Prediction of state-to-state dissociation rate coefficients using machine learning algorithms

Abstract

We study the possibility of using machine learning algorithms to optimize the prediction of state-to-state (STS) dissociation rate coefficients in modeling nonequilibrium air flows. A rigorous but computationally complex theoretical model of reaction rate coefficients, which takes into account electronic and vibrational excitation of all reaction participants (products and reagents), is taken as a basis. Several algorithms have been considered for predicting the STS dissociation rate coefficients of air components: k-Nearest Neighbours (k-NN) and Decision Tree (DT) regression, as well as neural networks; their accuracy and efficiency have been analyzed. It is shown that the use of regression (k-NN and DT) is inappropriate for our problem; neural network algorithms have clear advantages over classical regression algorithms in terms of time and scalability. Validation of the neural network approach is carried out in simulations of vibrational-chemical relaxation behind a shock wave. Satisfactory agreement with experiment and almost complete coincidence of the results with the solution obtained by theoretical methods without the use of machine learning are shown. The approach to data representation and processing proposed in the paper is easily scalable to more complex models accounting for the excitation of internal degrees of freedom. Thus, when accounting for the electronic excitation of a molecule, speedup of about 1-2 orders is achieved without significant loss of accuracy. As the result, this study has demonstrated that the use of neural network methods makes it possible to predict state-specific reaction rate coefficients with a high degree of accuracy without performing direct calculations using resource-intensive theoretical formulas directly in the working code. This approach scales as the complexity of the formulation increases (as shown in the case of accounting for the electron-vibrational excitation of the reagents), which allows us to reduce the time required to perform the calculations. At the same time, such a result is achieved through serious preliminary work and requires the development of large arrays of preliminary data. If we automate this process using neural networks, we can obtain a computationally efficient tool for systematic predictions of state-to-state reaction rate coefficients.

Keywords:

chemical reaction rate, state-to-state kinetics, dissociation, nonlinear regression, machine learning, neural networks, optimization of numerical calculations