Machine Learning for Observables: Reactant to Product State Distributions for Atom–Diatom Collisions
- 23 July 2020
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 124 (35), 7177-7190
- https://doi.org/10.1021/acs.jpca.0c05173
Abstract
Machine learning- (ML) based models to predict product state distributions from a distribution of reactant conditions for atom-diatom collisions are presented and quantitatively tested. The models are based on function-, kernel- and grid-based representations of the reactant and product state distributions. All three methods predict final state distributions from explicit quasi-classical trajectory simulations with $R^2 > 0.998$. Although a function-based approach is found to be more than two times better in computational performance, the kernel- and grid-based approaches are preferred in terms of prediction accuracy, practicability and generality. For the function-based approach the choice of parametrized functions is crucial and this aspect is explicitly probed for final state vibrational distributions. Applications of the grid-based approach to non-equilibrium, multi-temperature initial state distributions are presented, a situation common to energy and state distributions in hypersonic flows. The role of such models in Direct Simulation Monte Carlo and computational fluid dynamics simulations is also discussed.
Funding Information
- Schweizerischer Nationalfonds zur F?rderung der Wissenschaftlichen Forschung (200020-188724, 200021-117810)
- Universit?t Basel
- NCCRR MUST
This publication has 43 references indexed in Scilit:
- Coarse-grain model for internal energy excitation and dissociation of molecular nitrogenChemical Physics, 2011
- The HITRAN 2004 molecular spectroscopic databaseJournal of Quantitative Spectroscopy and Radiative Transfer, 2005
- Fifty years of hypersonics: where we've been, where we're goingProgress in Aerospace Sciences, 2003
- Data-Parallel Line Relaxation Method for the Navier-Stokes EquationsAIAA Journal, 1998
- Growth, income distribution, and democracy: What the data sayJournal of Economic Growth, 1996
- Review of chemical-kinetic problems of future NASA missions. I - Earth entriesJournal of Thermophysics and Heat Transfer, 1993
- Theoretical studies of collisional energy transfer in highly excited molecules: temperature and potential surface dependence of relaxation in helium, neon, argon + carbon disulfideThe Journal of Physical Chemistry, 1988
- Information Theory Approach to Molecular Reaction DynamicsAnnual Review of Physical Chemistry, 1978
- Statistical collision model for Monte Carlo simulation of polyatomic gas mixtureJournal of Computational Physics, 1975
- Theory of reproducing kernelsTransactions of the American Mathematical Society, 1950