SEG Technical Program Expanded Abstracts 2018最新文献_第5页

Distributed acoustic sensing (DAS) field trials for near-surface geotechnical properties, earthquake seismology, and mine monitoring 分布式声传感(DAS)近地表岩土特性、地震地震学和矿山监测的现场试验

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2997833.1

Herbert Wang, D. Fratta, N. Lord, Xiangfang Zeng, T. Coleman

引用次数: 5

2D-seismic random-noise attenuation by self-pace nonnegative dictionary learning 基于自步进非负字典学习的二维地震随机噪声衰减

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2997442.1

Yang Yang, Jinghuai Gao, Guowei Zhang, Xiangxiang Zhu

引用次数: 0

A time-domain electromagnetic survey of Wainui Valley, Banks Peninsula: Equivalence, sensitivity, local geological constraints, and groundwater resource implications 班克斯半岛瓦努伊河谷的时域电磁测量:等效性、敏感性、局部地质约束和地下水资源影响

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2965139.1

D. Nobes

引用次数: 1

Velocity-independent Marchenko method in time- and depth-imaging domains 时间和深度成像域的速度无关马尔琴科方法

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2992237.1

Y. Sripanich, I. Vasconcelos, K. Wapenaar, J. Trampert

{"title":"Velocity-independent Marchenko method in time- and depth-imaging domains","authors":"Y. Sripanich, I. Vasconcelos, K. Wapenaar, J. Trampert","doi":"10.1190/SEGAM2018-2992237.1","DOIUrl":"https://doi.org/10.1190/SEGAM2018-2992237.1","url":null,"abstract":"The Marchenko method represents a constructive technique to obtain Green’s functions between the acquisition surface and any arbitrary point in the medium. The process generally involves solving an inversion starting with a direct-wave Green’s function from the desired subsurface position, which is typically obtained using an approximate velocity model. In this study, we first propose to formulate the Marchenko method in the time-imaging domain. We recognize that the traveltime of the direct-wave Green’s function is related to the Cheop’s traveltime pyramid commonly used in time-domain processing and can be readily obtained from the local slopes of the common-midpoint (CMP) gathers. This observation allows us to substitute the need for a prior velocity model with the data-driven slope estimation process. Moreover, we show that working in the time-imaging domain allows for the specification of the desired subsurface position in terms of vertical time, which is connected to the Cartesian depth position via the timeto-depth conversion. Our results suggest that the prior velocity model is only required when specifying the position in depth but this requirement can be circumvented by making use of the time-imaging domain and its usual assumptions. Provided that those assumptions are satisfied, the estimated Green’s functions from the proposed method have comparable quality to those obtained with the knowledge of a prior velocity model.","PeriodicalId":158800,"journal":{"name":"SEG Technical Program Expanded Abstracts 2018","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124668118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Automated interpretation of top and base salt using deep-convolutional networks 使用深度卷积网络自动解释顶盐和底盐

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2996306.1

O. Gramstad, M. Nickel

引用次数: 23

Including internal multiples in joint migration inversion and redatuming of North Sea field data 包括联合迁移反演和北海油田资料重新恢复的内部倍数

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2998168.1

A. Garg, D. Verschuur

引用次数: 0

Learning to label seismic structures with deconvolution networks and weak labels 学习用反卷积网络和弱标记标记地震结构

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/segam2018-2997865.1

Yazeed Alaudah, Shan Gao, G. AlRegib

{"title":"Learning to label seismic structures with deconvolution networks and weak labels","authors":"Yazeed Alaudah, Shan Gao, G. AlRegib","doi":"10.1190/segam2018-2997865.1","DOIUrl":"https://doi.org/10.1190/segam2018-2997865.1","url":null,"abstract":"Recently, there has been increasing interest in using deep learning techniques for various seismic interpretation tasks. However, unlike shallow machine learning models, deep learning models are often far more complex and can have hundreds of millions of free parameters. This not only means that large amounts of computational resources are needed to train these models, but more critically, they require vast amounts of labeled training data as well. In this work, we show how automatically-generated weak labels can be effectively used to overcome this problem and train powerful deep learning models for labeling seismic structures in large seismic volumes. To achieve this, we automatically generate thousands of weak labels and use them to train a deconvolutional network for labeling fault, salt dome, and chaotic regions within the Netherlands F3 block. Furthermore, we show how modifying the loss function to take into account the weak training labels helps reduce false positives in the labeling results. The benefit of this work is that it enables the effective training and deployment of deep learning models to various seismic interpretation tasks without requiring any manual labeling effort. We show excellent results on the Netherlands F3 block, and show how our model outperforms other baseline models.","PeriodicalId":158800,"journal":{"name":"SEG Technical Program Expanded Abstracts 2018","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126995184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 25

Reducing artifacts of elastic reverse time migration with de-primary 减少弹性逆时偏移的伪影

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2992968.1

Yang Zhao, H. Zhang, T. Fei, Jidong Yang, Hejun Zhu

引用次数: 0

Magnetotelluric imaging for exploration in fold-and-thrust belt settings: A feasibility and case study 大地电磁成像在褶皱冲断带勘探中的应用:可行性与实例研究

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2995134.1

R. Streich, Akshat Abhishek

引用次数: 0

Intersectional approaches to counter harassment and discrimination in geophysics 在地球物理学中对抗骚扰和歧视的交叉方法

SEG Technical Program Expanded Abstracts 2018 Pub Date : 2018-08-27 DOI: 10.1190/SEGAM2018-2998379.1

A. Mattheis, B. Schneider

引用次数: 1