Materials-Discovery Workflows Guided by Symbolic Regression: Identifying Acid-Stable Oxides for Electrocatalysis

TL;DR

This paper introduces a symbolic regression-based active learning workflow that efficiently identifies acid-stable oxides for electrocatalysis by uncovering key parameters and reducing prediction uncertainty, significantly accelerating materials discovery.

Contribution

It develops a novel active learning method using SISSO symbolic regression with ensemble and dropout techniques to identify critical parameters and improve prediction reliability in materials discovery.

Findings

Identified 12 acid-stable oxides from 1470 candidates in 30 iterations.

Enhanced prediction accuracy and uncertainty quantification with ensemble SISSO models.

Reduced risk of missing promising materials by mapping property landscapes with uncertainty estimates.

Abstract

The efficiency of active learning (AL) approaches to identify materials with desired properties relies on the knowledge of a few parameters describing the property. However, these parameters are unknown if the property is governed by a high intricacy of many atomistic processes. Here, we develop an AL workflow based on the sure-independence screening and sparsifying operator (SISSO) symbolic-regression approach. SISSO identifies the few, key parameters correlated with a given materials property via analytical expressions, out of many offered primary features. Crucially, we train ensembles of SISSO models in order to quantify mean predictions and their uncertainty, enabling the use of SISSO in AL. By combining bootstrap sampling to obtain training datasets with Monte-Carlo feature dropout, the high prediction errors observed by a single SISSO model are improved. Besides, the feature dropout procedure alleviates the overconfidence issues observed in the widely used bagging approach. We demonstrate the SISSO-guided AL workflow by identifying acid-stable oxides for water splitting using high-quality DFT-HSE06 calculations. From a pool of 1470 materials, 12 acid-stable materials are identified in only 30 AL iterations. The materials property maps provided by SISSO along with the uncertainty estimates reduce the risk of missing promising portions of the materials space that were overlooked in the initial, possibly biased dataset.