FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891891274> ?p ?o ?g. }

• W2891891274 abstract "This paper presents a detailed comparison between 3 methods for emulating CPU-intensive reactive transport models (RTMs): Gaussian processes (GPs), polynomial chaos expansion (PCE) and deep neural networks (DNNs). Besides direct emulation of the simulated uranium concentration time series, replacing the original RTM by its emulator is also investigated for global sensitivity analysis (GSA), uncertainty propagation (UP) and probabilistic calibration using Markov chain Monte Carlo (MCMC) sampling. The selected DNN is found to be superior to both GPs and PCE in reproducing the input - output behavior of the considered 8-dimensional and 13-dimensional CPU-intensive RTMs. Furthermore, the two used PCE variants: standard PCE and sparse PCE (sPCE) appear to always provide the least accuracy while not differing much in performance. As a consequence of its better emulation capabilities, the used DNN outperforms the two other methods for UP. In addition, DNNs and GPs offer equally good approximations to the true first-order and total-order Sobol sensitivity indices while PCE does somewhat less well. Most surprisingly, despite its superior emulation skills the DNN approach leads to the worst solution of the considered synthetic inverse problem which involves 1224 measurement data with low noise. This apparently contradicting behavior is at least partially due to the small but complicated deterministic noise that affects the DNN-based predictions. Indeed, this complex error structure can drive the emulated solutions far away from the true posterior distribution. Overall, our findings indicate that when the available training set is relatively small (75 - to 500 input - output examples) and fixed beforehand, DNNs can well emulate RTMs but are not suited to emulation-based inversion. In contrast, GPs perform fairly well across all considered tasks: direct emulation, GSA, UP, and inversion." @default.
• W2891891274 created "2018-09-27" @default.
• W2891891274 creator A5039866434 @default.
• W2891891274 creator A5042170410 @default.
• W2891891274 date "2018-09-19" @default.
• W2891891274 modified "2023-09-27" @default.
• W2891891274 title "Emulation of CPU-demanding reactive transport models: comparison of Gaussian processes, polynomial chaos expansion and deep neural networks" @default.
• W2891891274 cites W105972687 @default.
• W2891891274 cites W1538934584 @default.
• W2891891274 cites W1746819321 @default.
• W2891891274 cites W1954090063 @default.
• W2891891274 cites W1988115241 @default.
• W2891891274 cites W1993286134 @default.
• W2891891274 cites W2006037565 @default.
• W2891891274 cites W2038669746 @default.
• W2891891274 cites W2042777693 @default.
• W2891891274 cites W2047476280 @default.
• W2891891274 cites W2049774453 @default.
• W2891891274 cites W2088765131 @default.
• W2891891274 cites W2092047866 @default.
• W2891891274 cites W2094354171 @default.
• W2891891274 cites W2101589741 @default.
• W2891891274 cites W2115172989 @default.
• W2891891274 cites W2116572416 @default.
• W2891891274 cites W2117681582 @default.
• W2891891274 cites W2119179880 @default.
• W2891891274 cites W2127700578 @default.
• W2891891274 cites W2148534890 @default.
• W2891891274 cites W2153859116 @default.
• W2891891274 cites W2167608136 @default.
• W2891891274 cites W2212616210 @default.
• W2891891274 cites W2263291128 @default.
• W2891891274 cites W2271840356 @default.
• W2891891274 cites W2540189295 @default.
• W2891891274 cites W2557332290 @default.
• W2891891274 cites W2587346616 @default.
• W2891891274 cites W2785267058 @default.
• W2891891274 cites W2949338784 @default.
• W2891891274 cites W2995161752 @default.
• W2891891274 cites W3005347330 @default.
• W2891891274 hasPublicationYear "2018" @default.
• W2891891274 type Work @default.
• W2891891274 sameAs 2891891274 @default.
• W2891891274 citedByCount "0" @default.
• W2891891274 crossrefType "posted-content" @default.
• W2891891274 hasAuthorship W2891891274A5039866434 @default.
• W2891891274 hasAuthorship W2891891274A5042170410 @default.
• W2891891274 hasConcept C105795698 @default.
• W2891891274 hasConcept C107673813 @default.
• W2891891274 hasConcept C111350023 @default.
• W2891891274 hasConcept C11413529 @default.
• W2891891274 hasConcept C121332964 @default.
• W2891891274 hasConcept C126255220 @default.
• W2891891274 hasConcept C127413603 @default.
• W2891891274 hasConcept C149810388 @default.
• W2891891274 hasConcept C154945302 @default.
• W2891891274 hasConcept C162324750 @default.
• W2891891274 hasConcept C163716315 @default.
• W2891891274 hasConcept C19499675 @default.
• W2891891274 hasConcept C197656079 @default.
• W2891891274 hasConcept C21200559 @default.
• W2891891274 hasConcept C24326235 @default.
• W2891891274 hasConcept C33923547 @default.
• W2891891274 hasConcept C41008148 @default.
• W2891891274 hasConcept C50522688 @default.
• W2891891274 hasConcept C50644808 @default.
• W2891891274 hasConcept C62520636 @default.
• W2891891274 hasConceptScore W2891891274C105795698 @default.
• W2891891274 hasConceptScore W2891891274C107673813 @default.
• W2891891274 hasConceptScore W2891891274C111350023 @default.
• W2891891274 hasConceptScore W2891891274C11413529 @default.
• W2891891274 hasConceptScore W2891891274C121332964 @default.
• W2891891274 hasConceptScore W2891891274C126255220 @default.
• W2891891274 hasConceptScore W2891891274C127413603 @default.
• W2891891274 hasConceptScore W2891891274C149810388 @default.
• W2891891274 hasConceptScore W2891891274C154945302 @default.
• W2891891274 hasConceptScore W2891891274C162324750 @default.
• W2891891274 hasConceptScore W2891891274C163716315 @default.
• W2891891274 hasConceptScore W2891891274C19499675 @default.
• W2891891274 hasConceptScore W2891891274C197656079 @default.
• W2891891274 hasConceptScore W2891891274C21200559 @default.
• W2891891274 hasConceptScore W2891891274C24326235 @default.
• W2891891274 hasConceptScore W2891891274C33923547 @default.
• W2891891274 hasConceptScore W2891891274C41008148 @default.
• W2891891274 hasConceptScore W2891891274C50522688 @default.
• W2891891274 hasConceptScore W2891891274C50644808 @default.
• W2891891274 hasConceptScore W2891891274C62520636 @default.
• W2891891274 hasLocation W28918912741 @default.
• W2891891274 hasOpenAccess W2891891274 @default.
• W2891891274 hasPrimaryLocation W28918912741 @default.
• W2891891274 hasRelatedWork W2253712742 @default.
• W2891891274 hasRelatedWork W2765384635 @default.
• W2891891274 hasRelatedWork W2786098160 @default.
• W2891891274 hasRelatedWork W2791139006 @default.
• W2891891274 hasRelatedWork W2798751785 @default.
• W2891891274 hasRelatedWork W2799069698 @default.
• W2891891274 hasRelatedWork W2809263290 @default.
• W2891891274 hasRelatedWork W2870050732 @default.
• W2891891274 hasRelatedWork W2890311316 @default.
• W2891891274 hasRelatedWork W2895982930 @default.

• next