Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion
In this Letter, we introduce FusionNet, a multi-modality deep learning framework designed to predict and analyze output pulses in high-power rare-earth-doped laser systems driving parametric conversion in homogeneous guided nonlinear media. FusionNet integrates temporal, spectral, and physical exper...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-05-01
|
| Series: | APL Photonics |
| Online Access: | http://dx.doi.org/10.1063/5.0252720 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850250050675933184 |
|---|---|
| author | Hao Zhang Linshan Sun Jack Hirschman Sergio Carbajo |
| author_facet | Hao Zhang Linshan Sun Jack Hirschman Sergio Carbajo |
| author_sort | Hao Zhang |
| collection | DOAJ |
| description | In this Letter, we introduce FusionNet, a multi-modality deep learning framework designed to predict and analyze output pulses in high-power rare-earth-doped laser systems driving parametric conversion in homogeneous guided nonlinear media. FusionNet integrates temporal, spectral, and physical experimental conditions to model ultrafast nonlinear phenomena, including parametric nonlinear frequency conversion, self-phase modulation, and cross-phase modulation in homogeneous guided systems such as gas-filled hollow-core fibers. These systems bridge physical models with experimental data, advancing our understanding of light-guiding principles and nonlinear interactions while expediting the design and optimization of on-demand high-power, high-brightness systems. Our results demonstrate a 73% reduction in prediction error and an 83% improvement in computational efficiency compared to conventional neural networks. This work establishes a new paradigm for accelerating parametric simulations and optimizing experimental designs in high-power laser systems, with further implications for high-precision spectroscopy, quantum information science, and distributed entangled interconnects. |
| format | Article |
| id | doaj-art-9268efaf48ee4d55a7fcfde8a784a452 |
| institution | OA Journals |
| issn | 2378-0967 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Photonics |
| spelling | doaj-art-9268efaf48ee4d55a7fcfde8a784a4522025-08-20T01:58:19ZengAIP Publishing LLCAPL Photonics2378-09672025-05-01105050803050803-1010.1063/5.0252720Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversionHao Zhang0Linshan Sun1Jack Hirschman2Sergio Carbajo3Department of Electrical and Computer Engineering, University of California Los Angeles, Los Angeles, California 90095, USADepartment of Electrical and Computer Engineering, University of California Los Angeles, Los Angeles, California 90095, USASLAC National Accelerator Laboratory, Stanford University, Menlo Park, California 94025, USADepartment of Electrical and Computer Engineering, University of California Los Angeles, Los Angeles, California 90095, USAIn this Letter, we introduce FusionNet, a multi-modality deep learning framework designed to predict and analyze output pulses in high-power rare-earth-doped laser systems driving parametric conversion in homogeneous guided nonlinear media. FusionNet integrates temporal, spectral, and physical experimental conditions to model ultrafast nonlinear phenomena, including parametric nonlinear frequency conversion, self-phase modulation, and cross-phase modulation in homogeneous guided systems such as gas-filled hollow-core fibers. These systems bridge physical models with experimental data, advancing our understanding of light-guiding principles and nonlinear interactions while expediting the design and optimization of on-demand high-power, high-brightness systems. Our results demonstrate a 73% reduction in prediction error and an 83% improvement in computational efficiency compared to conventional neural networks. This work establishes a new paradigm for accelerating parametric simulations and optimizing experimental designs in high-power laser systems, with further implications for high-precision spectroscopy, quantum information science, and distributed entangled interconnects.http://dx.doi.org/10.1063/5.0252720 |
| spellingShingle | Hao Zhang Linshan Sun Jack Hirschman Sergio Carbajo Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion APL Photonics |
| title | Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion |
| title_full | Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion |
| title_fullStr | Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion |
| title_full_unstemmed | Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion |
| title_short | Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion |
| title_sort | multi modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion |
| url | http://dx.doi.org/10.1063/5.0252720 |
| work_keys_str_mv | AT haozhang multimodalitydeeplearningforpulsepredictioninhomogeneousnonlinearsystemsviaparametricconversion AT linshansun multimodalitydeeplearningforpulsepredictioninhomogeneousnonlinearsystemsviaparametricconversion AT jackhirschman multimodalitydeeplearningforpulsepredictioninhomogeneousnonlinearsystemsviaparametricconversion AT sergiocarbajo multimodalitydeeplearningforpulsepredictioninhomogeneousnonlinearsystemsviaparametricconversion |