A Fluid Flow Data Set for Machine Learning and its Application to Neural Flow Map Interpolation

In recent years, deep learning has opened countless research opportunities across many different disciplines. At present, visualization is mainly applied to explore and explain neural networks. Its counterpart-the application of deep learning to visualization problems-requires us to share data more openly in order to enable more scientists to engage in data-driven research. In this paper, we construct a large fluid flow data set and apply it to a deep learning problem in scientific visualization. Parameterized by the Reynolds number, the data set contains a wide spectrum of laminar and turbulent fluid flow regimes. The full data set was simulated on a high-performance compute cluster and contains 8000 time-dependent 2D vector fields, accumulating to more than 16 TB in size. Using our public fluid data set, we trained deep convolutional neural networks in order to set a benchmark for an improved post-hoc Lagrangian fluid flow analysis. In in-situ settings, flow maps are exported and interpolated in order to assess the transport characteristics of time-dependent fluids. Using deep learning, we improve the accuracy of flow map interpolations, allowing a more precise flow analysis at a reduced memory IO footprint.

[1]  Changbo Wang,et al.  A Streampath-Based RCNN Approach to Ocean Eddy Detection , 2019, IEEE Access.

[2]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Wei Wang,et al.  Deep Learning for Single Image Super-Resolution: A Brief Review , 2018, IEEE Transactions on Multimedia.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Ribana Roscher,et al.  Ocean Eddy Identification and Tracking Using Neural Networks , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[6]  Chih-Yuan Yang,et al.  Single-Image Super-Resolution: A Benchmark , 2014, ECCV.

[7]  Yubo Tao,et al.  CNNs Based Viewpoint Estimation for Volume Visualization , 2018, ACM Trans. Intell. Syst. Technol..

[8]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Christoph Peters,et al.  Void-and-Cluster Sampling of Large Scattered Data and Trajectories , 2019, IEEE Transactions on Visualization and Computer Graphics.

[10]  Tony DeRose,et al.  Wavelet noise , 2005, SIGGRAPH 2005.

[11]  Doug L. James,et al.  Wavelet turbulence for fluid simulation , 2008, SIGGRAPH 2008.

[12]  J. Marsden,et al.  Definition and properties of Lagrangian coherent structures from finite-time Lyapunov exponents in two-dimensional aperiodic flows , 2005 .

[13]  Yifan Wang,et al.  A Fully Progressive Approach to Single-Image Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Filip Sadlo,et al.  Efficient Visualization of Lagrangian Coherent Structures by Filtered AMR Ridge Extraction , 2007, IEEE Transactions on Visualization and Computer Graphics.

[15]  Jun Tao,et al.  FlowNet: A Deep Learning Framework for Clustering and Selection of Streamlines and Stream Surfaces , 2020, IEEE Transactions on Visualization and Computer Graphics.

[16]  Steven L Brunton,et al.  Fast computation of finite-time Lyapunov exponent fields for unsteady flows. , 2010, Chaos.

[17]  Jian Huang,et al.  Photo-Guided Exploration of Volume Data Features , 2017, EGPGV@EuroVis.

[18]  Helwig Hauser,et al.  Personalized Sketch-Based Brushing in Scatterplots , 2019, IEEE Computer Graphics and Applications.

[19]  Wei Zeng,et al.  LassoNet: Deep Lasso-Selection of 3D Point Clouds , 2019, IEEE Transactions on Visualization and Computer Graphics.

[20]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[21]  M. Botur,et al.  Lagrangian coherent structures , 2009 .

[22]  Olga Sorkine-Hornung,et al.  Blind image super-resolution with spatially variant degradations , 2019, ACM Trans. Graph..

[23]  Roxana Bujack,et al.  An Interpolation Scheme for VDVP Lagrangian Basis Flows , 2019, EGPGV@EuroVis.

[24]  Joshua A. Levine,et al.  A Generative Model for Volume Rendering , 2017, IEEE Transactions on Visualization and Computer Graphics.

[25]  Wenke Wang,et al.  Oceanic Mesoscale Eddy Detection Method Based on Deep Learning , 2019, Remote. Sens..

[26]  Hans Hagen,et al.  Efficient Computation and Visualization of Coherent Structures in Fluid Flow Applications , 2007, IEEE Transactions on Visualization and Computer Graphics.

[27]  Kenneth I. Joy,et al.  Interpolation-Based Pathline Tracing in Particle-Based Flow Visualization , 2015, IEEE Transactions on Visualization and Computer Graphics.

[28]  Direct numerical simulations for liquid metal applications , 2019, Thermal Hydraulics Aspects of Liquid Metal Cooled Nuclear Reactors.

