Deep Learning the Physics of Transport Phenomena

TL;DR

This paper introduces a deep learning framework using cGANs to directly generate solutions for steady state heat conduction and fluid flow, enabling rapid, accurate, and data-driven modeling without solving traditional equations.

Contribution

It presents a novel application of cGANs for physics-based problem solving, bypassing numerical solvers and learning from observational data.

Findings

High accuracy in solution generation (MAE<1%)

Fast computational performance

Applicable to complex or unknown physical models

Abstract

We have developed a new data-driven paradigm for the rapid inference, modeling and simulation of the physics of transport phenomena by deep learning. Using conditional generative adversarial networks (cGAN), we train models for the direct generation of solutions to steady state heat conduction and incompressible fluid flow purely on observation without knowledge of the underlying governing equations. Rather than using iterative numerical methods to approximate the solution of the constitutive equations, cGANs learn to directly generate the solutions to these phenomena, given arbitrary boundary conditions and domain, with high test accuracy (MAE$<$1\%) and state-of-the-art computational performance. The cGAN framework can be used to learn causal models directly from experimental observations where the underlying physical model is complex or unknown.