A physics-informed neural network framework for modeling obstacle-related equations
This work addresses a computational challenge in PDE modeling for domains like physics or engineering, but it is incremental as it builds on existing PINN methods.
The authors tackled the problem of solving obstacle-related partial differential equations (PDEs) by extending physics-informed neural networks (PINNs), demonstrating performance in multiple scenarios for linear and nonlinear PDEs with regular and irregular obstacles.
Deep learning has been highly successful in some applications. Nevertheless, its use for solving partial differential equations (PDEs) has only been of recent interest with current state-of-the-art machine learning libraries, e.g., TensorFlow or PyTorch. Physics-informed neural networks (PINNs) are an attractive tool for solving partial differential equations based on sparse and noisy data. Here extend PINNs to solve obstacle-related PDEs which present a great computational challenge because they necessitate numerical methods that can yield an accurate approximation of the solution that lies above a given obstacle. The performance of the proposed PINNs is demonstrated in multiple scenarios for linear and nonlinear PDEs subject to regular and irregular obstacles.