Layered Media Parameter Inversion Method Based on Deconvolution Autoencoder and Self-Attention Mechanism Using GPR Data
Layered medium parameter inversion is a crucial technique in ground-penetrating radar (GPR) data processing and has wide application in civil engineering and geological exploration. In response to the issues of high computational complexity and low accuracy associated with existing methods, a novel...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on geoscience and remote sensing Jg. 62; S. 1 - 14 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
New York
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
2024
|
| Schlagworte: | |
| ISSN: | 0196-2892, 1558-0644 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Layered medium parameter inversion is a crucial technique in ground-penetrating radar (GPR) data processing and has wide application in civil engineering and geological exploration. In response to the issues of high computational complexity and low accuracy associated with existing methods, a novel layered medium parameter inversion approach is proposed, comprising the deconvolution autoencoder and the parameter inversion network. First, the deconvolution autoencoder is introduced to solve the pulse response of layered medium systems in an unsupervised manner, which enhances the computational efficiency of deconvolution and decouples the data acquisition system from the supervised model. Subsequently, a parameter inversion network, including a self-attention module and a residual multilayer perceptron (MLP), is proposed to address the challenge posed by the excessively sparse pulse responses. The self-attention module calculates the autocorrelation of the pulse sequence, providing temporal delay information between pulses and reducing the sparsity of the pulse response to facilitate feature extraction. Meanwhile, the residual MLP, known for its low information loss and adaptability to different output dimensions, is employed for model-based and pixel-based inversions in situations with and without prior knowledge of the layer number, respectively. Finally, simulated and measured datasets are constructed to comprehensively train and evaluate the proposed method. The results demonstrate that the proposed method exhibits better performance of inversion accuracy, computational efficiency, robustness, generalization capability, and noise resistance. In addition, it remains applicable even when prior knowledge of the layer number is unknown. |
|---|---|
| AbstractList | Layered medium parameter inversion is a crucial technique in ground-penetrating radar (GPR) data processing and has wide application in civil engineering and geological exploration. In response to the issues of high computational complexity and low accuracy associated with existing methods, a novel layered medium parameter inversion approach is proposed, comprising the deconvolution autoencoder and the parameter inversion network. First, the deconvolution autoencoder is introduced to solve the pulse response of layered medium systems in an unsupervised manner, which enhances the computational efficiency of deconvolution and decouples the data acquisition system from the supervised model. Subsequently, a parameter inversion network, including a self-attention module and a residual multilayer perceptron (MLP), is proposed to address the challenge posed by the excessively sparse pulse responses. The self-attention module calculates the autocorrelation of the pulse sequence, providing temporal delay information between pulses and reducing the sparsity of the pulse response to facilitate feature extraction. Meanwhile, the residual MLP, known for its low information loss and adaptability to different output dimensions, is employed for model-based and pixel-based inversions in situations with and without prior knowledge of the layer number, respectively. Finally, simulated and measured datasets are constructed to comprehensively train and evaluate the proposed method. The results demonstrate that the proposed method exhibits better performance of inversion accuracy, computational efficiency, robustness, generalization capability, and noise resistance. In addition, it remains applicable even when prior knowledge of the layer number is unknown. |
| Author | Yang, Xiaopeng Li, Yixuan Qu, Xiaodong Guo, Conglong Gong, Junbo Sun, Haoran Lan, Tian |
