AI-based geological subsurface reconstruction using sparse convolutional autoencoders
Subsurface reconstruction is critical for geological modeling and resource exploration. Conventional spatial interpolation methods are limited by stationarity and spatial isotropy assumptions, while advanced geostatistical techniques require specialized datasets. Deep learning approaches often need...
Uložené v:
| Vydané v: | Computers & geosciences Ročník 204; s. 105981 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Ltd
01.10.2025
|
| Predmet: | |
| ISSN: | 0098-3004 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Subsurface reconstruction is critical for geological modeling and resource exploration. Conventional spatial interpolation methods are limited by stationarity and spatial isotropy assumptions, while advanced geostatistical techniques require specialized datasets. Deep learning approaches often need large datasets, which is impractical for geoscientific applications. This study presents an AI-based methodology using a sparse convolutional autoencoder for robust subsurface modeling under data constraints and integrating secondary data sources such as Vertical Electrical Sounding (VES) data. A four-stage testing framework was implemented: (1) emulating conventional interpolation for baseline performance; (2) reconstructing subsurface geometries from synthetic data; (3) incorporating geophysical constraints through VES forward modeling; and (4) validating the methodology using a real-world case study from the Huancayo tectonic basin in the Peruvian Andes, using 41 VES measurements across two cross-sections (12 and 14 km long). Results demonstrate that the proposed model effectively emulates kriging interpolation (mean squared error: 1.5 × 10−3 to 1.2 × 10−3 with 100–800 training examples) through transfer learning from an inverse-distance, pre-trained model. In subsurface reconstruction, the model outperforms kriging (37.4–61.7 % improvement across 1–15 % sampling densities) through its ability to adapt to non-stationary conditions. When incorporating synthetic VES data, the model effectively reconstructed subsurface geometries with error reduction from 4.1 × 10−1 to 9.1 × 10−3 as stations increased from 1 to 40, demonstrating diminishing returns beyond this point. Application to the Huancayo basin case study validated the model's practical applicability by successfully identifying previously unmapped features including the contact between basement and sedimentary infill, folds and faults. The methodology demonstrates the AI's capability to enhance geological understanding in complex tectonic settings, revealing subtle features and refining existing assumptions about subsurface architecture.
[Display omitted]
•Novel AI method reconstructs subsurface properties with geophysical integration.•AI model reproduces conventional techniques using minimal training data.•Method outperformed conventional estimation in complex geological settings.•The new method enabled the identification of previously unknown subsurface features. |
|---|---|
| AbstractList | Subsurface reconstruction is critical for geological modeling and resource exploration. Conventional spatial interpolation methods are limited by stationarity and spatial isotropy assumptions, while advanced geostatistical techniques require specialized datasets. Deep learning approaches often need large datasets, which is impractical for geoscientific applications. This study presents an AI-based methodology using a sparse convolutional autoencoder for robust subsurface modeling under data constraints and integrating secondary data sources such as Vertical Electrical Sounding (VES) data. A four-stage testing framework was implemented: (1) emulating conventional interpolation for baseline performance; (2) reconstructing subsurface geometries from synthetic data; (3) incorporating geophysical constraints through VES forward modeling; and (4) validating the methodology using a real-world case study from the Huancayo tectonic basin in the Peruvian Andes, using 41 VES measurements across two cross-sections (12 and 14 km long). Results demonstrate that the proposed model effectively emulates kriging interpolation (mean squared error: 1.5 × 10−3 to 1.2 × 10−3 with 100–800 training examples) through transfer learning from an inverse-distance, pre-trained model. In subsurface reconstruction, the model outperforms kriging (37.4–61.7 % improvement across 1–15 % sampling densities) through its ability to adapt to non-stationary conditions. When incorporating synthetic VES data, the model effectively reconstructed subsurface geometries with error reduction from 4.1 × 10−1 to 9.1 × 10−3 as stations increased from 1 to 40, demonstrating diminishing returns beyond this point. Application to the Huancayo basin case study validated the model's practical applicability by successfully identifying previously unmapped features including the contact between basement and sedimentary infill, folds and faults. The methodology demonstrates the AI's capability to enhance geological understanding in complex tectonic settings, revealing subtle features and refining existing assumptions about subsurface architecture.
