Large chemical kinetic mechanisms are vital to understanding many complex chemical processes, but can involve the estimation of &gt;100,000 of reaction rates, far too many to determine from experiments or quantum chemical methods. Modern ab initio methods can now provide us with enough kinetic data to approach this problem from a machine learning perspective. However, rate estimation is highly nonlinear and kinetic datasets are very sparse. For these reasons we need a demanding combination of properties unattainable from conventional machine learning approaches from our estimator: nonlinear, easy to diagnose, incorporation of qualitative chemical knowledge and uncertainty estimation. We have developed a subgraph-isomorphic decision-tree based method that has all of these properties. The only inputs for construction are a set of kinetic data for training and a starting reaction template. In the tree all kinetic data matching a given template are treated as samples from a lognormal rate distribution. Each template is branched into subgraph-isomorphic structures that minimize the resulting uncertainty in the means. Subgraph properties that do not affect this uncertainty are identified and adjusted based on a chemical knowledge based algorithm. Rates and uncertainties can then be estimated treating each reaction rate as a sample of the distributions at each template it is subgraph-isomorphic to.

A machine learning based approach to rate estimation

256th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.