[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127365-en":3,"doc-seo-127365-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127365,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Applying spectral decomposition to seismic facies clustering with unsupervised machine learning","Seismic facies analysis supports subsurface geological exploration, but traditional interpretation struggles with subtle variations in complex stratigraphic settings. This study integrates spectral decomposition with unsupervised machine learning using the Kohonen Self-Organizing Map to classify detailed seismic facies. Continuous Wavelet Transform decomposes seismic signals into frequency components, which are then clustered by SOM. Validation on South Caspian Basin data shows improved identification of channel systems and facies boundaries, strengthening delineation and enabling more accurate interpretation of internal variability, useful for reservoir characterization and hydrocarbon exploration.","УДК 551: 004.89 DOI: [https://doi.org/10.24028/gj.v47i3.320290](https://doi.org/10.24028/gj.v47i3.320290)  \nApplying spectral decomposition to seismic facies clustering with unsupervised machine learning  \nR. Malikov, G. Babayev, 2025  \nInstitute of Geology and Geophysics of the Ministry of Science and Education of the Republic of Azerbaijan, Baku, Azerbaijan Received 5 January 2025  \nSeismic facies analysis, essential for subsurface geological exploration, has traditionally challenged the ability to capture subtle variations in complex stratigraphic environments. This study uses spectral decomposition and unsupervised machine learning, specifically the Kohonen Self-Organizing Map, to improve the identification of detailed seismic facies. Spectral decomposition enables frequency-based seismic data analysis, capturing intricate geological features often missed by traditional methods. The Continuous Wavelet Transform was applied to decompose seismic signals, and the resulting frequency components were clustered using a Self-Organizing Map to classify seismic facies. This paper validated this approach using seismic data from the South Caspian Basin. The results successfully identified channel systems and facies boundaries, enhancing their delineation and enabling a more accurate interpretation of channel systems and their internal variability. This automated methodology offers valuable insights for reservoir characterization and hydrocarbon exploration, potentially reducing exploration risks and enhancing resource estimation.  \nKey words: seismic facies, spectral decomposition, self-organizing map, continuous wavelet transform, unsupervised learning, machine learning.  \nIntroduction. One of the techniques uti- ficiency of subsurface interpretations [Roden lized to explore subsurface geology is seis- et al. , 2015; Meyer et al. , 2022] .  \nmic facies analysis, which uses seismic data The frequency content of seismic data conto classify seismic wave behavior and features tains more information than is immediately to extract subsurface stratigraphic character- apparent. Spectral decomposition, a techistics [Brown, 2011; Kourki, Ali Riahi, 2014; nique that decomposes seismic signals into Song et al. , 2017; Wrona et al. , 2018] . While their component frequencies, is known for its effective in identifying major geological fea- ability to highlight subtle geological features tures, traditional seismic interpretation meth- such as thin beds, fluid content, and stratiods often fall short in capturing subtle varia- graphic variations [Partyka et al. , 1999; Shantions in complex stratigraphic environments et al. , 2019; Castagna et al. , 2003] . Focusing [Partyka et al. , 1999; Chopra, Marfurt, 2008] . on the frequency domain, this approach proThe recent rise in machine learning technolo- vides a more detailed representation of subgies, particularly unsupervised learning algo- surface structures than traditional amplituderithms such as the Kohonen Self-Organizing based methods, which often fail to capture the Map (SOM), provides new opportunities for full complexity of the geological signal [Sinha automating the classification of seismic fa- et al. , 2005] . The power of spectral decomcies, thereby improving the accuracy and ef- position lies in its ability to reveal geological  \nCitation: Malikov, R. , & Babayev, G. (2025) . Applying spectral decomposition to seismic facies clustering with unsupervised machine learning. geofizychnyi Zhurnal, 47(3), 43—53. [https://doi.org/10.24028/gj.](https://doi.org/10.24028/gj.v47i3.320290)[v47i3.320290](https://doi.org/10.24028/gj.v47i3.320290) . Publisher S. Subbotin Institute of Geophysics of NAS of Ukraine, 2025. This is an open access article under the CC BY-NC-SA license ([https://creativecommons.org/licenses/by-nc-sa/4.0/](https://creativecommons.org/licenses/by-nc-sa/4.0/)).  \nissn 0203-3100. geophysical Journal. 2025. Vol. 47. № 3 43  \nheterogeneities at multiple scales, making ita valuable t","cbCaisOnopt2JE2G","https://ap.wps.com/l/cbCaisOnopt2JE2G","pdf",3764058,2,1,11,"English","en",105,"# Introduction\n## Seismic facies analysis and challenges\n## Spectral decomposition for frequency-domain interpretation\n## Unsupervised learning and the Kohonen Self-Organizing Map","[{\"question\":\"What workflow combines spectral decomposition and unsupervised learning in this study?\",\"answer\":\"The method applies the Continuous Wavelet Transform to decompose seismic signals into frequency components, then clusters these components using a Kohonen Self-Organizing Map to classify seismic facies.\"},{\"question\":\"Why is spectral decomposition important for seismic facies analysis?\",\"answer\":\"It highlights frequency-based geological features, helping capture subtle stratigraphic variations that conventional amplitude-based interpretation may miss.\"},{\"question\":\"How were the results validated, and what geologic targets improved?\",\"answer\":\"The approach was validated using seismic data from the South Caspian Basin, successfully identifying channel systems and facies boundaries while improving delineation of internal variability.\"}]","Applying spectral decomposition to seismic facies clustering with unsupervised machine learning | PDF",1785938516,28,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"applying-spectral-decomposition-to-seismic-facies-clustering-with-unsupervised-machine-learning","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/applying-spectral-decomposition-to-seismic-facies-clustering-with-unsupervised-machine-learning/127365/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What workflow combines spectral decomposition and unsupervised learning in this study?","Question",{"text":76,"@type":77},"The method applies the Continuous Wavelet Transform to decompose seismic signals into frequency components, then clusters these components using a Kohonen Self-Organizing Map to classify seismic facies.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Why is spectral decomposition important for seismic facies analysis?",{"text":81,"@type":77},"It highlights frequency-based geological features, helping capture subtle stratigraphic variations that conventional amplitude-based interpretation may miss.",{"name":83,"@type":74,"acceptedAnswer":84},"How were the results validated, and what geologic targets improved?",{"text":85,"@type":77},"The approach was validated using seismic data from the South Caspian Basin, successfully identifying channel systems and facies boundaries while improving delineation of internal variability.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]