Machine Learning and Data-Driven Methods in Computational Surface and Interface Science

Abstract

Nanoscale design of surfaces and interfaces is essential for modern technologies like organic LEDs, batteries, fuel cells, superlubricating surfaces, and heterogeneous catalysis. However, these systems often exhibit complex surface reconstructions and polymorphism, with properties influenced by kinetic processes and dynamic behavior. A lack of accurate and scalable simulation tools has limited computational modeling of surfaces and interfaces. Recently, machine learning and data-driven methods have expanded the capabilities of theoretical modeling, enabling, for example, the routine use of machine-learned interatomic potentials to predict energies and forces across numerous structures. Despite these advances, significant challenges remain, including the scarcity of large, consistent datasets and the need for computational and data-efficient machine learning methods. Additionally, a major challenge lies in the lack of accurate reference data and electronic structure methods for interfaces. Density Functional Theory, while effective for bulk materials, is less reliable for surfaces, and too few accurate experimental studies on interface structure and stability exist. Here, we will sketch the current state of data-driven methods and machine learning in computational surface science and provide a perspective on how these methods will shape the field in the future.

27 pages, 5 figures

References in corpus (19)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• An Accurate and Transferable Machine Learning Potential for Carbon
• Representing molecule-surface interactions with symmetry-adapted neural networks
• Nudged elastic band calculations accelerated with Gaussian process regression
• Ab-initio tensorial electronic friction for molecules on metal surfaces: nonadiabatic vibrational relaxation
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Tutorial: How to Train a Neural Network Potential
• DFT Modelling of Explicit Solid-Solid Interfaces in Batteries: Methods and Challenges
• Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
• Machine Learning Quantum Reaction Rate Constants
• Minimum energy path calculations with Gaussian process regression
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Transfer learning for chemically accurate interatomic neural network potentials
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Reproducibility of Potential Energy Surfaces of Organic/Metal Interfaces on the Example of PTCDA on Ag(111)
• FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Cited by in corpus (4)

• Active Δ-learning with universal potentials for global structure optimization
• M-CODE: Materials Categorization via Ontology, Dimensionality and Evolution
• FreeBird.jl: An Extensible Toolbox for Simulating Interfacial Phase Equilibria
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence