Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
This work addresses the challenge of discovering PDEs from data for researchers in mathematical physics and computational science, representing an incremental advancement in physics-informed deep learning.
The authors tackled the problem of data-driven discovery of nonlinear partial differential equations by introducing physics-informed neural networks, achieving effectiveness across benchmark problems like conservation laws and fluid flow.
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this second part of our two-part treatise, we focus on the problem of data-driven discovery of partial differential equations. Depending on whether the available data is scattered in space-time or arranged in fixed temporal snapshots, we introduce two main classes of algorithms, namely continuous time and discrete time models. The effectiveness of our approach is demonstrated using a wide range of benchmark problems in mathematical physics, including conservation laws, incompressible fluid flow, and the propagation of nonlinear shallow-water waves.