Machine Learning in Computational Surface Science and Catalysis: Case Studies on Water and Metal–Oxide Interfaces

Abstract

The goal of many computational physicists and chemists is the ability to bridge the gap between atomistic length scales of about a few multiples of an Ångström (Å), i. e., 10−10 m, and meso- or macroscopic length scales by virtue of simulations. The same applies to timescales. Machine learning techniques appear to bring this goal into reach. This work applies the recently published on-the-fly machine-learned force field techniques using a variant of the Gaussian approximation potentials combined with Bayesian regression and molecular dynamics as efficiently implemented in the Vienna ab initio simulation package, VASP. The generation of these force fields follows active-learning schemes. We apply these force fields to simple oxides such as MgO and more complex reducible oxides such as iron oxide, examine their generalizability, and further increase complexity by studying water adsorption on these metal oxide surfaces. We successfully examined surface properties of pristine and reconstructed MgO and Fe3O4 surfaces. However, the accurate description of water–oxide interfaces by machine-learned force fields, especially for iron oxides, remains a field offering plenty of research opportunities.

Ab Initio Simulations of Water/Metal Interfaces

“…Recently, techniques based on machine learning such as artificial networks have become rather popular as a tool to represent interaction potentials. ,,− They are very versatile and in principle can reproduce any multidimensional potential energy surface. In fact, they have already been successfully applied to address structural properties of liquid water, water/metal interfaces, and water/oxide interfaces . However, because their construction procedure is not based on any chemical insights, their fitting usually requires large training sets .…”

“…In fact, they have already been successfully applied to address structural properties of liquid water, 57 water/metal interfaces, 27 and water/oxide interfaces. 59 However, because their construction procedure is not based on any chemical insights, their fitting usually requires large training sets. 53 Furthermore, similar to many other interpolation schemes, the effort to obtain neural-network interaction potentials often scales exponentially with the number of atom types considered in the potential.…”

Bridging the Gap between the X-ray Absorption Spectroscopy and the Computational Catalysis Communities in Heterogeneous Catalysis: A Perspective on the Current and Future Research Directions

“…The past decade has seen significant advances in the development of open-source software, computational databases (e.g., for adsorption energies), automated workflow managers, and postanalysis tools . We emphasize that the creation of large, standardized data sets using automated high-throughput calculation protocols was the precursor for developing data science tools capable of addressing long-standing questions within computational catalysis. ,− …”

Advanced Machine Learning Methods for Learning from Sparse Data in High-Dimensional Spaces: A Perspective on Uses in The Upstream of Development of Novel Energy Technologies

“…Computations play a key role in rational design of catalysts with or without machine learning, as many properties are either not directly accessible experimentally or cannot be measured with high throughput and modest cost. All together this makes a lot of variables on which catalytic activity depends and one needs to perform searches and uncover relations in multidimensional spaces, which can be done with the help of machine learning [25][26][27][28][29]. are used for automated slab generation and enumeration of possible adsorption sites.…”

“…One area where ML is gaining more and more traction are novel energy conversion and storage technologies. These techniques are, in particular, intensely explored for application to the development of technologies typically associated with sustainable generation and use of energy such as advanced types (organic and inorganic materials based) of solar cells and LED (light-emitting diodes) [10][11][12][13][14][15][16][17][18][19][20][21][22], inorganic and organic metal ion batteries [23,24], fuel cells and generally heterogeneous catalysis including electro-and photocatalysis [25][26][27][28][29][30][31][32][33][34]. This is natural in the sense that the development of these technologies often passes through optimization and balancing of multiple factors acting simultaneously and to opposite ends; for example, in the case of organic solar cells, there is an optimum to be sought between the donor's bandgap, the band offset between the donor and the acceptor, the reorganization energies of both the donor and the acceptor, the charge transfer integral etc.…”