On the use of surrogate modelling in parameter selection
Ronald B.J. Brinkgreve (TU Delft - Civil Engineering & Geosciences)
Majd Ahmad (TU Delft - Civil Engineering & Geosciences)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Surrogate modelling is an application of Artificial Intelligence in which a Machine Learning model is trained to produce results that are originally obtained from a more complicated (numerical) model, especially when numerous such results are required. This article demonstrates two examples of using surrogate modelling in geotechnical applications involving (constitutive) model parameter selection as part of model fitting (parameter optimization) and probabilistic analysis. It gives some practical ideas on how to maintain the consistency of parameter sets in the case of parameter inter-dependencies, how to improve the quality of the surrogate in the case of large parameter variations, and how to improve model fitting to a target curve.