[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125473-en":3,"doc-seo-125473-105":30,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125473,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Machine learning approach to Nemrut Dağ and Bingöl obsidians - insights from Tūlūl al Baqarat obsidian prehistoric tools - IOP","A machine learning approach was employed to determine the source material of nine obsidian blades from the archaeological site of Tulūl al Baqarat (Iraq) using geo-referenced reference datasets from Nemrut Dağ stratovolcano and Bingöl volcanic plateaux. Chemical characterization used non-invasive, non-destructive methods: low-vacuum SEM-EDS for major and minor elements and bench-to-top micro-XRF for trace elements. A comparative geochemical study combined with a first-time machine learning workflow minimized discrepancies from differing analytical techniques and laboratory variability, enabling robust discrimination and classification. The results indicate a peraluminous rhyolite composition with high Zr content consistent with Nemrut Dağ mild alkaline rhyolitic obsidians from pre-caldera eruptions, supporting possible attribution to specific Nemrut Dağ flows and suggesting trade/exchange along the Tigris River since the 4th millennium BC.","ANNALS OF GEOPHYSICS, 69, 2026; doi:10.4401/ag-9369 OPEN ACCESS  \nMachine learning approach to Nemrut Dağ and Bingöl obsidians: insights from Tūlūl al Baqarat obsidian prehistoric tools (Iraq, IV millennium BC) and volcanological implications  \nGloria Vaggelli *,1, Alessandro Borghi2, Roberto Cossio2, Stefano Ghignone2, Carlo Lippolis3  \n(1) Istituto di Geoscienze e Georisorse, CNR, Via Valperga Caluso, 35, I‑10123 Torino  \n(2) Dipartimento di Scienze della Terra, Università degli Studi di Torino, Via Valperga Caluso, 35, I‑10123 Torino  \n(3) Dipartimento di Studi Storici, Università degli Studi di Torino, via Sant’Ottavio 20, I‑10124 Torino Article history: received May 16, 2025; accepted December 2, 2025  \nAbstract  \nA machine learning approach was employed to determine the source material of nine obsidian blades from the archaeological site of Tulūl al Baqarat (Iraq) employing geo‑referenced obsidians from Nemrut Dağ stratovolcano and Bingöl volcanic plateaux as the reference dataset for the investigation. On the obsidian tools were performed chemical analysis using non‑invasive and non‑destructive techniques. Major and minor elements were determined using a low vacuum SEM‑EDS microprobe, while trace elements were analyzed using a bench‑to‑top micro‑XRF.  \nTo determine the provenance of obsidian artifacts and identify the volcanic complex from which the tools were sourced, through a comparative geochemical study, we used the chemical composition of georeferenced obsidian samples reported in literature. To minimize the differences related to different analytical techniques and different laboratory variability, we applied, for the first time, a machine learning approach. Indeed, in this study we demonstrated that only the machine learning approach proved an exhaustive method to discriminate and classify a dataset, complemented by well‑known geochemical comparisons. The analyzed nine obsidian tools display a peraluminous rhyolite composition with a peculiar high Zr content which excludes most obsidian outcrops in Turkish and Armenian volcanic sites as potential original sources. Nevertheless, a machine learning approach applied to selected major, minor, and trace elements indicate the obsidian tools results comparable to Nemrut Dağ mild alkaline rhyolitic obsidians from pre‑caldera eruptions. These obsidians are now exposed within the caldera and in Sicaksu outcrop (SE Türkiye). Therefore, the artifacts may even be attributed to specific Nemrut Dağ flows using geochemically significant elements. The provenance of the source from the Nemrut Dağ stratovolcano in south‑eastern Türkiye, situated along the Turkish route of the Tigris River, supports the hypothesis of a network of trade and broad exchange since the 4th millennium BC, from southeastern Anatolia, which is presumed to have occurred along the Tigris River up to the shores ofthe Persian Gulf.  \nKeywords: Obsidian; Provenance; Machine learning; Bingöl; Nemrut Dağ  \nGloria Vaggelli et al.  \n1. Introduction  \nObsidian is an excellent natural row material widely used for making tools and precious objects by prehistoric people in Mediterranean area (Tykot, 1996) and in the Middle and Near East (Chataigner et al., 1998). When chipped, it creates exceptionally sharp and durable cutting edges thanks to its high hardness (5‑5.5 on the Mohs scale) and conchoidal fracturing. To some extent, obsidian tools are better than chert and jasper for cutting softer materials like plants and animal flesh. Obsidian tools are also found in archaeological sites hundreds of kilometers away from their geological source (Tykot, 2002), even when alternative materials were available at minor distances, suggesting obsidians high value for ancient societies.  \nIn archaeological reconstructions, obsidian tools play a significant archaeological and historical role for tracing the geological source and provenance by comparing chemical analysis with natural outcrops. This allows us to study interactions b","cbCaicUboLq3lZ0A","https://ap.wps.com/l/cbCaicUboLq3lZ0A","pdf",5415272,1,18,"English","en",105,"# Introduction\n# Archaeological and geological setting","[{\"question\":\"What is the document’s main goal in studying the nine obsidian tools?\",\"answer\":\"To determine the provenance/source material of nine obsidian blades from Tulūl al Baqarat by comparing their geochemical signatures with reference datasets from Nemrut Dağ and Bingöl.\"},{\"question\":\"Which analytical techniques were used to measure the obsidian chemistry?\",\"answer\":\"Major and minor elements were measured with a low-vacuum SEM-EDS microprobe, while trace elements were analyzed using bench-to-top micro-XRF, using non-invasive and non-destructive procedures.\"},{\"question\":\"Why was machine learning used, and what did it improve?\",\"answer\":\"Machine learning was applied to address differences caused by varying analytical methods and laboratory variability, producing an exhaustive way to discriminate and classify the dataset alongside standard geochemical comparisons.\"}]","Machine learning approach to Nemrut Dağ and Bingöl obsidians - insights from Tūlūl al Baqarat obsidian prehistoric tools - IOP | PDF",1785899193,45,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-approach-to-nemrut-dag-and-bingol-obsidians-insights-from-tulul-al-baqarat-obsidian-prehistoric-tools","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-approach-to-nemrut-dag-and-bingol-obsidians-insights-from-tulul-al-baqarat-obsidian-prehistoric-tools/125473/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the document’s main goal in studying the nine obsidian tools?","Question",{"text":75,"@type":76},"To determine the provenance/source material of nine obsidian blades from Tulūl al Baqarat by comparing their geochemical signatures with reference datasets from Nemrut Dağ and Bingöl.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which analytical techniques were used to measure the obsidian chemistry?",{"text":80,"@type":76},"Major and minor elements were measured with a low-vacuum SEM-EDS microprobe, while trace elements were analyzed using bench-to-top micro-XRF, using non-invasive and non-destructive procedures.",{"name":82,"@type":73,"acceptedAnswer":83},"Why was machine learning used, and what did it improve?",{"text":84,"@type":76},"Machine learning was applied to address differences caused by varying analytical methods and laboratory variability, producing an exhaustive way to discriminate and classify the dataset alongside standard geochemical comparisons.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]