Deep Learning Convective Flow Using Conditional Generative Adversarial Networks
This work addresses the challenge of modeling complex multiphysics phenomena in fluid dynamics, which is incremental as it applies existing conditional GAN methods to a new domain.
The authors tackled the problem of predicting time-dependent convective flow coupled with energy transport by developing FluidGAN, a deep learning framework that learns and predicts these flows with high speed and accuracy without prior knowledge of underlying physics.
We developed a general deep learning framework, FluidGAN, capable of learning and predicting time-dependent convective flow coupled with energy transport. FluidGAN is thoroughly data-driven with high speed and accuracy and satisfies the physics of fluid without any prior knowledge of underlying fluid and energy transport physics. FluidGAN also learns the coupling between velocity, pressure, and temperature fields. Our framework helps understand deterministic multiphysics phenomena where the underlying physical model is complex or unknown.