Exploratory Lagrangian-Based Particle Tracing Using Deep Learning

Abstract

Time-varying vector fields produced by computational fluid dynamics simulations are often prohibitively large and pose challenges for accurate interactive analysis and exploration. To address these challenges, reduced Lagrangian representations have been increasingly researched as a means to improve scientific time-varying vector field exploration capabilities. This paper presents a novel deep neural network-based particle tracing method to explore time-varying vector fields represented by Lagrangian flow maps. In our workflow, in situ processing is first utilized to extract Lagrangian flow maps, and deep neural networks then use the extracted data to learn flow field behavior. Using a trained model to predict new particle trajectories offers a fixed small memory footprint and fast inference. To demonstrate and evaluate the proposed method, we perform an in-depth study of performance using a well-known analytical data set, the Double Gyre. Our study considers two flow map extraction strategies as well as the impact of the number of training samples and integration durations on efficacy, evaluates multiple sampling options for training and testing and informs hyperparameter settings. Overall, we find our method requires a fixed memory footprint of 10.5 MB to encode a Lagrangian representation of a time-varying vector field while maintaining accuracy. For post hoc analysis, loading the trained model costs only two seconds, significantly reducing the burden of I/O when reading data for visualization. Moreover, our parallel implementation can infer one hundred locations for each of two thousand new pathlines across the entire temporal resolution in 1.3 seconds using one NVIDIA Titan RTX GPU.

arXiv commentThe paper has been accepted to publish by Journal of Flow Visualization and Image Processing

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Machine Learning for Fluid Mechanics
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• A Critical Comparison of Lagrangian Methods for Coherent Structure Detection
• EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies
• InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
• A Generative Model for Volume Rendering
• Coherent structure coloring: identification of coherent structures from sparse data using graph theory
• Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields
• Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution
• Robust Reference Frame Extraction from Unsteady 2D Vector Fields with Convolutional Neural Networks
• Void-and-Cluster Sampling of Large Scattered Data and Trajectories
• Deep Volumetric Ambient Occlusion
• Scalable In Situ Lagrangian Flow Map Extraction: Demonstrating the Viability of a Communication-Free Model

Cited by in corpus (1)

• Local Latent Representation based on Geometric Convolution for Particle Data Feature Exploration