Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks
We report on the reconstruction of ultrashort laser pulses from computer-simulated and experimental second harmonic generation-frequency resolved optical gating (SHG-FROG) spectrograms. In order to retrieve the spectral amplitude and phase we use a convolutional neural network trained on simulated S...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/10/11/1195 |
| _version_ | 1797458021010374656 |
|---|---|
| author | István Tóth Ana Maria Mihaela Gherman Katalin Kovács Wosik Cho Hyeok Yun Valer Toşa |
| author_facet | István Tóth Ana Maria Mihaela Gherman Katalin Kovács Wosik Cho Hyeok Yun Valer Toşa |
| author_sort | István Tóth |
| collection | DOAJ |
| description | We report on the reconstruction of ultrashort laser pulses from computer-simulated and experimental second harmonic generation-frequency resolved optical gating (SHG-FROG) spectrograms. In order to retrieve the spectral amplitude and phase we use a convolutional neural network trained on simulated SHG-FROG spectrograms and the corresponding spectral-domain fields employed as labels for the network, which is a complex field encompassing the full information about the amplitude and phase. Our results show excellent retrieval capabilities of the neural network in case of the simulated pulses. Although trained only on computer generated data, the method shows promising results regarding experimentally measured pulses. |
| first_indexed | 2024-03-09T16:31:06Z |
| format | Article |
| id | doaj.art-2024a0910e1d44a1941746da6857ab7a |
| institution | Directory Open Access Journal |
| issn | 2304-6732 |
| language | English |
| last_indexed | 2024-03-09T16:31:06Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj.art-2024a0910e1d44a1941746da6857ab7a2023-11-24T15:01:19ZengMDPI AGPhotonics2304-67322023-10-011011119510.3390/photonics10111195Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural NetworksIstván Tóth0Ana Maria Mihaela Gherman1Katalin Kovács2Wosik Cho3Hyeok Yun4Valer Toşa5National Institute for Research and Development of Isotopic and Molecular Technologies, 67-103 Donat Str., 400293 Cluj-Napoca, RomaniaNational Institute for Research and Development of Isotopic and Molecular Technologies, 67-103 Donat Str., 400293 Cluj-Napoca, RomaniaNational Institute for Research and Development of Isotopic and Molecular Technologies, 67-103 Donat Str., 400293 Cluj-Napoca, RomaniaCenter for Relativistic Laser Science, Institute for Basic Science, Gwangju 61005, Republic of KoreaAdvanced Photonics Research Institute, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of KoreaNational Institute for Research and Development of Isotopic and Molecular Technologies, 67-103 Donat Str., 400293 Cluj-Napoca, RomaniaWe report on the reconstruction of ultrashort laser pulses from computer-simulated and experimental second harmonic generation-frequency resolved optical gating (SHG-FROG) spectrograms. In order to retrieve the spectral amplitude and phase we use a convolutional neural network trained on simulated SHG-FROG spectrograms and the corresponding spectral-domain fields employed as labels for the network, which is a complex field encompassing the full information about the amplitude and phase. Our results show excellent retrieval capabilities of the neural network in case of the simulated pulses. Although trained only on computer generated data, the method shows promising results regarding experimentally measured pulses.https://www.mdpi.com/2304-6732/10/11/1195ultra-short laser pulsepulse reconstructionfrequency resolved optical gatingconvolutional neural networkdeep learning |
| spellingShingle | István Tóth Ana Maria Mihaela Gherman Katalin Kovács Wosik Cho Hyeok Yun Valer Toşa Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks Photonics ultra-short laser pulse pulse reconstruction frequency resolved optical gating convolutional neural network deep learning |
| title | Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks |
| title_full | Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks |
| title_fullStr | Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks |
| title_full_unstemmed | Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks |
| title_short | Reconstruction of Femtosecond Laser Pulses from FROG Traces by Convolutional Neural Networks |
| title_sort | reconstruction of femtosecond laser pulses from frog traces by convolutional neural networks |
| topic | ultra-short laser pulse pulse reconstruction frequency resolved optical gating convolutional neural network deep learning |
| url | https://www.mdpi.com/2304-6732/10/11/1195 |
| work_keys_str_mv | AT istvantoth reconstructionoffemtosecondlaserpulsesfromfrogtracesbyconvolutionalneuralnetworks AT anamariamihaelagherman reconstructionoffemtosecondlaserpulsesfromfrogtracesbyconvolutionalneuralnetworks AT katalinkovacs reconstructionoffemtosecondlaserpulsesfromfrogtracesbyconvolutionalneuralnetworks AT wosikcho reconstructionoffemtosecondlaserpulsesfromfrogtracesbyconvolutionalneuralnetworks AT hyeokyun reconstructionoffemtosecondlaserpulsesfromfrogtracesbyconvolutionalneuralnetworks AT valertosa reconstructionoffemtosecondlaserpulsesfromfrogtracesbyconvolutionalneuralnetworks |