Combined DFT and Machine Learning Study of the Dissociation and Migration of H in Pyrrole Derivatives

Abstract

Systematic DFT calculations of model coal-pyrrole derivatives substituted by different functional groups are carried out. The N-H bond dissociation energies (N-H BDEs) and H-transfer activation energies (H-TAEs) of pyrrole derivatives are fully evaluated to elucidate the effect of the type of substituents and their position on the molecular reactivity. The results indicate that compounds substituted with electron-donating groups (EDGs) are more prone to pyrolysis while those substituted with electron-withdrawing groups (EWGs) are difficult to pyrolyze. Furthermore, quantitative structure−property relationship (QSPR) models for N-H BDEs and H-TAEs about pyrrole derivatives are built with multiple linear regression (MLR) and support vector machine (SVM). The final results show that the SVM-QSPR model has better fitness, prediction, and robustness, while the MLR-QSPR model can express the physical meaning better. The effects of functional groups on pyrolysis are clarified by the models presented in this paper, which will support the optimization of ultra-low NO x combustion.

Precise Regulation on the Bond Dissociation Energy of Exocyclic C–N Bonds in Various N-Heterocycle Electron Donors via Machine Learning

“…41 RF is an integrated algorithm based on a decision tree, which could process high-dimensional data with high accuracy. 39,41 XGBoost is based on an optimized decision tree with high efficiency, which is popular in the field of data science. 31 The data set was randomly divided into the training set and test set at the ratio of 8:2.…”

“…Then, we employed ordinary least squares (OLS), random forest (RF), and extreme gradient boost (XGBoost) algorithms to establish ML models and compared their performances (Figure ). OLS is a widely known regression algorithm that linearly correlates input features and output results, which could feasibly provide insight into the underlying QSPR . RF is an integrated algorithm based on a decision tree, which could process high-dimensional data with high accuracy. , XGBoost is based on an optimized decision tree with high efficiency, which is popular in the field of data science .…”

“…In recent years, machine learning (ML) has exhibited great potential in rapidly predicting material properties and accelerating material discovery. − With the aid of ML approaches, researchers could efficiently establish the mapping relationship between input features and output results, such as QSPR between the molecular structure and specific properties for OLED materials. − ML approaches have also been employed to rapidly and accurately predict BDE values of organic compounds, such as carbonyls, hypervalent iodine, pyrrole derivatives, and drug-like molecules . However, the study of using ML to predict BDE values for OLED materials is still lacking, let alone a comprehensive study on the underlying QSPR of various molecular structures upon BDE, which is in urgent need.…”

“…OLS is a widely known regression algorithm that linearly correlates input features and output results, which could feasibly provide insight into the underlying QSPR . RF is an integrated algorithm based on a decision tree, which could process high-dimensional data with high accuracy. , XGBoost is based on an optimized decision tree with high efficiency, which is popular in the field of data science . The data set was randomly divided into the training set and test set at the ratio of 8:2.…”