Professional Documents
Culture Documents
Introduction
UQ Software
PCES
References
bjdebus@sandia.gov
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Acknowledgement
Omar Knio Roger Ghanem Olivier Le Matre and many others ...
Duke University, Raleigh, NC University of Southern California, Los Angeles, CA LIMSI-CNRS, Orsay, France
US Department of Energy (DOE), Ofce of Advanced Scientic Computing Research (ASCR), Scientic Discovery through Advanced Computing (SciDAC) and Applied Mathematics Research (AMR) programs.
Sandia National Laboratories is a multi-program laboratory managed and operated by Sandia Corporation, a wholly owned subsidiary of Lockheed Martin Corporation, for the U.S. Department of Energys National Nuclear Security Administration under contract DE-AC04-94AL85000.
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
An overview of the key aspects of uncertainty quantication 4 Lectures Lecture 1: Context and Fundamentals
Introduction to uncertainty The various aspects of UQ Software for UQ Spectral representation of random variables
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Outline
Introduction The Many Aspects of Uncertainty Quantication Software for Uncertainty Quantication Spectral Representation of Random Variables References
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Predictive simulations provide insight into the underlying physics that drive complex systems
Identication of key mechanisms Allows for rigorous optimization strategies
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Mixture Fraction!
Temperature!
Experiment!
DLR-A Flame: Red = 15,200 !
Fuel: 22.1% CH4, 33.2% H2, 44.7% N2! Coow: 99.2% Air, 0.8% H2O ! Detailed Chemistry and Transport: 12-Step Mechanism (J.-Y. Chen, UC Berkeley) !
LES!
Large Eddy Simulation (LES) validation on turbulent ame (courtesy J. Oefelein, SNL)
Debusschere SNL UQ
Introduction
Introduction
UQ Software
PCES
References
Predictive simulation requires careful assessment of all sources of error and uncertainty
Numerical errors Grid resolution Time step Time integration order Spatial derivative order Tolerance on iterative solvers Condition number of matrices Uncertainties Initial and boundary conditions Model parameters Model equations Coupling between models Sampling noise in particle models Stochastic forcing terms
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Introduction
Introduction
UQ Software
PCES
References
Theory
Debusschere SNL
UQ
Introduction
du to enable UQ methods extract information from all Introduction sources Introduction UQ Software predictive PCES = f (u ; ) P (D|, I d)tP (, I ) P (|D, I ) = Formulation simulation P (D )
Introduction Introduction
Formulation
Introduction
= f (u ; ) UQ Software
du dt
PCES
References
Summary
Formulation
du = f (u ; ) dt
u = f (u ; ) d t Experiments P (u ) P ()du = P (D|, I )p(, I ) P (D|, I )P (, I ) f (u ; ) Predictive P (|D, I ) = P (|D, I ) = P (D|, I )p(, I ) dt P (D ) P (|D , P I )(D =) Simulation P (D ) P (D|, I )P (, I ) P (|D, I ) = u du P (D) = f (u ; ) dt du = u( ; ) d u u P (u ) f (P dt = f (u ; ) Debusschere SNL UQ Forward P (D|, I )P (, I ) dt P (|D, I ) = P (D|, I )p(, IPropagation ) P (D ) P ( u ) P ( ) P (|D, I ) = P (D|, I )p(, I ) Debusschere SNL UQ Theory P (D ) P (|D, I ) = P u(D)
du P (u ) P () dt Inference = f (u ; )
Debusschere SNL UQ UQ not just about propagating uncertainties
Debusschere SNL UQ
du
Formulation Formulation
P (|D, I ) = u
PCES PCES
Sum
P (u ) P ()
Debusschere SNL
UQ
UQ
Introduction
Introduction
UQ Software
PCES
References
UQ assesses condence in model predictions and allows resource allocation for delity improvements
Parameter inference Determine parameters from data Characterize uncertainties in inferred parameters Propagate input uncertainties through computational models Account for uncertainty from all sources Resolve coupling between sources Analysis Sensitivity analysis Attributions Model calibration, validation, selection, averaging
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Types of uncertainty
Epistemic uncertainty Variable has one particular value, but we dont know what it is Reducible: by taking more measurements, we can get to know the value of the variable better Examples
The mass of the planet Neptune Temperature of the ocean at a particular point and time
Aleatory uncertainty Intrinsic or inherent uncertainty: variable is random; different value each time it is observed Irreducible: taking more measurements will not reduce uncertainty in the value of the variable Examples:
Collisions interactions in molecular systems Sampling noise
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Viewpoints matter
Epistemic versus aleatory sometimes depends on scale level In fully resolved turbulent simulations, velocity eld near a wall is deterministic In mesoscale channel ow, near wall velocity eld is turbulent forcing term (aleatory) In macroscale channel ow, near wall velocity eld provides friction term (epistemic) These lectures follow the Bayesian view: probability represents the
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
UQ in computational sciences is maturing Algorithms and research codes are transitionting into engineering
sciences software
QUEST: Quantication of Uncertainty in Extreme Scale Simulations DOE SciDAC institute: http://quest-scidac.org/ One of the key goals is to make extreme scale UQ approaches available to the scientic community Various UQ methods offered under 4 software products
