Error estimation of the parametric non-intrusive reduced order model using machine learning

Abstract A novel error estimation method for the parametric non-intrusive reduced order model (P-NIROM) based on machine learning is presented. This method relies on constructing a set of response functions for the errors between the high fidelity full model solutions and P-NIROM using machine learning method, particularly, Gaussian process regression method. This yields closer solutions agreement with the high fidelity full model. The novelty of this work is that it is the first time to use machine learning method to derive error estimate for the P-NIROM. The capability of the new error estimation method is demonstrated using three numerical simulation examples: flow past a cylinder, dam break and 3D fluvial channel. It is shown that the results are closer to those of the high fidelity full model when considering error terms. In addition, the interface between two phases of dam break case is captured well if the error estimator is involved in the P-NIROM.

[1]  Malte Kuß,et al.  Gaussian process models for robust regression, classification, and reinforcement learning , 2006 .

[2]  L. Franca,et al.  Stabilized finite element methods. II: The incompressible Navier-Stokes equations , 1992 .

[3]  Tao Yu,et al.  Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression , 2008 .

[4]  Adrian Sandu,et al.  Multivariate predictions of local reduced‐order‐model errors and dimensions , 2017, ArXiv.

[5]  L. Heltai,et al.  Reduced Basis Isogeometric Methods (RB-IGA) for the real-time simulation of potential flows about parametrized NACA airfoils , 2015 .

[6]  C.R.E. de Oliveira,et al.  Three-dimensional unstructured mesh ocean modelling , 2005 .

[7]  Scott T. M. Dawson,et al.  Modal analysis of fluid flows using variants of proper orthogonal decomposition , 2017 .

[8]  Danny C. Sorensen,et al.  A State Space Error Estimate for POD-DEIM Nonlinear Model Reduction , 2012, SIAM J. Numer. Anal..

[9]  Han Chen,et al.  Blackbox Stencil Interpolation Method for Model Reduction , 2012 .

[10]  Feriedoun Sabetghadam,et al.  α Regularization of the POD-Galerkin dynamical systems of the Kuramoto-Sivashinsky equation , 2012, Appl. Math. Comput..

[11]  P. Nair,et al.  Nonintrusive reduced‐order modeling of parametrized time‐dependent partial differential equations , 2013 .

[12]  Min Chen,et al.  A non-intrusive reduced-order model for compressible fluid and fractured solid coupling and its application to blasting , 2017, J. Comput. Phys..

[13]  M. Piggott,et al.  A POD goal‐oriented error measure for mesh optimization , 2009 .

[14]  Y. Tourbier,et al.  A parametric and non-intrusive reduced order model of car crash simulation , 2018, Computer Methods in Applied Mechanics and Engineering.

[15]  J. Hesthaven,et al.  Data-driven reduced order modeling for time-dependent problems , 2019, Computer Methods in Applied Mechanics and Engineering.

[16]  M. Blunt,et al.  Reservoir Modeling for Flow Simulation by Use of Surfaces, Adaptive Unstructured Meshes, and an Overlapping-Control-Volume Finite-Element Method , 2015 .

[17]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[18]  Jan S. Hesthaven,et al.  Reduced order modeling for nonlinear structural analysis using Gaussian process regression , 2018, Computer Methods in Applied Mechanics and Engineering.

[19]  Mehdi Ghommem,et al.  Global-Local Nonlinear Model Reduction for Flows in Heterogeneous Porous Media Dedicated to Mary Wheeler on the occasion of her 75-th birthday anniversary , 2014, 1407.0782.

[20]  Adrian Sandu,et al.  Parametric domain decomposition for accurate reduced order models: Applications of MP-LROM methodology , 2017, J. Comput. Appl. Math..

[21]  B. R. Noack,et al.  On long-term boundedness of Galerkin models , 2013, Journal of Fluid Mechanics.

[22]  James Demmel,et al.  LAPACK Users' Guide, Third Edition , 1999, Software, Environments and Tools.

[23]  Caroline Sainvitu,et al.  LPC Blade and Non-Axisymmetric Hub Profiling Optimization Using Multi-Fidelity Non-Intrusive POD Surrogates , 2017 .

[24]  Bernard Haasdonk,et al.  Efficient a-posteriori error estimation for nonlinear kernel-based reduced systems , 2012, Syst. Control. Lett..

