Combined first-principles calculation and neural-network correction approach for heat of formation

摘要

Despite their success,the results of first-principles quantum mechaniical calculations contain inherent numerical errors caused by various intrinsic approximations.We propose here a neural-network-based algorithm to greatly reduce these inherent errors.As a demonstraton,this combined quantum mechanical calculation and neural-network correction approach is applied to the evaluation of standard heat of formation DELTA_fH~- for 180 small- to medium-sized organic molecules at 298 K.A dramatc reduction of numerical errors is claerly shown with systematic deviation being eliminated.For example,the root-mean-square deviation of the calculated DELTA_fH~- for the 180 moleules is reduced from 21.4 to 3.1 kcal mol~-1 for B3LYP/6-311+G(d,p) and from 12.0 to 3.3 kcal mol`-1 for B3LYP/6-311+G(3df,2p) before and after the neural0network correction.