FIRE-GNN: Force-informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties

TL;DR

FIRE-GNN is a novel graph neural network that incorporates force information and symmetry considerations to accurately and rapidly predict surface properties like work function and cleavage energy, outperforming previous models.

Contribution

The paper introduces FIRE-GNN, a new GNN architecture that integrates force data and symmetry breaking, achieving significant improvements in surface property predictions.

Findings

FIRE-GNN reduces mean absolute error to 0.065 eV for work function prediction.

It outperforms existing models in accuracy and generalization.

The model enables rapid screening of materials for surface properties.

Abstract

The work function and cleavage energy of a surface are critical properties that determine the viability of materials in electronic emission applications, semiconductor devices, and heterogeneous catalysis. While first principles calculations are accurate in predicting these properties, their computational expense combined with the vast search space of surfaces make a comprehensive screening approach with density functional theory (DFT) infeasible. Here, we introduce FIRE-GNN (Force-Informed, Relaxed Equivariance Graph Neural Network), which integrates surface-normal symmetry breaking and machine learning interatomic potential (MLIP)-derived force information, achieving a twofold reduction in mean absolute error (down to 0.065 eV) over the previous state-of-the-art for work function prediction. We additionally benchmark recent invariant and equivariant architectures, analyze the impact of symmetry breaking, and evaluate out-of-distribution generalization, demonstrating that FIRE-GNN consistently outperforms competing models for work function predictions. This model enables accurate and rapid predictions of the work function and cleavage energy across a vast chemical space and facilitates the discovery of materials with tuned surface properties