Physics-Informed Echo State Networks for Chaotic Systems Forecasting

By N. Doan, W. Polifke, L. Magri. 2019

42 citations recorded by the source corpus.

We propose a physics-informed Echo State Network (ESN) to predict the evolution of chaotic systems. Compared to conventional ESNs, the physics-informed ESNs are trained to solve supervised learning tasks while ensuring that their predictions do not violate physical laws. This is achieved by introducing an additional loss function during the training of the ESNs, which penalizes non-physical predictions without the need of any additional training data. This approach is demonstrated on a chaotic Lorenz system, where the physics-informed ESNs improve the predictability horizon by about two Lyapunov times as compared to conventional ESNs. The proposed framework shows the potential of using machine learning combined with prior physical knowledge to improve the time-accurate prediction of chaotic dynamical systems.

Subfields: Artificial Intelligence, Atomic and Molecular Physics, and Optics, Statistical and Nonlinear Physics

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

  1. Xuhui Meng
  2. Dongkun Zhang
  3. G. Em Karniadakis
  4. Michael S. Steinbach
  5. Vipin Kumar
  6. Xiaowei Jia
  7. Jared D. Willard
  8. Shaoming Xu

In Atomic and Molecular Physics, and Optics

  1. G. Em Karniadakis
  2. Dongkun Zhang
  3. Zhen Li

In Statistical and Nonlinear Physics

  1. Xuhui Meng
  2. G. Em Karniadakis
  3. Michael S. Steinbach
  4. Xiaowei Jia
  5. Jared D. Willard
  6. Dongkun Zhang
  7. Shaoming Xu
  8. Vipin Kumar

Citations in the corpus