Linear Discriminant Analysis Based Machine Learning and All-Atom Molecular Dynamics Simulations for Probing Electroosmotic Transport in Cationic-Polyelectrolyte-Brush-Grafted Nanochannels

Deciphering the correct mechanism governing certain phenomenon in polyelectrolyte (PE) brush grafted systems, revealed through atomistic simulations, is an extremely challenging problem. In a recent study, our all-atom molecular dynamics (MD) simulations revealed a non-linearly large electroosmotic flow (in the presence of an applied electric field) in nanochannels grafted with PMETAC [Poly(2-(methacryloyloxy)ethyl trimethylammonium chloride] brushes. Given the lack of any formal mechanism that would have directed us to identify the correct factors responsible for such an occurrence, we needed to spend several months and devote significant analysis to unravel the involved mechanism. In this paper, we propose a Linear Discriminant Analysis (LDA) based ML approach to address this gap. At first, we obtain data on certain basic features from the all-atom MD data for a reference case (case with a smaller electric field) and the perturbed case in bins in which the nanochannel half height has been divided into. These datasets are high-dimensional dataset, to which the LDA is applied. This leads to the projection of the data (between the reference and the perturbed states) in a highly separated form on a 1D line. From such LDA calculations, we are able to identify the importance scores for the different features, which in turn tell us what to study and where to study. Such knowledge enables us to rapidly identify the key factors responsible for the non-linearly large EOS transport in PMETAC-brush-grafted nanochannels.