{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:17:00Z","timestamp":1775870220806,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T00:00:00Z","timestamp":1676332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Basic Research Program of Shaanxi","award":["2023-JC-YB-269"],"award-info":[{"award-number":["2023-JC-YB-269"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Seismic fault structures are important for the detection and exploitation of hydrocarbon resources. Due to their development and popularity in the geophysical community, deep-learning-based fault detection methods have been proposed and achieved SOTA results. Due to the efficiency and benefits of full spatial information extraction, 3D convolutional neural networks (CNNs) are used widely to directly detect faults on seismic data volumes. However, using 3D data for training requires expensive computational resources and can be limited by hardware facilities. Although 2D CNN methods are less computationally intensive, they lead to the loss of correlation between seismic slices. To mitigate the aforementioned problems, we propose to predict a 2D fault section using multiple neighboring seismic profiles, that is, 2.5D fault detection. In CNNs, convolution layers mainly extract local information and pooling layers may disrupt the edge features in seismic data, which tend to cause fault discontinuities. To this end, we incorporate the Transformer module in U-net for feature extraction to enhance prediction continuity. To reduce the data discrepancies between synthetic and different real seismic datasets, we apply a seismic data standardization workflow to improve the prediction stability on real datasets. Netherlands F3 real data tests show that, when training on synthetic data labels, the proposed 2.5D Transformer U-net-based method predicts more subtle faults and faults with higher spatial continuity than the baseline full 3D U-net model.<\/jats:p>","DOI":"10.3390\/rs15041039","type":"journal-article","created":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T01:38:18Z","timestamp":1676425098000},"page":"1039","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Fault Detection via 2.5D Transformer U-Net with Seismic Data Pre-Processing"],"prefix":"10.3390","volume":"15","author":[{"given":"Zhanxin","family":"Tang","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-9071","authenticated-orcid":false,"given":"Bangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"given":"Weihua","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"given":"Debo","family":"Ma","sequence":"additional","affiliation":[{"name":"Research Institute of Petroleum Exploration & Development, PetroChina, Beijing 100083, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5695","DOI":"10.1029\/1999JB900351","article-title":"Global Positioning System constraints on plate kinematics and dynamics in the eastern Mediterranean and Caucasus","volume":"105","author":"McClusky","year":"2000","journal-title":"J. Geophys. Res."},{"key":"ref_2","first-page":"34","article-title":"Velocity and deformation fields in the North Aegean domain, Greece, and implications for fault kinematics, derived from GPS data 1993\u20132009","volume":"597\u2013598","author":"Geiger","year":"2013","journal-title":"Tectonophysics"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Lazos, I., Papanikolaou, I., Sboras, S., Foumelis, M., and Pikridas, C. (2022). Geodetic Upper Crust Deformation Based on Primary GNSS and INSAR Data in the Strymon Basin, Northern Greece\u2014Correlation with Active Faults. Appl. Sci., 12.","DOI":"10.3390\/app12189391"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2003JB002830","article-title":"New constraints on the active tectonic deformation of the Aegean","volume":"109","author":"Nyst","year":"2004","journal-title":"J. Geophys. Res. B Solid Earth"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1190\/1.1437077","article-title":"3-D seismic discontinuity for faults and stratigraphic features: The coherence cube","volume":"14","author":"Bahorich","year":"1995","journal-title":"Lead. Edge"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1190\/1.1444415","article-title":"3-D seismic attributes using a semblance-based coherency algorithm","volume":"63","author":"Marfurt","year":"1998","journal-title":"Geophysics"},{"key":"ref_7","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"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1007\/s10712-021-09670-4","article-title":"Seismic coherence for discontinuity interpretation","volume":"42","author":"Li","year":"2021","journal-title":"Surv. Geophys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"O97","DOI":"10.1190\/geo2017-0666.1","article-title":"Seismic fault detection with convolutional neural network","volume":"83","author":"Xiong","year":"2018","journal-title":"Geophysics"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhao, T., and Mukhopadhyay, P. (2018, January 16). A fault detection workflow using deep learning and image processing. Proceedings of the 2018 SEG International Exposition and Annual Meeting, Anaheim, CA, USA.","DOI":"10.1190\/segam2018-2997005.1"},{"key":"ref_11","first-page":"1","article-title":"3D convolutional neural networks for fault interpretation","volume":"Volume 2018","author":"Guitton","year":"2018","journal-title":"Proceedings of the 80th EAGE Conference and Exhibition"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"IM35","DOI":"10.1190\/geo2018-0646.1","article-title":"FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation","volume":"84","author":"Wu","year":"2019","journal-title":"Geophysics"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104776","DOI":"10.1016\/j.cageo.2021.104776","article-title":"Deep convolutional neural network for automatic fault recognition from 3D seismic datasets","volume":"153","author":"An","year":"2021","journal-title":"Comput. Geosci."