Complex-valued neural operator assisted soliton identification
Abstract
The numerical determination of solitary states is an important topic for such research areas as Bose-Einstein condensates, nonlinear optics, plasma physics, etc. In this paper, we propose a data-driven approach for identifying solitons based on dynamical solutions of real-time differential equations. Our approach combines a machine-learning architecture called the complex-valued neural operator (CNO) with an energy-restricted gradient optimization. The former serves as a generalization of the traditional neural operator to the complex domain, and constructs a smooth mapping between the initial and final states; the latter facilitates the search for solitons by constraining the energy space. We concretely demonstrate this approach on the quasi-one-dimensional Bose-Einstein condensate with homogeneous and inhomogeneous nonlinearities. Our work offers a new idea for data-driven effective modeling and studies of solitary waves in nonlinear physical systems.
Cite
@article{arxiv.2305.18209,
title = {Complex-valued neural operator assisted soliton identification},
author = {Ming Zhang and Qi Meng and Deng Zhang and Yue Wang and Guanghui Wang and Zhiming Ma and Li Chen and Tie-Yan Liu},
journal= {arXiv preprint arXiv:2305.18209},
year = {2023}
}
Comments
9 pages, 5 figures