Data-Driven Ringed Residual U-Net Scheme for Full Waveform Inversion

残余物 反演(地质) 波形 遥感 计算机科学 地质学 算法 电信 雷达 地震学 构造学
作者
Xingguo Huang,Cong Wang,Wenrui Ye,Stewart Alan Greenhalgh,Yue Li
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-15 被引量:8
标识
DOI:10.1109/tgrs.2024.3436688
摘要

Full waveform inversion (FWI) is a powerful means for accurately reconstructing subsurface velocity models at high resolution. Yet it is nevertheless a nonlinear and ill-posed problem. Physics-driven FWI methods employ gradient-based optimization algorithms to minimize the error between the observed seismic data and the synthetically generated seismic data. The solution may converge to a local rather than global minimum. The cycle-skipping problem occurs when the synthetic data exceed a half-wavelength shift relative to the observed data. FWI relies on an accurate initial velocity model to mitigate the cycle-skipping problem. Moreover, due to the increasing size and desired resolution of seismic data, FWI costs a great deal of computational time. To obviate these problems, we present a data-driven FWI scheme based on a deep learning architecture called U-Net. The network consists of the ringed residual unit, which integrates residual propagation and residual feedback. It beneficially achieves correspondence between the seismic data domain and the velocity model domain. The features of the shallow layers are connected with the deep layers by a skip connection to facilitate seismic data spatial information propagation and utilization. They improve inversion accuracy and make the network more generalizable and robust. We utilize the Society of Exploration Geophysicists (SEGs)/European Association of Geoscientists and Engineers (EAGE) overthrust and salt models to verify our proposed method’s impressive performance. The experimental results clearly demonstrate that the proposed method can produce high-quality velocity models. Compared with the conventional physics-informed FWI, it has advantages in both computational time and initial model dependence.
最长约 10秒,即可获得该文献文件

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
1秒前
六里桥发布了新的文献求助10
1秒前
1秒前
1秒前
2秒前
2秒前
文献乞讨者完成签到 ,获得积分10
2秒前
李爱国的应助被大胆的乐荷采纳,获得10
2秒前
还差发布了新的文献求助20
2秒前
科研通AI6.2的应助被阳光雨堂采纳,获得10
3秒前
Hello的应助被颖zi采纳,获得10
4秒前
baire发布了新的文献求助10
6秒前
瓦力完成签到,获得积分10
6秒前
7秒前
CodeCraft的应助被深情雅柔采纳,获得10
7秒前
7秒前
六里桥完成签到,获得积分10
9秒前
无语的映完成签到,获得积分10
9秒前
酷波er的应助被OSBORN采纳,获得10
9秒前
10秒前
orixero的应助被GUO采纳,获得10
10秒前
娇气的夜香完成签到,获得积分10
10秒前
10秒前
11秒前
yyychenn发布了新的文献求助10
11秒前
科目三的应助被Wyhyhy采纳,获得10
12秒前
科研通AI6.2的应助被youyou采纳,获得10
12秒前
英俊的铭的应助被慢羊羊采纳,获得10
12秒前
阱红豆发布了新的文献求助10
12秒前
13秒前
英姑的应助被光亮雨采纳,获得10
13秒前
Akim的应助被迷路手机采纳,获得10
14秒前
安详香旋发布了新的文献求助10
14秒前
14秒前
蓝天的应助被胡萝卜卜采纳,获得10
14秒前
Tuniverse_发布了新的文献求助10
16秒前
初海歌完成签到,获得积分10
16秒前
高高朋友完成签到,获得积分10
17秒前
17秒前
吃葡萄不吐葡萄皮的应助被xl采纳,获得10
17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
Markov Decision Processes and Reinforcement Learning 700
八旗制度の研究 600
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 8170866
求助须知:如何正确求助?哪些是违规求助? 9563691
关于积分的说明 21771699
捐赠科研通 7762353
什么是DOI,文献DOI怎么找? 3430767
关于科研通互助平台的介绍 2554622
邀请新用户注册赠送积分活动 2475597