Multi-fidelity Physics-informed Generative Adversarial Network for Solving Partial Differential Equations

This paper explores a multi-fidelity physics-informed generative adversarial framework for solving partial differential equations. The work combines generative modeling with physical structure so that lower-cost and higher-cost simulation data can be used together, improving data efficiency for PDE approximation while preserving important governing-physics signals.

Recommended citation: Taghizadeh, M., Nabian, M. A., & Alemazkoor, N. (2024). "Multi-fidelity Physics-informed Generative Adversarial Network for Solving Partial Differential Equations." ASME Journal of Computing and Information Science in Engineering.