Machine learning (ML) has emerged as a powerful tool for accelerating catalyst discovery by integrating computational and experimental data. While ML excels at pattern detection in large datasets, many catalyst studies rely on limited experimental data. Our approach combines ML with first-principles calculations to extract insights from small experimental datasets. We train a complex ML model on a large computational library of transition-state energies and complement it with simple linear regression models fitted to experimental data. This method allows us to explore the catalytic activity of monolayer bimetallic catalysts for ethanol reforming, identifying key reactions and predicting promising compositions.

In another study, we applied ML-driven molecular dynamics and metadynamics simulations to investigate the oxygen evolution reaction (OER) on pristine and Ni-doped BaTiO3. Using a neural network potential, we captured dynamic mechanistic details, revealing the impact of nickel doping on BaTiO3, a perovskite oxide synthesized from earth-abundant precursors. These case studies demonstrate the versatility of ML in guiding the design of efficient and sustainable catalysts, from ethanol reforming to water splitting.

Nong Artrith is an Assistant Professor in the Materials Chemistry and Catalysis Group at the Debye Institute for Nanomaterials Science, Utrecht University, and a Visiting Researcher at Microsoft Research Amsterdam Lab (2022-2023).  Prior to joining Utrecht University, Nong was a Research Scientist at Columbia University, USA, and a PI in the Columbia Center for Computational Electrochemistry. Nong obtained her PhD in Theoretical Chemistry from Ruhr University Bochum, Germany, for the development of machine-learning (ML) models for materials chemistry.  She was awarded a Schlumberger Foundation fellowship for postdoctoral research at MIT and subsequently joined UC Berkeley as an associate specialist.  In 2019, Nong has been named a Scialog Fellow for Advanced Energy Storage.  Since 2023, Nong is a member of the NL ARC CBBC (https://arc-cbbc.nl).  She is the main developer of the open-source ML package ænet (http://ann.atomistic.net) for atomistic simulations.  Her research interests focus on the development and application of first principles and ML methods for the computational discovery of energy materials and for the interpretation of experimental observations.