| Author_xml | – sequence: 1 givenname: Xiaopeng orcidid: 0000-0003-2750-6944 surname: Yang fullname: Yang, Xiaopeng organization: School of Information and Electronics, Beijing Institute of Technology, Beijing, China – sequence: 2 givenname: Haoran orcidid: 0000-0001-7565-009X surname: Sun fullname: Sun, Haoran organization: School of Information and Electronics, Beijing Institute of Technology, Beijing, China – sequence: 3 givenname: Conglong orcidid: 0009-0002-2062-3486 surname: Guo fullname: Guo, Conglong organization: School of Information and Electronics, Beijing Institute of Technology, Beijing, China – sequence: 4 givenname: Yixuan orcidid: 0000-0002-2013-5346 surname: Li fullname: Li, Yixuan organization: School of Information and Electronics, Beijing Institute of Technology, Beijing, China – sequence: 5 givenname: Junbo orcidid: 0009-0001-5299-3206 surname: Gong fullname: Gong, Junbo organization: Chongqing Innovation Center, Beijing Institute of Technology, Chongqing, China – sequence: 6 givenname: Xiaodong orcidid: 0000-0002-2170-8978 surname: Qu fullname: Qu, Xiaodong organization: School of Information and Electronics, Beijing Institute of Technology, Beijing, China – sequence: 7 givenname: Tian orcidid: 0000-0002-2811-2261 surname: Lan fullname: Lan, Tian organization: School of Information and Electronics, Beijing Institute of Technology, Beijing, China |
| BookMark | eNp9kMtOwzAQRS0EEqXwAewisU7xOC97WV6lUhFVH-vIcSYQlNpgO0X9exyVFQtWo9GcM6O5F-RUG42EXAOdAFBxu5mt1hNGWTpJkgy4SE_ICLKMxzRP01MyoiDymHHBzsmFcx-UQppBMSLfC3lAi3X0gnUro6W0cocebTTXe7SuNTpM_LupozvpAhb6B1RG703X-2E67b1BrUwdHKnraI1dE0-9R-2PsnqXunW7aOta_RbNlqvoQXp5Sc4a2Tm8-q1jsn163Nw_x4vX2fx-uogVKxIfs6yqlWp4xlghGDYigQISBTWtClVBVoma8QDkmDc8F1UmkQclAY6S5wDJmNwc935a89Wj8-WH6a0OJ0smgFOW5ykNFBwpZY1zFpvy07Y7aQ8l0HLItxzyLYd8y998g1P8cVTr5fC0t7Lt_jF_AMEdgnQ |
| CitedBy_id | crossref_primary_10_1109_LGRS_2024_3449390 |
| Cites_doi | 10.1029/2012JE004053 10.1007/s10712-019-09556-6 10.1109/TAP.2021.3069519 10.1109/TGRS.2007.900980 10.1109/TGRS.2012.2189777 10.1016/j.ndteint.2017.04.002 10.1016/S0926-9851(99)00052-X 10.1109/TGRS.2022.3219138 10.1190/1.9781560801719.ch11 10.1109/9780470547052 10.1016/j.conbuildmat.2005.06.005 10.1190/1.1441367 10.1016/j.sigpro.2016.06.015 10.1109/TGRS.2020.3046454 10.1109/TGRS.2014.2313603 10.1109/TGRS.2019.2891206 10.1016/j.ndteint.2007.09.001 10.1109/ICASSP.1984.1172389 10.1117/12.541748 10.1016/j.ndteint.2006.09.001 10.1016/b978-0-444-53348-7.x0001-4 10.1002/2013JB010544 10.3141/1861-10 10.1109/TGRS.2018.2862627 10.1109/JSEN.2021.3050618 10.1016/j.cpc.2016.08.020 10.1016/j.ndteint.2015.03.001 10.1109/LGRS.2019.2953708 10.5555/3454287.3455008 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| DBID | AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
| DOI | 10.1109/TGRS.2024.3351894 |
| DatabaseName | CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management |
| DatabaseTitleList | Aerospace Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics |
| EISSN | 1558-0644 |
| EndPage | 14 |
| ExternalDocumentID | 10_1109_TGRS_2024_3351894 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH AAYXX ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CITATION CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R 7UA 8FD AARMG ABAZT C1K F1W FR3 H8D H96 KR7 L.G L7M |
| ID | FETCH-LOGICAL-c273t-25bdccf8522792ef931713c1d0b7cb15b9d28ccf6e6f869b5ae85bd318ea86113 |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001173248900055&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0196-2892 |
| IngestDate | Mon Jun 30 08:27:31 EDT 2025 Sat Nov 29 03:32:31 EST 2025 Tue Nov 18 22:11:35 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c273t-25bdccf8522792ef931713c1d0b7cb15b9d28ccf6e6f869b5ae85bd318ea86113 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-2013-5346 0000-0003-2750-6944 0009-0002-2062-3486 0000-0001-7565-009X 0009-0001-5299-3206 0000-0002-2170-8978 0000-0002-2811-2261 |
| PQID | 2918026640 |
| PQPubID | 85465 |
| PageCount | 14 |
| ParticipantIDs | proquest_journals_2918026640 crossref_primary_10_1109_TGRS_2024_3351894 crossref_citationtrail_10_1109_TGRS_2024_3351894 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-00-00 20240101 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – year: 2024 text: 2024-00-00 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on geoscience and remote sensing |
| PublicationYear | 2024 |
| Publisher | The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref15 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 Vaswani (ref31); 30 ref19 ref18 ref24 ref26 ref25 ref20 Al-Qadi (ref16) 2004; 73 ref22 ref21 ref28 ref27 ref29 ref8 ref7 Li (ref23) 2019 ref9 ref4 ref3 ref6 ref5 Sakamoto (ref14) 1986; 81 |
| References_xml | – ident: ref4 doi: 10.1029/2012JE004053 – ident: ref30 doi: 10.1007/s10712-019-09556-6 – ident: ref24 doi: 10.1109/TAP.2021.3069519 – ident: ref1 doi: 10.1109/TGRS.2007.900980 – ident: ref26 doi: 10.1109/TGRS.2012.2189777 – ident: ref3 doi: 10.1016/j.ndteint.2017.04.002 – volume: 81 start-page: 26853 volume-title: Akaike Information Criterion Statistics year: 1986 ident: ref14 – ident: ref2 doi: 10.1016/S0926-9851(99)00052-X – ident: ref20 doi: 10.1109/TGRS.2022.3219138 – ident: ref29 doi: 10.1190/1.9781560801719.ch11 – volume: 30 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref31 article-title: Attention is all you need – ident: ref27 doi: 10.1109/9780470547052 – ident: ref9 doi: 10.1016/j.conbuildmat.2005.06.005 – ident: ref8 doi: 10.1190/1.1441367 – volume: 73 start-page: 28 issue: 501 year: 2004 ident: ref16 article-title: Use of GPR for thickness measurement and quality control of flexible pavements publication-title: J. Assoc. Asphalt Paving Technol. – ident: ref6 doi: 10.1016/j.sigpro.2016.06.015 – ident: ref21 doi: 10.1109/TGRS.2020.3046454 – ident: ref12 doi: 10.1109/TGRS.2014.2313603 – ident: ref18 doi: 10.1109/TGRS.2019.2891206 – ident: ref10 doi: 10.1016/j.ndteint.2007.09.001 – ident: ref13 doi: 10.1109/ICASSP.1984.1172389 – year: 2019 ident: ref23 article-title: Deep-learning inversion of seismic data publication-title: arXiv:1901.07733 – ident: ref15 doi: 10.1117/12.541748 – ident: ref28 doi: 10.1016/j.ndteint.2006.09.001 – ident: ref5 doi: 10.1016/b978-0-444-53348-7.x0001-4 – ident: ref25 doi: 10.1002/2013JB010544 – ident: ref7 doi: 10.3141/1861-10 – ident: ref11 doi: 10.1109/TGRS.2018.2862627 – ident: ref22 doi: 10.1109/JSEN.2021.3050618 – ident: ref33 doi: 10.1016/j.cpc.2016.08.020 – ident: ref17 doi: 10.1016/j.ndteint.2015.03.001 – ident: ref19 doi: 10.1109/LGRS.2019.2953708 – ident: ref32 doi: 10.5555/3454287.3455008 |
| SSID | ssj0014517 |
| Score | 2.4476738 |
| Snippet | Layered medium parameter inversion is a crucial technique in ground-penetrating radar (GPR) data processing and has wide application in civil engineering and... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Enrichment Source Index Database |
| StartPage | 1 |
| SubjectTerms | Accuracy Adaptability Autocorrelation Civil engineering Computational efficiency Computer applications Computing time Data acquisition Data analysis Data processing Deconvolution Feature extraction Geological surveys Ground penetrating radar Inversions Mathematical models Modules Multilayer perceptrons Parameters Radar Robustness (mathematics) |
| Title | Layered Media Parameter Inversion Method Based on Deconvolution Autoencoder and Self-Attention Mechanism Using GPR Data |
| URI | https://www.proquest.com/docview/2918026640 |
| Volume | 62 |
| WOSCitedRecordID | wos001173248900055&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELfKAAkeEAwmNgbyA09UGXHSuPZj-eoeyjRtBZWnKHacqVKVTGvSlf-NP4472wktE4g98BI1rnNJe7_cnc_3QchrBTa4jgsRhLqIA9R4gcwHLEiYKpSKEiVtVtrXyfDkRMxm8rTX-9HmwqwWw7IU67W8_K-shjFgNqbO3oLdHVEYgM_AdDgC2-H4T4yfZN-x_6bdgsnAQsToK6yEiBU1rG8MvsGu0f13oMBy3Cz4gIvilX-o_qipK6xuiUUmbFynWRTBqK59XORng7nC2FrDRRuMT88AOnW2aeXiChKbT7SdyO2WxIWp2hwiG9NuACSmv8QAeq89Ufh49_VsnmFfr278vLHS8TgDxHZwHjfOz1uVF4vq19yJDVD4Nl83fqp3args6tbDKXkAq0Anoo2XygmAibtCka3Y9kLcyV22ocBdUupN1WArq07HZ-dHeMejOE6YcA2Wt8tw_6Yeu6BFu1wKZYokUiSRehJ3yN1omEjhsge7PaxBwnyyvvtBfk8dSLy98RTbVtG2UWAtnelj8sgvUejIQesJ6ZlylzzcKFy5S-7bwGG9fEquPdyohRvt4EY7uFEHN2rhRuF8C250A24UcEG34UY7uFELNwpwowi3Z-TLp4_T98eBb-YRaLCQ6wBe-1zrQiS2ZKUpJBiuLNYsD9VQKwZCIY8ETOCGF4JLlWRGwCWgckwmOGPxHtkpq9I8J1RxkQnDRaSkGAgNBhVoKZ1wnZgwVFm0T8L2z0y1r3SPDVcW6R9ZuE_edJdcujIvf5t82HIo9S_-Mo0k1lLkfBAe3IbWC_IAT51T75Ds1FeNeUnu6VU9X169soD6CdvIqiE |
| linkProvider | IEEE |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Layered+Media+Parameter+Inversion+Method+Based+on+Deconvolution+Autoencoder+and+Self-Attention+Mechanism+Using+GPR+Data&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Yang%2C+Xiaopeng&rft.au=Sun%2C+Haoran&rft.au=Guo%2C+Conglong&rft.au=Li%2C+Yixuan&rft.date=2024&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=62&rft.spage=1&rft.epage=14&rft_id=info:doi/10.1109%2FTGRS.2024.3351894&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2024_3351894 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon |