Conference paper
Distance and spectral power profile shaping using machine learning enabled Raman amplifiers
Department of Photonics Engineering, Technical University of Denmark1
Machine Learning in Photonic Systems, Department of Photonics Engineering, Technical University of Denmark2
Centre of Excellence for Silicon Photonics for Optical Communications, Centers, Technical University of Denmark3
Ultra-fast Optical Communication, Department of Photonics Engineering, Technical University of Denmark4
Polytechnic University of Turin5
We propose a Convolutional Neural Network (CNN) to learn the mapping between the 2D power profiles, (distance and frequency), and the Raman pumps. Using the CNN, the pump powers and wavelengths for arbitrary 2D profiles can be determined with high accuracy.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2021 |
Pages: | 1-2 |
Proceedings: | 2021 IEEE Photonics Society Summer Topicals Meeting Series |
ISBN: | 1665416009 , 1665446730 , 9781665416009 and 9781665446730 |
ISSN: | 23768614 and 10994742 |
Types: | Conference paper |
DOI: | 10.1109/SUM48717.2021.9505741 |
ORCIDs: | Soltani, M. , Da Ros, F. and Zibar, D. |