New models compare physics-informed neural networks and tensorial reduced-order models for dam-break…

Researchers have developed and compared two parametric data-driven reduced models for the shallow-water dam-break problem. The models, a physics-informed neural network (PINN) and a non-intrusive tensorial reduced-order model (TROM), both learn a direct solution map from parameters to the physical state without requiring time integration. The study highlights the importance of incorporating shock-aware collocation to enhance the robustness of the PINN model, especially for out-of-sample and extrapolated parameter values. AI

IMPACT This research contributes to the development of more efficient simulation techniques for complex physical phenomena, potentially impacting fields requiring fluid dynamics modeling.

RANK_REASON The cluster contains a research paper detailing a comparison of two modeling approaches for a specific scientific problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Physics-Informed Neural Network
• ScienceCast
• Shallow-Water Dam-Break Problem
• Tensorial Reduced-Order Model

• paper
• other

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