AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion

TL;DR

AdsorbDiff introduces a novel diffusion-based method for predicting optimal adsorbate configurations on slabs, significantly accelerating and improving the accuracy of adsorbate placement in catalyst design.

Contribution

This work presents the first application of denoising diffusion models for adsorbate placement, offering an end-to-end framework that surpasses traditional heuristics and brute-force methods.

Findings

Achieves up to 5x faster prediction of optimal configurations.

Improves accuracy by up to 3.5x over previous methods.

Provides insights into the effects of pre-training and model architecture.

Abstract

Determining the optimal configuration of adsorbates on a slab (adslab) is pivotal in the exploration of novel catalysts across diverse applications. Traditionally, the quest for the lowest energy adslab configuration involves placing the adsorbate onto the slab followed by an optimization process. Prior methodologies have relied on heuristics, problem-specific intuitions, or brute-force approaches to guide adsorbate placement. In this work, we propose a novel framework for adsorbate placement using denoising diffusion. The model is designed to predict the optimal adsorbate site and orientation corresponding to the lowest energy configuration. Further, we have an end-to-end evaluation framework where diffusion-predicted adslab configuration is optimized with a pretrained machine learning force field and finally evaluated with Density Functional Theory (DFT). Our findings demonstrate an acceleration of up to 5x or 3.5x improvement in accuracy compared to the previous best approach. Given the novelty of this framework and application, we provide insights into the impact of pre-training, model architectures, and conduct extensive experiments to underscore the significance of this approach.