{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T22:10:42Z","timestamp":1779228642600,"version":"3.51.4"},"reference-count":43,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41974154"],"award-info":[{"award-number":["41974154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["PRP\/open-2108"],"award-info":[{"award-number":["PRP\/open-2108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["33550000-22-ZC0613-0295"],"award-info":[{"award-number":["33550000-22-ZC0613-0295"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["202210491071"],"award-info":[{"award-number":["202210491071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of the State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Beijing","award":["41974154"],"award-info":[{"award-number":["41974154"]}]},{"name":"Foundation of the State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Beijing","award":["PRP\/open-2108"],"award-info":[{"award-number":["PRP\/open-2108"]}]},{"name":"Foundation of the State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Beijing","award":["33550000-22-ZC0613-0295"],"award-info":[{"award-number":["33550000-22-ZC0613-0295"]}]},{"name":"Foundation of the State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum, Beijing","award":["202210491071"],"award-info":[{"award-number":["202210491071"]}]},{"name":"Opening Fund of the State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development","award":["41974154"],"award-info":[{"award-number":["41974154"]}]},{"name":"Opening Fund of the State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development","award":["PRP\/open-2108"],"award-info":[{"award-number":["PRP\/open-2108"]}]},{"name":"Opening Fund of the State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development","award":["33550000-22-ZC0613-0295"],"award-info":[{"award-number":["33550000-22-ZC0613-0295"]}]},{"name":"Opening Fund of the State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development","award":["202210491071"],"award-info":[{"award-number":["202210491071"]}]},{"name":"Opening Fund of the Sinopec Key Laboratory of Seismic Elastic Wave Technology","award":["41974154"],"award-info":[{"award-number":["41974154"]}]},{"name":"Opening Fund of the Sinopec Key Laboratory of Seismic Elastic Wave Technology","award":["PRP\/open-2108"],"award-info":[{"award-number":["PRP\/open-2108"]}]},{"name":"Opening Fund of the Sinopec Key Laboratory of Seismic Elastic Wave Technology","award":["33550000-22-ZC0613-0295"],"award-info":[{"award-number":["33550000-22-ZC0613-0295"]}]},{"name":"Opening Fund of the Sinopec Key Laboratory of Seismic Elastic Wave Technology","award":["202210491071"],"award-info":[{"award-number":["202210491071"]}]},{"name":"Hubei Subsurface Multi-scale Imaging Key Laboratory (China University of Geosciences) Program, National Students\u2019 Innovation and Entrepreneurship Training Program","award":["41974154"],"award-info":[{"award-number":["41974154"]}]},{"name":"Hubei Subsurface Multi-scale Imaging Key Laboratory (China University of Geosciences) Program, National Students\u2019 Innovation and Entrepreneurship Training Program","award":["PRP\/open-2108"],"award-info":[{"award-number":["PRP\/open-2108"]}]},{"name":"Hubei Subsurface Multi-scale Imaging Key Laboratory (China University of Geosciences) Program, National Students\u2019 Innovation and Entrepreneurship Training Program","award":["33550000-22-ZC0613-0295"],"award-info":[{"award-number":["33550000-22-ZC0613-0295"]}]},{"name":"Hubei Subsurface Multi-scale Imaging Key Laboratory (China University of Geosciences) Program, National Students\u2019 Innovation and Entrepreneurship Training Program","award":["202210491071"],"award-info":[{"award-number":["202210491071"]}]},{"name":"China University of Geosciences (Wuhan) Postgraduate Joint-Training Practice Base Construction Project","award":["41974154"],"award-info":[{"award-number":["41974154"]}]},{"name":"China University of Geosciences (Wuhan) Postgraduate Joint-Training Practice Base Construction Project","award":["PRP\/open-2108"],"award-info":[{"award-number":["PRP\/open-2108"]}]},{"name":"China University of Geosciences (Wuhan) Postgraduate Joint-Training Practice Base Construction Project","award":["33550000-22-ZC0613-0295"],"award-info":[{"award-number":["33550000-22-ZC0613-0295"]}]},{"name":"China University of Geosciences (Wuhan) Postgraduate Joint-Training Practice Base Construction Project","award":["202210491071"],"award-info":[{"award-number":["202210491071"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Low frequencies are vital for full-waveform inversion (FWI) to retrieve long-scale features and reliable subsurface properties from seismic data. Unfortunately, low frequencies are missing because of limitations in seismic acquisition steps. Furthermore, there is no explicit expression for transforming high frequencies into low frequencies. Therefore, low-frequency reconstruction (LFR) is imperative. Recently developed deep-learning (DL)-based LFR methods are based on either 1D or 2D convolutional neural networks (CNNs), which cannot take full advantage of the information contained in 3D prestack seismic data. Therefore, we present a DL-based LFR approach in which high frequencies are transformed into low frequencies by training an approximately symmetric encoding-decoding-type bridge-shaped 3D CNN. Our motivation is that the 3D CNN can naturally exploit more information that can be effectively used to improve the LFR result. We designed a Hanning-based window for suppressing the Gibbs effect associated with the hard splitting of the low- and high-frequency data. We report the significance of the convolutional kernel size on the training stage convergence rate and the performance of CNN\u2019s generalization ability. CNN with reasonably large kernel sizes has a large receptive field and is beneficial to long-wavelength LFR. Experiments indicate that our approach can accurately reconstruct low frequencies from bandlimited high frequencies. The results of 3D CNN are distinctly superior to those of 2D CNN in terms of precision and highly relevant low-frequency energy. FWI on synthetic data indicates that the DL-predicted low frequencies nearly resemble those of actual low frequencies, and the DL-predicted low frequencies are accurate enough to mitigate the FWI\u2019s cycle-skipping problems. Codes and data of this work are shared via a public repository.<\/jats:p>","DOI":"10.3390\/rs15051387","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T01:39:21Z","timestamp":1677721161000},"page":"1387","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Deep-Learning-Based Low-Frequency Reconstruction in Full-Waveform Inversion"],"prefix":"10.3390","volume":"15","author":[{"given":"Zhiyuan","family":"Gu","sequence":"first","affiliation":[{"name":"Consortium for Seismic Data Processing and Imaging (CSD\u03c0), Team of Geophysics-Constrained Machine Learning for Seismic Data Processing and Imaging (GCML4SD\u03c0), Hubei Subsurface Multiscale Imaging Key Laboratory, School of Geophysics and Geomatics, China University of Geosciences (Wuhan), Wuhan 430074, China"},{"name":"Changjiang Geophysical Exploration & Testing Co., Ltd., (Wuhan), Wuhan 430010, China"},{"name":"Department of Earth and Atmospheric Sciences, Saint Louis University, Saint Louis, MO 63108, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1362-4491","authenticated-orcid":false,"given":"Xintao","family":"Chai","sequence":"additional","affiliation":[{"name":"Consortium for Seismic Data Processing and Imaging (CSD\u03c0), Team of Geophysics-Constrained Machine Learning for Seismic Data Processing and Imaging (GCML4SD\u03c0), Hubei Subsurface Multiscale Imaging Key Laboratory, School of Geophysics and Geomatics, China University of Geosciences (Wuhan), Wuhan 430074, China"},{"name":"State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Changping, Beijing 102249, China"},{"name":"State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development, Beijing 100083, China"},{"name":"Sinopec Key Laboratory of Seismic Elastic Wave Technology, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2981-3120","authenticated-orcid":false,"given":"Taihui","family":"Yang","sequence":"additional","affiliation":[{"name":"Consortium for Seismic Data Processing and Imaging (CSD\u03c0), Team of Geophysics-Constrained Machine Learning for Seismic Data Processing and Imaging (GCML4SD\u03c0), Hubei Subsurface Multiscale Imaging Key Laboratory, School of Geophysics and Geomatics, China University of Geosciences (Wuhan), Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"WCC1","DOI":"10.1190\/1.3238367","article-title":"An overview of full-waveform inversion in exploration geophysics","volume":"74","author":"Virieux","year":"2009","journal-title":"Geophysics"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"R339","DOI":"10.1190\/geo2016-0038.1","article-title":"Full-waveform inversion with extrapolated low-frequency data","volume":"81","author":"Li","year":"2016","journal-title":"Geophysics"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1190\/1.1443880","article-title":"Multiscale seismic waveform inversion","volume":"60","author":"Bunks","year":"1995","journal-title":"Geophysics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"R275","DOI":"10.1190\/geo2019-0195.1","article-title":"Extrapolated full-waveform inversion with deep learning","volume":"85","author":"Sun","year":"2020","journal-title":"Geophysics"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1190\/tle32111366.1","article-title":"The feasibility and value of low-frequency data collected using colocated 2-Hz and 10-Hz geophones","volume":"32","author":"Chiu","year":"2013","journal-title":"Lead. Edge"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1093\/gji\/ggv305","article-title":"Full-waveform inversion of conventional Vibroseis data recorded along a regional profile from southeast Poland","volume":"203","author":"Adamczyk","year":"2015","journal-title":"Geophys. J. Int."},{"key":"ref_7","unstructured":"Hu, W. (2014). SEG Technical Program Expanded Abstracts 2014, Society of Exploration Geophysicists."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"R989","DOI":"10.1190\/geo2018-0884.1","article-title":"Deep learning for low-frequency extrapolation from multioffset seismic data","volume":"84","author":"Ovcharenko","year":"2019","journal-title":"Geophysics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1785\/0220180259","article-title":"Machine learning in seismology: Turning data into insights","volume":"90","author":"Kong","year":"2018","journal-title":"Seismol. Res. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e2021RG000742","DOI":"10.1029\/2021RG000742","article-title":"Deep learning for Geophysics: Current and future trends","volume":"59","author":"Yu","year":"2021","journal-title":"Rev. Geophys."},{"key":"ref_11","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_12","doi-asserted-by":"crossref","first-page":"V11","DOI":"10.1190\/geo2017-0495.1","article-title":"Deep-learning-based seismic data interpolation: A preliminary result","volume":"84","author":"Wang","year":"2019","journal-title":"Geophysics"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4406","DOI":"10.1109\/TGRS.2020.2963928","article-title":"Deep learning for regularly missing data reconstruction","volume":"58","author":"Chai","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6244","DOI":"10.1109\/TGRS.2020.3016343","article-title":"Deep learning for irregularly and regularly missing 3-D data reconstruction","volume":"59","author":"Chai","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"U31","DOI":"10.1190\/geo2018-0591.1","article-title":"Velocity model building in a crosswell acquisition geometry with image-trained artificial neural networks","volume":"85","author":"Wang","year":"2020","journal-title":"Geophysics"},{"key":"ref_16","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_17","doi-asserted-by":"crossref","first-page":"e2021JB023842","DOI":"10.1029\/2021JB023842","article-title":"3D microseismic monitoring using machine learning","volume":"127","author":"Chen","year":"2022","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"V207","DOI":"10.1190\/geo2020-0342.1","article-title":"Deep learning for multitrace sparse-spike deconvolution","volume":"86","author":"Chai","year":"2021","journal-title":"Geophysics"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chai, X., Yang, T., Gu, H., Tang, G., Cao, W., and Wang, Y. (Geophys. J. Int., 2023). Geophysics-steered self-supervised learning for deconvolution, Geophys. J. Int., in press.","DOI":"10.1093\/gji\/ggad015"},{"key":"ref_20","first-page":"1","article-title":"Physics-constrained seismic impedance inversion based on deep learning","volume":"19","author":"Wang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1794","DOI":"10.1785\/0220190353","article-title":"Comparison of single-trace and multiple-trace polarity determination for surface microseismic data using deep learning","volume":"91","author":"Tian","year":"2020","journal-title":"Seismol. Res. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2282","DOI":"10.1785\/0220200420","article-title":"Inversion for shear-tensile focal mechanisms using an unsupervised physics-guided neural network","volume":"92","author":"Zhang","year":"2021","journal-title":"Seismol. Res. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1785\/0220220147","article-title":"CubeNet: Array-based seismic phase picking with deep learning","volume":"93","author":"Chen","year":"2022","journal-title":"Seismol. Res. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3144666","article-title":"An open-source package for deep-learning-based seismic facies classification: Benchmarking experiments on the SEG 2020 open data","volume":"60","author":"Chai","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"eabm4470","DOI":"10.1126\/science.abm4470","article-title":"Deep-learning seismology","volume":"377","author":"Mousavi","year":"2022","journal-title":"Science"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"A37","DOI":"10.1190\/geo2020-0159.1","article-title":"Data-driven low-frequency signal recovery using deep-learning predictions in full-waveform inversion","volume":"85","author":"Fang","year":"2020","journal-title":"Geophysics"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4366","DOI":"10.1109\/TMTT.2021.3098769","article-title":"Low-frequency data prediction with iterative learning for highly nonlinear inverse scattering problems","volume":"69","author":"Lin","year":"2021","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3185794","article-title":"Multi-task learning for low-frequency extrapolation and elastic model building from seismic data","volume":"60","author":"Ovcharenko","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41592-018-0261-2","article-title":"U-Net: Deep learning for cell counting, detection, and morphometry","volume":"16","author":"Falk","year":"2019","journal-title":"Nat. Methods"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1190\/1.2172306","article-title":"Marmousi2: An elastic upgrade for Marmousi","volume":"25","author":"Martin","year":"2006","journal-title":"Lead. Edge"},{"key":"ref_31","unstructured":"Hewett, R.J., Demanet, L., and The PySIT Team (2020). PySIT: Python Seismic Imaging Toolbox, European Organization for Nuclear Research."},{"key":"ref_32","unstructured":"Oppenheim, A.V., Schafer, R.W., and Buck, J.R. (1999). Discrete-Time Signal Processing, Prentice-Hall, Inc.. [2nd ed.]."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1190\/1.1581036","article-title":"Processing, inversion, and interpretation of a 2D seismic data set from the North Viking Graben, North Sea","volume":"68","author":"Madiba","year":"2003","journal-title":"Geophysics"},{"key":"ref_34","unstructured":"Keys, R.G., and Foster, D.J. (2012). Comparison of Seismic Inversion Methods on a Single Real Data Set, SEG Books."},{"key":"ref_35","first-page":"1","article-title":"Automatic differentiation in machine learning: A survey","volume":"18","author":"Baydin","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref_36","unstructured":"Kingma, D., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_37","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1190\/1.1437051","article-title":"The Marmousi experience: Velocity model determination on a synthetic complex data set","volume":"13","author":"Versteeg","year":"1994","journal-title":"Lead. Edge"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1007\/s00024-017-1734-4","article-title":"The linearized Bregman method for frugal full-waveform inversion with compressive sensing and sparsity-promoting","volume":"175","author":"Chai","year":"2017","journal-title":"Pure Appl. Geophys."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/BF01589116","article-title":"On the limited memory BFGS method for large scale optimization","volume":"45","author":"Liu","year":"1989","journal-title":"Math. Program."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Billette, F., and Brandsberg-Dahl, S. (2005, January 13\u201316). The 2004 BP velocity benchmark. Proceedings of the 67th EAGE Conference & Exhibition, Madrid, Spain.","DOI":"10.3997\/2214-4609-pdb.1.B035"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3302","DOI":"10.1038\/s41598-020-59801-x","article-title":"Deep learning for irregularly and regularly missing data reconstruction","volume":"10","author":"Chai","year":"2020","journal-title":"Sci. Rep."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/5\/1387\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:45:07Z","timestamp":1760121907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/5\/1387"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["rs15051387"],"URL":"https:\/\/doi.org\/10.3390\/rs15051387","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]}}}