A Promising Tool to Achieve Chemical Accuracy for Density Functional Theory Calculations on Y-NO Homolysis Bond Dissociation Energies

Abstract

A DFT-SOFM-RBFNN method is proposed to improve the accuracy of DFT calculations on Y-NO (Y = C, N, O, S) homolysis bond dissociation energies (BDE) by combining density functional theory (DFT) and artificial intelligence/machine learning methods, which consist of self-organizing feature mapping neural networks (SOFMNN) and radial basis function neural networks (RBFNN). A descriptor refinement step including SOFMNN clustering analysis and correlation analysis is implemented. The SOFMNN clustering analysis is applied to classify descriptors, and the representative descriptors in the groups are selected as neural network inputs according to their closeness to the experimental values through correlation analysis. Redundant descriptors and intuitively biased choices of descriptors can be avoided by this newly introduced step. Using RBFNN calculation with the selected descriptors, chemical accuracy (≤1 kcal·mol−1) is achieved for all 92 calculated organic Y-NO homolysis BDE calculated by DFT-B3LYP, and the mean absolute deviations (MADs) of the B3LYP/6-31G(d) and B3LYP/STO-3G methods are reduced from 4.45 and 10.53 kcal·mol−1 to 0.15 and 0.18 kcal·mol−1, respectively. The improved results for the minimal basis set STO-3G reach the same accuracy as those of 6-31G(d), and thus B3LYP calculation with the minimal basis set is recommended to be used for minimizing the computational cost and to expand the applications to large molecular systems. Further extrapolation tests are performed with six molecules (two containing Si-NO bonds and two containing fluorine), and the accuracy of the tests was within 1 kcal·mol−1. This study shows that DFT-SOFM-RBFNN is an efficient and highly accurate method for Y-NO homolysis BDE. The method may be used as a tool to design new NO carrier molecules.

An Accurate and Efficient Method to Predict Y-NO Bond Homolysis Bond Dissociation Energies

“…In this study, 80 molecules selected with the Kenstone method are regarded as the training set and 12 molecules represent the test set. Molecules 13,19,21,27,31,35,36,43,55,70,78, and 81 are in the test set, and the rest are in the training set. It can be seen from the Kenstone calculation results that molecules 13,19,21,27,31,35,36, and 43 contain N-NO; molecule 55 contains O-NO; molecules 70 and 78 contain S-NO; and molecule 81 contains C-NO.…”

Prediction of “Aggregation-Prone” Peptides with Hybrid Classification Approach

“…For a given dataset, all these values can be obtained from the decision function with fixed cutoff [33][34][35][36][37]. Table 1.…”

A machine learning approach for increased throughput of density functional theory substitutional alloy studies

“…This study focused on the substitution of La and Yb into the bismuth-based structure (Bi 2 MoO 6 ) as shown in Figure 1. The main structure modification that was looked at is the substitution of La and Yb atoms for the Bi atoms in various combinations of the 8 possible positions occupied in the unit cell expressed in Figure 1 for atom position numbers 3,16,17,18,19,20,21,22. Thus all combination of Bi and Yb, Bi and La are explored in an attempt to express a method for machine learning that can reduce the computational cost of exploring the substitution for a structure system.…”