DeepAI AI Chat
Log In Sign Up

SPNets: Differentiable Fluid Dynamics for Deep Neural Networks

by   Connor Schenck, et al.
University of Washington

In this paper we introduce Smooth Particle Networks (SPNets), a framework for integrating fluid dynamics with deep networks. SPNets adds two new layers to the neural network toolbox: ConvSP and ConvSDF, which enable computing physical interactions with unordered particle sets. We use these lay- ers in combination with standard neural network layers to directly implement fluid dynamics inside a deep network, where the parameters of the network are the fluid parameters themselves (e.g., viscosity, cohesion, etc.). Because SPNets are imple- mented as a neural network, the resulting fluid dynamics are fully differentiable. We then show how this can be successfully used to learn fluid parameters from data, perform liquid control tasks, and learn policies to manipulate liquids.


page 5

page 6

page 12


NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields

Deep learning has shown great potential for modeling the physical dynami...

Fluid Property Prediction Leveraging AI and Robotics

Inferring liquid properties from vision is a challenging task due to the...

Model-Predictive Control of Blood Suction for Surgical Hemostasis using Differentiable Fluid Simulations

Recent developments in surgical robotics have led to new advancements in...

Flow Completion Network: Inferring the Fluid Dynamics from Incomplete Flow Information using Graph Neural Networks

This paper introduces a novel neural network – the flow completion netwo...

Inferring Fluid Dynamics via Inverse Rendering

Humans have a strong intuitive understanding of physical processes such ...

Deep Learning of Chaos Classification

We train an artificial neural network which distinguishes chaotic and re...

Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

The Eulerian fluid simulation is an important HPC application. The neura...