New Weak-Entropy PINN framework tackles discontinuous solutions in hyperbolic conservation laws

Researchers have developed a novel Weak-Entropy PINN (WEPINN) framework to address the challenge of solving hyperbolic conservation laws with discontinuous solutions using neural networks. This new method enforces governing equations in their weak formulation and integrates the entropy condition to ensure physically admissible solutions, utilizing the discrete fast Fourier transform (DFFT) for efficient numerical integration. Extensive experiments show WEPINN can accurately resolve sharp discontinuities and capture complex wave interactions in both scalar and system conservation laws across one and two dimensions. AI

IMPACT Introduces a novel neural network approach for accurately modeling complex physical phenomena with discontinuous solutions.

RANK_REASON This is a research paper detailing a new method for solving a class of differential equations using neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• discrete fast Fourier transform
• Gotit.pub
• Hugging Face
• neural networks
• physics-informed neural networks
• ScienceCast
• WEPINN

• paper
• other

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