FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176843930> ?p ?o ?g. }

• W3176843930 endingPage "067123" @default.
• W3176843930 startingPage "067123" @default.
• W3176843930 abstract "The unprecedented amount of data generated from experiments, field observations, and large-scale numerical simulations at a wide range of spatiotemporal scales has enabled the rapid advancement of data-driven and especially deep learning models in the field of fluid mechanics. Although these methods are proven successful for many applications, there is a grand challenge of improving their generalizability. This is particularly essential when data-driven models are employed within outer-loop applications like optimization. In this work, we put forth a physics-guided machine learning (PGML) framework that leverages the interpretable physics-based model with a deep learning model. Leveraging a concatenated neural network design from multi-modal data sources, the PGML framework is capable of enhancing the generalizability of data-driven models and effectively protects against or inform about the inaccurate predictions resulting from extrapolation. We apply the PGML framework as a novel model fusion approach combining the physics-based Galerkin projection model and long- to short-term memory (LSTM) network for parametric model order reduction of fluid flows. We demonstrate the improved generalizability of the PGML framework against a purely data-driven approach through the injection of physics features into intermediate LSTM layers. Our quantitative analysis shows that the overall model uncertainty can be reduced through the PGML approach, especially for test data coming from a distribution different than the training data. Moreover, we demonstrate that our approach can be used as an inverse diagnostic tool providing a confidence score associated with models and observations. The proposed framework also allows for multi-fidelity computing by making use of low-fidelity models in the online deployment of quantified data-driven models." @default.
• W3176843930 created "2021-07-05" @default.
• W3176843930 creator A5028149900 @default.
• W3176843930 creator A5032407979 @default.
• W3176843930 creator A5037019234 @default.
• W3176843930 creator A5072774082 @default.
• W3176843930 creator A5085671233 @default.
• W3176843930 date "2021-06-01" @default.
• W3176843930 modified "2023-10-16" @default.
• W3176843930 title "Model fusion with physics-guided machine learning: Projection-based reduced-order modeling" @default.
• W3176843930 cites W1633869374 @default.
• W3176843930 cites W1967568606 @default.
• W3176843930 cites W1991179992 @default.
• W3176843930 cites W1992326791 @default.
• W3176843930 cites W2027973545 @default.
• W3176843930 cites W2064675550 @default.
• W3176843930 cites W2073787051 @default.
• W3176843930 cites W2080556931 @default.
• W3176843930 cites W2083307976 @default.
• W3176843930 cites W2096126718 @default.
• W3176843930 cites W2112823474 @default.
• W3176843930 cites W2129832613 @default.
• W3176843930 cites W2135348862 @default.
• W3176843930 cites W2137983211 @default.
• W3176843930 cites W2147414751 @default.
• W3176843930 cites W2152896489 @default.
• W3176843930 cites W2346717862 @default.
• W3176843930 cites W2524575205 @default.
• W3176843930 cites W2534240011 @default.
• W3176843930 cites W2586938721 @default.
• W3176843930 cites W2618068449 @default.
• W3176843930 cites W2728522078 @default.
• W3176843930 cites W2734256217 @default.
• W3176843930 cites W2738335552 @default.
• W3176843930 cites W2768460243 @default.
• W3176843930 cites W2782714865 @default.
• W3176843930 cites W2795982117 @default.
• W3176843930 cites W2811395263 @default.
• W3176843930 cites W2885469054 @default.
• W3176843930 cites W2899283552 @default.
• W3176843930 cites W2913323966 @default.
• W3176843930 cites W2946794331 @default.
• W3176843930 cites W2951392159 @default.
• W3176843930 cites W2953410468 @default.
• W3176843930 cites W2966284335 @default.
• W3176843930 cites W2973136764 @default.
• W3176843930 cites W2974596687 @default.
• W3176843930 cites W2981080108 @default.
• W3176843930 cites W2981246174 @default.
• W3176843930 cites W2986795381 @default.
• W3176843930 cites W2989594843 @default.
• W3176843930 cites W2998104826 @default.
• W3176843930 cites W3003667836 @default.
• W3176843930 cites W3004360475 @default.
• W3176843930 cites W3004876052 @default.
• W3176843930 cites W3012621877 @default.
• W3176843930 cites W3047626512 @default.
• W3176843930 cites W3081067503 @default.
• W3176843930 cites W3082988878 @default.
• W3176843930 cites W3099969702 @default.
• W3176843930 cites W3100255097 @default.
• W3176843930 cites W3102140816 @default.
• W3176843930 cites W3105919389 @default.
• W3176843930 cites W3112714421 @default.
• W3176843930 cites W3114871366 @default.
• W3176843930 cites W3119005585 @default.
• W3176843930 cites W3123789135 @default.
• W3176843930 cites W3133294546 @default.
• W3176843930 cites W4238160257 @default.
• W3176843930 doi "https://doi.org/10.1063/5.0053349" @default.
• W3176843930 hasPublicationYear "2021" @default.
• W3176843930 type Work @default.
• W3176843930 sameAs 3176843930 @default.
• W3176843930 citedByCount "20" @default.
• W3176843930 countsByYear W31768439302021 @default.
• W3176843930 countsByYear W31768439302022 @default.
• W3176843930 countsByYear W31768439302023 @default.
• W3176843930 crossrefType "journal-article" @default.
• W3176843930 hasAuthorship W3176843930A5028149900 @default.
• W3176843930 hasAuthorship W3176843930A5032407979 @default.
• W3176843930 hasAuthorship W3176843930A5037019234 @default.
• W3176843930 hasAuthorship W3176843930A5072774082 @default.
• W3176843930 hasAuthorship W3176843930A5085671233 @default.
• W3176843930 hasBestOaLocation W31768439301 @default.
• W3176843930 hasConcept C105795698 @default.
• W3176843930 hasConcept C108583219 @default.
• W3176843930 hasConcept C11413529 @default.
• W3176843930 hasConcept C117251300 @default.
• W3176843930 hasConcept C119857082 @default.
• W3176843930 hasConcept C121332964 @default.
• W3176843930 hasConcept C132459708 @default.
• W3176843930 hasConcept C134306372 @default.
• W3176843930 hasConcept C154945302 @default.
• W3176843930 hasConcept C202444582 @default.
• W3176843930 hasConcept C27158222 @default.
• W3176843930 hasConcept C33923547 @default.
• W3176843930 hasConcept C41008148 @default.
• W3176843930 hasConcept C50644808 @default.

• next