},{"key":"ref_14","first-page":"1","article-title":"Distilling knowledge from an ensemble of convolutional neural networks for seismic fault detection","volume":"19","author":"Wang","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dou, Y., Li, K., Zhu, J., Li, T., Tan, S., and Huang, Z. (2021). Efficient training of 3d seismic image fault segmentation network under sparse labels by weakening anomaly annotation. arXiv.","DOI":"10.1109\/TGRS.2022.3196810"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"SC17","DOI":"10.1190\/INT-2021-0137.1","article-title":"Machine-learning assisted interpretation: Integrated fault prediction and extraction case study from the Groningen gas field, Netherlands","volume":"10","author":"Smith","year":"2022","journal-title":"Interpretation"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"IM111","DOI":"10.1190\/geo2021-0805.1","article-title":"Automatic geologic fault identification from seismic data using 2.5 D channel attention U-net","volume":"87","author":"Lin","year":"2022","journal-title":"Geophysics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/LGRS.2018.2875836","article-title":"Seismic fault detection using convolutional neural networks trained on synthetic poststacked amplitude maps","volume":"16","author":"Pochet","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","first-page":"1","article-title":"Seismic attribute-guided automatic fault prediction by deep learning","volume":"Volume 2020","author":"Jiang","year":"2020","journal-title":"Proceedings of the EAGE 2020 Annual Conference Exhibition"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"104968","DOI":"10.1016\/j.cageo.2021.104968","article-title":"Seismic fault detection using convolutional neural networks with focal loss","volume":"158","author":"Wei","year":"2022","journal-title":"Comput. Geosci."},{"key":"ref_21","unstructured":"Wang, E., Amaru, M., Jayr, S., and Payne, B. (2021). First International Meeting for Applied Geoscience & Energy, Society of Exploration Geophysicists."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"N13","DOI":"10.1190\/geo2020-0945.1","article-title":"Automatic fault detection on seismic images using a multiscale attention convolutional neural network","volume":"87","author":"Gao","year":"2022","journal-title":"Geophysics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3228927","article-title":"Seismic impedance inversion based on residual attention network","volume":"60","author":"Wu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3040273","article-title":"Attention and hybrid loss guided deep learning for consecutively missing seismic data reconstruction","volume":"60","author":"Yu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","first-page":"1","article-title":"Deep learning prior model for unsupervised seismic data random noise attenuation","volume":"19","author":"Qiu","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1016\/j.petsci.2022.01.013","article-title":"A comparison of deep learning methods for seismic impedance inversion","volume":"19","author":"Zhang","year":"2022","journal-title":"Pet. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.petsci.2021.09.038","article-title":"Seismic impedance inversion based on cycle-consistent generative adversarial network","volume":"19","author":"Wang","year":"2022","journal-title":"Pet. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1016\/j.petsci.2022.02.008","article-title":"Predicting gas-bearing distribution using DNN based on multi-component seismic data: Quality evaluation using structural and fracture factors","volume":"19","author":"Zhang","year":"2022","journal-title":"Pet. Sci."},{"key":"ref_29","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_30","first-page":"1","article-title":"MD Loss: Efficient Training of 3-D Seismic Fault Segmentation Network Under Sparse Labels by Weakening Anomaly Annotation","volume":"60","author":"Dou","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Stephen, L., and Guo, B. (2021, January 12\u201313). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Virtual.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_33","unstructured":"Guarido, M., Wozniakowska, P., Emery, D.J., Lume, M., Trad, D.O., and Innanen, K.A. (2021). First International Meeting for Applied Geoscience Energy, Society of Exploration Geophysicists."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"IM101","DOI":"10.1190\/geo2021-0474.1","article-title":"Automated fault detection in the Arabian Basin","volume":"87","author":"Alohali","year":"2022","journal-title":"Geophysics"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1111\/1365-2478.13097","article-title":"Learning from unlabelled real seismic data: Fault detection based on transfer learning","volume":"69","author":"Zhou","year":"2021","journal-title":"Geophys. Prospect."},{"key":"ref_36","unstructured":"Pham, N., and Fomel, S. (2022). Second International Meeting for Applied Geoscience Energy, American Association of Petroleum Geologists."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yan, Z., Jing, J., Gu, H., and Li, H. (2023). Generating Paired Seismic Training Data with Cycle-Consistent Adversarial Networks. Remote Sens., 15.","DOI":"10.3390\/rs15010265"},{"key":"ref_38","first-page":"1JF-Y3","article-title":"Fault detection using a CNN trained with PSF-Convolution-based samples","volume":"88","author":"Jing","year":"2022","journal-title":"Geophysics"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Xie, S., and Tu, Z. (2015, January 7\u201313). Holistically-nested edge detection. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"V389","DOI":"10.1190\/geo2020-0017.1","article-title":"Deep learning spectral enhancement considering features of seismic field data","volume":"86","author":"Choi","year":"2021","journal-title":"Geophysics"},{"key":"ref_41","first-page":"1","article-title":"Disentangling Noise Patterns from Seismic Images: Noise Reduction and Style Transfer","volume":"60","author":"Du","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yang, Y., and Soatto, S. (2020, January 13\u201319). Fda: Fourier domain adaptation for semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B.V.K., and Wang, J. (2018, January 8\u201314). Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., and Ispir, M. (2016, January 15). Wide & deep learning for recommender systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, New York, NY, USA.","DOI":"10.1145\/2988450.2988454"},{"key":"ref_45","first-page":"1530","article-title":"Variational inference with normalizing flows. In International Conference on Machine Learning","volume":"37","author":"Rezende","year":"2015","journal-title":"PMLR"},{"key":"ref_46","first-page":"1","article-title":"Attention-Based 3-D Seismic Fault Segmentation Training by a Few 2-D Slice Labels","volume":"60","author":"Dou","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"IM143","DOI":"10.1190\/geo2020-0905.1","article-title":"3D Fault Detection: Using human reasoning to improve performance of convolutional neural networks","volume":"87","author":"Zhu","year":"2022","journal-title":"Geophysics"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/1039\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:35:26Z","timestamp":1760121326000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/1039"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,14]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["rs15041039"],"URL":"https:\/\/doi.org\/10.3390\/rs15041039","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,14]]}}}