[Display omitted]
•Novel AI method reconstructs subsurface properties with geophysical integration.•AI model reproduces conventional techniques using minimal training data.•Method outperformed conventional estimation in complex geological settings.•The new method enabled the identification of previously unknown subsurface features. |
| ArticleNumber | 105981 |
| Author | Barriga-Berrios, Yoan Barriga-Gamarra, Jorge Baby, Patrice Viveen, Willem Uribe-Ventura, Rodrigo |
| Author_xml | – sequence: 1 givenname: Rodrigo orcidid: 0009-0003-9771-1094 surname: Uribe-Ventura fullname: Uribe-Ventura, Rodrigo organization: Grupo de Investigación en Geología Sedimentaria, Departamento de Ingeniería, Pontificia Universidad Católica del Perú, Lima, Peru – sequence: 2 givenname: Yoan surname: Barriga-Berrios fullname: Barriga-Berrios, Yoan organization: Grupo de Investigación en Geología Sedimentaria, Departamento de Ingeniería, Pontificia Universidad Católica del Perú, Lima, Peru – sequence: 3 givenname: Jorge surname: Barriga-Gamarra fullname: Barriga-Gamarra, Jorge organization: Universidad Nacional Jorge Basadre Grohmann, Avenida Miraflores s/n, 316, Tacna, Peru – sequence: 4 givenname: Patrice surname: Baby fullname: Baby, Patrice organization: Grupo de Investigación en Geología Sedimentaria, Departamento de Ingeniería, Pontificia Universidad Católica del Perú, Lima, Peru – sequence: 5 givenname: Willem surname: Viveen fullname: Viveen, Willem email: wviveen@pucp.pe organization: Grupo de Investigación en Geología Sedimentaria, Departamento de Ingeniería, Pontificia Universidad Católica del Perú, Lima, Peru |
| BookMark | eNp9kM9qwzAMh33oYO22J9glL5BOtuM2OexQyv4UCrusZyM7cnHJ4mInhb39nHXnXSTQj09I34LN-tATY48clhz46um0tHiksBQgVJ6opuYzNgdo6lICVLdskdIJAISo1ZwdNrvSYKK2yEwXjt5iV6TRpDE6tFREsqFPQxzt4ENfjMn3xyKdMSYqcnIJ3TgFGcJxCNTb0FJM9-zGYZfo4a_fscPry-f2vdx_vO22m32JYl0PpbPOSW7X1VRXgAK542DQSLuW5FARVk1lFTnVKuTKtQatdbIxDSgBRt4xed1rY0gpktPn6L8wfmsOerKhT_rXhp5s6KuNTD1fKcqnXTxFnazPp1Pr87uDboP_l_8B4pBw4w |
| Cites_doi | 10.1016/j.eswa.2025.128166 10.1016/j.gloplacha.2019.03.001 10.1007/s10596-024-10330-w 10.1007/978-3-319-65633-5_8 10.1007/s11004-012-9428-z 10.1016/j.envsoft.2013.12.008 10.1023/A:1014009426274 10.1007/s11004-018-09782-5 10.1190/1.3386676 10.1145/3658226 10.1145/3446776 10.1038/s41586-019-0912-1 10.1016/j.tecto.2021.228942 10.1007/s10064-020-01867-y 10.1016/j.neunet.2014.09.003 10.1016/j.earscirev.2024.104998 10.1016/j.jappgeo.2017.02.007 10.1038/nature14539 10.1109/TKDE.2018.2861006 10.1007/s11004-009-9229-1 10.1109/TPAMI.2020.3031898 10.1016/j.cageo.2020.104423 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.cageo.2025.105981 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geology |
| ExternalDocumentID | 10_1016_j_cageo_2025_105981 S0098300425001311 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1RT 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAHBH AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABQEM ABQYD ABWVN ABXDB ACDAQ ACGFS ACLVX ACNNM ACRLP ACRPL ACSBN ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO ADXHL AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRNS AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP ASPBG ATOGT AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EFKBS EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HMA HVGLF HZ~ IHE IMUCA J1W KOM LG9 LY3 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SEP SES SEW SPC SPCBC SSE SSV SSZ T5K TN5 WUQ ZCA ZMT ~02 ~G- 9DU AAYXX ACLOT CITATION EFLBG ~HD |
| ID | FETCH-LOGICAL-a278t-fcff31c74f31c60a2a1f10bab3c73efa5ea494c5ef5d5a15fdbaccf39b90520b3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001502921300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0098-3004 |
| IngestDate | Sat Nov 29 07:45:59 EST 2025 Sat Aug 09 17:32:02 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Andes Huancayo basin Electrical resistivity Geophysics Basin structure |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-a278t-fcff31c74f31c60a2a1f10bab3c73efa5ea494c5ef5d5a15fdbaccf39b90520b3 |
| ORCID | 0009-0003-9771-1094 |
| ParticipantIDs | crossref_primary_10_1016_j_cageo_2025_105981 elsevier_sciencedirect_doi_10_1016_j_cageo_2025_105981 |
| PublicationCentury | 2000 |
| PublicationDate | October 2025 2025-10-00 |
