A deep learning framework for mesh relaxation in arbitrary Lagrangian-Eulerian simulations

The Arbitrary Lagrangian-Eulerian (ALE) method is used in a variety of engineering and scientific applications for enabling multi-physics simulations. Unfortunately, the ALE method can suffer from failures that require users to adjust a set of parameters to control mesh relaxation. In this paper, we present a deep learning framework for predicting mesh relaxation in ALE simulations. Our framework is designed to train a neural network using data generated from existing ALE simulations developed by expert users. In order to capture the spatial coherence inherent in simulations, we apply convolutional-deconvolutional neural networks to achieve up to 0.99 F1 score in predicting mesh relaxation.

[1]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[2]  Tzanio V. Kolev,et al.  High-Order Curvilinear Finite Element Methods for Lagrangian Hydrodynamics , 2012, SIAM J. Sci. Comput..

[3]  Erik E. Santiso,et al.  A general set of order parameters for molecular crystals. , 2011, The Journal of chemical physics.

[4]  Hank Childs,et al.  VisIt: An End-User Tool for Visualizing and Analyzing Very Large Data , 2011 .

[5]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[6]  Julia Ling,et al.  Using Machine Learning to Understand and Mitigate Model Form Uncertainty in Turbulence Models , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Bernhardt L Trout,et al.  Extensions to the likelihood maximization approach for finding reaction coordinates. , 2007, The Journal of chemical physics.

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

[10]  Mikhail J. Shashkov,et al.  Adaptive reconnection-based arbitrary Lagrangian Eulerian method , 2015, J. Comput. Phys..

[11]  P. G. Eltgroth,et al.  KULL: LLNL's ASCI Inertial Confinement Fusion Simulation Code , 2000 .

[12]  Ioannis G. Kevrekidis,et al.  Nonlinear dimensionality reduction in molecular simulation: The diffusion map approach , 2011 .

[13]  Carolyn L. Phillips,et al.  Discovering crystals using shape matching and machine learning , 2013 .

[14]  David W. Aha,et al.  Ensembles of Classifiers for Morphological Galaxy Classification , 2001 .

[15]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  P. Knupp,et al.  Reference Jacobian optimization-based rezone strategies for arbitrary Lagrangian Eulerian methods , 2002 .

[17]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[18]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[19]  Philippe Pierre Pebay,et al.  The verdict geometric quality library. , 2006 .

[20]  Aaron R Dinner,et al.  Automatic method for identifying reaction coordinates in complex systems. , 2005, The journal of physical chemistry. B.

[21]  Raphaël Loubère,et al.  ReALE: A reconnection-based arbitrary-Lagrangian-Eulerian method , 2010, J. Comput. Phys..

[22]  J. Templeton.  Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty , 2015 .

[23]  Jiang Ming,et al.  A Supervised Learning Framework for Arbitrary Lagrangian-Eulerian Simulations , 2016 .

[24]  Jonas A. Zukas,et al.  Introduction to Hydrocodes , 2004 .

[25]  Sven Leyffer,et al.  Unsupervised cell identification on multidimensional X-ray fluorescence datasets , 2013, SIGGRAPH '13.

[26]  A. Huerta,et al.  Arbitrary Lagrangian–Eulerian Methods , 2004 .

[27]  Veselin Dobrev,et al.  Curvilinear finite elements for Lagrangian hydrodynamics , 2011 .

[28]  Jianxiong Xiao,et al.  DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[29]  Andreas Ziehe,et al.  Learning Invariant Representations of Molecules for Atomization Energy Prediction , 2012, NIPS.

[30]  D. Benson.  Computational methods in Lagrangian and Eulerian hydrocodes , 1992 .

[31]  S. Bailey,et al.  How to Find More Supernovae with Less Work: Object Classification Techniques for Difference Imaging , 2006, 0705.0493.

[32]  Julia Ling,et al.  Machine learning strategies for systems with invariance properties , 2016, J. Comput. Phys..

[33]  L. G. Margolin,et al.  Arbitrary Lagrangian-Eulerian (Ale) Methods a Personal Perspective , 2013 .

[34]  Veselin Dobrev,et al.  Monotonicity in high‐order curvilinear finite element arbitrary Lagrangian–Eulerian remap , 2015 .

[35]  Klaus-Robert Müller,et al.  Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies. , 2013, Journal of chemical theory and computation.