FIRE-GNN: Force-informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties
This work addresses the need for rapid and accurate screening of materials surfaces for applications in electronics and catalysis, representing a strong specific gain in prediction accuracy.
The paper tackled the problem of predicting surface properties like work function and cleavage energy, which are computationally expensive with traditional methods, by introducing FIRE-GNN, a graph neural network that integrates force information and symmetry breaking, achieving a mean absolute error of 0.065 eV for work function prediction, a twofold reduction over previous state-of-the-art.
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