Accelerating models for multiphase chemical kinetics through machine learning with polynomial chaos expansion and neural networks

Abstract

The heterogeneous chemistry of atmospheric aerosols involves multiphase chemical kinetics that can be described by kinetic multi-layer models (KMs) that explicitly resolve mass transport and chemical reactions. However, KMs are computationally too expensive to be used as sub-modules in large-scale atmospheric models, and the computational costs also limit their utility in inverse-modeling approaches commonly used to infer aerosol kinetic parameters from laboratory studies. In this study, we show how machine learning methods can generate inexpensive surrogate models for the kinetic multi-layer model of aerosol surface and bulk chemistry (KM-SUB) to predict reaction times in multiphase chemical systems. We apply and compare two common and openly available methods for the generation of surrogate models, polynomial chaos expansion (PCE) with UQLab and neural networks (NNs) through the Python package Keras. We show that the PCE method is well suited to determining global sensitivity indices of the KMs, and we demonstrate how inverse-modeling applications can be enabled or accelerated with NN-suggested sampling. These qualities make them suitable supporting tools for laboratory work in the interpretation of data and the design of future experiments. Overall, the KM surrogate models investigated in this study are fast, accurate, and robust, which suggests their applicability as sub-modules in large-scale atmospheric models.