FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3084045284> ?p ?o ?g. }

• W3084045284 endingPage "110551" @default.
• W3084045284 startingPage "110551" @default.
• W3084045284 abstract "Timely completion of design cycles for complex systems ranging from consumer electronics to hypersonic vehicles relies on rapid simulation-based prototyping. The latter typically involves high-dimensional spaces of possibly correlated control variables (CVs) and quantities of interest (QoIs) with non-Gaussian and possibly multimodal distributions. We develop a model-agnostic, moment-independent global sensitivity analysis (GSA) that relies on differential mutual information to rank the effects of CVs on QoIs. The data requirements of this information-theoretic approach to GSA are met by replacing computationally intensive components of the physics-based model with a deep neural network surrogate. Subsequently, the GSA is used to explain the surrogate predictions, and the surrogate-driven GSA is deployed as an uncertainty quantification emulator to close design loops. Viewed as an uncertainty quantification method for interrogating the surrogate, this framework is compatible with a wide variety of black-box models. We demonstrate that the surrogate-driven mutual information GSA provides useful and distinguishable rankings via a validation step for applications of interest in energy storage. Consequently, our information-theoretic GSA provides an “outer loop” for accelerated product design by identifying the most and least sensitive input directions and performing subsequent optimization over appropriately reduced parameter subspaces." @default.
• W3084045284 created "2020-09-14" @default.
• W3084045284 creator A5007235196 @default.
• W3084045284 creator A5034268630 @default.
• W3084045284 creator A5045079747 @default.
• W3084045284 creator A5049066010 @default.
• W3084045284 date "2021-11-01" @default.
• W3084045284 modified "2023-10-18" @default.
• W3084045284 title "Mutual information for explainable deep learning of multiscale systems" @default.
• W3084045284 cites W1678356000 @default.
• W3084045284 cites W1964404845 @default.
• W3084045284 cites W1976068406 @default.
• W3084045284 cites W1981618598 @default.
• W3084045284 cites W1994080277 @default.
• W3084045284 cites W2002771148 @default.
• W3084045284 cites W2009804339 @default.
• W3084045284 cites W2013062353 @default.
• W3084045284 cites W2014017759 @default.
• W3084045284 cites W2026645785 @default.
• W3084045284 cites W2031724906 @default.
• W3084045284 cites W2034972421 @default.
• W3084045284 cites W2079960826 @default.
• W3084045284 cites W2080315277 @default.
• W3084045284 cites W2092939357 @default.
• W3084045284 cites W2102300987 @default.
• W3084045284 cites W2104930019 @default.
• W3084045284 cites W2115821110 @default.
• W3084045284 cites W2125847307 @default.
• W3084045284 cites W2141771360 @default.
• W3084045284 cites W2149350210 @default.
• W3084045284 cites W2156541178 @default.
• W3084045284 cites W2170468508 @default.
• W3084045284 cites W2196140673 @default.
• W3084045284 cites W2337566500 @default.
• W3084045284 cites W248058805 @default.
• W3084045284 cites W2585285496 @default.
• W3084045284 cites W2626223001 @default.
• W3084045284 cites W2749028154 @default.
• W3084045284 cites W2750261997 @default.
• W3084045284 cites W2770250658 @default.
• W3084045284 cites W2786232134 @default.
• W3084045284 cites W2791399053 @default.
• W3084045284 cites W2811395263 @default.
• W3084045284 cites W2887002214 @default.
• W3084045284 cites W2890968382 @default.
• W3084045284 cites W2899283552 @default.
• W3084045284 cites W2900369848 @default.
• W3084045284 cites W2908541468 @default.
• W3084045284 cites W2908828908 @default.
• W3084045284 cites W2913750233 @default.
• W3084045284 cites W2919958648 @default.
• W3084045284 cites W2921941871 @default.
• W3084045284 cites W2948230027 @default.
• W3084045284 cites W2952155575 @default.
• W3084045284 cites W2964076844 @default.
• W3084045284 cites W2972944294 @default.
• W3084045284 cites W2973325107 @default.
• W3084045284 cites W3006609207 @default.
• W3084045284 cites W3037717442 @default.
• W3084045284 cites W3093223909 @default.
• W3084045284 cites W3104298728 @default.
• W3084045284 cites W3104712395 @default.
• W3084045284 doi "https://doi.org/10.1016/j.jcp.2021.110551" @default.
• W3084045284 hasPublicationYear "2021" @default.
• W3084045284 type Work @default.
• W3084045284 sameAs 3084045284 @default.
• W3084045284 citedByCount "7" @default.
• W3084045284 countsByYear W30840452842020 @default.
• W3084045284 countsByYear W30840452842021 @default.
• W3084045284 countsByYear W30840452842022 @default.
• W3084045284 countsByYear W30840452842023 @default.
• W3084045284 crossrefType "journal-article" @default.
• W3084045284 hasAuthorship W3084045284A5007235196 @default.
• W3084045284 hasAuthorship W3084045284A5034268630 @default.
• W3084045284 hasAuthorship W3084045284A5045079747 @default.
• W3084045284 hasAuthorship W3084045284A5049066010 @default.
• W3084045284 hasBestOaLocation W30840452841 @default.
• W3084045284 hasConcept C119857082 @default.
• W3084045284 hasConcept C12362212 @default.
• W3084045284 hasConcept C124101348 @default.
• W3084045284 hasConcept C126255220 @default.
• W3084045284 hasConcept C127413603 @default.
• W3084045284 hasConcept C131675550 @default.
• W3084045284 hasConcept C152139883 @default.
• W3084045284 hasConcept C154945302 @default.
• W3084045284 hasConcept C158154518 @default.
• W3084045284 hasConcept C17744445 @default.
• W3084045284 hasConcept C199539241 @default.
• W3084045284 hasConcept C21200559 @default.
• W3084045284 hasConcept C24326235 @default.
• W3084045284 hasConcept C2524010 @default.
• W3084045284 hasConcept C32230216 @default.
• W3084045284 hasConcept C33923547 @default.
• W3084045284 hasConcept C41008148 @default.
• W3084045284 hasConcept C80444323 @default.
• W3084045284 hasConceptScore W3084045284C119857082 @default.
• W3084045284 hasConceptScore W3084045284C12362212 @default.
• W3084045284 hasConceptScore W3084045284C124101348 @default.

• next