Predicting Rate Constants of Hydroxyl Radical Reactions with Alkanes Using Machine Learning

Prediction of Hydrogen Abstraction Rate Constants at the Allylic Site between Alkenes and OH with Multiple Machine Learning Models

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.

Structure-Based Reaction Descriptors for Predicting Rate Constants by Machine Learning: Application to Hydrogen Abstraction from Alkanes by CH3/H/O Radicals

Accurate determination of the thermal rate constants for combustion reactions is a highly challenging task, both experimentally and theoretically. Machine learning has been proven to be a powerful tool to predict reaction rate constants in recent years. In this work, three supervised machine learning algorithms, including XGB, FNN, and XGB-FNN, are used to develop quantitative structure-property relationship models for the estimation of the rate constants of hydrogen abstraction reactions from alkanes by the free radicals CH3, H, and O. The molecular similarity based on Morgan molecular fingerprints combined with the topological indices are proposed to represent chemical reactions in the machine learning models. Using the newly constructed descriptors, the hybrid XGB-FNN algorithm yields average deviations of 65.4%, 12.1%, and 64.5% on the prediction sets of alkanes + CH3, H, and O, respectively, whose performance is comparable and even superior to the corresponding one using the activation energy as a descriptor. The use of activation energy as a descriptor has previously been shown to significantly improve prediction accuracy ( Fuel 2022, 322, 124150) but typically requires cumbersome ab initio calculations. In addition, the XGB-FNN models could reasonably predict reaction rate constants of hydrogen abstractions from different sites of alkanes and their isomers, indicating a good generalization ability. It is expected that the reaction descriptors proposed in this work can be applied to build machine learning models for other reactions.

Photodehydration of Ethanol Mediated by CuCl2-Ethanol Complex

Biomass ethanol is regarded as a renewable resource but it is not economically viable to transform it to high-value industrial chemicals at present. Herein, a simple, green, and low-cost CuCl₂-ethanol complex is reported for ethanol dehydration to produce ethylene and acetal simultaneously with high selectivity under sunlight irradiation. Under N₂ atmosphere, the generation rates of ethylene and acetal were 165 and 3672 μmol g^-1 h^-1, accounting for 100% in gas products and 97% in liquid products, respectively. An outstanding apparent quantum yield of 13.2% (365 nm) and the maximum conversion rate of 32% were achieved. The dehydration reactions start from the photoexcited CuCl₂-ethanol complex, and then go through the energy transfer (EnT) and ligand to metal charge transfer (LMCT) mechanisms to produce ethylene and acetal, respectively. The formation energies of the CuCl₂-ethanol complex and the key intermediate radicals (e.g., ·OH, CH₃CH₂·, and CH₃CH₂O·) were validated to clarify the mechanisms. Different from previous CuCl₂-based oxidation and addition reactions, this work is anticipated to supply new insights into the dehydration reaction of ethanol to produce useful chemical feedstocks.

Transfer Learning Approach to Multitarget Temperature-Dependent Reaction Rate Prediction

Accurate prediction of temperature-dependent reaction rate constants of organic compounds is of great importance to both atmospheric chemistry and combustion science. Extensive work has been done on developing automated mechanism generation systems but the lack of quality reaction rate data remains a huge bottleneck in the application of highly detailed mechanisms. Machine learning prediction models have been recently adopted to alleviate the data gap in thermochemistry and have great potential to do the same for kinetic data with the recent release of quality reaction rate data compilations. The ultimate goal is to formulate easily accessible, general-purpose, temperature-dependent, and multitarget models for the prediction of reaction rates. To that end, we propose a model that depends on the well-known Morgan fingerprints as well as learned representations transferred from the QM9 data set. We propose the use of an Arrhenius-based loss where predictions of the three modified-Arrhenius parameters (A, n, and B = E_a/R) are given instead of the direct prediction of reaction rate constants. Our model is >35% more accurate compared to a baseline model of feed forward network (FFN) on Morgan fingerprints.

Fast Predictions of Reaction Barrier Heights: Toward Coupled-Cluster Accuracy

Quantitative estimates of reaction barriers are essential for developing kinetic mechanisms and predicting reaction outcomes. However, the lack of experimental data and the steep scaling of accurate quantum calculations often hinder the ability to obtain reliable kinetic values. Here, we train a directed message passing neural network on nearly 24,000 diverse gas-phase reactions calculated at CCSD(T)-F12a/cc-pVDZ-F12//ωB97X-D3/def2-TZVP. Our model uses 75% fewer parameters than previous studies, an improved reaction representation, and proper data splits to accurately estimate performance on unseen reactions. Using information from only the reactant and product, our model quickly predicts barrier heights with a testing MAE of 2.6 kcal mol^-1 relative to the coupled-cluster data, making it more accurate than a good density functional theory calculation. Furthermore, our results show that future modeling efforts to estimate reaction properties would significantly benefit from fine-tuning calibration using a transfer learning technique. We anticipate this model will accelerate and improve kinetic predictions for small molecule chemistry.

Progress towards machine learning reaction rate constants

Quantum and classical reaction rate constant calculations come at the cost of exploring potential energy surfaces. Due to the "curse of dimensionality", their evaluation quickly becomes unfeasible as the system size grows. Machine learning algorithms can accelerate the calculation of reaction rate constants by predicting them using low cost input features. In this perspective, we briefly introduce supervised machine learning algorithms in the context of reaction rate constant prediction. We discuss existing and recently created kinetic datasets and input feature representations as well as the use and design of machine learning algorithms to predict reaction rate constants or quantities required for their computation. Amongst these, we first describe the use of machine learning to predict activation, reaction, solvation and dissociation energies. We then look at the use of machine learning to predict reactive force field parameters, reaction rate constants as well as to help accelerate the search for minimum energy paths. Lastly, we provide an outlook on areas which have yet to be explored so as to improve and evaluate the use of machine learning algorithms for chemical reaction rate constants.