Machine Learning for Observables: Reactant to Product State Distributions for Atom-Diatom Collisions

Abstract

Machine learning-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. While all three methods predict final state distributions from explicit quasi-classical trajectory simulations with R${}^2$ > 0.998, the grid-based approach performs best. 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. The function-based approach also suffers from lacking a general set of model functions. Applications of the grid-based approach to nonequilibrium, multi-temperature initial state distributions are presented, a situation common to energy distributions in hypersonic flows. The role of such models in Direct Simulation Monte Carlo and computational fluid dynamics simulations is also discussed.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• The spectrum of hot methane in astronomical objects using a comprehensive computed line list
• The $\mathrm{N}{(}^{4}S)+{\mathrm{O}}_2(X^3{\Sigma }_g^{-})\leftrightarrow \mathrm{O}{(}^{3}P)+\mathrm{NO}(X^2\Pi )$ Reaction: Thermal and Vibrational Relaxation Rates for the ${}^2$A${}^{\prime }$, ${}^4$A${}^{\prime }$ and ${}^2$A${}^{\prime \prime }$ States
• Non-Boltzmann Vibrational Energy Distributions and Coupling to Dissociation Rate
• Consistent Kinetic-Continuum Dissociation Model I: Kinetic Formulation
• Dynamics on Multiple Potential Energy Surfaces: Quantitative Studies of Elementary Processes Relevant to Hypersonics
• Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata

Cited by in corpus (6)

• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Machine Learning Product State Distributions from Initial Reactant States for a Reactive Atom-Diatom Collision System
• Combining Machine Learning and Spectroscopy to Model Reactive Atom + Diatom Collisions
• Transformative Applications of Machine Learning for Chemical Reactions
• Neural network ensemble for computing cross sections for rotational transitions in H${}_2$O + H${}_2$O collisions
• Quantitative Molecular Simulations