{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:07:43Z","timestamp":1774638463258,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T00:00:00Z","timestamp":1697068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Scientific Research Fund of the Second Institute of Oceanography","award":["JG2201"],"award-info":[{"award-number":["JG2201"]}]},{"name":"Scientific Research Fund of the Second Institute of Oceanography","award":["JG2205"],"award-info":[{"award-number":["JG2205"]}]},{"name":"Scientific Research Fund of the Second Institute of Oceanography","award":["41906197"],"award-info":[{"award-number":["41906197"]}]},{"name":"Scientific Research Fund of the Second Institute of Oceanography","award":["41976079"],"award-info":[{"award-number":["41976079"]}]},{"name":"Scientific Research Fund of the Second Institute of Oceanography","award":["IRASCC 01-03-01B"],"award-info":[{"award-number":["IRASCC 01-03-01B"]}]},{"name":"Scientific Research Fund of the Second Institute of Oceanography","award":["DH-2022ZY0007"],"award-info":[{"award-number":["DH-2022ZY0007"]}]},{"name":"Fundamental Research Funds for the National Natural Science Foundation of China","award":["JG2201"],"award-info":[{"award-number":["JG2201"]}]},{"name":"Fundamental Research Funds for the National Natural Science Foundation of China","award":["JG2205"],"award-info":[{"award-number":["JG2205"]}]},{"name":"Fundamental Research Funds for the National Natural Science Foundation of China","award":["41906197"],"award-info":[{"award-number":["41906197"]}]},{"name":"Fundamental Research Funds for the National Natural Science Foundation of China","award":["41976079"],"award-info":[{"award-number":["41976079"]}]},{"name":"Fundamental Research Funds for the National Natural Science Foundation of China","award":["IRASCC 01-03-01B"],"award-info":[{"award-number":["IRASCC 01-03-01B"]}]},{"name":"Fundamental Research Funds for the National Natural Science Foundation of China","award":["DH-2022ZY0007"],"award-info":[{"award-number":["DH-2022ZY0007"]}]},{"name":"program of Impact and Response of Antarctic Seas to Climate Change","award":["JG2201"],"award-info":[{"award-number":["JG2201"]}]},{"name":"program of Impact and Response of Antarctic Seas to Climate Change","award":["JG2205"],"award-info":[{"award-number":["JG2205"]}]},{"name":"program of Impact and Response of Antarctic Seas to Climate Change","award":["41906197"],"award-info":[{"award-number":["41906197"]}]},{"name":"program of Impact and Response of Antarctic Seas to Climate Change","award":["41976079"],"award-info":[{"award-number":["41976079"]}]},{"name":"program of Impact and Response of Antarctic Seas to Climate Change","award":["IRASCC 01-03-01B"],"award-info":[{"award-number":["IRASCC 01-03-01B"]}]},{"name":"program of Impact and Response of Antarctic Seas to Climate Change","award":["DH-2022ZY0007"],"award-info":[{"award-number":["DH-2022ZY0007"]}]},{"name":"Science Foundation of Donghai Laboratory","award":["JG2201"],"award-info":[{"award-number":["JG2201"]}]},{"name":"Science Foundation of Donghai Laboratory","award":["JG2205"],"award-info":[{"award-number":["JG2205"]}]},{"name":"Science Foundation of Donghai Laboratory","award":["41906197"],"award-info":[{"award-number":["41906197"]}]},{"name":"Science Foundation of Donghai Laboratory","award":["41976079"],"award-info":[{"award-number":["41976079"]}]},{"name":"Science Foundation of Donghai Laboratory","award":["IRASCC 01-03-01B"],"award-info":[{"award-number":["IRASCC 01-03-01B"]}]},{"name":"Science Foundation of Donghai Laboratory","award":["DH-2022ZY0007"],"award-info":[{"award-number":["DH-2022ZY0007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>This paper aims to solve the limitations of traditional gravity physical property inversion methods such as insufficient depth resolution and difficulties in parameter selection, by proposing an improved 3D gravity inversion method based on deep learning. The deep learning network model is established using the fully convolutional U-net network. To enhance the generalization ability of the sample set, the large-scale training set and test set are generated by the random walk, based on the forward theory. Founded on the traditional loss function\u2019s definition, this paper introduces an improvement incorporating a physical constraint to measure the degree of data fitting between the predicted and the real gravity data. This improvement significantly boosted the accuracy of the deep learning inversion method, as verified through both a single model and an intricate combination model. Finally, we applied this improved inversion method to the gravity data from the Gamburtsev Subglacial Mountains in the interior of East Antarctica, obtaining a comprehensive 3D crustal density structure. The results provide new evidence for the presence of a dense crustal root situated beneath the central Gamburtsev Province near the Gamburtsev Suture.<\/jats:p>","DOI":"10.3390\/rs15204933","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T12:46:13Z","timestamp":1697114773000},"page":"4933","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Improved Gravity Inversion Method Based on Deep Learning with Physical Constraint and Its Application to the Airborne Gravity Data in East Antarctica"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0053-4777","authenticated-orcid":false,"given":"Guochao","family":"Wu","sequence":"first","affiliation":[{"name":"Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China"},{"name":"Key Laboratory of Submarine Geosciences, Ministry of Natural Resources, Hangzhou 310012, China"}]},{"given":"Yue","family":"Wei","sequence":"additional","affiliation":[{"name":"College of GeoExploration Science and Technology, Jilin University, Changchun 130012, China"}]},{"given":"Siyuan","family":"Dong","sequence":"additional","affiliation":[{"name":"College of GeoExploration Science and Technology, Jilin University, Changchun 130012, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1205-989X","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China"},{"name":"Key Laboratory of Submarine Geosciences, Ministry of Natural Resources, Hangzhou 310012, China"},{"name":"Donghai Laboratory, Zhoushan 316000, China"}]},{"given":"Chunguo","family":"Yang","sequence":"additional","affiliation":[{"name":"Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China"},{"name":"Key Laboratory of Submarine Geosciences, Ministry of Natural Resources, Hangzhou 310012, China"}]},{"given":"Linjiang","family":"Qin","sequence":"additional","affiliation":[{"name":"Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China"},{"name":"Key Laboratory of Submarine Geosciences, Ministry of Natural Resources, Hangzhou 310012, China"}]},{"given":"Qingsheng","family":"Guan","sequence":"additional","affiliation":[{"name":"Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China"},{"name":"Key Laboratory of Submarine Geosciences, Ministry of Natural Resources, Hangzhou 310012, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1190\/1.1444302","article-title":"3-D inversion of gravity data","volume":"63","author":"Li","year":"1998","journal-title":"Geophysics"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"63ND","DOI":"10.1190\/1.2133785","article-title":"Historical development of the gravity method in exploration","volume":"70","author":"Nabighian","year":"2005","journal-title":"Geophysics"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1190\/1.1440444","article-title":"The Inversion and interpretation of gravity anomalies","volume":"39","author":"Oldenburg","year":"1974","journal-title":"Geophysics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"J51","DOI":"10.1190\/1.2236383","article-title":"Gravity inversion of basement relief and estimation of density contrast variation with depth","volume":"71","author":"Silva","year":"2006","journal-title":"Geophysics"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Tikhonov, A.N., Goncharsky, A.V., Stepanov, V.V., and Yagola, A.G. (1995). Numerical Methods for the Solution of Ill-Posed Problems, Springer.","DOI":"10.1007\/978-94-015-8480-7"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1190\/1.1443968","article-title":"3-D inversion of magnetic data","volume":"61","author":"Li","year":"1996","journal-title":"Geophysics"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1190\/1.1441501","article-title":"Compact gravity inversion","volume":"48","author":"Last","year":"2012","journal-title":"Geophysics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1190\/1.1444596","article-title":"Focusing geophysical inversion images","volume":"64","author":"Portniaguine","year":"1999","journal-title":"Geophysics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1186\/s40623-018-0825-5","article-title":"3D inversion of full gravity gradient tensor data in spherical coordinate system using local north-oriented frame","volume":"70","author":"Zhang","year":"2018","journal-title":"Earth Planets Space"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1190\/1.1512749","article-title":"3-D magnetic inversion with data compression and image focusing","volume":"67","author":"Portniaguine","year":"2002","journal-title":"Geophysics"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1046\/j.1365-246X.2003.01766.x","article-title":"Fast inversion of large-scale magnetic data using wavelet transforms and a logarithmic barrier method","volume":"152","author":"Li","year":"2003","journal-title":"Geophys. J. Int."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"IM1","DOI":"10.1190\/geo2013-0087.1","article-title":"Adaptive sampling of potential-field data: A direct approach to compressive inversion","volume":"79","author":"Foks","year":"2014","journal-title":"Geophysics"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5905918","DOI":"10.1109\/TGRS.2022.3220437","article-title":"Deep Learning for 3-D Inversion of Gravity Data","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"7982","DOI":"10.1109\/TGRS.2020.3032743","article-title":"Joint Inversion of Audio-Magnetotelluric and Seismic Travel Time Data With Deep Learning Constraint","volume":"59","author":"Guo","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1190\/tle37120894.1","article-title":"Geophysical inversion versus machine learning in inverse problems","volume":"37","author":"Kim","year":"2018","journal-title":"Lead. Edge"},{"key":"ref_16","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_17","doi-asserted-by":"crossref","first-page":"E163","DOI":"10.1190\/geo2019-0015.1","article-title":"Fast imaging of time-domain airborne EM data using deep learning technology","volume":"85","author":"Li","year":"2020","journal-title":"Geophysics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1093\/gji\/ggz204","article-title":"Deep learning electromagnetic inversion with convolutional neural networks","volume":"218","author":"Puzyrev","year":"2019","journal-title":"Geophys. J. Int."