DAKOTA QUESO GPMSA UQTk
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
UQ Tools DAKOTA: Design Analysis Kit for Optimization and Terascale Applications
http://dakota.sandia.gov/ Large-Scale Optimization, non-intrusive UQ Model calibration, global sensitivity analysis Design of Experiments solution verication, and parametric studies Over 4000 download registrations
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
UQ Tools QUESO
MPI/C++ library Large-scale inverse UQ Statistical algorithms for Bayesian inference model calibration, model validation, decision making under uncertainty Parallel multi-chain MCMC Being integrated with DAKOTA
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
http://www.sandia.gov/UQToolkit/ Lightweight C++ library Intrusive Polynomial Chaos UQ methods Non-intrusive sparse-quadrature UQ Bayesian inference Custom representations of uncertain information Well suited for prototyping, tutorial/training purposes
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Serial matlab code C++ conversion plans Integration with DAKOTA Bayesian inference Gaussian process surrogates Global sensitivity analysis, forward UQ Model calibration/parameter estimation Statistical models to characterize model discrepancy or structural model
error
Prototyping tool
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Representation of random variables with PCEs Convergence Galerkin projection Basis types
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
/2
dk x 2 /2 e , dx k
k = 1, 2, . . .
1 ( x ) = x ,
The Hermite polynomials form an orthogonal basis over [, ] with respect to the inner product 1 i j 2
2 (x ) = x 2 1,
3 (x ) = x 3 3 x , . . .
i (x )j (x )w (x )dx = ij i2
/2
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
u=
k =0
u k k ( )
4 3 2 1 0.5 1.0
0 0.0
order k
1.5
2.0
: Gaussian RV
A random quantity is represented with an expansion consisting of functions of random variables multiplied with deterministic coefcients
Set of deterministic PC coefcients fully describes RV Separates randomness from deterministic dimensions
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
The multidimensional Hermite polynomial i (1 , . . . , n ) is a tensor product of i i i the 1D Hermite polynomials, with a suitable multi-index i = (1 , 2 , . . . , n ),
n
=
k =1
i (k )
k
i 1 1 2 2 1 1 1 2 2 2 1 ...
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
i j
...
=
k =1
i (k )j (k ) = ij 2 i
k k
g ( )
e /2 2
u=
k =0
uk k
i u =
k =0
uk i k = ui 2 i
ui =
u i 2 i
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
uk k (1 , . . . , n )
u : Random Variable (RV) represented with multi-D PCE uk : PC coefcients (deterministic) k : Multi-D Hermite polynomials up to order p i : Gaussian RV n: Dimensionality of stochastic space P + 1: Number of PC terms: P + 1 =
(n+p)! n!p!
The number of stochastic dimensions represents the number of independent inputs, degrees of freedom that affect the random variable u
E.g. one stochastic dimension per uncertain model parameter Contributions from each uncertain input can be identied Compact representation of a random variable and its dependencies
Debusschere SNL UQ
Introduction
Introduction
UQ Software
PCES
References
> 1, > 1
Inner product: i j
b a
i ( ) j ( ) w ( ) d
Legendre-Uniform PC is a special case of Beta-Jacobi PC Beta-Jacobi PC allows tailored accuracy of the PC representation across the
Input parameter domain often dictates the most convenient choice of PC Polynomials functions can also be tailored to be orthogonal w.r.t.
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Gamma Distribution
1.0 0.8 0.6 PDF 0.4 0.2 0.00
=0 =1 =2 =3 =4
8 x
10
12
14
16
Introduction
Introduction
UQ Software
PCES
References
Beta Distribution
1.4 1.2 1.0 PDF 0.8 0.6 0.4 0.2 0.01.0 0.5 0.0 x 0.5 1.0
= =0.5 =5, =1 =1, =3 =2, =2 =2, =5
Useful to represent quantities that vary between set boundaries Can be tailored to give more importance to specic areas Support on [1, 1]
Debusschere SNL UQ
Introduction
Introduction
UQ Software
PCES
References
Let (, S, P) be a probability space is an event space S is a -algebra on P is a probability measure on (, S) Random variables are functions X : R with a measure
if X 1 (A) S, then dene (A) = P(X 1 (A)). p (x ) = d /dx : the density of the random variable X (with respect to Expectation: f =
f p(x ) dx
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Convergence of PC expansions
General convergence theorems are subject of ongoing research Depends on the type of underlying random variables Wiener-Hermite Chaos has been well-studied Generalized PC less so Ernst et al. 2011: Let : RN such that for i = 1, . . . , N each i : R, be a set of random variables S( ): -algebra generated by the set of random variables L2 (, S( ), P): Hilbert space of real-valued random variables dened on (, S( ), P) with nite second moments Any random variable in this -algebra can be represented with a Polynomial Chaos expansion with germ Does not say that any RV with nite variance can be represented with a
In practice, one rarely knows how many degrees of freedom a RV has Also, RV specication is rarely complete Often, in an engineering sense, PCE of a given order is seen as a model
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Approximation error in PCE is topic of a lot of research Rules of thumb: Higher order PC coefcients should decay Increase order until results no longer change Not always fail-proof ...
