Inherent Failure Modes of Physics-Informed Neural Networks for Buoyancy-Driven Flow: Role of Non-Dimensionalization in Network Training

Krishan Chand, Ahmad Peyvan, Haoxiang Luo

We investigate the influence of non-dimensionalization on the trainability and accuracy of physics-informed neural networks (PINNs) for buoyancy-driven flows. Using a differentiall…