A machine learning approach to Nemrut Dağ and Bingöl Obsidians: non-invasive and non-destructive geochemical analyses for provenance source of Tulūl al Baqarat tools (Iraq)

A groundbreaking analysis using machine learning has identified Nemrut Dağ, a stratovolcano in southeastern Turkey, as the likely source of obsidian tools found at the archaeological site of Tulūl al Baqarat in Iraq. The study employed non-invasive and non-destructive geochemical techniques, including SEM-EDS microprobe and micro-XRF, to analyze major, minor, and trace elements in nine obsidian blades. Unlike traditional methods, machine learning provided an exhaustive discriminative approach that confirmed the tools' composition matched Nemrut Dağ's mild alkaline rhyolitic obsidians from pre-caldera eruptions. This finding supports historical evidence of extensive trade networks spanning Turkey and the South Near East during the 4th Millennium BCE, likely facilitated by riverine routes along the Tigris and Euphrates to the Persian Gulf.

Vaggelli, G., Cossio, R., Borghi, A., & Lippolis, C. (2023). A machine learning approach to Nemrut Dağ and Bingöl Obsidians: non-invasive and non-destructive geochemical analyses for provenance source of Tulūl al Baqarat tools (Iraq). https://doi.org/10.21203/rs.3.rs-3646159/v1