{"614070":{"#nid":"614070","#data":{"type":"news","title":"ML@GT Presents Eight Papers at SEG2018","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EMachine Learning Center at Georgia Tech\u003C\/strong\u003E Professor \u003Cstrong\u003EGhassan AlRegib\u003C\/strong\u003E led the way with six of eight Georgia Tech papers published at the \u003Ca href=\u0022https:\/\/seg.org\/Annual-Meeting-2018\u0022\u003ESociety of Exploration Geophysicists (SEG) 2018.\u003C\/a\u003E, Oct. 14-19 in Anaheim, Calif.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe conference is a premier conference for AlRegib and his colleagues at Georgia Tech\u0026rsquo;s \u003Ca href=\u0022http:\/\/cegp.ece.gatech.edu\/\u0022\u003ECenter for Energy and Geo Processing (CeGP).\u003C\/a\u003E\u0026nbsp;The conference featured more than 1,080 presentations, 22 postconvention workshops, and more.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Tech\u0026rsquo;s papers focused on the applications of signal processing and machine and deep learning in seismic processing and interpretation.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;SEG is a great opportunity to bring together machine learning and geophysics. It is a true testament of ML@GT\u0026rsquo;s collaborative spirit and machine learning\u0026rsquo;s ability to be implemented across a broad range of topics,\u0026rdquo; said AlRegib.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFor information on Georgia Tech\u0026rsquo;s presented papers please see below.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E1.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Towards Understanding Common Features Between Natural and Seismic Images\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: M. A. Shafiq, M. Prabushankar, H. Di, and G. AlRegib\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn this paper, the authors propose an unsupervised learning framework that aims at evaluating the applicability of the broad domain knowledge from natural images and videos in assisting seismic interpretation, such as seismic attributes, structural automation, and seismic image processing.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ERead More\u003C\/strong\u003E:\u0026nbsp;\u003Ca href=\u0022http:\/\/bit.ly\/2DfZEkj\u00a0\u0022\u003Ehttp:\/\/bit.ly\/2DfZEkj\u0026nbsp;\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E2.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Petrophysical Property Estimation from Seismic Data Using Recurrent Neural Networks\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: M. Alfarraj and G. AlRegib\u003C\/p\u003E\r\n\r\n\u003Cp\u003EReservoir characterization involves the estimation of petrophysical properties from well-log data and seismic data. Estimating such properties is a challenging task due to the non-linearity and heterogeneity of the subsurface. Researchers propose an algorithm for property estimation in seismic data using recurrent neural networks.\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003ERead More:\u003C\/strong\u003E\u0026nbsp;\u003Ca href=\u0022http:\/\/bit.ly\/2Durw4Z\u0022\u003Ehttp:\/\/bit.ly\/2Durw4Z\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E3.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Learning to Label Seismic Structures with Deconvolution Networks and Weak Labels\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors:\u003C\/strong\u003E Y. Alaudah, S. Gao, and G. AlRegib\u003C\/p\u003E\r\n\r\n\u003Cp\u003ERecently, 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. AlRegib and his co-authors 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.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ERead More:\u0026nbsp;\u003C\/strong\u003E\u003Ca href=\u0022http:\/\/bit.ly\/2DclAwk\u0022\u003Ehttp:\/\/bit.ly\/2DclAwk\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E4.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Real-time seismic-image interpretation via deconvolutional neural network\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: H. Di, Z. Wang, and G. AlRegib\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESeismic interpretation is now serving as a fundamental tool for depicting subsurface geology and assisting activities in various domains, such as environmental engineering and petroleum exploration. This study proposes implementing the deconvolutional neural network (DCNN) for the purpose of real-time seismic interpretation, so that all the important features in a seismic image can be identified and interpreted both accurately and simultaneously.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ERead More:\u0026nbsp;\u003C\/strong\u003E\u003Ca href=\u0022http:\/\/bit.ly\/2Oy9AHF\u0022\u003Ehttp:\/\/bit.ly\/2Oy9AHF\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E5.