Extreme Events Prediction from Nonlocal Partial Information in a Spatiotemporally Chaotic Microcavity Laser.

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 event occurrences 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 of at least twice the time horizon predicted from the nonlinear local Lyapunov exponent.

[1]  A. Mussot,et al.  Precursors-driven machine learning prediction of chaotic extreme pulses in Kerr resonators , 2022, Chaos, Solitons & Fractals.

[2]  P. Koumoutsakos,et al.  Multiscale simulations of complex systems by learning their effective dynamics , 2020, Nature Machine Intelligence.

[3]  J. Dudley,et al.  Machine learning analysis of rogue solitons in supercontinuum generation , 2020, Scientific Reports.

[4]  Cristina Masoller,et al.  Machine learning algorithms for predicting the amplitude of chaotic laser pulses. , 2019, Chaos.

[5]  M. C. Soriano,et al.  Cross-predicting the dynamics of an optically injected single-mode semiconductor laser using reservoir computing. , 2019, Chaos.

[6]  Jaideep Pathak,et al.  Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics , 2019, Neural Networks.

[7]  Themistoklis P. Sapsis,et al.  Machine Learning Predictors of Extreme Events Occurring in Complex Dynamical Systems , 2019, Entropy.

[8]  Jeong-Hwan Kim,et al.  Deep learning for multi-year ENSO forecasts , 2019, Nature.

[9]  Thomas Dimpfl,et al.  RTransferEntropy - Quantifying information flow between different time series using effective transfer entropy , 2019, SoftwareX.

[10]  Sylvain Barbay,et al.  Alternation of Defects and Phase Turbulence Induces Extreme Events in an Extended Microcavity Laser , 2018, Entropy.

[11]  Ulrich Parlitz,et al.  Observing spatio-temporal dynamics of excitable media using reservoir computing. , 2018, Chaos.

[12]  Robert Jenssen,et al.  Reservoir Computing Approaches for Representation and Classification of Multivariate Time Series , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Petros Koumoutsakos,et al.  Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks , 2018, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[14]  Cristina Masoller,et al.  Predictability of extreme intensity pulses in optically injected semiconductor lasers , 2017, 2017 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC).

[15]  C. Bayındır.  Early detection of rogue waves by the wavelet transforms , 2015, 1512.02583.

[16]  M. Erkintalo.  Predicting the unpredictable? , 2015, Nature Photonics.

[17]  Umberto Bortolozzo,et al.  Rogue waves and their generating mechanisms in different physical contexts , 2013 .

[18]  Arnida L. Latifah,et al.  Coherence and predictability of extreme events in irregular waves , 2012 .

[19]  Grégoire Nicolis,et al.  Foundations of Complex Systems: Emergence, Information and Prediction , 2012 .

[20]  John M. Dudley,et al.  Rogue wave early warning through spectral measurements , 2011 .

[21]  Frédéric Dias,et al.  The Peregrine soliton in nonlinear fibre optics , 2010 .

[22]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[23]  B. Jalali,et al.  Optical rogue waves , 2007, Nature.

[24]  Jianping Li,et al.  Nonlinear finite-time Lyapunov exponent and predictability , 2007 .

[25]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[26]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[27]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[28]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .