Rapid and Accurate Estimation of Activation Free Energy in Hydrogen Atom Transfer-Based C-H Activation Reactions: From Empirical Model to Artificial Neural Networks.

Abstract

A well-performing machine learning (ML) model is obtained by using proper descriptors and artificial neural network (ANN) algorithms, which can quickly and accurately predict activation free energy in hydrogen atom transfer (HAT)-based sp3 C–H activation. Density functional theory calculations (UωB97X-D) are used to establish the reaction system data sets of methoxyl (CH3O·), trifluoroethoxyl (CF3CH2O·), tert-butoxyl (tBuO·), and cumyloxyl (CumO·) radicals. The simplified Roberts’ equation proposed in our recent study works here [R2 = 0.84, mean absolute error (MAE) = 0.85 kcal/mol]. Its performance is comparable with univariate Mulliken-type electronegativity (χ) with the ANN model. The ANN model with bond dissociation free energy, χ, α-unsaturation, and Nolan buried volume (%Vburied) successively improves R2 and MAE to 0.93 and 0.54 kcal/mol, respectively. It reproduces the test sets of trichloroethoxyl (CCl3CH2O·) with R2 = 0.87 and MAE = 0.89 kcal/mol and accurately predicts the relative experimental barrier of the HAT reactions with CumO· and the site selectivity of CH3O·.