Low-cost prediction of molecular and transition state partition functions via machine learning

TL;DR

This paper introduces machine learning models trained on a large dataset to accurately predict molecular and transition state partition functions, significantly reducing computational costs in chemical kinetics.

Contribution

The authors developed deep neural network estimators that predict partition functions from geometries, enabling efficient computation of reaction rate constants.

Findings

Maximum mean absolute error of 2.7% in predicting partition functions

Predicted reaction rate constants agree with ab initio calculations at 98.3% accuracy

Models reduce computational cost for reaction kinetics analysis

Abstract

We have generated an open-source dataset of over 30000 organic chemistry gas phase partition functions. With this data, a machine learning deep neural network estimator was trained to predict partition functions of unknown organic chemistry gas phase transition states. This estimator only relies on reactant and product geometries and partition functions. A second machine learning deep neural network was trained to predict partition functions of chemical species from their geometry. Our models accurately predict the logarithm of test set partition functions with a maximum mean absolute error of 2.7%. Thus, this approach provides a means to reduce the cost of computing reaction rate constants ab initio. The models were also used to compute transition state theory reaction rate constants prefactors and the results were in quantitative agreement with the corresponding ab initio calculations with an accuracy of 98.3% on the log scale.