(147ah) Machine Learning Enabled Development of Accurate Force Fields for Refrigerants

Research Interests: Molecular modeling and simulations, free energy calculations, machine learning, force field development, ionic liquids, hydrofluorocarbon

Hydrofluorocarbon (HFC) refrigerants with zero ozone depleting potential have replaced chlorofluorocarbons and are now ubiquitous. However, some HFCs have high global warming potential, which has led to calls by governments to phase these HFCs out. Technologies to recycle and repurpose these HFCs need to be developed. Therefore, thermophysical properties of HFCs are needed over a wide range of conditions. Molecular simulations can help understand and predict thermophysical properties of HFCs. The prediction capability of a molecular simulation is directly tied to the accuracy of the force field. In this work, we applied and refined a machine learning based workflow to optimize the Lennard-Jones parameters of classical HFC force fields for HFC-143a (CF₃CH₃), HFC-134a (CH₂FCF₃), R-50 (CH₄), R-170 (C₂H₆), and R-14 (CF₄). Our workflow involves liquid density iterations with molecular dynamics simulations and vapor-liquid equilibrium (VLE) iterations with Gibbs ensemble Monte Carlo simulations. Support vector machine classifiers and Gaussian process surrogate models save considerable simulation time and can efficiently select optimal parameters from half a million data sets. Excellent agreement of simulated liquid density, vapor density, vapor pressure, enthalpy of vaporization, and critical properties relative to experiments were obtained. The performance of each new parameter set was superior or similar to the best force field in literature. We find that the new force fields both yield excellent VLE properties and are transferable to a broader scope of properties including transport properties. Future work will use these simulation results as the training set to calibrate a generalized force field for HFCs, and this workflow is extensible to other complex molecular systems.