Imperial College London
Portrait Picture

Luca Magri

Faculty of Engineering, Department of Aeronautics

Professor of Scientific Machine Learning
 
 
 
//

Contact

 

l.magri Website

 
 
//

Location

 

CAGB324City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inbook{Doan:2019:10.1007/978-3-030-22747-0_15,
author = {Doan, NAK and Polifke, W and Magri, L},
doi = {10.1007/978-3-030-22747-0_15},
pages = {192--198},
title = {Physics-Informed Echo State Networks for Chaotic Systems Forecasting},
url = {http://dx.doi.org/10.1007/978-3-030-22747-0_15},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - CHAP
AB  - © 2019, Springer Nature Switzerland AG. 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.
AU  - Doan,NAK
AU  - Polifke,W
AU  - Magri,L
DO  - 10.1007/978-3-030-22747-0_15
EP  - 198
PY  - 2019///
SN  - 9783030227463
SP  - 192
TI  - Physics-Informed Echo State Networks for Chaotic Systems Forecasting
UR  - http://dx.doi.org/10.1007/978-3-030-22747-0_15
ER  -
Download