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Postprocessing / Analysis
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
u=
k =0
uk k ( )
Expectation: u = u0 Variance 2
= =
(u u )2
P
(
k =1 P
uk k ( ))2
P
=
k =1 j =1 P P
uj uk j ( )k ( ) uj uk j ( )k ( )
k =1 j =1 P 2 uk k ( )2
=
k =1
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
u=
k =0
uk k ( )
Analytical formula formula for PDF(u ) exists Involves polynomial root nding, and is hard to generalize to multi-D PCE is cheap to sample Brute-force sampling and bin samples into histogram Use Kernel Density Estimation (KDE) to get smoother PDF with fewer samples ui PDF(u ) = 1 Ns h
Ns
K
i =1
u ui h
x2 2
, leading to
PDF(u ) =
1 2 Ns h
Ns
exp
i =1
(u ui )2 2h2
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
Source Wikipedia, Drleft; licensed under the Creative Commons Attribution-ShareAlike 3.0 License
Debusschere SNL
UQ
Introduction
Introduction
UQ Software
PCES
References
0.25
Random variable
Bandwidth h needs to be chosen carefully to avoid oversmoothing Scotts rule-of-thumb is optimal for Gaussian r. v., h = N d +4 With smaller h, the KDE becomes more accurate, but more noisy Binning is similar to smaller h case, but it requires a good choice of Nbins
Debusschere SNL UQ 1
Introduction
Introduction
UQ Software
PCES
References
0.15
Random variable
Bandwidth h needs to be chosen carefully to avoid oversmoothing Scotts rule-of-thumb is optimal for Gaussian r. v., h = N d +4 With smaller h, the KDE becomes more accurate, but more noisy Binning is similar to smaller h case, but it requires a good choice of Nbins
Debusschere SNL UQ 1
Introduction
Introduction
UQ Software
PCES
References
0.15
Random variable
Bandwidth h needs to be chosen carefully to avoid oversmoothing Scotts rule-of-thumb is optimal for Gaussian r. v., h = N d +4 With smaller h, the KDE becomes more accurate, but more noisy Binning is similar to smaller h case, but it requires a good choice of Nbins
Debusschere SNL UQ 1
Introduction
Introduction
UQ Software
PCES
References
Further Reading
N. Wiener, Homogeneous Chaos", American Journal of Mathematics, 60:4, pp. 897-936, 1938. M. Rosenblatt, Remarks on a Multivariate Transformation", Ann. Math. Statist., 23:3, pp. 470-472, 1952. R. Ghanem and P. Spanos, Stochastic Finite Elements: a Spectral Approach", Springer, 1991. O. Le Matre and O. Knio, Spectral Methods for Uncertainty Quantication with Applications to Computational Fluid Dynamics", Springer, 2010. D. Xiu, Numerical Methods for Stochastic Computations: A Spectral Method Approach", Princeton U. Press, 2010. O.G. Ernst, A. Mugler, H.-J. Starkloff, and E. Ullmann, On the convergence of generalized polynomial chaos expansions, ESAIM: M2AN, 46:2, pp. 317-339, 2011. D. Xiu and G.E. Karniadakis, The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations", SIAM J. Sci. Comput., 24:2, 2002. Le Matre, Ghanem, Knio, and Najm, J. Comp. Phys., 197:28-57 (2004) Le Matre, Najm, Ghanem, and Knio, J. Comp. Phys., 197:502-531 (2004) B. Debusschere, H. Najm, P. Pbay, O. Knio, R. Ghanem and O. Le Matre, Numerical Challenges in the Use of Polynomial Chaos Representations for Stochastic Proecesses", SIAM J. Sci. Comp., 26:2, 2004. S. Ji, Y. Xue and L. Carin, Bayesian Compressive Sensing", IEEE Trans. Signal Proc., 56:6, 2008. K. Sargsyan, B. Debusschere, H. Najm and O. Le Matre, Spectral representation and reduced order modeling of the dynamics of stochastic reaction networks via adaptive data partitioning". SIAM J. Sci. Comp., 31:6, 2010. K. Sargsyan, B. Debusschere, H. Najm and Y. Marzouk, Bayesian inference of spectral expansions for predictability assessment in stochastic reaction networks". J. Comp. Theor. Nanosc., 6:10, 2009.
Debusschere SNL
UQ