[25]  B. R. Noack,et al.  On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high-Reynolds-number flow over an Ahmed body , 2013, Journal of Fluid Mechanics.

[26]  Christopher C. Pain,et al.  A POD reduced order model for resolving angular direction in neutron/photon transport problems , 2015, J. Comput. Phys..

[27]  P. A. Newman,et al.  Approximation and Model Management in Aerodynamic Optimization with Variable-Fidelity Models , 2001 .

[28]  Danny C. Sorensen,et al.  Nonlinear Model Reduction via Discrete Empirical Interpolation , 2010, SIAM J. Sci. Comput..

[29]  Juan Du,et al.  Non-linear model reduction for the Navier-Stokes equations using residual DEIM method , 2014, J. Comput. Phys..

[30]  Christopher C. Pain,et al.  Reduced order modelling of an unstructured mesh air pollution model and application in 2D/3D urban street canyons , 2014 .

[31]  Ionel M. Navon,et al.  A parameterized non-intrusive reduced order model and error analysis for general time-dependent nonlinear partial differential equations and its applications , 2017 .

[32]  Razvan Stefanescu,et al.  POD/DEIM nonlinear model order reduction of an ADI implicit shallow water equations model , 2012, J. Comput. Phys..

[33]  Charbel Farhat,et al.  Stabilization of projection‐based reduced‐order models , 2012 .

[34]  Ionel M. Navon,et al.  Non-intrusive reduced order modelling of the Navier-Stokes equations , 2015 .

[35]  M. Diez,et al.  Design-space dimensionality reduction in shape optimization by Karhunen–Loève expansion , 2015 .

[36]  Saifon Chaturantabut Dimension reduction for unsteady nonlinear partial differential equations via empirical interpolation methods , 2009 .

[37]  A. Quarteroni,et al.  Reduced Order Modeling for Cardiac Electrophysiology and Mechanics: New Methodologies, Challenges and Perspectives , 2018 .

[38]  Danny C. Sorensen,et al.  A Posteriori Error Estimation for DEIM Reduced Nonlinear Dynamical Systems , 2014, SIAM J. Sci. Comput..

[39]  Ionel M. Navon,et al.  Non-linear Petrov-Galerkin methods for reduced order modelling of the Navier-Stokes equations using a mixed finite element pair , 2013 .

[40]  Alfio Quarteroni,et al.  An algebraic least squares reduced basis method for the solution of nonaffinely parametrized Stokes equations , 2019, Computer Methods in Applied Mechanics and Engineering.

[41]  Christopher C. Pain,et al.  Non-intrusive reduced order modelling of fluid–structure interactions , 2016 .

[42]  Matthew D. Jackson,et al.  Surface-Based Geological Reservoir Modelling Using Grid-Free NURBS Curves and Surfaces , 2018, Mathematical Geosciences.

[43]  Carl E. Rasmussen,et al.  Sparse Spectrum Gaussian Process Regression , 2010, J. Mach. Learn. Res..

[44]  Linda R. Petzold,et al.  Approved for public release; further dissemination unlimited Error Estimation for Reduced Order Models of Dynamical Systems ∗ , 2003 .

[45]  C. Pain,et al.  Model identification of reduced order fluid dynamics systems using deep learning , 2017, International Journal for Numerical Methods in Fluids.

[46]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[47]  Jan S. Hesthaven,et al.  Non-intrusive reduced order modeling of nonlinear problems using neural networks , 2018, J. Comput. Phys..

[48]  Monica Z. Weiland,et al.  Gaussian Process Regression for Predictive But Interpretable Machine Learning Models: An Example of Predicting Mental Workload across Tasks , 2017, Front. Hum. Neurosci..

[49]  Donald Estep,et al.  Exploration of efficient reduced‐order modeling and a posteriori error estimation , 2017 .

[50]  Adrian Sandu,et al.  Comparison of POD reduced order strategies for the nonlinear 2D shallow water equations , 2014, International Journal for Numerical Methods in Fluids.

[51]  Ionel M. Navon,et al.  A Dual-Weighted Approach to Order Reduction in 4DVAR Data Assimilation , 2008, Monthly Weather Review.

[52]  Deborah Greaves,et al.  Simulation of viscous water column collapse using adapting hierarchical grids , 2006 .

[53]  Kevin Carlberg,et al.  The ROMES method for statistical modeling of reduced-order-model error , 2014, SIAM/ASA J. Uncertain. Quantification.