• Corpus ID: 523487

Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations

@article{Raissi2018DeepHP,
  title={Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations},
  author={Maziar Raissi},
  journal={J. Mach. Learn. Res.},
  year={2018},
  volume={19},
  pages={25:1-25:24}
}
  • M. Raissi
  • Published 20 January 2018
  • Computer Science
  • J. Mach. Learn. Res.
A long-standing problem at the interface of artificial intelligence and applied mathematics is to devise an algorithm capable of achieving human level or even superhuman proficiency in transforming observed data into predictive mathematical models of the physical world. In the current era of abundance of data and advanced machine learning capabilities, the natural question arises: How can we automatically uncover the underlying laws of physics from high-dimensional data generated from… 

Figures and Tables from this paper

Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
Physics-informed learning of governing equations from scarce data
TLDR
The efficacy and robustness of this method are demonstrated, both numerically and experimentally, on discovering a variety of partial differential equation systems with different levels of data scarcity and noise accounting for different initial/boundary conditions.
Hard Encoding of Physics for Learning Spatiotemporal Dynamics
TLDR
A novel deep learning architecture that forcibly encodes known physics knowledge to facilitate learning in a data-driven manner is proposed and possesses remarkable robustness against data noise/scarcity and generalizability compared with some state-of-the-art models for data- driven modeling.
Bayesian Deep Learning for Partial Differential Equation Parameter Discovery with Sparse and Noisy Data
TLDR
This paper proposes to use Bayesian neural networks (BNN) in order to recover the full system states from measurement data, and uses Hamiltonian Monte-Carlo to sample the posterior distribution of a deep and dense BNN, showing that it is possible to accurately capture physics of varying complexity, without overfitting.
Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations
  • M. Raissi
  • Computer Science, Mathematics
    ArXiv
  • 2018
TLDR
This work approximate the unknown solution by a deep neural network which essentially enables the author to benefit from the merits of automatic differentiation in partial differential equations.
Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data
TLDR
This work introduces a novel model comprising "leaf" modules that learn to represent distinct experiments' spatiotemporal functional data as neural networks and a single "root" module that expresses a nonparametric distribution over their governing nonlinear differential operator as a Gaussian process.
Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
TLDR
The proposed methodology is a simple and elegant way to instill physical knowledge to machine-learning algorithms that alleviates the two most significant shortcomings of machine- learning algorithms: the requirement for large datasets and the reliability of extrapolation.
Embedding Physics to Learn Spatiotemporal Dynamics from Sparse Data
TLDR
A novel deep learning architecture is proposed that forcibly embedded known physics knowledge in a residual-recurrent Π-block network, to facilitate the learning of the spatiotemporal dynamics in a data-driven manner.
Data-Driven Deep Learning of Partial Differential Equations in Modal Space
...
...

References

SHOWING 1-10 OF 62 REFERENCES
Hidden physics models: Machine learning of nonlinear partial differential equations
Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
TLDR
This two part treatise introduces 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 and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.
Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
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
Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations
  • M. Raissi
  • Computer Science, Mathematics
    ArXiv
  • 2018
TLDR
This work approximate the unknown solution by a deep neural network which essentially enables the author to benefit from the merits of automatic differentiation in partial differential equations.
Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
TLDR
This work puts forth a machine learning approach for identifying nonlinear dynamical systems from data that combines classical tools from numerical analysis with powerful nonlinear function approximators to distill the mechanisms that govern the evolution of a given data-set.
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
TLDR
This work develops a novel framework to discover governing equations underlying a dynamical system simply from data measurements, leveraging advances in sparsity techniques and machine learning and using sparse regression to determine the fewest terms in the dynamic governing equations required to accurately represent the data.
Compressed modes for variational problems in mathematics and physics
TLDR
This article describes a general formalism for obtaining spatially localized solutions to a class of problems in mathematical physics, which can be recast as variational optimization problems, such as the important case of Schrödinger’s equation in quantum mechanics.
Automated reverse engineering of nonlinear dynamical systems
TLDR
This work introduces for the first time a method that can automatically generate symbolic equations for a nonlinear coupled dynamical system directly from time series data, applicable to any system that can be described using sets of ordinary nonlinear differential equations.
...
...