Model-based design of experiments in the presence of structural model uncertainty: an extended information matrix approach

Abstract The identification of a parametric model, once a suitable model structure is proposed, requires the estimation of its non-measurable parameters. Model-based design of experiment (MBDoE) methods have been proposed in the literature for maximising the collection of information whenever there is a limited amount of resources available for conducting the experiments. Conventional MBDoE methods do not take into account the structural uncertainty on the model equations and this may lead to a substantial miscalculation of the information in the experimental design stage. In this work, an extended formulation of the Fisher information matrix is proposed as a metric of information accounting for model misspecification. The properties of the extended Fisher information matrix are presented and discussed with the support of two simulated case studies.

[1]  P. Rao,et al.  Some Notes on Misspecification in Multiple Regressions , 1971 .

[2]  Massimiliano Barolo,et al.  A general model-based design of experiments approach to achieve practical identifiability of pharmacokinetic and pharmacodynamic models , 2013, Journal of Pharmacokinetics and Pharmacodynamics.

[3]  Massimiliano Barolo,et al.  Online model-based redesign of experiments with erratic models: A disturbance estimation approach , 2012, Comput. Chem. Eng..

[4]  Sandro Macchietto,et al.  Designing robust optimal dynamic experiments , 2002 .

[5]  J. F. Van Impe,et al.  On the unicity of optimal experimental design solutions for parameter estimation of microbial kinetics , 1997, 1997 European Control Conference (ECC).

[6]  Sandro Macchietto,et al.  The optimal design of dynamic experiments , 1989 .

[7]  Vivek Dua,et al.  A joint model-based experimental design approach for the identification of kinetic models in continuous flow laboratory reactors , 2016, Comput. Chem. Eng..

[8]  Andrew White,et al.  The Limitations of Model-Based Experimental Design and Parameter Estimation in Sloppy Systems , 2016, PLoS Comput. Biol..

[9]  Sandro Macchietto,et al.  Model-based design of experiments for parameter precision: State of the art , 2008 .

[10]  José Carlos Pinto,et al.  Sequential experimental design for model discrimination: Taking into account the posterior covariance matrix of differences between model predictions , 2008 .

[11]  I Stamati,et al.  Optimal experimental design for discriminating between microbial growth models as function of suboptimal temperature: From in silico to in vivo. , 2016, Food research international.

[12]  Filip Logist,et al.  Robustifying optimal experiment design for nonlinear, dynamic (bio)chemical systems , 2014, Comput. Chem. Eng..

[13]  R. R. Hocking.  The analysis and selection of variables in linear regression , 1976 .

[14]  Johannes P. Schlöder,et al.  Numerical methods for optimal control problems in design of robust optimal experiments for nonlinear dynamic processes , 2004, Optim. Methods Softw..

[15]  Eric Walter,et al.  Identification of Parametric Models: from Experimental Data , 1997 .

[16]  Guido Buzzi-Ferraris,et al.  An improved version of a sequential design criterion for discriminating among rival multiresponse models , 1990 .

[17]  Ursula Klingmüller,et al.  Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood , 2009, Bioinform..

[18]  Massimiliano Barolo,et al.  Online Model-Based Redesign of Experiments for Parameter Estimation in Dynamic Systems , 2009 .

[19]  Vinay Prasad,et al.  Multiscale Model and Informatics-Based Optimal Design of Experiments : Application to the Catalytic Decomposition of Ammonia on Ruthenium , 2008 .

[20]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[21]  G. Box.  Science and Statistics , 1976 .

[22]  Sandro Macchietto,et al.  Statistical tools for optimal dynamic model building , 2000 .

[23]  H. L. Lucas,et al.  DESIGN OF EXPERIMENTS IN NON-LINEAR SITUATIONS , 1959 .

[24]  William J. Hill,et al.  Discrimination Among Mechanistic Models , 1967 .

[25]  M. Barolo,et al.  Linking Models and Experiments , 2016 .

[26]  S. D. Silvey,et al.  Statistical Inference , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[27]  J. Dirion,et al.  Kinetic parameter estimation from TGA: Optimal design of TGA experiments , 2008 .

[28]  Stefan Streif,et al.  A Probabilistic Approach to Robust Optimal Experiment Design with Chance Constraints , 2014, ArXiv.

[29]  Filip Logist,et al.  Optimal experiment design under process noise using riccati differential equations , 2013 .

[30]  T. Brubaker,et al.  Nonlinear Parameter Estimation , 1979 .

[31]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

[32]  Michael Nikolaou,et al.  Modelling time-kill studies to discern the pharmacodynamics of meropenem. , 2005, The Journal of antimicrobial chemotherapy.