First order Sobol indices for physical models via inverse regression
- Authors
- Publication Date
- Jun 07, 2021
- Source
- HAL-Descartes
- Keywords
- Language
- English
- License
- Unknown
- External links
Abstract
In a bayesian inverse problem context, we aim at performing sensitivity analysis to help understand and adjust the physical model. To do so, we introduce indicators inspired by Sobol indices but focused on the inverse model. Since this inverse model is not generally available in closed form, we propose to use a parametric surrogate model to approximate it. The parameters of this model may be estimated via standard EM inference. Then we can exploit its tractable form and perform Monte-Carlo integration to efficiently estimate these pseudo Sobol indices.