Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm

Abstract

Catalytic activities are often dominated by a few specific surface sites, and designing active sites is the key to realize high-performance heterogeneous catalysts. The great triumphs of modern surface science lead to reproduce catalytic reaction rates by modeling the arrangement of surface atoms with well-defined single-crystal surfaces. However, this method has limitations in the case for highly inhomogeneous atomic configurations such as on alloy nanoparticles with atomic-scale defects, where the arrangement cannot be decomposed into single crystals. Here, we propose a universal machine-learning scheme using a local similarity kernel, which allows interrogation of catalytic activities based on local atomic configurations. We then apply it to direct NO decomposition on RhAu alloy nanoparticles. The proposed method can efficiently predict energetics of catalytic reactions on nanoparticles using DFT data on single crystals, and its combination with kinetic analysis can provide detailed information on structures of active sites and size- and composition-dependent catalytic activities.

A Critical Review of Machine Learning of Energy Materials

“…The Gaussian kernel has been routinely applied in other kernel‐based methods, including Bayesian linear regression, support vector machine/regression/classification (SVM/SVR/SVC), kernel ridge regression (KRR), Gaussian process regression (GPR), etc. Kernel‐based models have been widely used in materials ML, for example, in constructing Gaussian approximation potential (GAP), predicting molecular properties, adsorption of gases on alloy nanoparticles, lithium conductivity in LISCON, thermal conductivity in solids, potential energy surfaces, etc.…”

“…c) Activity map on atoms with different Au concentration. Adapted with permission . Copyright 2017 American Chemical Society.…”

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

“…Several successful examples have already been reported for organic chemistry reactions, including those that involve homogeneous catalysts . However, the applicability of ML predictions for heterogeneous catalysis have been limited mainly to computationally determined values such as band gaps, d‐band centers, and adsorption energies . For the practical use of ML for discovering new solid catalytic materials, not only first‐principles calculated values but also experimental values for specific catalytic reactions are needed, especially in heterogeneous catalysis because an adequate theoretical model for heterogeneous catalysis is not available.…”

Nanomaterials Discovery and Design through Machine Learning

“…It will be urgent and promising to optimize or develop machine learning algorithms that can efficiently train the data on a small database, especially when the amount of data is intrinsically small in nanomaterials domain. (3)Machine learning can enhance the existing theoretical computational approaches. The traditional quantum/molecular mechanics, such as density functional theory, molecular dynamics, and Monte Carlo techniques, have been combined with machine learning for materials research . Coupling with the high throughput computational screening method and evolutionary algorithms, machine learning approach is becoming a powerful tool to design synthesis method and predict complicated properties of nanomaterials, even discover new nanomaterials.…”

“…f) Density functional theory. Reproduced with permission . Copyright 2017, American Chemical Society.…”