Deep Fluids: A Generative Network for Parameterized Fluid Simulations

Abstract

This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to the capability of deep learning architectures to learn representative features of the data, our generative model is able to accurately approximate the training data set, while providing plausible interpolated in-betweens. The proposed generative model is optimized for fluids by a novel loss function that guarantees divergence-free velocity fields at all times. In addition, we demonstrate that we can handle complex parameterizations in reduced spaces, and advance simulations in time by integrating in the latent space with a second network. Our method models a wide variety of fluid behaviors, thus enabling applications such as fast construction of simulations, interpolation of fluids with different parameters, time re-sampling, latent space simulations, and compression of fluid simulation data. Reconstructed velocity fields are generated up to 700x faster than re-simulating the data with the underlying CPU solver, while achieving compression rates of up to 1300x.

arXiv commentComputer Graphics Forum (Proceedings of EUROGRAPHICS 2019), additional materials: http://www.byungsoo.me/project/deep-fluids/

References in corpus (8)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
• Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors
• Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks
• Interpolations of Smoke and Liquid Simulations

Cited by in corpus (36)

• Machine Learning for Fluid Mechanics
• Machine learning accelerated computational fluid dynamics
• Learning data driven discretizations for partial differential equations
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Deep Learning in Deterministic Computational Mechanics
• Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• LaSDI: Parametric Latent Space Dynamics Identification
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media
• Conditional physics informed neural networks
• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learning
• Fully probabilistic deep models for forward and inverse problems in parametric PDEs
• Sampling and resolution characteristics in reduced order models of shallow water equations: intrusive vs non-intrusive
• Learning magnetization dynamics
• Towards learning Lattice Boltzmann collision operators
• Physics-Infused Fuzzy Generative Adversarial Network for Robust Failure Prognosis
• Physics-informed neural network for acoustic resonance analysis in a one-dimensional acoustic tube
• Exploratory Lagrangian-Based Particle Tracing Using Deep Learning
• Machine learning methods for the prediction of micromagnetic magnetization dynamics
• MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction
• IDLat: An Importance-Driven Latent Generation Method for Scientific Data
• Black Hole Weather Forecasting with Deep Learning: A Pilot Study
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty
• Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids
• Combining high-performance hardware, cloud computing, and deep learning frameworks to accelerate physical simulations: probing the Hopfield network
• A Study on the Performance of Distributed Training of Data-driven CFD Simulations
• Reduced order modeling of dynamical systems using artificial neural networks applied to water circulation
• Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow
• A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• Adaptation of AI-accelerated CFD Simulations to the IPU platform
• Application of Video-to-Video Translation Networks to Computational Fluid Dynamics
• Projection-based model-order reduction via graph autoencoders suited for unstructured meshes