The present paper describes further development of the multiscale informatics approach to kinetic model formulation of Burke et al. (Burke, M. P.; Klippenstein, S. J.; Harding, L. B. Proc. Combust. Inst. 2013, 34, 547-555) that directly incorporates elementary kinetic theories as a means to provide reliable, physics-based extrapolation of kinetic models to unexplored conditions. Here, we extend and generalize the multiscale informatics strategy to treat systems of considerable complexity-involving multiwell reactions, potentially missing reactions, nonstatistical product branching ratios, and non-Boltzmann (i.e., nonthermal) reactant distributions. The methodology is demonstrated here for a subsystem of low-temperature propane oxidation, as a representative system for low-temperature fuel oxidation. A multiscale model is assembled and informed by a wide variety of targets that include ab initio calculations of molecular properties, rate constant measurements of isolated reactions, and complex systems measurements. Active model parameters are chosen to accommodate both "parametric" and "structural" uncertainties. Theoretical parameters (e.g., barrier heights) are included as active model parameters to account for parametric uncertainties in the theoretical treatment; experimental parameters (e.g., initial temperatures) are included to account for parametric uncertainties in the physical models of the experiments. RMG software is used to assess potential structural uncertainties due to missing reactions. Additionally, branching ratios among product channels are included as active model parameters to account for structural uncertainties related to difficulties in modeling sequences of multiple chemically activated steps. The approach is demonstrated here for interpreting time-resolved measurements of OH, HO2, n-propyl, i-propyl, propene, oxetane, and methyloxirane from photolysis-initiated low-temperature oxidation of propane at pressures from 4 to 60 Torr and temperatures from 300 to 700 K. In particular, the multiscale informed model provides a consistent quantitative explanation of both ab initio calculations and time-resolved species measurements. The present results show that interpretations of OH measurements are significantly more complicated than previously thought-in addition to barrier heights for key transition states considered previously, OH profiles also depend on additional theoretical parameters for R + O-2 reactions, secondary reactions, QOOH + O-2 reactions, and treatment of non-Boltzmann reaction sequences. Extraction of physically rigorous information from those measurements may require more sophisticated treatment of all of those model aspects, as well as additional experimental data under more conditions, to discriminate among possible interpretations and ensure model reliability.
