Deep learning of parameterized equations with applications to uncertainty quantification

Qin, Tong; Chen, Zhen; Jakeman, John; Xiu, Dongbin

doi:10.1615/int.j.uncertaintyquantification.2020034123

Deep learning of parameterized equations with applications to uncertainty quantification

Journal Article · Sun Jan 31 23:00:00 EST 2021 · International Journal for Uncertainty Quantification

DOI:https://doi.org/10.1615/int.j.uncertaintyquantification.2020034123· OSTI ID:1738923

Qin, Tong ^[1]; Chen, Zhen ^[1]; Jakeman, John ^[2]; Xiu, Dongbin ^[1]

The Ohio State Univ., Columbus, OH (United States)
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

We propose a learning algorithm for discovering unknown parameterized dynamical systems by using observational data of the state variables. Our method is built upon and extends the recent work of discovering unknown dynamical systems, in particular those using deep neural network (DNN). We propose a DNN structure, largely based upon the residual network (ResNet), to not only learn the unknown form of the governing equation but also take into account the random effect embedded in the system, which is generated by the random parameters. Once the DNN model is successfully constructed, it is able to produce system prediction over longer term and for arbitrary parameter values. For uncertainty quantification, it allows us to conduct uncertainty analysis by evaluating solution statistics over the parameter space.

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR). Scientific Discovery through Advanced Computing (SciDAC); USDOE National Nuclear Security Administration (NNSA); US Air Force Office of Scientific Research (AFOSR)

Grant/Contract Number:: AC04-94AL85000; NA0003525

OSTI ID:: 1738923

Report Number(s):: SAND--2020-10596J; 691098

Journal Information:: International Journal for Uncertainty Quantification, Journal Name: International Journal for Uncertainty Quantification Journal Issue: 2 Vol. 11; ISSN 2152-5080

Publisher:: Begell HouseCopyright Statement

Country of Publication:: United States

Language:: English

References (11)

Approximation capabilities of multilayer feedforward networks Hornik, Kurt Neural Networks, Vol. 4, Issue 2 https://doi.org/10.1016/0893-6080(91)90009-t	journal	January 1991
An adaptive hierarchical sparse grid collocation algorithm for the solution of stochastic differential equations Ma, Xiang; Zabaras, Nicholas Journal of Computational Physics, Vol. 228, Issue 8 https://doi.org/10.1016/j.jcp.2009.01.006	journal	May 2009
Numerical approach for quantification of epistemic uncertainty Jakeman, John; Eldred, Michael; Xiu, Dongbin Journal of Computational Physics, Vol. 229, Issue 12 https://doi.org/10.1016/j.jcp.2010.03.003	journal	June 2010
Time-dependent generalized polynomial chaos Gerritsma, Marc; van der Steen, Jan-Bart; Vos, Peter Journal of Computational Physics, Vol. 229, Issue 22 https://doi.org/10.1016/j.jcp.2010.07.020	journal	November 2010
Non-intrusive reduced order modeling of nonlinear problems using neural networks Hesthaven, J. S.; Ubbiali, S. Journal of Computational Physics, Vol. 363 https://doi.org/10.1016/j.jcp.2018.02.037	journal	June 2018
An artificial neural network as a troubled-cell indicator Ray, Deep; Hesthaven, Jan S. Journal of Computational Physics, Vol. 367 https://doi.org/10.1016/j.jcp.2018.04.029	journal	August 2018
Detecting troubled-cells on two-dimensional unstructured grids using a neural network Ray, Deep; Hesthaven, Jan S. Journal of Computational Physics, Vol. 397 https://doi.org/10.1016/j.jcp.2019.07.043	journal	November 2019
Approximation theory of the MLP model in neural networks Pinkus, Allan Acta Numerica, Vol. 8 https://doi.org/10.1017/s0962492900002919	journal	January 1999
On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep Architectures Bianchini, Monica; Scarselli, Franco IEEE Transactions on Neural Networks and Learning Systems, Vol. 25, Issue 8 https://doi.org/10.1109/tnnls.2013.2293637	journal	August 2014
Autocrine loops with positive feedback enable context-dependent cell signaling Shvartsman, S. Y.; Hagan, M. P.; Yacoub, A. American Journal of Physiology-Cell Physiology, Vol. 282, Issue 3 https://doi.org/10.1152/ajpcell.00260.2001	journal	March 2002
Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification Tripathy, Rohit; Bilionis, Ilias arXiv https://doi.org/10.48550/arxiv.1802.00850	text	January 2018

Similar Records

Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi‐Member and Stochastic Parameterizations

Journal Article · Sun Apr 13 00:00:00 EDT 2025 · Journal of Advances in Modeling Earth Systems · OSTI ID:2555915

Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles

Journal Article · Fri Aug 04 00:00:00 EDT 2023 · Physica. D, Nonlinear Phenomena · OSTI ID:2584756

Surrogate construction via weight parameterization of residual neural networks

Journal Article · Wed Oct 30 00:00:00 EDT 2024 · Computer Methods in Applied Mechanics and Engineering · OSTI ID:2476624

Related Subjects

97 MATHEMATICS AND COMPUTING
deep neural network
residual network
uncertainty quantification

Deep learning of parameterized equations with applications to uncertainty quantification

Citation Formats

References (11)

Similar Records

Related Subjects