Machine learning activation energies of chemical reactions

Application of machine learning (ML) to the prediction reaction activation barriers is a new and exciting field for these algorithms. The works covered here are specifically those in which ML trained predict energies homogeneous chemical reactions, where energy given by difference between reactants transition state reaction. Particular attention paid that have applied directly energies, limitations may be found studies, comparisons different types features models been made. Also explored able obtain high predictive accuracies, but with reduced datasets, using Gaussian process regression model. In reactions modeled include involving small organic molecules, aromatic rings, organometallic catalysts. provided brief explanations some most popular used chemistry, as beginner's guide unfamiliar. This article categorized under: Structure Mechanism > Reaction Mechanisms Catalysis Computer Information Science Visualization