Accelerating High-Throughput Catalyst Screening by Direct Generation of Equilibrium Adsorption Structures

TL;DR

This paper introduces DBCata, a deep generative model that rapidly produces accurate equilibrium adsorption structures, significantly improving catalyst screening efficiency by reducing reliance on costly DFT calculations.

Contribution

The novel DBCata model integrates a Brownian-bridge framework with equivariant neural networks to generate high-fidelity adsorption geometries without explicit energy data.

Findings

Achieves DMAE of 0.035 Å, outperforming current models.

Improves DFT accuracy within 0.1 eV in 94% of cases.

Enables accelerated high-throughput catalyst screening.

Abstract

The adsorption energy serves as a crucial descriptor for the large-scale screening of catalysts. Nevertheless, the limited distribution of training data for the extensively utilised machine learning interatomic potential (MLIP), predominantly sourced from near-equilibrium structures, results in unreliable adsorption structures and consequent adsorption energy predictions. In this context, we present DBCata, a deep generative model that integrates a periodic Brownian-bridge framework with an equivariant graph neural network to establish a low-dimensional transition manifold between unrelaxed and DFT-relaxed structures, without requiring explicit energy or force information. Upon training, DBCata effectively generates high-fidelity adsorption geometries, achieving an interatomic distance mean absolute error (DMAE) of 0.035 \text{\AA} on the Catalysis-Hub dataset, which is nearly three times superior to that of the current state-of-the-art machine learning potential models. Moreover, the corresponding DFT accuracy can be improved within 0.1 eV in 94\% of instances by identifying and refining anomalous predictions through a hybrid chemical-heuristic and self-supervised outlier detection approach. We demonstrate that the remarkable performance of DBCata facilitates accelerated high-throughput computational screening for efficient alloy catalysts in the oxygen reduction reaction, highlighting the potential of DBCata as a powerful tool for catalyst design and optimisation.