Heymann, W.; Glaser, J.; Schlegel, F.; Johnson, W.; Rolandi, P.; von Lieres, E.: Advanced error modeling and Bayesian uncertainty quantification in
mechanistic liquid chromatography modeling, Journal of Chromatography A 1708 (2023): 464329.
Bill has analyzed root causes of non-Gaussian sources of uncertainty. A Bayesian approach allows to propagate the impacts of uncertainty across four levels of parameter estimation using chromatogram data under bypass, non-pore penetrating, pore-penetrating, and binding conditions. The method is demonstratet using synthetic and industrial process data.