| PublicationDateYYYYMMDD | 2025-10-01 |
| PublicationDate_xml | – month: 10 year: 2025 text: October 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Computers & geosciences |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | LeCun, Bengio, Hinton (bib30) 2015; 521 Pan, Ni, Sun, Yang, Chen (bib42) 2010 Blanchy, Saneiyan, Boyd, McLachlan, Binley (bib8) 2020; 137 Reichstein, Camps-Valls, Stevens, Jung, Denzler, Carvalhais, Prabhat (bib46) 2019; 566 Banerjee, Nguyen, Fookes, Raissi (bib3) 2025; 287 Horton, Folguera (bib24) 2022 Viveen, Zevallos-Valdivia, Sanjurjo-Sanchez (bib54) 2019; 176 Liu, Mao, Wu, Feichtenhofer, Darrell, Xie (bib34) 2022 Boisvert, Manchuk, Deutsch (bib9) 2009; 41 Pineda, Ayma, Beltran (bib44) 2020; 43 Simonyan, K., & Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations (ICLR 2015), 1–14. Caers (bib10) 2011 Paredes (bib43) 1994; 48 Akanmu, Adewumi (bib1) 2016; 4 Bergen, Johnson, de Hoop, Beroza (bib6) 2019; 363 Mariethoz, Caers (bib37) 2014 Liu, Salazar, Jo, Prodanović, Pyrcz (bib33) 2025; 29 Goovaerts (bib19) 1997; vol. 483 Graham (bib20) 2015 Tian, Jiang, Diao, Lin, Wang, Yuan (bib53) Zhang, Bengio, Hardt, Recht, Vinyals (bib61) 2021; 64 Jaillard, Hérail, Monfret, Díaz-Martínez, Baby, Lavenu, Dumont, Cordani, Milani, Campos (bib26) 2000 Mallet (bib38) 2002 Baby, Prudhomme, Brusset, Robert, Roddaz, Calderon, Eude, Gil, Hermoza, Hurtado, Brichau, Calvès, Antoine, Salas-Gismondi (bib2) 2025; 260 Woo, Debnath, Hu, Chen, Liu, Kweon, Xie (bib58) 2023 Chiles, Delfiner (bib11) 2012; vol 713 Feng, Grana, Mosegaard (bib16) 2025 Graham, Engelcke, Van Der Maaten (bib21) 2018 Yin, Tao, Xia (bib59) 2020; 79 Wise (bib56) 2007; vol 102 Karpatne, Ebert-Uphoff, Ravela, Babaie, Kumar (bib27) 2018; 31 Cressie (bib12) 2015 Grana, Della Rossa (bib22) 2010; 75 Huang, Liu, Van Der Maaten, Weinberger (bib25) 2017 Lary, Zewdie, Liu, Wu, Levetin, Allee, Malakar, Walker, Mussa, Mannino, Aurin (bib29) 2018; 165 Yosinski, Clune, Bengio, Lipson (bib60) 2014; 27 Deng, Dong, Socher, Li, Li, Fei-Fei (bib14) 2009 He, Zhang, Ren, Sun (bib23) 2016 Krizhevsky, Sutskever, Hinton (bib28) 2012; 25 Viveen, Baby, Hurtado-Enríquez (bib55) 2021; 813 Williams, Huang, Swartz, Klar, Thakkar, Cong, Ren, Li, Fuji-Tsang, Fidler, Sifakis (bib57) 2024; 43 Silva, Deutsch (bib49) 2019; 51 Schmidhuber (bib48) 2015; 61 Qi, Luo (bib45) 2020; 44 Strebelle (bib51) 2002; 34 Machuca-Mory, Deutsch (bib36) 2013; 45 Dollfus, Mégard (bib15) 1968; 10 Lyster, Deutsch, Dose (bib35) 2006 Li, Heap (bib31) 2014; 53 Mégard (bib39) 1968 Tejero, Gomez-Ortiz, Heydt, Toledo, Martínez, Rodriguez, Suarez (bib52) 2017; 139 Reichstein (10.1016/j.cageo.2025.105981_bib46) 2019; 566 Machuca-Mory (10.1016/j.cageo.2025.105981_bib36) 2013; 45 Goovaerts (10.1016/j.cageo.2025.105981_bib19) 1997; vol. 483 Viveen (10.1016/j.cageo.2025.105981_bib55) 2021; 813 Strebelle (10.1016/j.cageo.2025.105981_bib51) 2002; 34 Huang (10.1016/j.cageo.2025.105981_bib25) 2017 Mallet (10.1016/j.cageo.2025.105981_bib38) 2002 Liu (10.1016/j.cageo.2025.105981_bib33) 2025; 29 Feng (10.1016/j.cageo.2025.105981_bib16) 2025 Karpatne (10.1016/j.cageo.2025.105981_bib27) 2018; 31 Grana (10.1016/j.cageo.2025.105981_bib22) 2010; 75 Banerjee (10.1016/j.cageo.2025.105981_bib3) 2025; 287 Liu (10.1016/j.cageo.2025.105981_bib34) 2022 Dollfus (10.1016/j.cageo.2025.105981_bib15) 1968; 10 Boisvert (10.1016/j.cageo.2025.105981_bib9) 2009; 41 Graham (10.1016/j.cageo.2025.105981_bib21) 2018 Woo (10.1016/j.cageo.2025.105981_bib58) 2023 Akanmu (10.1016/j.cageo.2025.105981_bib1) 2016; 4 Wise (10.1016/j.cageo.2025.105981_bib56) 2007; vol 102 Horton (10.1016/j.cageo.2025.105981_bib24) 2022 LeCun (10.1016/j.cageo.2025.105981_bib30) 2015; 521 Chiles (10.1016/j.cageo.2025.105981_bib11) 2012; vol 713 Bergen (10.1016/j.cageo.2025.105981_bib6) 2019; 363 Yin (10.1016/j.cageo.2025.105981_bib59) 2020; 79 Qi (10.1016/j.cageo.2025.105981_bib45) 2020; 44 Caers (10.1016/j.cageo.2025.105981_bib10) 2011 Zhang (10.1016/j.cageo.2025.105981_bib61) 2021; 64 Blanchy (10.1016/j.cageo.2025.105981_bib8) 2020; 137 Baby (10.1016/j.cageo.2025.105981_bib2) 2025; 260 Pan (10.1016/j.cageo.2025.105981_bib42) 2010 Pineda (10.1016/j.cageo.2025.105981_bib44) 2020; 43 Li (10.1016/j.cageo.2025.105981_bib31) 2014; 53 10.1016/j.cageo.2025.105981_bib50 Graham (10.1016/j.cageo.2025.105981_bib20) 2015 Viveen (10.1016/j.cageo.2025.105981_bib54) 2019; 176 Deng (10.1016/j.cageo.2025.105981_bib14) 2009 Williams (10.1016/j.cageo.2025.105981_bib57) 2024; 43 Lyster (10.1016/j.cageo.2025.105981_bib35) 2006 Paredes (10.1016/j.cageo.2025.105981_bib43) 1994; 48 Tian (10.1016/j.cageo.2025.105981_bib53) Schmidhuber (10.1016/j.cageo.2025.105981_bib48) 2015; 61 Lary (10.1016/j.cageo.2025.105981_bib29) 2018; 165 He (10.1016/j.cageo.2025.105981_bib23) 2016 Yosinski (10.1016/j.cageo.2025.105981_bib60) 2014; 27 Krizhevsky (10.1016/j.cageo.2025.105981_bib28) 2012; 25 Mégard (10.1016/j.cageo.2025.105981_bib39) 1968 Jaillard (10.1016/j.cageo.2025.105981_bib26) 2000 Mariethoz (10.1016/j.cageo.2025.105981_bib37) 2014 Silva (10.1016/j.cageo.2025.105981_bib49) 2019; 51 Tejero (10.1016/j.cageo.2025.105981_bib52) 2017; 139 Cressie (10.1016/j.cageo.2025.105981_bib12) 2015 |
| References_xml | – volume: 48 year: 1994 ident: bib43 article-title: Geología del cuadrángulo de Jauja publication-title: Instituto Geol. Minero y Metalúrgico del Perú, Bol – volume: 61 start-page: 85 year: 2015 end-page: 117 ident: bib48 article-title: Deep learning in neural networks: an overview publication-title: Neural Netw. – start-page: 1 year: 2025 end-page: 24 ident: bib16 article-title: Geostatistical facies simulation based on training image using generative networks and gradual deformation publication-title: Math. Geosci. – start-page: 123 year: 1968 ident: bib39 article-title: - Geología del cuadrángulo de Huancayo publication-title: Bol. Servicio de Geol. y Minería, No. 18 – volume: 176 start-page: 1 year: 2019 end-page: 22 ident: bib54 article-title: The influence of centennial-scale variations in the South American summer monsoon and base-level fall on Holocene fluvial systems in the Peruvian Andes publication-title: Global Planet. Change – volume: vol 713 year: 2012 ident: bib11 publication-title: Geostatistics: Modeling Spatial Uncertainty – volume: vol. 483 year: 1997 ident: bib19 publication-title: Geostatistics for Natural Resources Evaluation – start-page: 9224 year: 2018 end-page: 9232 ident: bib21 article-title: 3d semantic segmentation with submanifold sparse convolutional networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 770 year: 2016 end-page: 778 ident: bib23 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 813 year: 2021 ident: bib55 article-title: Assessing the accuracy of combined DEM-based lineament mapping and the normalised SL-index as a tool for active fault mapping publication-title: Tectonophysics – volume: 34 start-page: 1 year: 2002 end-page: 21 ident: bib51 article-title: Conditional simulation of complex geological structures using multiple-point statistics publication-title: Math. Geol. – start-page: 16133 year: 2023 end-page: 16142 ident: bib58 article-title: Convnext v2: Co-designing and scaling convnets with masked autoencoders publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 25 year: 2012 ident: bib28 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inf. Process. Syst. – volume: 31 start-page: 1544 year: 2018 end-page: 1554 ident: bib27 article-title: Machine learning for the geosciences: challenges and opportunities publication-title: IEEE Trans. Knowl. Data Eng. – volume: 139 start-page: 54 year: 2017 end-page: 64 ident: bib52 article-title: Electrical resistivity imaging of the shallow structures of an intraplate basin: the Guadiana Basin (SW Spain) publication-title: J. Appl. Geophys. – volume: 75 start-page: O21 year: 2010 end-page: O37 ident: bib22 article-title: Probabilistic petrophysical-properties estimation integrating statistical rock physics with seismic inversion publication-title: Geophysics – start-page: 26 year: 2006 ident: bib35 article-title: A new MPS simulation algorithm based on Gibbs sampling publication-title: Centre Comput. Geostat. – year: 2015 ident: bib12 article-title: Statistics for Spatial Data – volume: 79 start-page: 5049 year: 2020 end-page: 5060 ident: bib59 article-title: Active faults and bedrock detection with super-high-density electrical resistivity imaging publication-title: Bull. Eng. Geol. Environ. – start-page: 481 year: 2000 end-page: 559 ident: bib26 publication-title: Tectonic Evolution of the Andes of Ecuador, Peru, Bolivia and Northern