Deep Learning the Physics of Transport Phenomena
This enables rapid inference and simulation for physics problems where underlying equations are complex or unknown, potentially benefiting fields like engineering and materials science, though it builds on existing cGAN methods.
The authors tackled the problem of simulating transport phenomena like heat conduction and fluid flow by developing a data-driven paradigm using conditional generative adversarial networks (cGANs) to directly generate solutions from observations, achieving high test accuracy (MAE < 1%) and state-of-the-art computational performance.
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.