Bayesian sparse modeling for interpretable prediction of hydroxide ion conductivity in anion-conductive polymer membranes

TL;DR

This paper employs Bayesian sparse modeling to identify key compositional features that predict hydroxide ion conductivity in anion-conductive polymer membranes, enhancing interpretability of the structure-property relationship.

Contribution

It introduces a Bayesian sparse modeling approach to quantitatively link copolymer composition with hydroxide ion conductivity, providing new insights into membrane design.

Findings

Identified critical composition-derived features for conductivity prediction

Established quantitative relationships between membrane structure and ion mobility

Enhanced interpretability of structure-property correlations

Abstract

Anion-conductive polymer membranes have attracted considerable attention as solid electrolytes for alkaline fuel cells and electrolysis cells. Their hydroxide ion conductivity varies depending on factors such as the type and distribution of quaternary ammonium groups, as well as the structure and connectivity of hydrophilic and hydrophobic domains. In particular, the size and connectivity of hydrophilic domains significantly influence the mobility of hydroxide ions; however, this relationship has remained largely qualitative. In this study, we calculated the number of key constituent elements in the hydrophilic and hydrophobic units based on the copolymer composition, and investigated their relationship with hydroxide ion conductivity by using Bayesian sparse modeling. As a result, we successfully identified composition-derived features that are critical for accurately predicting hydroxide ion conductivity.