Abstract
We constructed a physics-informed neural network (PINN) to solve the nonlinear Schrödinger equation for different input waveforms. Results show that PINN can accurately characterize pulse evolution in fibers with less complexity to SSFM methods.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
Xiaotian Jiang, Danshi Wang, and Min Zhang
T4A.81 Asia Communications and Photonics Conference (ACP) 2021
Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein, Tianyu Wang, Darren T. Schachter, Zoey Hu, and Peter L. McMahon
FF1A.4 CLEO: QELS_Fundamental Science (CLEO:FS) 2021
C.R. Menyuk
CMH3 Conference on Lasers and Electro-Optics (CLEO:S&I) 1999