Chile – ident: bib53 article-title: Designing bert for convolutional networks: sparse and hierarchical masked modeling – start-page: 4700 year: 2017 end-page: 4708 ident: bib25 article-title: Densely connected convolutional networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 44 start-page: 2168 year: 2020 end-page: 2187 ident: bib45 article-title: Small data challenges in big data era: a survey of recent progress on unsupervised and semi-supervised methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: vol 102 year: 2007 ident: bib56 publication-title: Tectono-stratigraphic history of the Huancayo intermontane basin, central Peru: Boletín de la Sociedad Geológica del Perú – volume: 51 start-page: 527 year: 2019 end-page: 552 ident: bib49 article-title: Multivariate categorical modeling with hierarchical truncated pluri-Gaussian simulation publication-title: Math. Geosci. – year: 2011 ident: bib10 article-title: Modeling Uncertainty in the Earth Sciences – volume: 41 start-page: 585 year: 2009 end-page: 601 ident: bib9 article-title: Kriging in the presence of locally varying anisotropy using non-Euclidean distances publication-title: Math. Geosci. – volume: 29 start-page: 6 year: 2025 ident: bib33 article-title: Minimum acceptance criteria for subsurface scenario-based uncertainty models from single image generative adversarial networks (SinGAN) publication-title: Comput. Geosci. – year: 2002 ident: bib38 article-title: Geomodeling – volume: 566 start-page: 195 year: 2019 end-page: 204 ident: bib46 article-title: Deep learning and process understanding for data-driven Earth system science publication-title: Nature – year: 2015 ident: bib20 article-title: Sparse 3D convolutional neural networks – volume: 43 start-page: 1 year: 2024 end-page: 15 ident: bib57 article-title: fVDB: a deep-learning framework for sparse, large scale, and high performance spatial intelligence publication-title: ACM Trans. Graph. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib30 article-title: Deep learning publication-title: Nature – volume: 53 start-page: 173 year: 2014 end-page: 189 ident: bib31 article-title: Spatial interpolation methods applied in the environmental sciences: a review publication-title: Environ. Model. Software – volume: 137 year: 2020 ident: bib8 article-title: ResIPy, an intuitive open source software for complex geoelectrical inversion/modeling publication-title: Comput. Geosci. – volume: 27 year: 2014 ident: bib60 article-title: How transferable are features in deep neural networks? publication-title: Adv. Neural Inf. Process. Syst. – volume: 64 start-page: 107 year: 2021 end-page: 115 ident: bib61 article-title: Understanding deep learning (still) requires rethinking generalization publication-title: Commun. ACM – volume: 363 year: 2019 ident: bib6 article-title: Machine learning for data-driven discovery in solid Earth geoscience publication-title: Sci. Technol. Humanit. – start-page: 248 year: 2009 end-page: 255 ident: bib14 article-title: Imagenet: a large-scale hierarchical image database publication-title: 2009 IEEE Conference on Computer Vision and Pattern Recognition – start-page: 11976 year: 2022 end-page: 11986 ident: bib34 article-title: A convnet for the 2020s publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 287 start-page: 128166 year: 2025 ident: bib3 article-title: A survey on physics informed reinforcement learning: review and open problems publication-title: Exp. Syst. Appl. – volume: 260 year: 2025 ident: bib2 article-title: The Northern Central Andes and Andean tectonic evolution revisited: an integrated stratigraphic and structural model of three superimposed orogens publication-title: Earth Sci. Rev. – volume: 165 year: 2018 ident: bib29 article-title: Machine learning applications for earth observation publication-title: Earth Observ. Open Sci. Innov. – volume: 43 start-page: 9 year: 2020 end-page: 14 ident: bib44 article-title: A generative adversarial network approach for super-resolution of Sentinel-2 satellite images publication-title: Int. Arch. Photogram. Rem. Sens. Spatial Inf. Sci. – volume: 10 start-page: 429 year: 1968 end-page: 440 ident: bib15 article-title: - Les formations quaternaires du basin de Huancayo et leur néotectonique (Andes centrales peruviennes) publication-title: Rev. Geogr. Phys. Geol. Dyn. – start-page: 3 year: 2022 end-page: 28 ident: bib24 article-title: Tectonic inheritance and structural styles in the Andean fold-thrust belt and foreland basin publication-title: Andean Structural Styles – volume: 4 start-page: 112 year: 2016 end-page: 126 ident: bib1 article-title: Geophysical characterization of aquifer parameters within basement complex rocks using electrical sounding data from the polytechnic, Ibadan, Southwestern Nigeria publication-title: Int. J. Sci. Res. Knowl. – start-page: 751 year: 2010 end-page: 760 ident: bib42 article-title: Cross-domain sentiment classification via spectral feature alignment publication-title: Proceedings of the 19th International Conference on World Wide Web – reference: Simonyan, K., & Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations (ICLR 2015), 1–14. – volume: 45 start-page: 31 year: 2013 end-page: 48 ident: bib36 article-title: Non-stationary geostatistical modeling based on distance weighted statistics and distributions publication-title: Math. Geosci. – year: 2014 ident: bib37 article-title: Multiple-point Geostatistics: Stochastic Modeling with Training Images – volume: 287 start-page: 128166 year: 2025 ident: 10.1016/j.cageo.2025.105981_bib3 article-title: A survey on physics informed reinforcement learning: review and open problems publication-title: Exp. Syst. Appl. doi: 10.1016/j.eswa.2025.128166 – volume: 25 year: 2012 ident: 10.1016/j.cageo.2025.105981_bib28 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inf. Process. Syst. – volume: 176 start-page: 1 year: 2019 ident: 10.1016/j.cageo.2025.105981_bib54 article-title: The influence of centennial-scale variations in the South American summer monsoon and base-level fall on Holocene fluvial systems in the Peruvian Andes publication-title: Global Planet. Change doi: 10.1016/j.gloplacha.2019.03.001 – start-page: 1 year: 2025 ident: 10.1016/j.cageo.2025.105981_bib16 article-title: Geostatistical facies simulation based on training image using generative networks and gradual deformation publication-title: Math. Geosci. – year: 2015 ident: 10.1016/j.cageo.2025.105981_bib20 article-title: Sparse 3D convolutional neural networks – volume: 29 start-page: 6 issue: 1 year: 2025 ident: 10.1016/j.cageo.2025.105981_bib33 article-title: Minimum acceptance criteria for subsurface scenario-based uncertainty models from single image generative adversarial networks (SinGAN) publication-title: Comput. Geosci. doi: 10.1007/s10596-024-10330-w – volume: 43 start-page: 9 year: 2020 ident: 10.1016/j.cageo.2025.105981_bib44 article-title: A generative adversarial network approach for super-resolution of Sentinel-2 satellite images publication-title: Int. Arch. Photogram. Rem. Sens. Spatial Inf. Sci. – start-page: 16133 year: 2023 ident: 10.1016/j.cageo.2025.105981_bib58 article-title: Convnext v2: Co-designing and scaling convnets with masked autoencoders – volume: vol 713 year: 2012 ident: 10.1016/j.cageo.2025.105981_bib11 – start-page: 3 year: 2022 ident: 10.1016/j.cageo.2025.105981_bib24 article-title: Tectonic inheritance and structural styles in the Andean fold-thrust belt and foreland basin – year: 2014 ident: 10.1016/j.cageo.2025.105981_bib37 – volume: 27 year: 2014 ident: 10.1016/j.cageo.2025.105981_bib60 article-title: How transferable are features in deep neural networks? publication-title: Adv. Neural Inf. Process. Syst. – volume: 165 year: 2018 ident: 10.1016/j.cageo.2025.105981_bib29 article-title: Machine learning applications for earth observation publication-title: Earth Observ. Open Sci. Innov. doi: 10.1007/978-3-319-65633-5_8 – volume: 45 start-page: 31 year: 2013 ident: 10.1016/j.cageo.2025.105981_bib36 article-title: Non-stationary geostatistical modeling based on distance weighted statistics and distributions publication-title: Math. Geosci. doi: 10.1007/s11004-012-9428-z – volume: 10 start-page: 429 year: 1968 ident: 10.1016/j.cageo.2025.105981_bib15 article-title: - Les formations quaternaires du basin de Huancayo et leur néotectonique (Andes centrales peruviennes) publication-title: Rev. Geogr. Phys. Geol. Dyn. – volume: 53 start-page: 173 year: 2014 ident: 10.1016/j.cageo.2025.105981_bib31 article-title: Spatial interpolation methods applied in the environmental sciences: a review publication-title: Environ. Model. Software doi: 10.1016/j.envsoft.2013.12.008 – volume: 34 start-page: 1 year: 2002 ident: 10.1016/j.cageo.2025.105981_bib51 article-title: Conditional simulation of complex geological structures using multiple-point statistics publication-title: Math. Geol. doi: 10.1023/A:1014009426274 – start-page: 248 year: 2009 ident: 10.1016/j.cageo.2025.105981_bib14 article-title: Imagenet: a large-scale hierarchical image database – volume: 51 start-page: 527 issue: 5 year: 2019 ident: 10.1016/j.cageo.2025.105981_bib49 article-title: Multivariate categorical modeling with hierarchical truncated pluri-Gaussian simulation publication-title: Math. Geosci. doi: 10.1007/s11004-018-09782-5 – start-page: 26 issue: 8 year: 2006 ident: 10.1016/j.cageo.2025.105981_bib35 article-title: A new MPS simulation algorithm based on Gibbs sampling publication-title: Centre Comput. Geostat. – volume: vol. 483 year: 1997 ident: 10.1016/j.cageo.2025.105981_bib19 – volume: 75 start-page: O21 issue: 3 year: 2010 ident: 10.1016/j.cageo.2025.105981_bib22 article-title: Probabilistic petrophysical-properties estimation integrating statistical rock physics with seismic inversion publication-title: Geophysics doi: 10.1190/1.3386676 – ident: 10.1016/j.cageo.2025.105981_bib53 – volume: 43 start-page: 1 issue: 4 year: 2024 ident: 10.1016/j.cageo.2025.105981_bib57 article-title: fVDB: a deep-learning framework for sparse, large scale, and high performance spatial intelligence publication-title: ACM Trans. Graph. doi: 10.1145/3658226 – year: 2011 ident: 10.1016/j.cageo.2025.105981_bib10 – start-page: 481 year: 2000 ident: 10.1016/j.cageo.2025.105981_bib26 – volume: 64 start-page: 107 issue: 3 year: 2021 ident: 10.1016/j.cageo.2025.105981_bib61 article-title: Understanding deep learning (still) requires rethinking generalization publication-title: Commun. ACM doi: 10.1145/3446776 – year: 2002 ident: 10.1016/j.cageo.2025.105981_bib38 – volume: 566 start-page: 195 issue: 7743 year: 2019 ident: 10.1016/j.cageo.2025.105981_bib46 article-title: Deep learning and process understanding for data-driven Earth system science publication-title: Nature doi: 10.1038/s41586-019-0912-1 – volume: 813 year: 2021 ident: 10.1016/j.cageo.2025.105981_bib55 article-title: Assessing the accuracy of combined DEM-based lineament mapping and the normalised SL-index as a tool for active fault mapping publication-title: Tectonophysics doi: 10.1016/j.tecto.2021.228942 – volume: 79 start-page: 5049 year: 2020 ident: 10.1016/j.cageo.2025.105981_bib59 article-title: Active faults and bedrock detection with super-high-density electrical resistivity imaging publication-title: Bull. Eng. Geol. Environ. doi: 10.1007/s10064-020-01867-y – volume: 4 start-page: 112 issue: 5 year: 2016 ident: 10.1016/j.cageo.2025.105981_bib1 article-title: Geophysical characterization of aquifer parameters within basement complex rocks using electrical sounding data from the polytechnic, Ibadan, Southwestern Nigeria publication-title: Int. J. Sci. Res. Knowl. – start-page: 9224 year: 2018 ident: 10.1016/j.cageo.2025.105981_bib21 article-title: 3d semantic segmentation with submanifold sparse convolutional networks – volume: 61 start-page: 85 year: 2015 ident: 10.1016/j.cageo.2025.105981_bib48 article-title: Deep learning in neural networks: an overview publication-title: Neural Netw. doi: 10.1016/j.neunet.2014.09.003 – start-page: 4700 year: 2017 ident: 10.1016/j.cageo.2025.105981_bib25 article-title: Densely connected convolutional networks – start-page: 11976 year: 2022 ident: 10.1016/j.cageo.2025.105981_bib34 article-title: A convnet for the 2020s – volume: 260 year: 2025 ident: 10.1016/j.cageo.2025.105981_bib2 article-title: The Northern Central Andes and Andean tectonic evolution revisited: an integrated stratigraphic and structural model of three superimposed orogens publication-title: Earth Sci. Rev. doi: 10.1016/j.earscirev.2024.104998 – ident: 10.1016/j.cageo.2025.105981_bib50 – year: 2015 ident: 10.1016/j.cageo.2025.105981_bib12 – volume: 363 issue: 6433 year: 2019 ident: 10.1016/j.cageo.2025.105981_bib6 article-title: Machine learning for data-driven discovery in solid Earth geoscience publication-title: Sci. Technol. Humanit. – volume: 139 start-page: 54 year: 