Machine learning analysis of extreme events in optical fibre modulation instability
Real-time characterisation of nonlinear processes in the time domain is challenging. Here, Närhi et al. show that machine learning techniques can help overcome this limitation and use them to infer time-domain properties of optical fibre modulation instability from spectral intensity measurements.
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2018-11-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-018-07355-y |
| _version_ | 1818956979119325184 |
|---|---|
| author | Mikko Närhi Lauri Salmela Juha Toivonen Cyril Billet John M. Dudley Goëry Genty |
| author_facet | Mikko Närhi Lauri Salmela Juha Toivonen Cyril Billet John M. Dudley Goëry Genty |
| author_sort | Mikko Närhi |
| collection | DOAJ |
| description | Real-time characterisation of nonlinear processes in the time domain is challenging. Here, Närhi et al. show that machine learning techniques can help overcome this limitation and use them to infer time-domain properties of optical fibre modulation instability from spectral intensity measurements. |
| first_indexed | 2024-12-20T11:02:33Z |
| format | Article |
| id | doaj.art-2189e5907a1e496d9adc09f2e86e99a5 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-12-20T11:02:33Z |
| publishDate | 2018-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-2189e5907a1e496d9adc09f2e86e99a52022-12-21T19:42:58ZengNature PortfolioNature Communications2041-17232018-11-019111110.1038/s41467-018-07355-yMachine learning analysis of extreme events in optical fibre modulation instabilityMikko Närhi0Lauri Salmela1Juha Toivonen2Cyril Billet3John M. Dudley4Goëry Genty5Tampere University of Technology, Laboratory of PhotonicsTampere University of Technology, Laboratory of PhotonicsTampere University of Technology, Laboratory of PhotonicsInstitut FEMTO-ST, Université Bourgogne Franche-Comté, CNRS UMR 6174Institut FEMTO-ST, Université Bourgogne Franche-Comté, CNRS UMR 6174Tampere University of Technology, Laboratory of PhotonicsReal-time characterisation of nonlinear processes in the time domain is challenging. Here, Närhi et al. show that machine learning techniques can help overcome this limitation and use them to infer time-domain properties of optical fibre modulation instability from spectral intensity measurements.https://doi.org/10.1038/s41467-018-07355-y |
| spellingShingle | Mikko Närhi Lauri Salmela Juha Toivonen Cyril Billet John M. Dudley Goëry Genty Machine learning analysis of extreme events in optical fibre modulation instability Nature Communications |
| title | Machine learning analysis of extreme events in optical fibre modulation instability |
| title_full | Machine learning analysis of extreme events in optical fibre modulation instability |
| title_fullStr | Machine learning analysis of extreme events in optical fibre modulation instability |
| title_full_unstemmed | Machine learning analysis of extreme events in optical fibre modulation instability |
| title_short | Machine learning analysis of extreme events in optical fibre modulation instability |
| title_sort | machine learning analysis of extreme events in optical fibre modulation instability |
| url | https://doi.org/10.1038/s41467-018-07355-y |
| work_keys_str_mv | AT mikkonarhi machinelearninganalysisofextremeeventsinopticalfibremodulationinstability AT laurisalmela machinelearninganalysisofextremeeventsinopticalfibremodulationinstability AT juhatoivonen machinelearninganalysisofextremeeventsinopticalfibremodulationinstability AT cyrilbillet machinelearninganalysisofextremeeventsinopticalfibremodulationinstability AT johnmdudley machinelearninganalysisofextremeeventsinopticalfibremodulationinstability AT goerygenty machinelearninganalysisofextremeeventsinopticalfibremodulationinstability |