Access through your institution Buy or subscribe arising from L. Salmela et al. _Nature Machine Intelligence_ https://www.nature.com/articles/s42256-021-00297-z (2021) With their internal

memory, recurrent neural networks can be used to learn and predict time-dependent behaviours. In their recent work, Salmela et al.1 present a recurrent neural network architecture to learn

and predict complex nonlinear propagation in an optical fibre based on the input pulse intensity profile in the time domain. Here, we use their model by extending it to the case of

spatiotemporal nonlinear propagation for an arbitrary number of modes in graded-index multimode fibres. In addition to the original work’s focus on predicting the temporal evolution of

days cancel any time Learn more Subscribe to this journal Receive 12 digital issues and online access to articles $119.00 per year only $9.92 per issue Learn more Buy this article * Purchase

on SpringerLink * Instant access to full article PDF Buy now Prices may be subject to local taxes which are calculated during checkout ADDITIONAL ACCESS OPTIONS: * Log in * Learn about

institutional subscriptions * Read our FAQs * Contact customer support DATA AVAILABILITY The data used in this paper is available at the following GitHub repository

https://github.com/ugurtegin/MMF_RNN_Reuse. CODE AVAILABILITY The code used in this paper is available at the following GitHub repository https://github.com/ugurtegin/MMF_RNN_Reuse.

REFERENCES * Salmela, L. et al. Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network. _Nat. Mach. Intell._ 3, 1–11 (2021). Article  Google Scholar  *

Rogel-Salazar, J. The Gross–Pitaevskii equation and Bose–Einstein condensates. _Eur. J. Phys._ 34, 247 (2013). Article  Google Scholar  * Krupa, K. et al. Observation of geometric parametric

instability induced by the periodic spatial self-imaging of multimode waves. _Phys. Rev. Lett._ 116, 183901 (2016). Article  Google Scholar  * Teğin, U. & Ortaç, B. Spatiotemporal

instability of femtosecond pulses in graded-index multimode fibers. _IEEE Photon. Technol. Lett._ 29, 2195–2198 (2017). Article  Google Scholar  * Wright, L. G., Christodoulides, D. N. &

Wise, F. W. Controllable spatiotemporal nonlinear effects in multimode fibres. _Nat. Photon._ 9, 306–310 (2015). Article  Google Scholar  * Renninger, W. H. et al. Optical solitons in

graded-index multimode fibres. _Nat. Commun._ 4, 1719 (2013). Article  Google Scholar  * Ahsan, A. S. & Agrawal, G. P. Graded-index solitons in multimode fibers. _Opt. Lett._ 43,

3345–3348 (2018). Article  Google Scholar  * Krupa, K. et al. Spatial beam self-cleaning in multimode fibres. _Nat. Photon._ 11, 237–241 (2017). Article  Google Scholar  * Krupa, K. et al.

Spatiotemporal light-beam compression from nonlinear mode coupling. _Phys. Rev. A_ 97, 043836 (2018). Article  Google Scholar  * Lopez-Galmiche, G. et al. Visible supercontinuum generation

in a graded index multimode fiber pumped at 1064 nm. _Opt. Lett._ 41, 2553–2556 (2016). Article  Google Scholar  * Teğin, U. & Ortaç, B. Cascaded Raman scattering based high power

octave-spanning supercontinuum generation in graded-index multimode fibers. _Sci. Rep._ 8, 1–7 (2018). Article  Google Scholar  * Wright, L. G., Christodoulides, D. N. & Wise, F. W.

Spatiotemporal mode-locking in multimode fiber lasers. _Science_ 358, 94–97 (2017). Article  Google Scholar  * Teğin, U., Kakkava, E., Rahmani, B., Psaltis, D. & Moser, C. Spatiotemporal

self-similar fiber laser. _Optica_ 6, 1412–1415 (2019). Article  Google Scholar  * Teğin, U., Rahmani, B., Kakkava, E., Psaltis, D. & Moser, C. Single-mode output by controlling the

spatiotemporal nonlinearities in mode-locked femtosecond multimode fiber lasers. _Adv. Photon._ 2, 1–8 (2020). Article  Google Scholar  * Tzang, O., Caravaca-Aguirre, A. M., Wagner, K. &

Piestun, R. Adaptive wavefront shaping for controlling nonlinear multimode interactions in optical fibres. _Nat. Photon._ 12, 368–374 (2018). Article  Google Scholar  * Teǧin, U. et al.

Controlling spatiotemporal nonlinearities in multimode fibers with deep neural networks. _APL Photon._ 5, 030804 (2020). Article  Google Scholar  * Teğin, U., Yıldırım, M., Oğuz, İ., Moser,

C. & Psaltis, D. Scalable optical learning operator. Preprint at https://arxiv.org/abs/2012.12404 (2020). * Poletti, F. & Horak, P. Dynamics of femtosecond supercontinuum generation

in multimode fibers. _Opt. Express_ 17, 6134–6147 (2009). Article  Google Scholar  * Mafi, A. Pulse propagation in a short nonlinear graded-index multimode optical fiber. _J. Lightwave

Technol._ 30, 2803–2811 (2012). Article  Google Scholar  * Genty, G. et al. Machine learning and applications in ultrafast photonics. _Nat. Photon._ 15, 1–11 (2020). Google Scholar  * An, Y.

et al. Learning to decompose the modes in few-mode fibers with deep convolutional neural network. _Opt. Express_ 27, 10127–10137 (2019). Article  Google Scholar  * Rothe, S., Zhang, Q.,

Koukourakis, N. & Czarske, J. W. Deep learning for computational mode decomposition in optical fibers. _Appl. Sci._ 10, 1367 (2020). Article  Google Scholar  Download references

ACKNOWLEDGEMENTS We thank M. Yıldırım for discussions. AUTHOR INFORMATION AUTHORS AND AFFILIATIONS * Optics Laboratory, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland Uğur

Teğin, Niyazi Ulaş Dinç & Demetri Psaltis * Laboratory of Applied Photonics Devices, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland Uğur Teğin, Niyazi Ulaş Dinç & 

Christophe Moser Authors * Uğur Teğin View author publications You can also search for this author inPubMed Google Scholar * Niyazi Ulaş Dinç View author publications You can also search for

this author inPubMed Google Scholar * Christophe Moser View author publications You can also search for this author inPubMed Google Scholar * Demetri Psaltis View author publications You

can also search for this author inPubMed Google Scholar CONTRIBUTIONS U.T. and N.U.D. performed simulations; C.M and D.P. supervised and directed the project. All the authors participated in

the analysis of the data and the writing process of the manuscript. CORRESPONDING AUTHORS Correspondence to Uğur Teğin or Niyazi Ulaş Dinç. ETHICS DECLARATIONS COMPETING INTERESTS The

authors declare no competing interests. ADDITIONAL INFORMATION PEER REVIEW INFORMATION _Nature Machine Intelligence_ thanks Yichen Wu and the other, anonymous, reviewer(s) for their

contribution to the peer review of this work. PUBLISHER’S NOTE Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

SUPPLEMENTARY INFORMATION SUPPLEMENTARY INFORMATION Supplementary Figures 1–6 and Supplementary Discussion RIGHTS AND PERMISSIONS Reprints and permissions ABOUT THIS ARTICLE CITE THIS

ARTICLE Teğin, U., Dinç, N.U., Moser, C. _et al._ Reusability report: Predicting spatiotemporal nonlinear dynamics in multimode fibre optics with a recurrent neural network. _Nat Mach

Intell_ 3, 387–391 (2021). https://doi.org/10.1038/s42256-021-00347-6 Download citation * Received: 27 February 2021 * Accepted: 15 April 2021 * Published: 13 May 2021 * Issue Date: May 2021

* DOI: https://doi.org/10.1038/s42256-021-00347-6 SHARE THIS ARTICLE Anyone you share the following link with will be able to read this content: Get shareable link Sorry, a shareable link

is not currently available for this article. Copy to clipboard Provided by the Springer Nature SharedIt content-sharing initiative