Data-integrated training of surrogate models for uncertainty quantification and diagnostics of complex biological systems models

PN 2-7

Project description

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.

Project information

Project title Data-integrated training of surrogate models for uncertainty quantification and diagnostics of complex biological systems models
Project leaders Anneli Guthke (Paul Bürkner)
Project staff Philipp Reiser, doctoral researcher
Project partners Nicole Radde
Project duration April 2022 - September 2025
Project number PN 2-7

Data and software publications PN 2-7

  1. P. L. Reiser, J. E. Aguilar, A. Guthke, and P.-C. Bürkner, “Replication Code for: Uncertainty Quantification and Propagation in Surrogate-based Bayesian Inference.” 2024. doi: 10.18419/darus-4093.
To the top of the page