802374采纳,获得10
5秒前
生性不爱说话完成签到,获得积分10
5秒前
5秒前
6秒前
dumeng发布了新的文献求助20
9秒前
花海发布了新的文献求助10
9秒前
9秒前
9秒前
10秒前
10秒前
乐空思的应助被zcl采纳,获得20
10秒前
SciGPT的应助被谨慎的秋烟采纳,获得30
11秒前
123发布了新的文献求助10
13秒前
脑洞疼的应助被包语梦采纳,获得10
14秒前
molihuakai的应助被Zzz采纳,获得10
14秒前
14秒前
ghw发布了新的文献求助10
14秒前
16秒前
陈婉鸿完成签到,获得积分10
16秒前
17秒前
wanci的应助被Monarch采纳,获得10
17秒前
打打的应助被晴朗采纳,获得10
18秒前
东都哈士奇完成签到,获得积分10
18秒前
19秒前
19秒前
19秒前
19秒前
田様的应助被归宁采纳,获得10
20秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8172327
求助须知:如何正确求助?哪些是违规求助? 9564990
关于积分的说明 21777687
捐赠科研通 7763968
什么是DOI,文献DOI怎么找? 3431223
关于科研通互助平台的介绍 2555098
邀请新用户注册赠送积分活动 2476246