What is physics-informed neural networks?

Physics-informed neural networks (PINNs) are a type of neural network that is trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations (PDEs). They embed these PDEs into the neural network training process. This is commonly achieved by adding a physics-informed loss term to the standard data-driven loss function. They are used for solving forward and inverse problems involving PDEs, where forward problems involve predicting the solution given the PDE and boundary conditions, and inverse problems involve inferring parameters or the PDE itself from observed data.