{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T03:59:35Z","timestamp":1792641575501,"version":"4.5.0"},"reference-count":38,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U20B2014"],"award-info":[{"award-number":["U20B2014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The full waveform inversion at this stage still has many problems in the recovery of deep background velocities. Velocity modeling based on end-to-end deep learning usually lacks a generalization capability. The proposed method is a multi-scale convolutional neural network velocity inversion (Ms-CNNVI) that incorporates a multi-scale strategy into the CNN-based velocity inversion algorithm for the first time. This approach improves the accuracy of the inversion by integrating a multi-scale strategy from low-frequency to high-frequency inversion and by incorporating a smoothing strategy in the multi-scale (MS) convolutional neural network (CNN) inversion process. Furthermore, using angle-domain reverse time migration (RTM) for dataset construction in Ms-CNNVI significantly improves the inversion efficiency. Numerical tests showcase the efficacy of the suggested approach.<\/jats:p>","DOI":"10.3390\/rs16050772","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T11:28:47Z","timestamp":1708601327000},"page":"772","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Scale Acoustic Velocity Inversion Based on a Convolutional Neural Network"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1464-5291","authenticated-orcid":false,"given":"Wenda","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China"},{"name":"Innovation Academy for Earth Science, Chinese Academy of Sciences, Beijing 100029, China"},{"name":"National Engineering Laboratory for Offshore Oil Exploration, University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianqi","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China"},{"name":"School of Geophysics and Information Technology, China University of Geoscience, Beijing 100083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China"},{"name":"Innovation Academy for Earth Science, Chinese Academy of Sciences, Beijing 100029, China"},{"name":"National Engineering Laboratory for Offshore Oil Exploration, University of Chinese Academy of Sciences, Beijing 100049, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1111\/j.1365-2478.2008.00698.x","article-title":"Migration velocity analysis and waveform inversion","volume":"56","author":"Symes","year":"2008","journal-title":"Geophys. Prospect."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1190\/1.1442625","article-title":"Inversion= migration+ tomography","volume":"54","author":"Mora","year":"1989","journal-title":"Geophysics"},{"key":"ref_3","unstructured":"Lailly, P. (1983). The Seismic Inverse Problem as a Sequence of Before Stack Migrations, SIAM."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1259","DOI":"10.1190\/1.1441754","article-title":"Inversion of seismic reflection data in the acoustic approximation","volume":"49","author":"Tarantola","year":"1984","journal-title":"Geophysics"},{"key":"ref_5","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_6","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.petsci.2022.01.015","article-title":"Research progress on seismic imaging technology","volume":"19","author":"Li","year":"2022","journal-title":"Pet. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1190\/1.1442305","article-title":"Wave-field transformations of vertical seismic profiles","volume":"52","author":"Hu","year":"1987","journal-title":"Geophysics"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, F., Chauris, H., Donno, D., and Calandra, H. (2013, January 10\u201313). Taking advantage of wave field decomposition in full waveform inversion. Proceedings of the 75th EAGE Conference & Exhibition Incorporating SPE EUROPEC 2013, London, UK.","DOI":"10.3997\/2214-4609.20130415"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.jappgeo.2018.06.013","article-title":"Enhancing low-wavenumber components of full-waveform inversion using an improved wavefield decomposition method in the time-space domain","volume":"157","author":"Lian","year":"2018","journal-title":"J. Appl. Geophys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.1093\/gji\/ggx283","article-title":"Efficient scattering-angle enrichment for a nonlinear inversion of the background and perturbations components of a velocity model","volume":"210","author":"Wu","year":"2017","journal-title":"Geophys. J. Int."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1783","DOI":"10.1007\/s11430-016-9091-9","article-title":"Reflection full waveform inversion","volume":"60","author":"Yao","year":"2017","journal-title":"Sci. China Earth Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1002\/2017JB015207","article-title":"Separation of migration and tomography modes of full-waveform inversion in the plane wave domain","volume":"123","author":"Yao","year":"2018","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1007\/s12182-020-00431-3","article-title":"A review on reflection-waveform inversion","volume":"17","author":"Yao","year":"2020","journal-title":"Pet. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"R701","DOI":"10.1190\/geo2020-0706.1","article-title":"Frequency-domain reflection waveform inversion with generalized internal multiple imaging","volume":"86","author":"Wang","year":"2021","journal-title":"Geophysics"},{"key":"ref_15","unstructured":"Wu, Y., Lin, Y., and Zhou, Z. (2018). SEG Technical Program Expanded Abstracts 2018, Society of Exploration Geophysicists."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"R583","DOI":"10.1190\/geo2018-0249.1","article-title":"Deep-learning inversion: A next-generation seismic velocity model building method","volume":"84","author":"Yang","year":"2019","journal-title":"Geophysics"},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"R31","DOI":"10.1190\/geo2019-0435.1","article-title":"Deep-learning seismic full-waveform inversion for realistic structural models","volume":"86","author":"Liu","year":"2021","journal-title":"Geophysics"},{"key":"ref_19","first-page":"5901818","article-title":"Deep-learning full-waveform inversion using seismic migration images","volume":"60","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8913","DOI":"10.1109\/TGRS.2020.3044065","article-title":"Adjoint-driven deep-learning seismic full-waveform inversion","volume":"59","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","unstructured":"Wu, Y., McMechan, G.A., and Wang, Y. (October, January 26). CNN-based gradient-free multiparameter reflection full-waveform inversion. Proceedings of the First International Meeting for Applied Geoscience & Energy, Denver, CO, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e2022JB024138","DOI":"10.1029\/2022JB024138","article-title":"Adaptive Feedback Convolutional-Neural-Network-Based High-Resolution Reflection-Waveform Inversion","volume":"127","author":"Wu","year":"2022","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1093\/gji\/ggac374","article-title":"Deep-Tomography: Iterative velocity model building with deep learning","volume":"232","author":"Muller","year":"2023","journal-title":"Geophys. J. Int."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Waheed, U.b., Alkhalifah, T., Haghighat, E., Song, C., and Virieux, J. (2021). PINNtomo: Seismic tomography using physics-informed neural networks. arXiv.","DOI":"10.3997\/2214-4609.202011041"},{"key":"ref_25","first-page":"5908012","article-title":"Wavefield reconstruction inversion via physics-informed neural networks","volume":"60","author":"Song","year":"2021","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"ref_26","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_27","doi-asserted-by":"crossref","first-page":"R159","DOI":"10.1190\/geo2017-0353.1","article-title":"Multiscale phase inversion of seismic data","volume":"83","author":"Fu","year":"2018","journal-title":"Geophysics"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"R125","DOI":"10.1190\/geo2010-0210.1","article-title":"Source-independent time-domain waveform inversion using convolved wavefields: Application to the encoded multisource waveform inversion","volume":"76","author":"Choi","year":"2011","journal-title":"Geophysics"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1071\/EG16037","article-title":"Multi-scale full waveform inversion for areas with irregular surface topography in an auxiliary coordinate system","volume":"49","author":"Qu","year":"2018","journal-title":"Explor. Geophys."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1093\/jge\/gxz013","article-title":"Multi-source multi-scale source-independent full waveform inversion","volume":"16","author":"Guo","year":"2019","journal-title":"J. Geophys. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1007\/s12182-019-00419-8","article-title":"Convolution-based multi-scale envelope inversion","volume":"17","author":"Liu","year":"2020","journal-title":"Pet. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5923011","DOI":"10.1109\/TGRS.2023.3329932","article-title":"Multi-scale Fusion Network with SR-attention for seismic velocity model building","volume":"61","author":"Lu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","first-page":"5918314","article-title":"A High Resolution Velocity Inversion Method Based on Attention Convolutional Neural Network","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1190\/1.1442384","article-title":"Nonlinear two-dimensional elastic inversion of multioffset seismic data","volume":"52","author":"Mora","year":"1987","journal-title":"Geophysics"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"WB135","DOI":"10.1190\/geo2010-0314.1","article-title":"Direct vector-field method to obtain angle-domain common-image gathers from isotropic acoustic and elastic reverse time migration","volume":"76","author":"Zhang","year":"2011","journal-title":"Geophysics"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, W., Wu, T., and Liu, H. (2022). Structure-Preserving Random Noise Attenuation Method for Seismic Data Based on a Flexible Attention CNN. Remote Sens., 14.","DOI":"10.3390\/rs14205240"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"R335","DOI":"10.1190\/geo2017-0712.1","article-title":"Near-surface velocity estimation using source-domain full traveltime inversion and early-arrival waveform inversion","volume":"83","author":"Liu","year":"2018","journal-title":"Geophysics"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1080\/08123985.2021.1993059","article-title":"Q-compensated full waveform inversion for velocity and density","volume":"53","author":"Wang","year":"2022","journal-title":"Explor. Geophys."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/5\/772\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:03:26Z","timestamp":1760105006000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/5\/772"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["rs16050772"],"URL":"https:\/\/doi.org\/10.3390\/rs16050772","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]}}}