Litcius/Paper detail

Understanding the role of metal oxide support in ruthenium-based catalysts for ammonia synthesis via interpretable machine learning

Rasika Jayarathna, Rahat Javaid, Jochen Lauterbach

2025Journal of Catalysis6 citationsDOIOpen Access PDF

Abstract

The results suggest that in addition to basicity, a certain acidity of metal oxide support and the ability to form metal hydrides could be critical to the NH 3 synthesis reaction. • The formation energies of the most thermodynamically stable support metal nitride and the support metal hydride were used as novel descriptors for the thermocatalytic NH 3 synthesis rate by unpromoted metal oxide-supported Ru catalysts. • A machine learning model trained on data extracted from the literature was developed using these descriptors to predict the NH 3 synthesis rate. • The model interpreted by SHAP values revealed a volcano-type relationship between the NH 3 synthesis rate and the novel descriptors for binary metal oxides in the dataset, which has basic sites. • Temperature-programmed desorption experiments verified volcano-type relationships for catalysts within the dataset. • The mean and the standard deviation of all thermodynamically stable and metastable support metal nitride formation energies are required to describe the NH 3 synthesis rate by all the binary metal oxide (with basic sites) supported Ru catalysts not in the dataset. The role of metal oxide supports is complex in heterogeneous catalysis due to acidity, basicity, and surface defects. Interpretable machine learning models trained on experimental data could lead to new insights about these complexities, which are rarely verified through detailed catalyst characterization. This study explores the role of metal oxide supports for the Ru-based ammonia synthesis catalysts using Shapley additive explanations (SHAP). The support metal nitride formation energy and the support metal hydride formation energy were identified as critical descriptors that could describe the ammonia synthesis activity. These descriptors and the related catalyst characterization by Ammonia-Temperature Programmed Desorption and Hydrogen-Temperature Programmed Desorption suggest new processes that could govern the ammonia synthesis reaction. It is suggested that in addition to basicity, the metal oxide support should possess a certain acidity to alleviate ammonia inhibition and form metal hydrides to alleviate hydrogen inhibition.

Topics & Concepts

ChemistryRutheniumCatalysisAmmoniaOxideAmmonia productionMetalInorganic chemistryOrganic chemistryAmmonia Synthesis and Nitrogen ReductionMachine Learning in Materials ScienceCatalytic Processes in Materials Science
Understanding the role of metal oxide support in ruthenium-based catalysts for ammonia synthesis via interpretable machine learning | Litcius