Topology-Informed Machine Learning for Efficient Prediction of Solid Oxide Fuel Cell Electrode Polarization

TL;DR

This paper introduces a topology-based machine learning approach that efficiently predicts solid oxide fuel cell electrode polarization curves from microstructure data, significantly reducing computational costs.

Contribution

It presents a novel persistence representation for microstructure data enabling accurate neural network predictions with less computational effort.

Findings

Accurately predicts polarization curves for unseen microstructures.

Reduces prediction time from hours to about 1 minute.

Uses topological data analysis for microstructure representation.

Abstract

Machine learning has emerged as a potent computational tool for expediting research and development in solid oxide fuel cell electrodes. The effective application of machine learning for performance prediction requires transforming electrode microstructure into a format compatible with artificial neural networks. Input data may range from a comprehensive digital material representation of the electrode to a selected set of microstructural parameters. The chosen representation significantly influences the performance and results of the network. Here, we show a novel approach utilizing persistence representation derived from computational topology. Using 500 microstructures and current-voltage characteristics obtained with 3D first-principles simulations, we have prepared an artificial neural network model that can replicate current-voltage characteristics of unseen microstructures based on their persistent image representation. The artificial neural network can accurately predict the polarization curve of solid oxide fuel cell electrodes. The presented method incorporates complex microstructural information from the digital material representation while requiring substantially less computational resources (preprocessing and prediction time approximately 1 min) compared to our high-fidelity simulations (simulation time approximately 1 hour) to obtain a single current-potential characteristic for one microstructure.