Machine learning analysis of rogue solitons in supercontinuum generation
Abstract Supercontinuum generation is a highly nonlinear process that exhibits unstable and chaotic characteristics when developing from long pump pulses injected into the anomalous dispersion regime of an optical fiber. A particular feature associated with this regime is the long-tailed “rogue wave...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2020-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-020-66308-y |
| _version_ | 1818435045673664512 |
|---|---|
| author | Lauri Salmela Coraline Lapre John M. Dudley Goëry Genty |
| author_facet | Lauri Salmela Coraline Lapre John M. Dudley Goëry Genty |
| author_sort | Lauri Salmela |
| collection | DOAJ |
| description | Abstract Supercontinuum generation is a highly nonlinear process that exhibits unstable and chaotic characteristics when developing from long pump pulses injected into the anomalous dispersion regime of an optical fiber. A particular feature associated with this regime is the long-tailed “rogue wave”-like statistics of the spectral intensity on the long-wavelength edge of the supercontinuum, linked to the generation of a small number of “rogue solitons” with extreme red-shifts. Whilst the statistical properties of rogue solitons can be conveniently measured in the spectral domain using the real-time dispersive Fourier transform technique, we cannot use this technique to determine any corresponding temporal properties since it only records the spectral intensity and one loses information about the spectral phase. And direct temporal characterization using methods such as the time-lens has resolution of typically 100’s of fs, precluding the measurement of solitons which possess typically much shorter durations. Here, we solve this problem by using machine learning. Specifically, we show how supervised learning can train a neural network to predict the peak power, duration, and temporal walk-off with respect to the pump pulse position of solitons at the edge of a supercontinuum spectrum from only the supercontinuum spectral intensity without phase information. Remarkably, the network accurately predicts soliton characteristics for a wide range of scenarios, from the onset of spectral broadening dominated by pure modulation instability to near octave-spanning supercontinuum with distinct rogue solitons. |
| first_indexed | 2024-12-14T16:46:39Z |
| format | Article |
| id | doaj.art-70f6bb7dc9094f1a9e9fa58746b9d1bf |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-14T16:46:39Z |
| publishDate | 2020-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-70f6bb7dc9094f1a9e9fa58746b9d1bf2022-12-21T22:54:10ZengNature PortfolioScientific Reports2045-23222020-06-011011810.1038/s41598-020-66308-yMachine learning analysis of rogue solitons in supercontinuum generationLauri Salmela0Coraline Lapre1John M. Dudley2Goëry Genty3Photonics Laboratory, Tampere UniversityInstitut FEMTO-ST, Université Bourgogne Franche-Comté CNRS UMR 6174Institut FEMTO-ST, Université Bourgogne Franche-Comté CNRS UMR 6174Photonics Laboratory, Tampere UniversityAbstract Supercontinuum generation is a highly nonlinear process that exhibits unstable and chaotic characteristics when developing from long pump pulses injected into the anomalous dispersion regime of an optical fiber. A particular feature associated with this regime is the long-tailed “rogue wave”-like statistics of the spectral intensity on the long-wavelength edge of the supercontinuum, linked to the generation of a small number of “rogue solitons” with extreme red-shifts. Whilst the statistical properties of rogue solitons can be conveniently measured in the spectral domain using the real-time dispersive Fourier transform technique, we cannot use this technique to determine any corresponding temporal properties since it only records the spectral intensity and one loses information about the spectral phase. And direct temporal characterization using methods such as the time-lens has resolution of typically 100’s of fs, precluding the measurement of solitons which possess typically much shorter durations. Here, we solve this problem by using machine learning. Specifically, we show how supervised learning can train a neural network to predict the peak power, duration, and temporal walk-off with respect to the pump pulse position of solitons at the edge of a supercontinuum spectrum from only the supercontinuum spectral intensity without phase information. Remarkably, the network accurately predicts soliton characteristics for a wide range of scenarios, from the onset of spectral broadening dominated by pure modulation instability to near octave-spanning supercontinuum with distinct rogue solitons.https://doi.org/10.1038/s41598-020-66308-y |
| spellingShingle | Lauri Salmela Coraline Lapre John M. Dudley Goëry Genty Machine learning analysis of rogue solitons in supercontinuum generation Scientific Reports |
| title | Machine learning analysis of rogue solitons in supercontinuum generation |
| title_full | Machine learning analysis of rogue solitons in supercontinuum generation |
| title_fullStr | Machine learning analysis of rogue solitons in supercontinuum generation |
| title_full_unstemmed | Machine learning analysis of rogue solitons in supercontinuum generation |
| title_short | Machine learning analysis of rogue solitons in supercontinuum generation |
| title_sort | machine learning analysis of rogue solitons in supercontinuum generation |
| url | https://doi.org/10.1038/s41598-020-66308-y |
| work_keys_str_mv | AT laurisalmela machinelearninganalysisofroguesolitonsinsupercontinuumgeneration AT coralinelapre machinelearninganalysisofroguesolitonsinsupercontinuumgeneration AT johnmdudley machinelearninganalysisofroguesolitonsinsupercontinuumgeneration AT goerygenty machinelearninganalysisofroguesolitonsinsupercontinuumgeneration |