2017 ident: 10.1016/j.cageo.2025.105981_bib52 article-title: Electrical resistivity imaging of the shallow structures of an intraplate basin: the Guadiana Basin (SW Spain) publication-title: J. Appl. Geophys. doi: 10.1016/j.jappgeo.2017.02.007 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.cageo.2025.105981_bib30 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 31 start-page: 1544 issue: 8 year: 2018 ident: 10.1016/j.cageo.2025.105981_bib27 article-title: Machine learning for the geosciences: challenges and opportunities publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2018.2861006 – volume: vol 102 year: 2007 ident: 10.1016/j.cageo.2025.105981_bib56 – volume: 41 start-page: 585 year: 2009 ident: 10.1016/j.cageo.2025.105981_bib9 article-title: Kriging in the presence of locally varying anisotropy using non-Euclidean distances publication-title: Math. Geosci. doi: 10.1007/s11004-009-9229-1 – volume: 44 start-page: 2168 issue: 4 year: 2020 ident: 10.1016/j.cageo.2025.105981_bib45 article-title: Small data challenges in big data era: a survey of recent progress on unsupervised and semi-supervised methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.3031898 – volume: 48 year: 1994 ident: 10.1016/j.cageo.2025.105981_bib43 article-title: Geología del cuadrángulo de Jauja publication-title: Instituto Geol. Minero y Metalúrgico del Perú, Bol – volume: 137 year: 2020 ident: 10.1016/j.cageo.2025.105981_bib8 article-title: ResIPy, an intuitive open source software for complex geoelectrical inversion/modeling publication-title: Comput. Geosci. doi: 10.1016/j.cageo.2020.104423 – start-page: 751 year: 2010 ident: 10.1016/j.cageo.2025.105981_bib42 article-title: Cross-domain sentiment classification via spectral feature alignment – start-page: 770 year: 2016 ident: 10.1016/j.cageo.2025.105981_bib23 article-title: Deep residual learning for image recognition – start-page: 123 year: 1968 ident: 10.1016/j.cageo.2025.105981_bib39 article-title: - Geología del cuadrángulo de Huancayo publication-title: Bol. Servicio de Geol. y Minería, No. 18 |
| SSID | ssj0002285 |
| Score | 2.4505825 |
| Snippet | Subsurface reconstruction is critical for geological modeling and resource exploration. Conventional spatial interpolation methods are limited by stationarity... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 105981 |
| SubjectTerms | Andes Basin structure Deep learning Electrical resistivity Geophysics Huancayo basin |
| Title | AI-based geological subsurface reconstruction using sparse convolutional autoencoders |
| URI | https://dx.doi.org/10.1016/j.cageo.2025.105981 |
| Volume | 204 |
| WOSCitedRecordID | wos001502921300001&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0098-3004 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0002285 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9QwFLaGFiQuiFWUTT5wK0aJE4_j44BKKYeKQwcNp8h27NFUJakyi8qf4DfzvCSZoaiiBy5WlhnH8vv0Nj1_D6G3lFlqMpuQRPKE5FynRGRGEDOucpYkJmVV5ZtN8NPTYjYTX0ejX91ZmM0Fr-vi6kpc_ldRwzMQtjs6ewtx95PCA7gGocMIYofxnwQ_OSHONFWHc9MrtiWoh3VrpXZNUnQzsMYern2uANRKG-rWN3FtjkJgvWoczWUVi-R7QoPYCGLpYQNfiVa0986n7UIZ8s2bs-CbNlW7mDdD1rSFW0k-OFbIUOb3vRlQ2r0-lj_gKtTyusT98D6wgYbuAmY7b0FZXwHX62JREMf3ta2LabwN2tT5fqGhyzVFH3IO5xDEz_0ZTsreD7_epdX-w9z1RYhdfdt56Scp3SRlmOQO2qecCVD0-5OTo9mX3rZTWrCOhdWtveOx8hWD19byd19ny385e4gexMADTwJgHqGRqR-je8ceIz-foGkHGzzABg-wwbuwwR42OMAG78AGb8PmKZp-Ojr7-JnElhtEUl6siNXWZqnmuRvHiaQytWmipMo0z4yVzMhc5JoZyyomU2YrJbW2mVDCFVSp7Bnaq5vaPEfYQmTNZGLTlKtcaSlM5uIJqSCCLnhhD9C7bnPKy8CsUt4gkgM07jawjLAOTl8JkLjpjy9u952X6P6A1ldoDzbWvEZ39Wa1WLZvIh5-A3DKi04 |
| linkProvider | Elsevier |
| 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=AI-based+geological+subsurface+reconstruction+using+sparse+convolutional+autoencoders&rft.jtitle=Computers+%26+geosciences&rft.au=Uribe-Ventura%2C+Rodrigo&rft.au=Barriga-Berrios%2C+Yoan&rft.au=Barriga-Gamarra%2C+Jorge&rft.au=Baby%2C+Patrice&rft.date=2025-10-01&rft.issn=0098-3004&rft.volume=204&rft.spage=105981&rft_id=info:doi/10.1016%2Fj.cageo.2025.105981&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cageo_2025_105981 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0098-3004&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0098-3004&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0098-3004&client=summon |