English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We investigate the physics informed neural network method, a deep learningapproach, to approximate soliton solution of the nonlinear Schr\"odingerequation with parity time symmetric potentials. We consider three differentparity time symmetric potentials, namely Gaussian, periodic and Rosen-Morsepotentials. We use physics informed neural network to solve the considerednonlinear partial differential equation with the above three potentials. Wecompare the predicted result with actual result and analyze the ability of deeplearning in solving the considered partial differential equation. We check theability of deep learning in approximating the soliton solution by takingsquared error between real and predicted values. {Further, we examine thefactors that affect the performance of the considered deep learning method withdifferent activation functions, namely ReLU, sigmoid and tanh. We also use anew activation function, namely sech which is not used in the field of deeplearning and analyze whether this new activation function is suitable for theprediction of soliton solution of nonlinear Schr\"odinger equation for theaforementioned parity time symmetric potentials. In addition to the above, wepresent how the network's structure and the size of the training data influencethe performance of the physics informed neural network. Our results show thatthe constructed deep learning model successfully approximates the solitonsolution of the considered equation with high accuracy.

Data driven soliton solution of the nonlinear Schr\"odinger equation with certain $\mathcal{PT}$-symmetric potentials via deep learning