Extreme events prediction from nonlocal ...
Document type :
Compte-rendu et recension critique d'ouvrage
Title :
Extreme events prediction from nonlocal partial information in a spatiotemporally chaotic microcavity laser
Author(s) :
Pammi, V. A. [Auteur]
Centre de Nanosciences et de Nanotechnologies [C2N]
Clerc, M. G. [Auteur]
Universidad de Santiago de Chile [Santiago] [USACH]
Coulibaly, S. [Auteur]
Laboratoire de Physique des Lasers, Atomes et Molécules - UMR 8523 [PhLAM]
Barbay, Sylvain [Auteur]
Centre de Nanosciences et de Nanotechnologies [C2N]
Centre de Nanosciences et de Nanotechnologies [C2N]
Clerc, M. G. [Auteur]
Universidad de Santiago de Chile [Santiago] [USACH]
Coulibaly, S. [Auteur]
Laboratoire de Physique des Lasers, Atomes et Molécules - UMR 8523 [PhLAM]
Barbay, Sylvain [Auteur]
Centre de Nanosciences et de Nanotechnologies [C2N]
Journal title :
Physical Review Letters
Pages :
223801
Publisher :
American Physical Society
Publication date :
2023-03-03
ISSN :
0031-9007
HAL domain(s) :
Science non linéaire [physics]/Dynamique Chaotique [nlin.CD]
English abstract : [en]
The forecasting of high-dimensional, spatiotemporal nonlinear systems has made tremendous progress with the advent of model-free machine learning techniques. However, in real systems it is not always possible to have all ...
Show more >The forecasting of high-dimensional, spatiotemporal nonlinear systems has made tremendous progress with the advent of model-free machine learning techniques. However, in real systems it is not always possible to have all the information needed; only partial information is available for learning and forecasting. This can be due to insufficient temporal or spatial samplings, to inaccessible variables or to noisy training data. Here, we show that it is nevertheless possible to forecast extreme events occurrence in incomplete experimental recordings from a spatiotemporally chaotic microcavity laser using reservoir computing. Selecting regions of maximum transfer entropy, we show that it is possible to get higher forecasting accuracy using nonlocal data vs local data thus allowing greater warning times, at least twice the time horizon predicted from the nonlinear local Lyapunov exponent.Show less >
Show more >The forecasting of high-dimensional, spatiotemporal nonlinear systems has made tremendous progress with the advent of model-free machine learning techniques. However, in real systems it is not always possible to have all the information needed; only partial information is available for learning and forecasting. This can be due to insufficient temporal or spatial samplings, to inaccessible variables or to noisy training data. Here, we show that it is nevertheless possible to forecast extreme events occurrence in incomplete experimental recordings from a spatiotemporally chaotic microcavity laser using reservoir computing. Selecting regions of maximum transfer entropy, we show that it is possible to get higher forecasting accuracy using nonlocal data vs local data thus allowing greater warning times, at least twice the time horizon predicted from the nonlinear local Lyapunov exponent.Show less >
Language :
Anglais
Popular science :
Non
Source :
Files
- 2303.03097
- Open access
- Access the document
- document
- Open access
- Access the document
- 2303.03097.pdf
- Open access
- Access the document