Class schedule: Tuesday, Sep. 8th, 2015 from 02:30 pm to 04:00 pm
Location: Building 1, Room 4214
Abstract
We present a novel regularizing ensemble Kalman method for solving PDE-constrained inverse problems. By merging ideas from iterative regularisation approaches and ensemble Kalman algorithms we design a derivative-free solver for generic inverse problems. The proposed method can be used to estimate the parameters of large-scale PDE models in a black-box fashion. We provide numerical results to illustrate the efficacy of the proposed method for solving inverse problems that arise in a wide range of applications such as subsurface flow, medical imaging, and manufacturing composite materials.
