Uncertainty estimation is crucial to assess the predictive power and limitations of biological systems models. However, in the case of high-dimensional parameter spaces and/or complex functional relationships, physics-based simulation models are often computationally too demanding for rigorous Bayesian uncertainty quantification. Surrogate models allow for such analyses with much lower effort. They are typically trained such that they fit the simulation reference best. What is left unexplored is the possibility of surrogate models to actually fit observed data better than the reference model. This phenomenon occurs when structural misspecification of the physics-constrained reference model limits its performance, but at the same time, the more flexible data-driven surrogate model can better capture the relation of output and input data. Such situations offer huge potential for diagnostic evaluation of the modelling approach toward deeper system understanding and model improvement. We aim at developing (1) a weighted data-integrated surrogate training approach for improved prediction skill, (2) a diagnostic approach for structural error detection in the reference model, and (3) an uncertainty propagation analysis that accounts for the approximation error introduced by this novel as well as any type of surrogate. The developed methods will be directly applicable to simulation models and data of PN 2 and align well with the overall goal of coupling knowledge with data.
For more information see the project page of PN 2-7.