Rapid estimation of activation energy in heterogeneous catalytic reactions via machine learning

Abstract

Estimation of activation energies within heterogeneous catalytic reactions is performed using machine learning and catalysts dataset. In particular, descriptors for determining activation energy are revealed within the 788 activation energy dataset. With the implementation of machine learning and chosen descriptors, activation energy can be instantly predicted with over 90% accuracy during cross-validation. Thus, rapid estimation of activation energies within heterogeneous catalytic reactions can be made achievable via machine learning, leading toward the acceleration of catalysts design and characterization. © 2018 Wiley Periodicals, Inc.