Meta-LegNet: A Transferable and Interpretable Framework for Surface Adsorption Prediction via Self-Defined Adsorption-Environment Learning

TL;DR

Meta-LegNet is a graph learning framework that predicts adsorption sites on catalysts by learning transferable, interpretable local environments, reducing computational costs in catalyst screening.

Contribution

The paper introduces Meta-LegNet, a novel transferable and interpretable graph learning framework combining SE(3)-equivariant message passing and meta-learning for surface adsorption prediction.

Findings

Meta-LegNet accurately predicts adsorption sites on diverse surfaces.

The framework produces interpretable atom-resolved attribution maps.

It enables rapid screening by proposing likely adsorption sites without exhaustive enumeration.

Abstract

A central challenge in computational catalysis is the identification of low-energy and chemically plausible adsorption configurations, as these directly affect adsorption energies, reaction pathways, and catalytic performance. Existing approaches generally rely on enumerating candidate adsorption sites followed by iterative refinement through density functional theory calculations or machine-learning-based relaxations. However, such workflows remain computationally expensive and are difficult to scale to complex surfaces or multi-adsorbate systems. Here, we introduce Meta-LegNet, a graph learning framework that combines SE(3)-equivariant atom-level message passing with voxel-based multiscale aggregation and cross-domain meta-learning to learn transferable representations of local adsorption environments across diverse catalyst--adsorbate systems. Rather than following a conventional regression-only paradigm, Meta-LegNet encodes local chemical environments using invariant radial features and equivariant directional information, and further incorporates broader structural context through coordinate-frame voxel pooling, assignment-based upsampling, and gated feature fusion. The resulting local-global decomposition produces atom-resolved attribution maps, which are processed to identify adsorption-relevant local environments in an interpretable manner. Based on the learned representations, we further construct an adsorption-environment database and develop a template-matching strategy to propose likely adsorption sites on previously unexplored surfaces without exhaustive site enumeration. Overall, our results suggest that learning transferable adsorption environments provides an accurate, interpretable, and practical route for accelerating catalyst screening.