A Deep Learning Approximation of Non-Stationary Solutions to Wave Kinetic Equations

DOI10.1016/J.APNUM.2022.12.010MaRDI QIDQ6411871zbMATH OpenFDO

Authors Steven V. Walton, Minh-Binh Tran, Alain Bensoussan

Publication date 25 September 2022

Full work available at URL https://doi.org/10.1016/J.APNUM.2022.12.010

Mathematics Subject Classification ID

Qualitative properties of solutions to partial differential equations (35Bxx) Partial differential equations of mathematical physics and other areas of application (35Qxx) Time-dependent statistical mechanics (dynamic and nonequilibrium) (82Cxx)

Abstract: We present a deep learning approximation, stochastic optimization based, method for wave kinetic equations. To build confidence in our approach, we apply the method to a Smoluchowski coagulation equation with multiplicative kernel for which an analytic solution exists. Our deep learning approach is then used to approximate the non-stationary solution to a 3-wave kinetic equation corresponding to acoustic wave systems. To validate the neural network approximation, we compare the decay rate of the total energy with previously obtained theoretical results. A finite volume solution is presented and compared with the present method.

Recommendations

• Deep neural networks learning forward and inverse problems of two-dimensional nonlinear wave equations with rational solitons
• Solving the linear transport equation by a deep neural network approach
• Data-driven wave solutions of (2+1)-dimensional nonlinear dispersive long wave equation by deep learning
• Physics informed by deep learning: numerical solutions of modified Korteweg-de Vries equation
• Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes

Cited in

(5)

• Numerical schemes for a fully nonlinear coagulation-fragmentation model coming from wave kinetic theory
• On a wave kinetic equation with resonance broadening in oceanography and atmospheric sciences
• Spectral Algorithms for 3-Wave Kinetic and $C_{12}$ Quantum Boltzmann Equations with General Resonance Manifolds in $\mathbb{R}^d$
• Condensation and non-condensation times for 4-wave kinetic equations
• On the energy transfer toward large values of wavenumbers for solutions of 4-wave kinetic equations

This page was built for publication: A Deep Learning Approximation of Non-Stationary Solutions to Wave Kinetic Equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6411871)