{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T12:19:18Z","timestamp":1772021958496,"version":"3.50.1"},"reference-count":16,"publisher":"Society of Exploration Geophysicists","issue":"4","content-domain":{"domain":["library.seg.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Recently, the computation of seismic fault attribute that may be significant in seismic interpretation is that seismic fault detection is treated as an image segmentation problem using different deep-learning (DL) architectures. To do this, researchers have concentrated on applying cutting-edge DL architectures in computing seismic fault attributes. To explore the factors that may affect the accuracy of seismic fault attribute, we compare the computed fault probability using DL architectures under different scenarios. The designed scenarios aim to highlight the leading factors that may affect the accuracy and resolution of seismic image segmentation. The discussed factors include the dimension and size of training data, training data preparation, ensemble learning, and batch size in DL. The proposed comparisons are applied to one marine seismic survey from New Zealand and one land seismic survey from China. The results demonstrate that properly preparing training data is far more important than choosing a cutting-edge DL architecture in computing seismic fault attribute. We also propose a practical workflow that can include real seismic data and corresponding interpreted fault sticks in training data for a specific seismic survey.<\/jats:p>","DOI":"10.1190\/int-2022-0007.1","type":"journal-article","created":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T09:40:28Z","timestamp":1654422028000},"page":"T619-T636","update-policy":"https:\/\/doi.org\/10.1190\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Exploring factors affecting the performance of deep learning in seismic fault attribute computation"],"prefix":"10.1190","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7937-0826","authenticated-orcid":false,"given":"Bo","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Alabama 1 , Department of Geological Science, Tuscaloosa, Alabama, USA. bzhang33@ua.edu"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0772-9171","authenticated-orcid":false,"given":"Yitao","family":"Pu","sequence":"additional","affiliation":[{"name":"University of Alabama 1 , Department of Geological Science, Tuscaloosa, Alabama, USA. ypu@crimson.ua.edu"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3600-8341","authenticated-orcid":false,"given":"Zhaohui","family":"Xu","sequence":"additional","affiliation":[{"name":"China University of Petroleum (Beijing) 2 , College of Geosciences, Beijing, China. xuzhaohui@cup.edu.cn (corresponding author)"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2609-7408","authenticated-orcid":false,"given":"Naihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University 3 , School of Information and Communications Engineering, Xi\u2019an, China. naihao_liu@mail.xjtu.edu.cn"}]},{"given":"Shizhen","family":"Li","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University 4 , College of Artificial Intelligence, Xi\u2019an, China. 1176082342@qq.com"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2340-3622","authenticated-orcid":false,"given":"Fangyu","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology 5 , Ministry of Education, Engineering Research Center of Digital Community, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China and , Beijing Artificial Intelligence Institute, Beijing, China. fangyu.li@bjut.edu.cn"},{"name":"Beijing University of Technology 5 , Ministry of Education, Engineering Research Center of Digital Community, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China and , Beijing Artificial Intelligence Institute, Beijing, China. fangyu.li@bjut.edu.cn"}]}],"member":"186","published-online":{"date-parts":[[2022,8,8]]},"reference":[{"key":"2025120914010633600_r1","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1190\/tle36030208.1","article-title":"Automated fault detection without seismic processing","volume":"36","author":"Araya-Polo","year":"2017","journal-title":"The Leading Edge"},{"key":"2025120914010633600_r2","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","ISSN":"https:\/\/id.crossref.org\/issn\/0162-8828","issn-type":"print"},{"key":"2025120914010633600_r3","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1190\/1.1437077","article-title":"3D seismic discontinuity for faults and stratigraphic features: The coherence cube","volume":"14","author":"Bahorich","year":"1995","journal-title":"The Leading Edge"},{"key":"2025120914010633600_r4","doi-asserted-by":"crossref","unstructured":"Di\n              H.\n            \n            \n              Shafiq\n              M.\n            \n            \n              AlRegib\n              G.\n            \n          , 2018, Patch-level MLP classification for improved fault detection: 88th Annual International Meeting, SEG, Expanded Abstracts, 2211\u20132215, doi: http:\/\/dx.doi.org\/10.1190\/segam2018-2996921.1.","DOI":"10.1190\/segam2018-2996921.1"},{"key":"2025120914010633600_r5","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1190\/1.1444651","article-title":"Eigenstructure-based coherence computations as an aid to 3-D structural and stratigraphic mapping","volume":"64","author":"Gersztenkorn","year":"1999","journal-title":"Geophysics","ISSN":"https:\/\/id.crossref.org\/issn\/0016-8033","issn-type":"print"},{"key":"2025120914010633600_r7","doi-asserted-by":"crossref","unstructured":"He\n              K.