Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366998443> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4366998443 abstract "Abstract Variational autoencoder (VAE) architectures have the potential to develop reduced-order models (ROMs) for chaotic fluid flows. We propose a method for learning compact and near-orthogonal ROMs using a combination of a β -VAE and a transformer, tested on numerical data from a two-dimensional viscous flow in both periodic and chaotic regimes. The β -VAE is trained to learn a compact latent representation of the flow velocity, and the transformer is trained to predict the temporal dynamics in latent space. Using the β -VAE to learn disentangled representations in latent space, we obtain a more interpretable flow model with features that resemble those observed in the proper orthogonal decomposition, but with a more efficient representation. Using Poincaré maps, the results show that our method can capture the underlying dynamics of the flow outperforming other prediction models. The proposed method has potential applications in other fields such as weather forecasting, structural dynamics or biomedical engineering." @default.
- W4366998443 created "2023-04-27" @default.
- W4366998443 creator A5034012424 @default.
- W4366998443 creator A5049616413 @default.
- W4366998443 creator A5062588973 @default.
- W4366998443 creator A5064597868 @default.
- W4366998443 creator A5066274202 @default.
- W4366998443 creator A5070059573 @default.
- W4366998443 creator A5088595213 @default.
- W4366998443 date "2023-04-26" @default.
- W4366998443 modified "2023-10-01" @default.
- W4366998443 title "β-Variational autoencoders and transformers for reduced-order modelling of fluid flows" @default.
- W4366998443 doi "https://doi.org/10.21203/rs.3.rs-2825880/v1" @default.
- W4366998443 hasPublicationYear "2023" @default.
- W4366998443 type Work @default.
- W4366998443 citedByCount "0" @default.
- W4366998443 crossrefType "posted-content" @default.
- W4366998443 hasAuthorship W4366998443A5034012424 @default.
- W4366998443 hasAuthorship W4366998443A5049616413 @default.
- W4366998443 hasAuthorship W4366998443A5062588973 @default.
- W4366998443 hasAuthorship W4366998443A5064597868 @default.
- W4366998443 hasAuthorship W4366998443A5066274202 @default.
- W4366998443 hasAuthorship W4366998443A5070059573 @default.
- W4366998443 hasAuthorship W4366998443A5088595213 @default.
- W4366998443 hasBestOaLocation W43669984431 @default.
- W4366998443 hasConcept C101738243 @default.
- W4366998443 hasConcept C11413529 @default.
- W4366998443 hasConcept C121332964 @default.
- W4366998443 hasConcept C153180895 @default.
- W4366998443 hasConcept C154945302 @default.
- W4366998443 hasConcept C165801399 @default.
- W4366998443 hasConcept C17744445 @default.
- W4366998443 hasConcept C199539241 @default.
- W4366998443 hasConcept C2524010 @default.
- W4366998443 hasConcept C2776359362 @default.
- W4366998443 hasConcept C2777052490 @default.
- W4366998443 hasConcept C33923547 @default.
- W4366998443 hasConcept C38349280 @default.
- W4366998443 hasConcept C41008148 @default.
- W4366998443 hasConcept C50644808 @default.
- W4366998443 hasConcept C57879066 @default.
- W4366998443 hasConcept C62520636 @default.
- W4366998443 hasConcept C66322947 @default.
- W4366998443 hasConcept C90278072 @default.
- W4366998443 hasConcept C94625758 @default.
- W4366998443 hasConceptScore W4366998443C101738243 @default.
- W4366998443 hasConceptScore W4366998443C11413529 @default.
- W4366998443 hasConceptScore W4366998443C121332964 @default.
- W4366998443 hasConceptScore W4366998443C153180895 @default.
- W4366998443 hasConceptScore W4366998443C154945302 @default.
- W4366998443 hasConceptScore W4366998443C165801399 @default.
- W4366998443 hasConceptScore W4366998443C17744445 @default.
- W4366998443 hasConceptScore W4366998443C199539241 @default.
- W4366998443 hasConceptScore W4366998443C2524010 @default.
- W4366998443 hasConceptScore W4366998443C2776359362 @default.
- W4366998443 hasConceptScore W4366998443C2777052490 @default.
- W4366998443 hasConceptScore W4366998443C33923547 @default.
- W4366998443 hasConceptScore W4366998443C38349280 @default.
- W4366998443 hasConceptScore W4366998443C41008148 @default.
- W4366998443 hasConceptScore W4366998443C50644808 @default.
- W4366998443 hasConceptScore W4366998443C57879066 @default.
- W4366998443 hasConceptScore W4366998443C62520636 @default.
- W4366998443 hasConceptScore W4366998443C66322947 @default.
- W4366998443 hasConceptScore W4366998443C90278072 @default.
- W4366998443 hasConceptScore W4366998443C94625758 @default.
- W4366998443 hasLocation W43669984431 @default.
- W4366998443 hasOpenAccess W4366998443 @default.
- W4366998443 hasPrimaryLocation W43669984431 @default.
- W4366998443 hasRelatedWork W2572600474 @default.
- W4366998443 hasRelatedWork W2592385986 @default.
- W4366998443 hasRelatedWork W2776466379 @default.
- W4366998443 hasRelatedWork W2785535669 @default.
- W4366998443 hasRelatedWork W2897995864 @default.
- W4366998443 hasRelatedWork W2966657595 @default.
- W4366998443 hasRelatedWork W2998168123 @default.
- W4366998443 hasRelatedWork W3090006671 @default.
- W4366998443 hasRelatedWork W4220775285 @default.
- W4366998443 hasRelatedWork W4287995534 @default.
- W4366998443 isParatext "false" @default.
- W4366998443 isRetracted "false" @default.
- W4366998443 workType "article" @default.