Diffusion Sampling of Adsorbate Configurations on Catalyst Surfaces

Akhila Ram, Juno Nam, Aaron J Havens, Benjamin Kurt Miller, Rafael Gomez-Bombarelli

Track: Track 1: Original Research/Position/Education/Attention Track

Keywords: adsorbate, catalyst, diffusion sampling, neural sampler, ML interatomic potentials

TL;DR: We introduce an energy-trained conditional diffusion sampler that generates diverse, valid, low-energy adsorbate configurations on catalyst surfaces.

Abstract: Reliable adsorption-energy estimation in heterogeneous catalysis requires sampling diverse low-energy adsorbate configurations on a slab, but existing data-driven methods rely on dense per-system placement labels that are expensive to obtain and typically constrain the search to global rigid-body translations and rotations. We instead cast adsorbate placement as conditional Boltzmann sampling under an energy induced by a pretrained ML interatomic potential, which removes the need for dense supervision and exposes the full adsorbate coordinate space, including internal conformer degrees of freedom. We introduce AdsorbSample, an energy-trained conditional diffusion sampler whose source, controller, and differentiable restraint potentials are tailored to adsorbate--surface geometry, so that physically implausible configurations are suppressed in the proposal. On the OC20-Dense benchmarks, AdsorbSample achieves the best success rate at low sample budgets while matching or exceeding baselines on validity and diversity.

Submission Number: 323