A Predictive Model for Maceral Discrimination by Means of Raman Spectra on Dispersed Organic Matter: A Case Study from the Carpathian Fold-and-Thrust Belt (Ukraine)

In this study, we propose a predictive model for maceral discrimination based on Raman spectroscopic analyses of dispersed organic matter. micro-spectroscopy was coupled with optical and Rock-Eval pyrolysis set seven samples collected from Mesozoic Cenozoic successions the Outer sector Carpathian fold thrust belt. Organic petrography evidence type II/III kerogen complex organofacies composed by coal groups vitrinite, inertinite, liptinite, while thermal maturity lies at onset oil window spanning between 0.42 0.61 Ro%. Micro-Raman were performed, approximately 30–100 spectra per sample but only relatively few fragments it possible to perform an classification according their macerals group. A multivariate statistical analysis identified vitrinite inertinite allows define variability develop PLS-DA identification spectra. Following first attempts made in last years, work outlines how machine learning techniques have become useful support classical assessment.