no code implementations • 6 Dec 2023 • Atul Agrawal, Erik Tamsen, Phaedon-Stelios Koutsourelakis, Joerg F. Unger
Designing civil structures such as bridges, dams or buildings is a complex task requiring many synergies from several experts.
no code implementations • 25 Nov 2023 • Atul Agrawal, Kislaya Ravi, Phaedon-Stelios Koutsourelakis, Hans-Joachim Bungartz
Constrained optimization of the parameters of a simulator plays a crucial role in a design process.
no code implementations • 5 Jul 2023 • Atul Agrawal, Phaedon-Stelios Koutsourelakis
A fully Bayesian formulation is proposed, combined with a sparsity-inducing prior in order to identify regions in the problem domain where the parametric closure is insufficient and where stochastic corrections to the Reynolds stress tensor are needed.
no code implementations • 3 Mar 2023 • Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis, Petros Koumoutsakos
To this end, we combine a non-linear autoencoder architecture with a time-continuous model for the latent dynamics in the complex space.
1 code implementation • 6 Sep 2022 • Sebastian Kaltenbach, Paris Perdikaris, Phaedon-Stelios Koutsourelakis
Neural Operators offer a powerful, data-driven tool for solving parametric PDEs as they can represent maps between infinite-dimensional function spaces.
1 code implementation • 19 Nov 2021 • Jonas Eichelsdörfer, Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis
Identifying the dynamics of physical systems requires a machine learning model that can assimilate observational data, but also incorporate the laws of physics.
1 code implementation • 5 Aug 2021 • Maximilian Rixner, Phaedon-Stelios Koutsourelakis
While the forward and backward modeling of the process-structure-property chain has received a lot of attention from the materials community, fewer efforts have taken into consideration uncertainties.
no code implementations • 8 Feb 2021 • Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis
The data-based discovery of effective, coarse-grained (CG) models of high-dimensional dynamical systems presents a unique challenge in computational physics and particularly in the context of multiscale problems.
no code implementations • ICLR 2021 • Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis
Given (small amounts of) time-series' data from a high-dimensional, fine-grained, multiscale dynamical system, we propose a generative framework for learning an effective, lower-dimensional, coarse-grained dynamical model that is predictive of the fine-grained system's long-term evolution but also of its behavior under different initial conditions.
1 code implementation • 2 Jun 2020 • Maximilian Rixner, Phaedon-Stelios Koutsourelakis
We advocate a probabilistic (Bayesian) model in which equalities that are available from the physics (e. g. residuals, conservation laws) can be introduced as virtual observables and can provide additional information through the likelihood.
no code implementations • 24 Feb 2020 • Markus Schöberl, Nicholas Zabaras, Phaedon-Stelios Koutsourelakis
Rather than separating model learning from the data-generation procedure - the latter relies on simulating atomistic motions governed by force fields - we query the atomistic force field at sample configurations proposed by the predictive coarse-grained model.
1 code implementation • 30 Dec 2019 • Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis
Data-based discovery of effective, coarse-grained (CG) models of high-dimensional dynamical systems presents a unique challenge in computational physics and particularly in the context of multiscale problems.
1 code implementation • 11 Feb 2019 • Constantin Grigo, Phaedon-Stelios Koutsourelakis
The automated construction of coarse-grained models represents a pivotal component in computer simulation of physical systems and is a key enabler in various analysis and design tasks related to uncertainty quantification.
Small Data Image Classification Uncertainty Quantification +1
1 code implementation • 18 Jan 2019 • Yinhao Zhu, Nicholas Zabaras, Phaedon-Stelios Koutsourelakis, Paris Perdikaris
Surrogate modeling and uncertainty quantification tasks for PDE systems are most often considered as supervised learning problems where input and output data pairs are used for training.
1 code implementation • 18 Sep 2018 • Markus Schöberl, Nicholas Zabaras, Phaedon-Stelios Koutsourelakis
In this work, we formulate the discovery of CVs as a Bayesian inference problem and consider the CVs as hidden generators of the full-atomistic trajectory.
no code implementations • 21 Jun 2018 • Constantin Grigo, Phaedon-Stelios Koutsourelakis
Direct numerical simulation of Stokes flow through an impermeable, rigid body matrix by finite elements requires meshes fine enough to resolve the pore-size scale and is thus a computationally expensive task.
no code implementations • 2 Mar 2018 • Lukas Bruder, Phaedon-Stelios Koutsourelakis
This recasts the solution of both forward and inverse problems as probabilistic inference tasks where the problem's state variables should not only be compatible with the data but also with the governing equations as well.
no code implementations • 7 Nov 2017 • Constantin Grigo, Phaedon-Stelios Koutsourelakis
Both components are represented with latent variables in a probabilistic graphical model and are simultaneously trained using Stochastic Variational Inference methods.
no code implementations • 6 Mar 2017 • Constantin Grigo, Phaedon-Stelios Koutsourelakis
We discuss a Bayesian formulation to coarse-graining (CG) of PDEs where the coefficients (e. g. material parameters) exhibit random, fine scale variability.
no code implementations • 26 May 2016 • Markus Schöberl, Nicholas Zabaras, Phaedon-Stelios Koutsourelakis
We propose a data-driven, coarse-graining formulation in the context of equilibrium statistical mechanics.
no code implementations • 24 Jul 2015 • Phaedon-Stelios Koutsourelakis
The solution of such problems is hindered not only by the usual difficulties encountered in UQ tasks (e. g. the high computational cost of each forward simulation, the large number of random variables) but also by the need to solve a nonlinear optimization problem involving large numbers of design variables and potentially constraints.
Uncertainty Quantification Vocal Bursts Intensity Prediction