Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
By Maizar Raissi, Paris Perdikaris, G. Em Karniadakis. 2017
695 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Numerical Methods & Scientific Computing, AI for Physical Sciences
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- G. Em Karniadakis
- Paris Perdikaris
- Yibo Yang
- Liu Yang
- Maizar Raissi
- Lu Lu
- Dongkun Zhang
- Stefania Fresca
In Statistical and Nonlinear Physics
- G. Em Karniadakis
- Paris Perdikaris
- Lu Lu
- Andrea Manzoni
- Maizar Raissi
- Gianluigi Rozza
- Liu Yang
- Yibo Yang
In Numerical Methods & Scientific Computing
- G. Em Karniadakis
- Maizar Raissi
- Paris Perdikaris
- Yibo Yang
- Stefania Fresca
- Andrea Manzoni
- Dongkun Zhang
- Jens Berg
In AI for Physical Sciences
- G. Em Karniadakis
- Paris Perdikaris
- Maizar Raissi
- Stefania Fresca
- Andrea Manzoni
- Yibo Yang
- Dongkun Zhang
- Lu Lu
Citations in the corpus
- Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations (2018, methodology): “One could avoid the first drawback concerning numerical differentiation by assigning prior distributions in the forms of Gaussian processes [38, 39, 40, 41] or neural networks [35, 34] to the unknown solution u.”
- Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems (2018, background): “Inspired by recent developments in physics-informed deep learning [19, 20], we construct structured nonlinear regression models that can discover the dynamic dependencies in a given set of temporal data-snapshots, and return a closed form model that can be subsequently used to forecast future states”
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks (2018, methodology): “[6, 7] have also pointed out cases in which the training phase of these algorithms faces severe difficulties for reasons that are cur-”
- PDE-Net: Learning PDEs from Data (2017, methodology): “More recently, Raissi et al. (2017) introduced a new class of universal function approximators called the physics informed neural networks which is capable of discovering nonlinear PDEs parameterized by scalars.”
- DGM: A deep learning algorithm for solving partial differential equations (2017, neutral): “Recently, [40, 41] develop physics informed deep learning models.”
- Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations (2018, methodology): “Subsequently, we present solutions of stochastic PDEs for different types of available data and different dimensions.”
- GRAND: Graph Neural Diffusion (2021, background): “Using deep learning to solve PDEs was explored by Raissi et al. (2017).”
- Machine Learning in Aerodynamic Shape Optimization (2022, background): “[58] developed and defined PINN as “neural networks that are trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations” [280, 281].”
- Multiscale modeling meets machine learning: What can we learn? (2019, background): “Naturally, this brings up the question that, provided we know the underlying physics, can we integrate our prior knowledge to constrain the the space of admissible solutions to a manageable size [100]? Recent trends in computational physics suggest that exactly this approach [14]: to create data-eff”
- Data-driven discovery of PDEs in complex datasets (2018, methodology): “Depending on the choice of parametrization of L̂ it is possible to discover a wide range of PDEs and encompass the methods described in [31, 5, 33, 34, 25, 29] in a single framework.”
- Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks (2019, methodology): “Physics-informed neural network In this part, we briefly review using DNNs to solve the deterministic differential equations [26, 27, 28], and its generalization for solving deterministic inverse problems in [6].”
- A Comprehensive Deep Learning-Based Approach to Reduced Order Modeling of Nonlinear Time-Dependent Parametrized PDEs (2020, methodology): “, in the works by Karniadakis and coauthors [22, 23, 24, 25, 26]; rather, DL techniques are built upon it, to enhance the repeated evaluation of the FOM for different values of the parameters.”