Model-free forecasting of rogue waves using reservoir computing

DOI10.1016/J.CNSNS.2025.109087MaRDI QIDQ6869140zbMATH OpenFDO

Authors A. N. Hasmi, H. Susanto

Publication date 23 January 2026

Published in Communications in Nonlinear Science and Numerical Simulation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CNSNS.2025.109087

zbMATH Keywords

echo state networknonlinear Schrödinger equationreservoir computingrogue waves

Mathematics Subject Classification ID

Soliton solutions (35C08) PDEs in connection with fluid mechanics (35Q35) Time-dependent Schrödinger equations and Dirac equations (35Q41) NLS equations (nonlinear Schrödinger equations) (35Q55) Computational learning theory (68Q32) Artificial neural networks and deep learning (68T07) Geophysical flows (76U60) Hydrology, hydrography, oceanography (86A05)

Cites work

• Calibrated forecasts of quasi-periodic climate processes with deep echo state networks and penalized quantile regression
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Exact first-order solutions of the nonlinear Schrödinger equation
• Extreme waves that appear from nowhere: on the nature of rogue waves
• Invariant spectra of orbits in dynamical systems
• Learning unseen coexisting attractors
• Local Lyapunov exponents in chaotic systems
• Model-free inference of unseen attractors: reconstructing phase space features from a single noisy trajectory using Reservoir computing
• Model-free prediction of multistability using echo state network
• On the risks of using double precision in numerical simulations of spatio-temporal chaos
• Physical mechanisms of the rogue wave phenomenon.
• Reduced-order prediction of rogue waves in two-dimensional deep-water waves
• Reservoir computing approaches to recurrent neural network training
• Rogue waves in the ocean
• Rogue waves of the (2+1)-dimensional integrable reverse space-time nonlocal Schrödinger equation
• Short- and long-term predictions of chaotic flows and extreme events: a physics-constrained reservoir computing approach
• Statistics of extreme events in fluid flows and waves
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data

Cited in

(1)

• Emergence of spike patterns in a vegetation model: a combined theoretical-numerical study

This page was built for publication: Model-free forecasting of rogue waves using reservoir computing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6869140)