Machine Learning Quantum Reaction Rate Constants

TL;DR

This paper presents a deep neural network trained on extensive quantum reaction rate data to accurately predict reaction rate constants, enabling faster and more efficient reaction kinetics modeling in quantum chemistry.

Contribution

The study introduces a DNN model trained on 1.5 million quantum reaction rates, achieving high accuracy and enabling rapid predictions across various reactions and conditions.

Findings

DNN predicts the logarithm of rate constants with 1.1% relative error.

The model accurately captures quantum effects at different temperatures.

Good agreement with exact rates for complex reactions at high temperatures.

Abstract

The ab initio calculation of exact quantum reaction rate constants comes at a high cost due to the required dynamics of reactants on multidimensional potential energy surfaces. In turn, this impedes the rapid design of the kinetics for large sets of coupled reactions. In an effort to overcome this hurdle, a deep neural network (DNN) was trained to predict the logarithm of quantum reaction rate constants multiplied by their reactant partition function - rate products. The training dataset was generated inhouse and contains ~1.5 million quantum reaction rate constants for single, double, symmetric and asymmetric one-dimensional potentials computed over a broad range of reactant masses and temperatures. The DNN was able to predict the logarithm of the rate product with a relative error of 1.1%. Further, when comparing the difference between the DNN prediction and classical transition state theory at temperatures below 300K a relative percent error of 31% was found with respect to the exact difference. Systems beyond the test set were also studied, these included the $\sf{H}$ + $\sf{H_2}$ reaction, the diffusion of hydrogen on Ni(100), the Menshutkin reaction of pyridine with $\sf{CH_3Br}$ in the gas phase, the reaction of formalcyanohydrin with $\sf{HS^-}$ in water and the F + HCl reaction. For these reactions, the DNN predictions were accurate at high temperatures and in good agreement with the exact rates at lower temperatures. This work shows that one can take advantage of a DNN to gain insight on reactivity in the quantum regime.