Optimal design of experiments aim to minimize the uncertainty of model predictions. An experimental scheme refers to the choice of sampling locations, data types and system excitation to trigger and observe system responses. From an information-theoretic point of view, a sampling design is as informative on the prediction goal as the prediction goal is on the sampled data.
This project reverts the flow of information between data and prediction goal. This new approach will lead to a dramatic reduction of computational costs, and therefore allow to use much more accurate conditioning methods than usual. Exemplary applications in this project will be the investigation of contaminated sites and model selection problems.
With smaller computational costs and more accurate schemes, larger, more complex and more non-linear systems can be tackled.
|Principal investigator||Prof. Dr.-Ing. Wolfgang Nowak||Partner||Prof. Yoram Rubin, UC Berkeley (United States)|
|Duration||08/2009 - 02/2014||Financing||SimTech Cluster of Excellence; German Research Foundation (DFG)|