A Regression Model for Plasma Reaction Kinetics

Abstract Machine learning (ML) is used to provide reactions rates appropriate for models of low temperature plasmas
with a focus on A + B $\rightarrow$ C D binary chemical reactions. The regression model trained
on data extracted from the QBD, KIDA, NFRI and UfDA databases. variety data
on reactant product species, some which also had be estimated using ML.
The final voting regressor comprising three distinct optimized models: support vector
regressor, random forest gradient-boosted trees model; this made freely available via github repository.
As use case, ML results are augment chemistry BCl$_3$/H$_2$ gas mixture.