{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:04:42Z","timestamp":1760148282884,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T00:00:00Z","timestamp":1681516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Science and Engineering Research Council of Canada (NSERC)","doi-asserted-by":"publisher","award":["CRDPJ 543578-19"],"award-info":[{"award-number":["CRDPJ 543578-19"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Scholarship Council (CSC) Doctoral program","award":["CRDPJ 543578-19"],"award-info":[{"award-number":["CRDPJ 543578-19"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Reverse-time migration (RTM) has the advantage that it can handle steep dipping structures and offer high-resolution images of the complex subsurface. Nevertheless, there are some limitations to the chosen initial model, aperture illumination and computation efficiency. RTM has a strong dependency on the initial velocity model. The RTM result image will perform poorly if the input background velocity model is inaccurate. One solution is to apply least-squares reverse-time migration (LSRTM), which updates the reflectivity and suppresses artifacts through iterations. However, the output resolution still depends heavily on the input and accuracy of the velocity model, even more than for standard RTM. For the aperture limitation, RTM with multiple reflections (RTMM) is instrumental in improving the illumination but will generate crosstalks because of the interference between different orders of multiples. We proposed a method based on a convolutional neural network (CNN) that behaves like a filter applying the inverse of the Hessian. This approach can learn patterns representing the relation between the reflectivity obtained through RTMM and the true reflectivity obtained from velocity models through a residual U-Net with an identity mapping. Once trained, this neural network can be used to enhance the quality of RTMM images. Numerical experiments show that RTMM-CNN can recover major structures and thin layers with higher resolution and improved accuracy compared with the RTM-CNN method. Additionally, the proposed method demonstrates a significant degree of generalizability across diverse geology models, encompassing complex thin layers, salt bodies, folds, and faults. Moreover, The computational efficiency of the method is demonstrated by its lower computational cost compared with LSRTM.<\/jats:p>","DOI":"10.3390\/s23084012","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T02:26:02Z","timestamp":1681698362000},"page":"4012","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Convolutional Neural-Network-Based Reverse-Time Migration with Multiple Reflections"],"prefix":"10.3390","volume":"23","author":[{"given":"Shang","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Geoscience, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9726-789X","authenticated-orcid":false,"given":"Daniel","family":"Trad","sequence":"additional","affiliation":[{"name":"Department of Geoscience, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1190\/1.1441434","article-title":"Reverse time migration","volume":"48","author":"Baysal","year":"1983","journal-title":"Geophysics"},{"key":"ref_2","unstructured":"Whitmore, N.D. (1983). SEG Technical Program Expanded Abstracts 1983, Society of Exploration Geophysicists."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1111\/j.1365-2478.1983.tb01060.x","article-title":"Migration by extrapolation of time-dependent boundary values","volume":"31","author":"McMechan","year":"1983","journal-title":"Geophys. Prospect."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1190\/1.1441693","article-title":"Principle of reverse-time migration","volume":"49","author":"Levin","year":"1984","journal-title":"Geophysics"},{"key":"ref_5","unstructured":"Dong, S., Cai, J., Guo, M., Suh, S., Zhang, Z., Wang, B., and Li, Z. (2012). SEG Technical Program Expanded Abstracts 2012, Society of Exploration Geophysicists."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1111\/j.1365-2478.2011.01041.x","article-title":"Efficient least-squares imaging with sparsity promotion and compressive sensing","volume":"60","author":"Herrmann","year":"2012","journal-title":"Geophys. Prospect."},{"key":"ref_7","unstructured":"Herrmann, F.J., Siahkoohi, A., and Rizzuti, G. (2019). Learned imaging with constraints and uncertainty quantification. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jge\/gxab015","article-title":"Least-squares reverse-time migration with sparsity constraints","volume":"18","author":"Wu","year":"2021","journal-title":"J. Geophys. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1542","DOI":"10.1016\/j.petsci.2022.03.004","article-title":"Huber inversion-based reverse-time migration with de-primary imaging condition and curvelet-domain sparse constraint","volume":"19","author":"Wu","year":"2022","journal-title":"Pet. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"S151","DOI":"10.1190\/geo2021-0183.1","article-title":"Least-squares reverse time migration with a multiplicative Cauchy constraint","volume":"87","author":"Yao","year":"2022","journal-title":"Geophysics"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/gji\/ggv020","article-title":"Fast imaging with surface-related multiples by sparse inversion","volume":"201","author":"Tu","year":"2015","journal-title":"Geophys. J. Int."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"WB209","DOI":"10.1190\/geo2010-0312.1","article-title":"Reverse time migration of multiples for subsalt imaging","volume":"76","author":"Liu","year":"2011","journal-title":"Geophysics"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"S19","DOI":"10.1190\/geo2015-0710.1","article-title":"Reverse time migration of multiples based on different-order multiple separation","volume":"82","author":"Li","year":"2017","journal-title":"Geophysics"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"S307","DOI":"10.1190\/geo2016-0354.1","article-title":"Reverse time migration of multiples: Reducing migration artifacts using the wavefield decomposition imaging condition","volume":"82","author":"Wang","year":"2017","journal-title":"Geophysics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1111\/1365-2478.12851","article-title":"Reverse time migration using water-bottom-related multiples","volume":"68","author":"Zhang","year":"2020","journal-title":"Geophys. Prospect."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jia, Z., Lu, W., Zhang, M., and Miao, Y. (2018, January 17\u201319). Separating ground-roll from land seismic record via convolutional neural network. Proceedings of the SEG 2018 Workshop: SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, Beijing, China.","DOI":"10.1190\/AIML2018-16.1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1111\/1365-2478.12985","article-title":"Seismic ground-roll noise attenuation using deep learning","volume":"68","author":"Kaur","year":"2020","journal-title":"Geophys. Prospect."},{"key":"ref_18","unstructured":"Richardson, A. (2018). Seismic full-waveform inversion using deep learning tools and techniques. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"R87","DOI":"10.1190\/geo2019-0138.1","article-title":"A theory-guided deep-learning formulation and optimization of seismic waveform inversion","volume":"85","author":"Sun","year":"2020","journal-title":"Geophysics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"R303","DOI":"10.1190\/geo2020-0312.1","article-title":"Physics-guided deep learning for seismic inversion with hybrid training and uncertainty analysis","volume":"86","author":"Sun","year":"2021","journal-title":"Geophysics"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Vantassel, J.P., Kumar, K., and Cox, B.R. (2021). Using Convolutional Neural Networks to Develop Starting Models for 2D Full Waveform Inversion. arXiv.","DOI":"10.1093\/gji\/ggac179"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"A47","DOI":"10.1190\/geo2019-0056.1","article-title":"The importance of transfer learning in seismic modeling and imaging","volume":"84","author":"Siahkoohi","year":"2019","journal-title":"Geophysics"},{"key":"ref_23","unstructured":"Siahkoohi, A. (2022). Deep Generative Models for Solving Geophysical Inverse Problems. [Ph.D Thesis, Georgia Institute of Technology]."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"WA241","DOI":"10.1190\/geo2019-0412.1","article-title":"Deep convolutional neural network and sparse least-squares migration","volume":"85","author":"Liu","year":"2020","journal-title":"Geophysics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_26","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wu, D., Li, Q., Zhang, X., Li, J., and Wu, H. (2018, January 14\u201319). Least-squares reverse time migration with adaptive moment estimation method. Proceedings of the 2018 SEG International Exposition and Annual Meeting, Anaheim, CA, USA.","DOI":"10.1190\/segam2018-2996668.1"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"WA173","DOI":"10.1190\/geo2019-0315.1","article-title":"Improving the resolution of migrated images by approximating the inverse Hessian using deep learning","volume":"85","author":"Kaur","year":"2020","journal-title":"Geophysics"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"S269","DOI":"10.1190\/geo2019-0250.1","article-title":"Improving the image quality of elastic reverse-time migration in the dip-angle domain using deep learning","volume":"85","author":"Lu","year":"2020","journal-title":"Geophysics"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"S125","DOI":"10.1190\/geo2019-0707.1","article-title":"Minibatch least-squares reverse time migration in a deep-learning framework","volume":"86","author":"Vamaraju","year":"2021","journal-title":"Geophysics"},{"key":"ref_32","unstructured":"Torres, K., and Sacchi, M. (October, January 26). Deep learning based least-squares reverse-time migration. Proceedings of the First International Meeting for Applied Geoscience & Energy, Denver, CO, USA."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1190\/geo2021-0491.1","article-title":"Least-squares reverse time migration via deep learning-based updating operators","volume":"87","author":"Torres","year":"2022","journal-title":"Geophysics"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"104645","DOI":"10.1016\/j.jappgeo.2022.104645","article-title":"Deep-learning for accelerating prestack correlative least-squares reverse time migration","volume":"200","author":"Zhang","year":"2022","journal-title":"J. Appl. Geophys."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_36","unstructured":"Schuster, G.T. (2002). Joint migration of primaries and multiples by a semi-natural Green\u2019s functions. Utah Tomogr. Model. Consort. Annu. Rep., 141\u2013164."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Schuster, G.T. (2003, January 2\u20135). Imaging the most bounce out of multiples. Proceedings of the 65th EAGE Conference & Exhibition. European Association of Geoscientists & Engineers, Stavanger, Norway.","DOI":"10.3997\/2214-4609.201405725"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.1365-2478.2006.00598.x","article-title":"Migration methods for imaging different-order multiples","volume":"55","author":"Jiang","year":"2007","journal-title":"Geophys. Prospect."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11\u201314). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1190\/1.1444517","article-title":"Least-squares migration of incomplete reflection data","volume":"64","author":"Nemeth","year":"1999","journal-title":"Geophysics"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1190\/1.1444984","article-title":"Poststack migration deconvolution","volume":"66","author":"Hu","year":"2001","journal-title":"Geophysics"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1190\/1.1778244","article-title":"Amplitude and kinematic corrections of migrated images for nonunitary imaging operators","volume":"69","author":"Guitton","year":"2004","journal-title":"Geophysics"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"S53","DOI":"10.1190\/1.2187783","article-title":"Prestack migration deconvolution","volume":"71","author":"Yu","year":"2006","journal-title":"Geophysics"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"WCA83","DOI":"10.1190\/1.3155162","article-title":"Fast least-squares migration with a deblurring filter","volume":"74","author":"Aoki","year":"2009","journal-title":"Geophysics"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1093\/jge\/gxz098","article-title":"Image domain least-squares migration with a Hessian matrix estimated by non-stationary matching filters","volume":"17","author":"Guo","year":"2020","journal-title":"J. Geophys. Eng."},{"key":"ref_46","unstructured":"Erhan, D., Courville, A., Bengio, Y., and Vincent, P. (2010, January 13\u201315). Why does unsupervised pre-training help deep learning?. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1109\/34.58871","article-title":"Neural network ensembles","volume":"12","author":"Hansen","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_48","unstructured":"Krogh, A., and Vedelsby, J. (December, January 28). Neural network ensembles, cross validation, and active learning. Proceedings of the 8th Annual Meeting Neural Information Processing Systems: Natural and Synthetic (NIPS94), Denver, CO, USA."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Zhou, Z.H. (2021). Machine Learning, Springer.","DOI":"10.1007\/978-981-15-1967-3"},{"key":"ref_50","unstructured":"Trad, D. (2022, January 20\u201322). GPU applications for modelling, imaging, inversion and machine learning. Proceedings of the Geoconvention 2022, Vitual."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7\u201313). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/4012\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:16:28Z","timestamp":1760123788000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/4012"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,15]]},"references-count":51,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23084012"],"URL":"https:\/\/doi.org\/10.3390\/s23084012","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,4,15]]}}}