FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037369969> ?p ?o ?g. }

• W3037369969 abstract "Advection-dominated dynamical systems, characterized by partial differential equations, are found in applications ranging from weather forecasting to engineering design where accuracy and robustness are crucial. There has been significant interest in the use of techniques borrowed from machine learning to reduce the computational expense and/or improve the accuracy of predictions for these systems. These rely on the identification of a basis that reduces the dimensionality of the problem and the subsequent use of time series and sequential learning methods to forecast the evolution of the reduced state. Often, however, machine-learned predictions after reduced-basis projection are plagued by issues of stability stemming from incomplete capture of multiscale processes as well as due to error growth for long forecast durations. To address these issues, we have developed a emph{non-autoregressive} time series approach for predicting linear reduced-basis time histories of forward models. In particular, we demonstrate that non-autoregressive counterparts of sequential learning methods such as long short-term memory (LSTM) considerably improve the stability of machine-learned reduced-order models. We evaluate our approach on the inviscid shallow water equations and show that a non-autoregressive variant of the standard LSTM approach that is bidirectional in the PCA components obtains the best accuracy for recreating the nonlinear dynamics of partial observations. Moreover---and critical for many applications of these surrogates---inference times are reduced by three orders of magnitude using our approach, compared with both the equation-based Galerkin projection method and the standard LSTM approach." @default.
• W3037369969 created "2020-07-02" @default.
• W3037369969 creator A5048243433 @default.
• W3037369969 creator A5050542161 @default.
• W3037369969 creator A5068721920 @default.
• W3037369969 date "2020-06-25" @default.
• W3037369969 modified "2023-09-27" @default.
• W3037369969 title "Non-autoregressive time-series methods for stable parametric reduced-order models" @default.
• W3037369969 cites W1631484266 @default.
• W3037369969 cites W2041310345 @default.
• W3037369969 cites W2049753327 @default.
• W3037369969 cites W2064675550 @default.
• W3037369969 cites W2073594627 @default.
• W3037369969 cites W2084547407 @default.
• W3037369969 cites W2095705004 @default.
• W3037369969 cites W2101234009 @default.
• W3037369969 cites W2112823474 @default.
• W3037369969 cites W2143503258 @default.
• W3037369969 cites W2144144709 @default.
• W3037369969 cites W2147414751 @default.
• W3037369969 cites W2151549067 @default.
• W3037369969 cites W2159840341 @default.
• W3037369969 cites W2168090960 @default.
• W3037369969 cites W2462427028 @default.
• W3037369969 cites W2554748665 @default.
• W3037369969 cites W2618068449 @default.
• W3037369969 cites W2738335552 @default.
• W3037369969 cites W2749028154 @default.
• W3037369969 cites W2766298346 @default.
• W3037369969 cites W2794371820 @default.
• W3037369969 cites W2799217725 @default.
• W3037369969 cites W2899283552 @default.
• W3037369969 cites W2913525628 @default.
• W3037369969 cites W2949382160 @default.
• W3037369969 cites W2953410468 @default.
• W3037369969 cites W2963021886 @default.
• W3037369969 cites W2963112935 @default.
• W3037369969 cites W2964059111 @default.
• W3037369969 cites W2971162686 @default.
• W3037369969 cites W2985630280 @default.
• W3037369969 cites W2991023341 @default.
• W3037369969 cites W2998104826 @default.
• W3037369969 cites W3004006062 @default.
• W3037369969 cites W3021544678 @default.
• W3037369969 cites W3104397553 @default.
• W3037369969 cites W3206806480 @default.
• W3037369969 cites W3023071679 @default.
• W3037369969 hasPublicationYear "2020" @default.
• W3037369969 type Work @default.
• W3037369969 sameAs 3037369969 @default.
• W3037369969 citedByCount "0" @default.
• W3037369969 crossrefType "posted-content" @default.
• W3037369969 hasAuthorship W3037369969A5048243433 @default.
• W3037369969 hasAuthorship W3037369969A5050542161 @default.
• W3037369969 hasAuthorship W3037369969A5068721920 @default.
• W3037369969 hasConcept C104317684 @default.
• W3037369969 hasConcept C112972136 @default.
• W3037369969 hasConcept C11413529 @default.
• W3037369969 hasConcept C119857082 @default.
• W3037369969 hasConcept C121332964 @default.
• W3037369969 hasConcept C134306372 @default.
• W3037369969 hasConcept C143724316 @default.
• W3037369969 hasConcept C149782125 @default.
• W3037369969 hasConcept C151406439 @default.
• W3037369969 hasConcept C151730666 @default.
• W3037369969 hasConcept C154945302 @default.
• W3037369969 hasConcept C158622935 @default.
• W3037369969 hasConcept C159877910 @default.
• W3037369969 hasConcept C185592680 @default.
• W3037369969 hasConcept C2776214188 @default.
• W3037369969 hasConcept C28826006 @default.
• W3037369969 hasConcept C33923547 @default.
• W3037369969 hasConcept C41008148 @default.
• W3037369969 hasConcept C55493867 @default.
• W3037369969 hasConcept C62520636 @default.
• W3037369969 hasConcept C63479239 @default.
• W3037369969 hasConcept C86803240 @default.
• W3037369969 hasConcept C93779851 @default.
• W3037369969 hasConceptScore W3037369969C104317684 @default.
• W3037369969 hasConceptScore W3037369969C112972136 @default.
• W3037369969 hasConceptScore W3037369969C11413529 @default.
• W3037369969 hasConceptScore W3037369969C119857082 @default.
• W3037369969 hasConceptScore W3037369969C121332964 @default.
• W3037369969 hasConceptScore W3037369969C134306372 @default.
• W3037369969 hasConceptScore W3037369969C143724316 @default.
• W3037369969 hasConceptScore W3037369969C149782125 @default.
• W3037369969 hasConceptScore W3037369969C151406439 @default.
• W3037369969 hasConceptScore W3037369969C151730666 @default.
• W3037369969 hasConceptScore W3037369969C154945302 @default.
• W3037369969 hasConceptScore W3037369969C158622935 @default.
• W3037369969 hasConceptScore W3037369969C159877910 @default.
• W3037369969 hasConceptScore W3037369969C185592680 @default.
• W3037369969 hasConceptScore W3037369969C2776214188 @default.
• W3037369969 hasConceptScore W3037369969C28826006 @default.
• W3037369969 hasConceptScore W3037369969C33923547 @default.
• W3037369969 hasConceptScore W3037369969C41008148 @default.
• W3037369969 hasConceptScore W3037369969C55493867 @default.
• W3037369969 hasConceptScore W3037369969C62520636 @default.
• W3037369969 hasConceptScore W3037369969C63479239 @default.
• W3037369969 hasConceptScore W3037369969C86803240 @default.

• next