\n            \n            \n              Zhang\n              X.\n            \n            \n              Ren\n              S.\n            \n            \n              Sun\n              J.\n            \n          , 2016, Deep residual learning for image recognition: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2025120914010633600_r8","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1190\/tle36030249.1","article-title":"A scalable deep learning platform for identifying geologic features from seismic attributes","volume":"36","author":"Huang","year":"2017","journal-title":"The Leading Edge"},{"key":"2025120914010633600_r9","first-page":"1","article-title":"Automatic fault delineation in 3D seismic images with deep learning: Data augmentation or ensemble learning?","volume":"60","author":"Li","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing","ISSN":"https:\/\/id.crossref.org\/issn\/0196-2892","issn-type":"print"},{"issue":"3","key":"2025120914010633600_r10","doi-asserted-by":"crossref","first-page":"SM25","DOI":"10.1190\/INT-2019-0173.1","article-title":"Common-azimuth seismic data fault analysis using residual U-net","volume":"8","author":"Liu","year":"2020","journal-title":"Interpretation"},{"key":"2025120914010633600_r11","doi-asserted-by":"crossref","unstructured":"Long\n              J.\n            \n            \n              Shelhamer\n              E.\n            \n            \n              Darrell\n              T.\n            \n          , 2015, Fully convolutional networks for semantic segmentation: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2025120914010633600_r12","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1190\/1.1444415","article-title":"3D seismic attributes using a semblance-based coherency algorithm","volume":"63","author":"Marfurt","year":"1998","journal-title":"Geophysics","ISSN":"https:\/\/id.crossref.org\/issn\/0016-8033","issn-type":"print"},{"issue":"4","key":"2025120914010633600_r13","doi-asserted-by":"crossref","first-page":"O57","DOI":"10.1190\/geo2016-0641.1","article-title":"A workflow to skeletonize faults and stratigraphic features","volume":"82","author":"Qi","year":"2017","journal-title":"Geophysics","ISSN":"https:\/\/id.crossref.org\/issn\/0016-8033","issn-type":"print"},{"key":"2025120914010633600_r14","doi-asserted-by":"crossref","unstructured":"Ronneberger\n              O.\n            \n            \n              Fischer\n              P.\n            \n            \n              Brox\n              T.\n            \n          , 2015, U-Net: Convolutional networks for biomedical image segmentation: International Conference on Medical Image Computing and Computer-Assisted Intervention, 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"2025120914010633600_r15","doi-asserted-by":"crossref","first-page":"WA27","DOI":"10.1190\/geo2019-0375.1","article-title":"Building realistic structure models to train convolutional neural networks for seismic structural interpretation","volume":"85","author":"Wu","year":"2020","journal-title":"Geophysics","ISSN":"https:\/\/id.crossref.org\/issn\/0016-8033","issn-type":"print"},{"key":"2025120914010633600_r16","doi-asserted-by":"crossref","unstructured":"Xie\n              S.\n            \n            \n              Tu\n              Z.\n            \n          , 2015, Holistically-nested edge detection: Proceedings of the IEEE International Conference on Computer Vision, 1395\u20131403.","DOI":"10.1109\/ICCV.2015.164"},{"issue":"5","key":"2025120914010633600_r17","doi-asserted-by":"crossref","first-page":"O97","DOI":"10.1190\/geo2017-0666.1","article-title":"Seismic fault detection with a convolutional neural network","volume":"83","author":"Xiong","year":"2018","journal-title":"Geophysics","ISSN":"https:\/\/id.crossref.org\/issn\/0016-8033","issn-type":"print"}],"container-title":["Interpretation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.geoscienceworld.org\/seg\/interpretation\/article-pdf\/10\/4\/T619\/5733003\/int-2022-0007.1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.geoscienceworld.org\/seg\/interpretation\/article-pdf\/10\/4\/T619\/5733003\/int-2022-0007.1.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:01:14Z","timestamp":1765306874000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.geoscienceworld.org\/interpretation\/article\/10\/4\/T619\/616137\/Exploring-factors-affecting-the-performance-of"},"secondary":[{"URL":"https:\/\/pubs.geoscienceworld.org\/interpretation\/article\/10\/4\/t619\/616137\/exploring-factors-affecting-the-performance-of","label":"geoscienceworld"}]},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,5]]},"references-count":16,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,11,1]]}},"URL":"https:\/\/doi.org\/10.1190\/int-2022-0007.1","relation":{},"ISSN":["2324-8858","2324-8866"],"issn-type":[{"value":"2324-8858","type":"print"},{"value":"2324-8866","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,5]]},"assertion":[{"value":"2022-01-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-14","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-05-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}