Article ID Journal Published Year Pages File Type
6917932 Computer Methods in Applied Mechanics and Engineering 2013 14 Pages PDF
Abstract
► A practical nonlinear parameter estimation algorithm is proposed. ► Gradients are approximated using an ensemble of directional derivatives within a Gauss-Newton iteration. ► The ensemble output covariance matrix is regularized using the iterative ℓ2 Boosting method. ► The number of regularization iterations is selected based on Akaike information criterion (AIC). ► The proposed algorithm is successfully applied to the parameter estimation of several subsurface flow models.
Related Topics
Physical Sciences and Engineering Computer Science Computer Science Applications
Authors
, , , ,