High-Resolution Atomic Absorption Spectrometry Combined with Machine Learning Data Processing for Isotope Amount Ratio Analysis of Lithium

An alternative method for lithium isotope amount ratio analysis based on a combination of high-resolution atomic absorption spectrometry and spectral data analysis by machine learning (ML) is proposed herein. It is based on the well-known isotope shift of approximately 15 pm for the electronic transition 2²P←2²S at around the wavelength of 670.8 nm, which can be measured by state-of-the-art high-resolution continuum source graphite furnace atomic absorption spectrometry. For isotope amount ratio analysis, a scalable tree boosting ML algorithm (XGBoost) was employed and calibrated using a set of samples with ⁶Li isotope amount fractions ranging from 0.06 to 0.99 mol mol⁻¹, previously determined by multi-collector inductively coupled plasma mass spectrometry (MC-ICP-MS). The calibration ML model was validated with two certified reference materials (LSVEC and IRMM-016). The procedure was applied to the isotope amount ratio determination of a set of stock chemicals (Li₂CO₃, LiNO₃, LiCl, and LiOH) and a BAM candidate reference material, that is, LiNi_1/3Mn_1/3Co_1/3O₂ (NMC111) cathode material. The results of these determinations were compared with those obtained by MC-ICP-MS and found to be metrologically comparable and compatible. The residual bias was −1.8‰ and the precision obtained ranged from 1.9‰ to 6.2‰. This precision was sufficient to resolve naturally occurring variations, as demonstrated for samples ranging from approximately −3‰ to +15‰. To assess its suitability to technical applications, the NMC111 cathode candidate reference material was analyzed using high-resolution continuum source molecular absorption spectrometry with and without matrix purification. The results obtained were metrologically compatible with each other.