Applications of machine learning in surfaces and interfaces

2025-03-17

徐少锋 (Shaofeng Xu)

Jing‐Yuan Wu

Ying Guo *

张

张卿 (Qing Zhang)

钟

钟新仙 (Xiaoxia Zhong) *

Jinjin Li *

任

任伟 (Wei Ren) *

DOI：10.1063/5.0244175

Original

Original request for help

Save

Abstract

En 中文

Surfaces and interfaces play key roles in chemical and material science. Understanding physical and chemical processes at complex surfaces and interfaces is a challenging task. Machine learning provides a powerful tool to help analyze and accelerate simulations. This comprehensive review affords an overview of the applications of machine learning in the study of surfaces and interfaces of chemical systems and materials. We categorize surfaces and interfaces into the following broad categories: solid-solid interface, solid-liquid interface, liquid-liquid interface, surface of solid, surface of liquid, and three-phase interfaces. High-throughput screening, combined machine learning and first-principles calculations, and machine learning force field accelerated molecular dynamics simulations are used to rational design and study physical and chemical processes of surfaces and interfaces in systems such as all-solid-state batteries, solar cells, and heterogeneous catalysis. This review provides detailed and comprehensive information on the applications of machine learning on surfaces and interfaces for chemical and material science.

Keywords:

DENSITY-FUNCTIONAL THEORY

SINGLE-ATOM CATALYSTS

MOLECULAR-DYNAMICS SIMULATIONS

HIGH-THROUGHPUT CALCULATIONS

HETEROJUNCTION SOLAR-CELLS

THERMAL-CONDUCTIVITY

INTERATOMIC POTENTIALS

PREDICTION MODEL

DATA-EFFICIENT

ARTIFICIAL-INTELLIGENCE

Applications of machine learning in surfaces and interfaces

Abstract

Journal

Organization

Cited Papers

Citing Papers