Classification of biomass reactions and predictions of reaction energies through machine learning

DFT-based Machine Learning for Ensemble Effect of Pd@Au Electrocatalysts on CO2 Reduction Reaction

The ensemble effect due to variation of Pd content in Pd-Au alloys have been widely investigated for several important reactions, including CO₂ reduction reaction (CO₂ RR), however, identifying the stable Pd arrangements on the alloyed surface and picking out the active sites are still challenging. Here we use a density functional theory (DFT) based machine-learning (ML) approach to efficiently find the low-energy configurations of Pd-Au(111) surface alloys and the potentially active sites for CO₂ RR, fully covering the Pd content from 0 to 100 %. The ML model is actively learning process to improve the predicting accuracy for the configuration formation energy and to find the stable Pd-Au(111) alloyed surfaces, respectively. The local surface properties of adsorption sites are classified into two classes by the K-means clustering approach, which are closely related to the Pd content on Au surface. The classification is reflected in the variation of adsorption energy of CO and H: In the low Pd content range (0-60 %) the adsorption energies over the surface alloys can be tuned significantly, and in the medium Pd content (37-68 %), the catalytic activity of surface alloys for CO₂ RR can be increased by increase the Pd content and attributed to the meta-stable active site over the surface. Thus, the active site-dependent reaction mechanism is elucidated based on the ensemble effect, which provides new physical insights to understand the surface-related properties of catalysts.

Perspective on computational reaction prediction using machine learning methods in heterogeneous catalysis

Heterogeneous catalysis plays a significant role in the modern chemical industry. Towards the rational design of novel catalysts, understanding reactions over surfaces is the most essential aspect. Typical industrial catalytic processes such as syngas conversion and methane utilisation can generate a large reaction network comprising thousands of intermediates and reaction pairs. This complexity not only arises from the permutation of transformations between species but also from the extra reaction channels offered by distinct surface sites. Despite the success in investigating surface reactions at the atomic scale, the huge computational expense of ab initio methods hinders the exploration of such complicated reaction networks. With the proliferation of catalysis studies, machine learning as an emerging tool can take advantage of the accumulated reaction data to emulate the output of ab initio methods towards swift reaction prediction. Here, we briefly summarise the conventional workflow of reaction prediction, including reaction network generation, ab initio thermodynamics and microkinetic modelling. An overview of the frequently used regression models in machine learning is presented. As a promising alternative to full ab initio calculations, machine learning interatomic potentials are highlighted. Furthermore, we survey applications assisted by these methods for accelerating reaction prediction, exploring reaction networks, and computational catalyst design. Finally, we envisage future directions in computationally investigating reactions and implementing machine learning algorithms in heterogeneous catalysis.

Machine learning meets chemical physics

Over recent years, the use of statistical learning techniques applied to chemical problems has gained substantial momentum. This is particularly apparent in the realm of physical chemistry, where the balance between empiricism and physics-based theory has traditionally been rather in favor of the latter. In this guest Editorial for the special topic issue on "Machine Learning Meets Chemical Physics," a brief rationale is provided, followed by an overview of the topics covered. We conclude by making some general remarks.