CatFlow: Co-generation of Slab-Adsorbate Systems via Flow Matching

TL;DR

CatFlow is a flow matching framework that improves the design and prediction of heterogeneous catalysts by explicitly modeling surface geometry and adsorbate interactions, leading to more accurate and thermodynamically plausible structures.

Contribution

It introduces a novel flow matching-based approach for catalyst design that reduces model complexity and enhances structural fidelity compared to existing methods.

Findings

Significantly improves structural fidelity over autoregressive baselines

Accurately captures adsorption energy distributions of plausible interfaces

Structures are closer to thermodynamic local minima

Abstract

Discovering heterogeneous catalysts tailored for specific reaction intermediates remains a fundamental bottleneck in materials science. While traditional trial-and-error methods and recent generative models have shown promise, they struggle to capture the intrinsic coupling between surface geometry and adsorbate interactions. To address this limitation, we propose CatFlow, a flow matching-based framework for de novo design and structure prediction of heterogeneous catalysts. Our model operates on a primitive cell-based factorized representation of the slab-adsorbate complex, reducing the number of learnable variables by an average of 9.2x while explicitly encoding the surface orientation of the slab-adsorbate interface. Experiments on the Open Catalyst 2020 dataset demonstrate that CatFlow significantly improves the structural fidelity of generated catalysts compared to autoregressive and sequential baselines. Further experiments show that the generated structures accurately capture the adsorption energy distributions of physically plausible interfaces and lie closer to thermodynamic local minima.