The improved backward compatible physics-informed neural networks for reducing error accumulation and applications in data-driven higher-order rogue waves

TL;DR

This paper introduces an improved backward compatible physics-informed neural network (Ibc-PINN) that reduces error accumulation and enhances accuracy in simulating higher-order rogue waves for nonlinear PDEs, demonstrating superior performance over previous methods.

Contribution

The paper proposes modifications to bc-PINN, including a new loss term and solution concatenation, to improve accuracy and stability in data-driven rogue wave modeling.

Findings

Ibc-PINN outperforms bc-PINN in accuracy and stability.

Error slowdown in Ibc-PINN enhances solution precision.

Transfer learning accelerates training process.

Abstract

Due to the dynamic characteristics of instantaneity and steepness, employing domain decomposition techniques for simulating rogue wave solutions is highly appropriate. Wherein, the backward compatible PINN (bc-PINN) is a temporally sequential scheme to solve PDEs over successive time segments while satisfying all previously obtained solutions. In this work, we propose improvements to the original bc-PINN algorithm in two aspects based on the characteristics of error propagation. One is to modify the loss term for ensuring backward compatibility by selecting the earliest learned solution for each sub-domain as pseudo reference solution. The other is to adopt the concatenation of solutions obtained from individual subnetworks as the final form of the predicted solution. The improved backward compatible PINN (Ibc-PINN) is applied to study data-driven higher-order rogue waves for the nonlinear Schr\"{o}dinger (NLS) equation and the AB system to demonstrate the effectiveness and advantages. Transfer learning and initial condition guided learning (ICGL) techniques are also utilized to accelerate the training. Moreover, the error analysis is conducted on each sub-domain and it turns out that the slowdown of Ibc-PINN in error accumulation speed can yield greater advantages in accuracy. In short, numerical results fully indicate that Ibc-PINN significantly outperforms bc-PINN in terms of accuracy and stability without sacrificing efficiency.