TY - CONF A1 - Morcillo, Dalia A1 - Abad Andrade, Carlos Enrique A1 - Winckelmann, Alexander A1 - Frick, D. A1 - Jacobsen, L. A1 - Richter, Silke A1 - Recknagel, Sebastian A1 - Vogl, Jochen A1 - Panne, Ulrich T1 - Atomic absorption spectroscopy and machine learning for lithium isotopic study N2 - The isotopic analysis of lithium is also relevant to the study of geological phenomena.1 In this work we propose improvements to the method for the isotopic analysis of lithium using a high-resolution continuum source atomic absorption spectrometer (HR-CS-AAS) coupled to a double echelle modular spectrometer (DEMON). 2 This tool for isotopic ratio determination is based on monitoring the isotopic components of lithium by their spin-orbit coupling and its isotopic shift of about 15 pm for the 22P←2 2S electronic transition around 670.788 nm. The data analysis was carried out by using a decision-tree-based ensemble machine learning (ML) algorithm. For the training of the algorithm (XGBoost), a set of samples with 6Li isotope amount fractions ranging from 0.06 to 0.99 mol-1 was used. Subsequently, the procedure was validated of a set of stock chemicals (Li2CO3, LiNO3, LiCl and LiOH) and a BAM candidate reference material, the cathode material LiNi1/3Mn1/3Co1/3O2 (NMC111). Finally, the ML model was applied to the set of geological samples, previously digested, for the determination of their isotope ratio. The optical resolution was improved from 140,000 to 790,000 to better deconvolution the lithium isotopic components in the atomic spectrum. And the method was compared with multi-collector inductively coupled plasma mass spectrometry (MC-ICP-MS). The results are metrologically comparable. T2 - Colloquium Spectroscopicum Internationale XLII (CSI XLII) CY - Gijón, Spain DA - 30.05.2022 KW - Lithium isotope KW - Atomic absorption spectroscopy PY - 2022 AN - OPUS4-56357 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -