Long-range dispersion-inclusive machine learning potentials for structure search and optimization of hybrid organic-inorganic interfaces

TL;DR

This paper introduces a machine learning approach combining short-range neural network potentials and long-range dispersion models to efficiently predict and optimize hybrid organic-inorganic interface structures, reducing computational costs.

Contribution

It presents a novel ML framework that integrates local and long-range interactions for accurate and fast structure search in complex hybrid systems.

Findings

Models achieve high efficiency in structure optimization.

Semi-quantitative energy predictions are possible.

Approach is validated on gold nanoclusters and organic molecules.

Abstract

The computational prediction of the structure and stability of hybrid organic-inorganic interfaces provides important insights into the measurable properties of electronic thin film devices, coatings, and catalyst surfaces and plays an important role in their rational design. However, the rich diversity of molecular configurations and the important role of long-range interactions in such systems make it difficult to use machine learning (ML) potentials to facilitate structure exploration that otherwise require computationally expensive electronic structure calculations. We present an ML approach that enables fast, yet accurate, structure optimizations by combining two different types of deep neural networks trained on high-level electronic structure data. The first model is a short-ranged interatomic ML potential trained on local energies and forces, while the second is an ML model of effective atomic volumes derived from atoms-in-molecules partitioning. The latter can be used to connect short-range potentials to well-established density-dependent long-range dispersion correction methods. For two systems, specifically gold nanoclusters on diamond (110) surfaces and organic $\pi$-conjugated molecules on silver (111) surfaces, we train models on sparse structure relaxation data from density functional theory and show the ability of the models to deliver highly efficient structure optimizations and semi-quantitative energy predictions of adsorption structures.