no code implementations • 25 May 2021 • Lukas Mosser, Ehsan Zabihi Naeini
These methods are consistently applied to fault detection case studies where Deep Ensembles use independently trained models to provide fault probabilities, Concrete Dropout represents an extension to the popular Dropout technique to approximate Bayesian neural networks, and finally, we apply SWAG, a recent method that is based on the Bayesian inference equivalence of mini-batch Stochastic Gradient Descent.
no code implementations • 17 Feb 2020 • Andrea Gayon-Lombardo, Lukas Mosser, Nigel P. Brandon, Samuel J. Cooper
The generation of multiphase porous electrode microstructures is a critical step in the optimisation of electrochemical energy storage devices.
1 code implementation • 14 May 2019 • Lukas Mosser, Olivier Dubrule, Martin J. Blunt
Our contribution shows that for a synthetic test case, we are able to obtain solutions to the inverse problem by optimising in the latent variable space of a deep generative model, given a set of transient observations of a non-linear forward problem.
1 code implementation • 10 Jun 2018 • Lukas Mosser, Olivier Dubrule, Martin J. Blunt
We show that approximate MALA sampling allows efficient Bayesian inversion of model parameters obtained from a prior represented by a deep generative model, obtaining a diverse set of realizations that reflect the observed seismic response.
no code implementations • 22 May 2018 • Lukas Mosser, Wouter Kimman, Jesper Dramsch, Steve Purves, Alfredo De la Fuente, Graham Ganssle
Traditional physics-based approaches to infer sub-surface properties such as full-waveform inversion or reflectivity inversion are time-consuming and computationally expensive.
1 code implementation • 15 Feb 2018 • Lukas Mosser, Olivier Dubrule, Martin J. Blunt
Based on the previous work of Yeh et al. (2016), we use a content loss to constrain to the conditioning data and a perceptual loss obtained from the evaluation of the GAN discriminator network.
1 code implementation • 7 Dec 2017 • Lukas Mosser, Olivier Dubrule, Martin J. Blunt
Stochastic image reconstruction is a key part of modern digital rock physics and materials analysis that aims to create numerous representative samples of material micro-structures for upscaling, numerical computation of effective properties and uncertainty quantification.
2 code implementations • 11 Apr 2017 • Lukas Mosser, Olivier Dubrule, Martin J. Blunt
We present a novel method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image datasets.