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/JMMCT.2020.2995811","article-title":"Two-Dimensional Electromagnetic Solver Based on Deep Learning Technique","volume":"5","author":"Qi","year":"2020","journal-title":"IEEE J. Multiscale Multiphysics Comput. Tech."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"104701","DOI":"10.1016\/j.cageo.2021.104701","article-title":"3D geological structure inversion from Noddy-generated magnetic data using deep learning methods","volume":"149","author":"Guo","year":"2021","journal-title":"Comput. Geosci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7202304","DOI":"10.1109\/TMAG.2019.2899304","article-title":"Deep Learning for Magnetic Field Estimation","volume":"55","author":"Khan","year":"2019","journal-title":"IEEE Trans. Magn."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2101604","DOI":"10.1109\/TMAG.2021.3082431","article-title":"Inverse Design of Magnetic Fields Using Deep Learning","volume":"57","author":"Pollok","year":"2021","journal-title":"IEEE Trans. Magn."},{"key":"ref_23","first-page":"3001305","article-title":"3-D Gravity Inversion Based on Deep Convolution Neural Networks","volume":"19","author":"Yang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"G103","DOI":"10.1190\/geo2021-0744.1","article-title":"DecNet: Decomposition network for 3D gravity inversion","volume":"87","author":"Zhang","year":"2022","journal-title":"Geophysics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e2021JB022476","DOI":"10.1029\/2021JB022476","article-title":"Deep Learning 3D Sparse Inversion of Gravity Data","volume":"126","author":"Huang","year":"2021","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/s11770-021-0909-z","article-title":"Three-dimensional gravity inversion based on 3D U-Net++","volume":"18","author":"Wang","year":"2021","journal-title":"Appl. Geophys."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, Z., and Chen, Z. (2022). The Identification of Impact Craters from GRAIL-Acquired Gravity Data by U-Net Architecture. Remote Sens., 14.","DOI":"10.3390\/rs14122783"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1046\/j.1365-2478.2001.00254.x","article-title":"Constraints in 3D gravity inversion","volume":"49","author":"Boulanger","year":"2001","journal-title":"Geophys. Prospect."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1023\/A:1006554408567","article-title":"Three-Dimensional Gravity Modeling In All Space","volume":"19","author":"Li","year":"1998","journal-title":"Surv. Geophys."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1007\/s001900000116","article-title":"The gravitational potential and its derivatives for the prism","volume":"74","author":"Nagy","year":"2000","journal-title":"J. Geod."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.1126\/science.1200109","article-title":"Widespread Persistent Thickening of the East Antarctic Ice Sheet by Freezing from the Base","volume":"331","author":"Bell","year":"2011","journal-title":"Science"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wu, G., Ferraccioli, F., Zhou, W., Yuan, Y., Gao, J., and Tian, G. (2023). Tectonic Implications for the Gamburtsev Subglacial Mountains, East Antarctica, from Airborne Gravity and Magnetic Data. Remote Sens., 15.","DOI":"10.3390\/rs15020306"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1038\/nature10566","article-title":"East Antarctic rifting triggers uplift of the Gamburtsev Mountains","volume":"479","author":"Ferraccioli","year":"2011","journal-title":"Nature"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wu, G., Tian, G., Bangbing, W., Ferraccioli, F., Seddon, S., Finn, C., and Bell, R. (2017, January 24\u201329). Crustal structure of the Gamburtsev Province, East Antarctica, from airborne geophysics. Proceedings of the 2017 SEG International Exposition and Annual Meeting, Houston, TX, USA.","DOI":"10.1190\/segam2017-17744484.1"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1038\/nature08024","article-title":"The Gamburtsev mountains and the origin and early evolution of the Antarctic Ice Sheet","volume":"459","author":"Bo","year":"2009","journal-title":"Nature"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1002\/2014JB011332","article-title":"S-velocity model and inferred Moho topography beneath the Antarctic Plate from Rayleigh waves","volume":"120","author":"An","year":"2015","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"375","DOI":"10.5194\/tc-7-375-2013","article-title":"Bedmap2: Improved ice bed, surface and thickness datasets for Antarctica","volume":"7","author":"Fretwell","year":"2013","journal-title":"Cryosphere Discuss."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/20\/4933\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:05:37Z","timestamp":1760130337000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/20\/4933"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,12]]},"references-count":37,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["rs15204933"],"URL":"https:\/\/doi.org\/10.3390\/rs15204933","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,12]]}}}