Machine learning algorithms for predicting the amplitude of chaotic laser pulses

Forecasting the dynamics of chaotic systems from the analysis of their output signals is a challenging problem with applications in most fields of modern science. In this work, we use a laser model to compare the performance of several machine learning algorithms for forecasting the amplitude of upc...

Full description

Saved in:
Bibliographic Details
Published in:Chaos (Woodbury, N.Y.) N.Y.), 2019-11, Vol.29 (11), p.113111-113111
Main Authors: Amil, Pablo, Soriano, Miguel C., Masoller, Cristina
Format: Article
Language:English
Subjects:
Algorithms
Amplitudes
Aprenentatge automàtic
Artificial intelligence
Caos (Teoria de sistemes)
Chaos theory
Chaotic behavior in systems
Computer simulation
Economic forecasting
Física
Lasers
Làsers de semiconductors
Machine learning
Matemàtiques i estadística
Performance prediction
Semiconductor lasers
Support vector machines
Àrees temàtiques de la UPC
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Forecasting the dynamics of chaotic systems from the analysis of their output signals is a challenging problem with applications in most fields of modern science. In this work, we use a laser model to compare the performance of several machine learning algorithms for forecasting the amplitude of upcoming emitted chaotic pulses. We simulate the dynamics of an optically injected semiconductor laser that presents a rich variety of dynamical regimes when changing the parameters. We focus on a particular dynamical regime that can show ultrahigh intensity pulses, reminiscent of rogue waves. We compare the goodness of the forecast for several popular methods in machine learning, namely, deep learning, support vector machine, nearest neighbors, and reservoir computing. Finally, we analyze how their performance for predicting the height of the next optical pulse depends on the amount of noise and the length of the time series used for training.
ISSN:1054-1500
1089-7682
DOI:10.1063/1.5120755