Comparing Performance of Deep Convolution Networks in Reconstructing Soliton Molecules Dynamics from Real-Time Spectral Interference
Open Access
Abstract
Deep neural networks have enabled the reconstruction of optical soliton molecules with more complex structures using the real-time spectral interferences obtained by photonic time-stretch dispersive Fourier transformation (TS-DFT) technology. In this paper, we propose to use three kinds of deep convolution networks (DCNs), including VGG, ResNets, and DenseNets, for revealing internal dynamics evolution of soliton molecules based on the real-time spectral interferences. When analyzing soliton molecules with equidistant composite structures, all three models are effective. The DenseNets with layers of 48 perform the best for extracting the dynamic information of complex five-soliton molecules from TS-DFT data. The mean Pearson correlation coefficient (MPCC) between the predicted results and the real results is about 0.9975. Further, the ResNets in which the MPCC achieves 0.9906 also has the better ability of phase extraction than VGG which the MPCC is about 0.9739. The general applicability is demonstrated for extracting internal information from complex soliton molecule structures with high accuracy. The presented DCNs-based techniques can be employed to explore undiscovered mechanisms underlying the distribution and evolution of large numbers of solitons in dissipative systems in experimental research.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFB0504400)
- National Natural Science Foundation of China (61775107, 11674177, 61640408)
- Natural Science Foundation of Tianjin Municipality (19JCZDJC31200)
This publication has 32 references indexed in Scilit:
- Real-Time Observation of Internal Motion within Ultrafast Dissipative Optical Soliton MoleculesPhysical Review Letters, 2017
- Real-time spectral interferometry probes the internal dynamics of femtosecond soliton moleculesScience, 2017
- Identity Mappings in Deep Residual Networks2016
- Deep Residual Learning for Image Recognition2016
- Machine Learning Techniques in Optical CommunicationJournal of Lightwave Technology, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Observation of soliton explosions in a passively mode-locked fiber laserOptica, 2015
- Dissipative solitons for mode-locked lasersNature Photonics, 2012
- Dissipative soliton molecules with independently evolving or flipping phases in mode-locked fiber lasersPhysical Review A, 2009
- Experimental Observation of Temporal Soliton MoleculesPhysical Review Letters, 2005