no code implementations • 21 Feb 2022 • Sascha Ranftl, Malte Rolf-Pissarczyk, Gloria Wolkerstorfer, Antonio Pepe, Jan Egger, Wolfgang von der Linden, Gerhard A. Holzapfel
Then to assess the uncertainty in the output stress distribution due to this stochastic constitutive model, a convolutional neural network, specifically a Bayesian encoder-decoder, was used as a surrogate model that maps the random input fields to the output stress distribution obtained from the FE analysis.
no code implementations • 22 Feb 2021 • Simone Di Cataldo, Christoph Heil, Wolfgang von der Linden, Lilia Boeri
In the last five years a large number of new high-temperature superconductors have been predicted and experimentally discovered among hydrogen-rich crystals, at pressures which are way too high to meet any practical application.
Superconductivity
no code implementations • 30 Jan 2021 • Franz M. Rohrhofer, Santanu Saha, Simone Di Cataldo, Bernhard C. Geiger, Wolfgang von der Linden, Lilia Boeri
In this work we seek to understand in depth the effect that the choice of features and the properties of the database have on a machine learning application.
no code implementations • 11 Jan 2021 • Sascha Ranftl, Wolfgang von der Linden
In the process, the contribution of the uncertainties of the surrogate itself to the simulation output uncertainties are usually neglected.
Methodology Data Analysis, Statistics and Probability