Physics-informed echo state networks

N. A.K. Doan, W. Polifke, L. Magri

Research output: Contribution to journalArticlepeer-review

30 Scopus citations

Abstract

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, which is based on the system's governing equations. The additional loss function penalizes non-physical predictions without the need of any additional training data. This approach is demonstrated on a chaotic Lorenz system and a truncation of the Charney–DeVore system. Compared to the conventional ESNs, the physics-informed ESNs improve the predictability horizon by about two Lyapunov times. This approach is also shown to be robust with regard to noise. 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.

Original languageEnglish
Article number101237
JournalJournal of Computational Science
Volume47
DOIs
StatePublished - Nov 2020

Keywords

  • Chaotic dynamical systems
  • Echo state networks
  • Physics-informed neural networks

Fingerprint

Dive into the research topics of 'Physics-informed echo state networks'. Together they form a unique fingerprint.

Cite this