RESUMEN
This study presents the development of machine-learning-based quantitative structure-property relationship (QSPR) models for predicting electron affinity, ionization potential, and band gap of fusenes from different chemical classes. Three variants of the atom-based Weisfeiler-Lehman (WL) graph kernel method and the machine learning model Gaussian process regressor (GPR) were used. The data pool comprises polycyclic aromatic hydrocarbons (PAHs), thienoacenes, cyano-substituted PAHs, and nitro-substituted PAHs computed with density functional theory (DFT) at the B3LYP-D3/6-31+G(d) level of theory. The results demonstrate that the GPR/WL kernel methods can accurately predict the electronic properties of PAHs and their derivatives with root-mean-square deviations of 0.15 eV. Additionally, we also demonstrate the effectiveness of the active learning protocol for the GPR/WL kernel methods pipeline, particularly for data sets with greater diversity. The interpretation of the model for contributions of individual atoms to the predicted electronic properties provides reasons for the success of our previous degree of π-orbital overlap model.
RESUMEN
In this study, quantitative structure-property relationships (QSPR) based on a machine learning (ML) methodology and the truncated degree of π-orbital overlap (DPO) to predict the electronic properties, namely, the bandgaps, electron affinities, and ionization potentials of the cyano polycyclic aromatic hydrocarbon (CN-PAH) chemical class were developed. The level of theory B3LYP/6-31+G(d) of density functional theory (DFT) was used to calculate a total of 926 data points for the development of the QSPR model. To include the substituents effects, a new descriptor was added to the DPO model. Consequently, the new ML-DPO model yields excellent linear correlations to predict the desired electronic properties with high accuracy to within 0.2 eV for all multi-CN-substituted PAHs and 0.1 eV for the mono-CN-substituted PAH subclass.