[29]  Helwig Hauser,et al.  Fast and Accurate CNN‐based Brushing in Scatterplots , 2018, Comput. Graph. Forum.

[30]  Eric Krokos,et al.  Deep-Learning-Assisted Volume Visualization , 2019, IEEE Transactions on Visualization and Computer Graphics.

[31]  Nils Thuerey,et al.  ScalarFlow , 2019, ACM Trans. Graph..

[32]  Hongyu Wang,et al.  End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks , 2016, IEEE Access.

[33]  Richard D. Sandberg,et al.  A primer on direct numerical simulation of turbulence - methods, procedures and guidelines , 2010 .

[34]  Steffen Frey.  Sampling and Estimation of Pairwise Similarity in Spatio-Temporal Data Based on Neural Networks , 2017, Informatics.

[35]  Kenneth I. Joy,et al.  A multi-resolution interpolation scheme for pathline based Lagrangian flow representations , 2015, Electronic Imaging.

[36]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[37]  Hank Childs,et al.  Accelerating advection via approximate block exterior flow maps , 2017, Visualization and Data Analysis.

[38]  John Morrissey,et al.  Data driven. , 2019, Hospitals & health networks.

[39]  Chaoli Wang,et al.  TSR-TVD: Temporal Super-Resolution for Time-Varying Data Analysis and Visualization , 2020, IEEE Transactions on Visualization and Computer Graphics.

[40]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[41]  Michaël Gharbi,et al.  Basis Prediction Networks for Effective Burst Denoising With Large Kernels , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Markus H. Gross,et al.  Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation , 2019, ICML.

[44]  Xiaoou Tang,et al.  Accelerating the Super-Resolution Convolutional Neural Network , 2016, ECCV.

[45]  Rüdiger Westermann,et al.  Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution , 2019, IEEE Transactions on Visualization and Computer Graphics.

[46]  Jie Liu,et al.  A CNN-based vortex identification method , 2018, J. Vis..

[47]  Hai Lin,et al.  Volume upscaling with convolutional neural networks , 2017, CGI.

[48]  Xiaoru Yuan,et al.  Access Pattern Learning with Long Short-Term Memory for Parallel Particle Tracing , 2018, 2018 IEEE Pacific Visualization Symposium (PacificVis).

[49]  Sanaz Mostaghim,et al.  Vector Field Benchmark for Collective Search in Unknown Dynamic Environments , 2018, ANTS Conference.

[50]  Byungsoo Kim,et al.  Transport-based neural style transfer for smoke simulations , 2019, ACM Trans. Graph..

[51]  Redouane Lguensat,et al.  EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies , 2017, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[52]  P. Davies,et al.  Laboratory Studies of Orographic Effects in Rotating and Stratified Flows , 2000 .

[53]  Byungsoo Kim,et al.  Robust Reference Frame Extraction from Unsteady 2D Vector Fields with Convolutional Neural Networks , 2019, Comput. Graph. Forum.

[54]  G. Haller,et al.  Defining coherent vortices objectively from the vorticity , 2015, Journal of Fluid Mechanics.

[55]  Randal C. Burns,et al.  The Johns Hopkins Turbulence Databases: An Open Simulation Laboratory for Turbulence Research , 2015, Computing in Science & Engineering.

[56]  Mukund Raj,et al.  InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations , 2019, IEEE Transactions on Visualization and Computer Graphics.

[57]  Tang Bin and Li Yi,et al.  CNN-based Flow Field Feature Visualization Method , 2018 .

[58]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[59]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[60]  Nils Thuerey,et al.  A Multi-Pass GAN for Fluid Flow Super-Resolution , 2019, PACMCGIT.

[61]  Yueqing Wang,et al.  A rapid vortex identification method using fully convolutional segmentation network , 2020, Vis. Comput..

[62]  Markus H. Gross,et al.  Generic objective vortices for flow visualization , 2017, ACM Trans. Graph..

[63]  Nils Thürey,et al.  Data-driven synthesis of smoke flows with CNN-based feature descriptors , 2017, ACM Trans. Graph..

[64]  Heng Xiao,et al.  Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields using Convolutional Neural Networks , 2018, Communications in Computational Physics.

[65]  A. Kolmogorov.  Dissipation of energy in the locally isotropic turbulence , 1941, Proceedings of the Royal Society of London. Series A: Mathematical and Physical Sciences.

[66]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[67]  Danny Z. Chen,et al.  Flow Field Reduction Via Reconstructing Vector Data From 3-D Streamlines Using Deep Learning , 2019, IEEE Computer Graphics and Applications.

[68]  Xavier Tricoche,et al.  Adaptive Refinement of the Flow Map Using Sparse Samples , 2013, IEEE Transactions on Visualization and Computer Graphics.

[69]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.