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Why using CNN for seismic interpretation? An investigation\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: H. Di, Z. Wang, and G. AlRegib\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThree-dimensional seismic interpretation plays a key role in robust hydrocarbon exploration and production of subsurface reservoirs. With the dramatic growing size of 3D seismic surveys, however, manually interpreting a seismic volume turns to be even more challenging. In this study, researchers first apply two most popular neural network frameworks, the multi-layer perceptron (MLP) network and the convolutional neural network (CNN), to the problem of seismic salt-body delineation and compare their performance. They then investigate two factors that contribute to the better performance of the CNN framework in understanding seismic signals and identifying the important seismic structures.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ERead More:\u0026nbsp;\u003C\/strong\u003E\u003Ca href=\u0022http:\/\/bit.ly\/2z0nSvY\u0022\u003Ehttp:\/\/bit.ly\/2z0nSvY\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E6.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Patch-level MLP classification for improved fault detection\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: H. Di, M. A. Shafiq, and G. AlRegib\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFault detection and interpretation have been one of the routine tools used for subsurface structure mapping and reservoir characterization from three-dimensional (3D) seismic data. With the recent developments in machine learning and big data analysis, this study proposes an innovative method for efficient seismic fault detection based on semi-supervised classification of multiple attribute patches through the popular multi-layer perceptron (MLP) technique.\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003ERead More:\u003C\/strong\u003E\u0026nbsp;\u003Ca href=\u0022http:\/\/bit.ly\/2FbnrUZ\u0022\u003Ehttp:\/\/bit.ly\/2FbnrUZ\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E7.\u0026nbsp;\u003Cstrong\u003ETitle\u003C\/strong\u003E: Automatic microseismic event detection using constant false alarm rate processing in time-frequency domain\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: A. Raj, J.H. McClellan, N. Iqbal, A.A Al-Shuhail, and S.I. Kaka\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDetecting and monitoring microseismic events using surface sensors in unknown noise scenarios and low signal-to-noise ratio conditions is a challenging problem. Researchers propose a scheme for reliable automatic detection of microseismic events based on 2D Constant False Alarm Rate (CFAR) processing in the time-frequency (TF) domain, along with an efficient 2D filtering implementation of the 2D CFAR algorithm.\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003ERead More:\u003C\/strong\u003E\u0026nbsp;\u003Ca href=\u0022http:\/\/bit.ly\/2JQONhH\u0022\u003Ehttp:\/\/bit.ly\/2JQONhH\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E8.\u0026nbsp;\u003Cstrong\u003ETitle:\u003C\/strong\u003E Sum-Rate Maximization for Wireless Seismic Data Acquisition Systems\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAuthors\u003C\/strong\u003E: A.Othman, W. Mesbah, N. Iqbal, S. Al-Dharrab, A. Muqaibel, and G. Stuber\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn this paper, the authors consider the problem of maximizing the information theoretic sum-rate in a wireless geo-seismic acquisition system.\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003ERead More:\u003C\/strong\u003E\u0026nbsp;\u003Ca href=\u0022http:\/\/bit.ly\/2Feb8Y7\u0022\u003Ehttp:\/\/bit.ly\/2Feb8Y7\u003C\/a\u003E\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"The Machine Learning Center at Georgia Tech recently had a strong showing at the Society of Exploration Geophysicists (SEG) 2018."}],"uid":"34773","created_gmt":"2018-11-09 17:18:07","changed_gmt":"2018-11-09 19:27:19","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2018-11-09T00:00:00-05:00","iso_date":"2018-11-09T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"614069":{"id":"614069","type":"image","title":"SEG 2018 was held Oct. 14-19 in Anaheim, Calif.","body":null,"created":"1541783873","gmt_created":"2018-11-09 17:17:53","changed":"1541783873","gmt_changed":"2018-11-09 17:17:53","alt":"","file":{"fid":"233776","name":"ong_SEG18.jpg","image_path":"\/sites\/default\/files\/images\/ong_SEG18.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/ong_SEG18.jpg","mime":"image\/jpeg","size":116799,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/ong_SEG18.jpg?itok=-WUyR63-"}}},"media_ids":["614069"],"groups":[{"id":"576481","name":"ML@GT"}],"categories":[],"keywords":[],"core_research_areas":[{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EAllie McFadden\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer\u003C\/p\u003E\r\n\r\n\u003Cp\u003Eallie.mcfadden@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}