LSR-Net architecture learns nonlinear fluid dynamics evolution

Researchers have introduced LSR-Net, a novel neural operator architecture designed to model the forward evolution of nonlinear fluid dynamics. This network effectively learns the evolution operator from initial and future state snapshots by splitting the integral kernel into long-range and short-range components. The short-range component uses convolutions for local dynamics, while the long-range component utilizes a sum-of-exponentials representation for efficient global interaction computation. Evaluations on benchmark problems like the Burgers equation and shallow water equations show LSR-Net outperforming existing methods such as FNO and DeepONets in predictive accuracy. AI

IMPACT This new architecture could improve the accuracy and efficiency of modeling complex physical systems.

RANK_REASON The cluster contains a research paper detailing a new neural network architecture for scientific computing. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Burgers equation
• DeepONets
• Fourier Neural Operators
• Long-Short-Range Neural Network
• LSR-Net
• nonlinear shallow water equation
• shallow water equations
• SR-Net: A sequence offset fusion net and refine net for undersampled multislice MR image reconstruction
• wave equation

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →