State Dependent Regressions: From Sensitivity Analysis to Meta-modeling

State Dependent Parameter (SDP) modelling has been developed by Professor Peter Young in the 90’s to identify non-linearities in the context of dynamic transfer function models. SDP is a very efficient approach and it is based on recursive filtering and Fixed Interval Smoothing (FIS) algorithms. It has been applied successfully in many applications, especially to identify Data-Based Mechanistic models from observed time series data in environmental sciences. In this paper we highlight the role played by the SDP ideas, namely in the simplified State-Dependent Regression (SDR) form, in the context of sensitivity analysis and meta-modelling. Fruitful joint co-operation with Peter Young has led to a series of papers, where SDR has been applied to perform sensitivity analysis, to reduce model’s complexity and to build meta-models (or emulators) capable to reproduce the main features of large simulation models. Finally, we will describe how SDR algorithms can be effectively used in the context of the identification and estimation of tensor product smoothing splines ANOVA models, improving their performances.

RATTO Marco;  PAGANO Andrea; 

2012-07-04

Springer

JRC66586

978-0-85729-973-4,   

https://publications.jrc.ec.europa.eu/repository/handle/JRC66586,   

10.1007/978-0-85729-974-1_9,