Measuring the rogue wave pattern triggered from Gaussian perturbations by deep learning

Abstract

Weak Gaussian perturbations on a plane wave background could trigger lots of rogue waves, due to modulational instability. Numerical simulations showed that these rogue waves seemed to have similar unit structure. However, to the best of our knowledge, there is no relative result to prove that these rogue waves have the similar patterns for different perturbations, partly due to that it is hard to measure the rogue wave pattern automatically. In this work, we address these problems from the perspective of computer vision via using deep neural networks. We propose a Rogue Wave Detection Network (RWD-Net) model to automatically and accurately detect RWs on the images, which directly indicates they have the similar computer vision patterns. For this purpose, we herein meanwhile have designed the related dataset, termed as Rogue Wave Dataset-$10$K (RWD-$10$K), which has $10,191$ RW images with bounding box annotations for each RW unit. In our detection experiments, we get $99.29\%$ average precision on the test splits of the RWD-$10$K dataset. Finally, we derive our novel metric, the density of RW units (DRW), to characterize the evolution of Gaussian perturbations and obtain the statistical results on them.

8 pages, 6 figures

References in corpus (11)

• Instabilities, breathers and rogue waves in optics
• Vector Rogue Waves and Baseband Modulation Instability in the Defocusing Regime
• Optical Rogue Waves in integrable turbulence
• Rogue-wave solutions of a three-component coupled nonlinear Schrodinger equation
• Instability and Evolution of Nonlinearly Interacting Water Waves
• Localized nonlinear waves in a two-mode nonlinear fiber
• Machine learning algorithms for predicting the amplitude of chaotic laser pulses
• Higher-order vector Peregrine solitons and asymptotic estimates for the multi-component nonlinear Schrödinger equations
• Soliton gas in bidirectional dispersive hydrodynamics
• Solitons in inhomogeneous gauge potentials: integrable and nonintegrable dynamics
• Machine-learning enhanced dark soliton detection in Bose-Einstein condensates

Cited by in corpus (1)

• Rogue waves collision under incident momentum modulation in two-component Bose-Einstein condensates