Findings from Universidad Carlos III de Madrid Provide New Insights into Science (b-Variational autoencoders and transformers for reduced-order modelling of fluid flows).

Předmět:	REDUCED-order models FLUID flow PROPER orthogonal decomposition VISCOUS flow POINCARE maps (Mathematics)
Zdroj:	Blood Weekly; 3/21/2024, p243-243, 1p
Abstrakt:	A recent study conducted by researchers at the Universidad Carlos III de Madrid explores the use of variational autoencoder architectures to develop reduced-order models for chaotic fluid flows. The researchers propose a method that combines a b-variational autoencoder and a transformer to learn compact and near-orthogonal reduced-order models. The results show that this method outperforms other prediction models and has potential applications in fields such as weather forecasting, structural dynamics, and biomedical engineering. The full article can be accessed for free at the Nature Communications website. [Extracted from the article]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu