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

2025-08-21

AI Summary

First-principles calculations for predicting surface work functions and cleavage energies are computationally expensive and impractical for large-scale screening. To address this, we propose a graph neural network (GNN) method that jointly incorporates surface-normal symmetry breaking and force information derived from machine-learned interatomic potentials. By explicitly encoding orientation-induced symmetry breaking and enforcing physical constraints via atomic forces, the model achieves both equivariance and strong generalization across diverse surface configurations. On work function prediction, it achieves a mean absolute error of 0.065 eV—50% lower than the previous state-of-the-art—while simultaneously delivering high-accuracy cleavage energy predictions. The framework enables efficient, high-throughput screening of surface properties across broad chemical spaces, facilitating data-driven inverse design of functional materials.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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

Problem

• Predicting surface work function and cleavage energy accurately
• Reducing computational cost of surface property screening
• Improving generalization for material surface property prediction

Innovation

• Force-informed equivariant graph neural network
• Integrates surface-normal symmetry breaking
• Uses machine learning interatomic potential forces