Successes and challenges in using machine-learned activation energies in kinetic simulations

The prediction of the thermodynamic and kinetic properties of chemical reactions is increasingly being addressed by machine-learning (ML) methods, such as artificial neural networks (ANNs). While a number of recent studies have reported success in predicting chemical reaction activation energies, less attention has been focused on how the accuracy of ML predictions filters through to predictions of macroscopic observables. Here, we consider the impact of the uncertainty associated with ML prediction of activation energies on observable properties of chemical reaction networks, as given by microkinetics simulations based on ML-predicted reaction rates. After training an ANN to predict activation energies, given standard molecular descriptors for reactants and products alone, we performed microkinetics simulations of three different prototypical reaction networks: formamide decomposition, aldol reactions, and decomposition of 3-hydroperoxypropanal. We find that the kinetic modeling predictions can be in excellent agreement with corresponding simulations performed with ab initio calculations, but this is dependent on the inherent energetic landscape of the networks. We use these simulations to suggest some guidelines for when ML-based activation energies can be reliable and when one should take more care in applications to kinetics modeling. Published under an exclusive license by AIP Publishing.

Automated summary

Machine-learning methods, such as artificial neural networks, are increasingly used to predict the thermodynamic and kinetic properties of chemical reactions. This study investigates the impact of uncertainty associated with machine-learning predictions of activation energies on observable properties of chemical reaction networks. Guidelines for the reliability of machine-learning-based activation energies in kinetics modeling are suggested based on microkinetics simulations.