Prediction of Hydrogen Abstraction Rate Constants at the Allylic Site between Alkenes and OH with Multiple Machine Learning Models
- 18 January 2024
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 128 (4) , 761-772
Abstract
Hydrogen abstraction reactions between hydrocarbons and hydroxyl radicals are important propagation steps in radical chain reactions, playing a crucial role in atmospheric and combustion chemistry. This study focuses on predicting the rate constants of the prototype of the reaction class of hydrogen abstractions, i.e., the primary allylic hydrogen abstraction from alkenes by the OH radical, via utilizing machine learning (ML) methods. Specifically, three distinct models, namely, feedforward neural network (FNN), support vector regression (SVR), and Gaussian process regression (GPR), have been employed to construct robust ML models for prediction. We proposed a novel strategy that seamlessly integrates descriptor preprocessing, a pairwise linear correlation analysis, and a model-specific Wrapper method to enhance the effectiveness of the feature selection procedure. The selected feature subset was then evaluated using two cross-validation techniques, i.e., leave-one-group-out (LOGO) and K-fold cross-validations, for each of the three ML models (FNN, SVR, and GPR) to assess their predictive and stability performance. The results demonstrate that the FNN model, trained with seven representative descriptors, achieves superior performance compared to the other two methods. For the FNN model, the average percentage deviation is 39.06% on the test set by performing LOGO cross-validation, while the repeated 10-fold cross-validation achieves a percentage prediction deviation of 19.1%. Two larger alkenes with 10 carbons were selected to test the prediction performance of the trained FNN model on primary allylic hydrogen abstraction. Results show that the kinetic predictions follow well the modified three-parameter Arrhenius equation, indicating the reliable performance of FNN in predicting hydrogen abstraction rate constants, especially for the primary allylic site. Hopefully, this work can shed useful light on the application of ML in generating chemical kinetic parameters of hydrocarbon combustion chemistry.Keywords
Funding Information
- State Key Laboratory of Fire Science (HZ2021-KF13)
- National Natural Science Foundation of China (52276101)
This publication has 41 references indexed in Scilit:
- Kinetics of Hydrogen Abstraction Reactions of Butene Isomers by OH RadicalThe Journal of Physical Chemistry A, 2010
- Shock Tube/Laser Absorption Measurements of the Reaction Rates of OH with Ethylene and PropeneThe Journal of Physical Chemistry A, 2010
- Support Vector Machines for classification and regressionThe Analyst, 2009
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Reflected shock tube studies of high-temperature rate constants for OH + C2H2 and OH + C2H4Physical Chemistry Chemical Physics, 2007
- Emissions of volatile organic compounds from vegetation and the implications for atmospheric chemistryGlobal Biogeochemical Cycles, 1992
- Hydrogen-atom abstraction from alkenes by OH, ethene and 1-buteneChemical Physics Letters, 1988
- Laser pyrolysis studies of OH reaction rates with several butenes at 1200 KInternational Journal of Chemical Kinetics, 1987
- The development of the Arrhenius equationJournal of Chemical Education, 1984
- Laser photolysis/laser-induced fluorescence study of the reaction of hydroxyl radical with ethyleneChemical Physics Letters, 1983