FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212971657> ?p ?o ?g. }

• W4212971657 endingPage "553" @default.
• W4212971657 startingPage "533" @default.
• W4212971657 abstract "Recent progress in the particle filter has made it possible to use it for nonlinear or non-Gaussian data assimilation in high-dimensional systems, but a relatively large ensemble is still needed to outperform the ensemble Kalman filter (EnKF) in terms of accuracy. An alternative ensemble data assimilation method based on deep learning is presented, in which deep neural networks are locally embedded in the EnKF. This method is named the deep learning-ensemble Kalman filter (DL-EnKF). The DL-EnKF analysis ensemble is generated from the DL-EnKF analysis and the EnKF analysis deviation ensemble. The performance of the DL-EnKF is investigated through data assimilation experiments in both perfect and imperfect model scenarios using three versions of the Lorenz 96 model and a deterministic EnKF with an ensemble size of 10. Nonlinearity in data assimilation is controlled by changing the time interval between observations. Results demonstrate that despite being such a small ensemble, the DL-EnKF is superior to the EnKF in terms of accuracy in strongly nonlinear regimes and that the DL-EnKF analysis is more accurate than the output of deep learning because of positive feedback in assimilation cycles. Even if the target of training is an EnKF analysis with a large ensemble or a simulation by an imperfect model, the improvement introduced by the DL-EnKF is not very different from the case where the target of training is the true state." @default.
• W4212971657 created "2022-02-24" @default.
• W4212971657 creator A5041113825 @default.
• W4212971657 creator A5071621302 @default.
• W4212971657 date "2022-01-01" @default.
• W4212971657 modified "2023-10-10" @default.
• W4212971657 title "Nonlinear Data Assimilation by Deep Learning Embedded in an Ensemble Kalman Filter" @default.
• W4212971657 cites W1596195796 @default.
• W4212971657 cites W1896953440 @default.
• W4212971657 cites W1970847893 @default.
• W4212971657 cites W2001250891 @default.
• W4212971657 cites W2016165263 @default.
• W4212971657 cites W2025179796 @default.
• W4212971657 cites W2030774493 @default.
• W4212971657 cites W2034956278 @default.
• W4212971657 cites W2042151453 @default.
• W4212971657 cites W2049013344 @default.
• W4212971657 cites W2084547407 @default.
• W4212971657 cites W2092814042 @default.
• W4212971657 cites W2123940107 @default.
• W4212971657 cites W2127465530 @default.
• W4212971657 cites W2137432135 @default.
• W4212971657 cites W2147119488 @default.
• W4212971657 cites W2150951085 @default.
• W4212971657 cites W2157098139 @default.
• W4212971657 cites W2166317254 @default.
• W4212971657 cites W2173190456 @default.
• W4212971657 cites W2178778907 @default.
• W4212971657 cites W2179860363 @default.
• W4212971657 cites W2183182188 @default.
• W4212971657 cites W2502172102 @default.
• W4212971657 cites W2792452780 @default.
• W4212971657 cites W2809789958 @default.
• W4212971657 cites W2913323966 @default.
• W4212971657 cites W2919115771 @default.
• W4212971657 cites W2936908195 @default.
• W4212971657 cites W2963658076 @default.
• W4212971657 cites W2967254130 @default.
• W4212971657 cites W2976315714 @default.
• W4212971657 cites W2995571120 @default.
• W4212971657 cites W3043265588 @default.
• W4212971657 cites W3080545603 @default.
• W4212971657 cites W3093640818 @default.
• W4212971657 cites W3101082668 @default.
• W4212971657 cites W3101766586 @default.
• W4212971657 cites W3105299400 @default.
• W4212971657 cites W3122436375 @default.
• W4212971657 cites W3123384867 @default.
• W4212971657 cites W3133002925 @default.
• W4212971657 cites W3161808614 @default.
• W4212971657 doi "https://doi.org/10.2151/jmsj.2022-027" @default.
• W4212971657 hasPublicationYear "2022" @default.
• W4212971657 type Work @default.
• W4212971657 citedByCount "2" @default.
• W4212971657 countsByYear W42129716572022 @default.
• W4212971657 crossrefType "journal-article" @default.
• W4212971657 hasAuthorship W4212971657A5041113825 @default.
• W4212971657 hasAuthorship W4212971657A5071621302 @default.
• W4212971657 hasBestOaLocation W42129716571 @default.
• W4212971657 hasConcept C11413529 @default.
• W4212971657 hasConcept C119857082 @default.
• W4212971657 hasConcept C119898033 @default.
• W4212971657 hasConcept C121332964 @default.
• W4212971657 hasConcept C153294291 @default.
• W4212971657 hasConcept C154945302 @default.
• W4212971657 hasConcept C157286648 @default.
• W4212971657 hasConcept C158622935 @default.
• W4212971657 hasConcept C205649164 @default.
• W4212971657 hasConcept C206833254 @default.
• W4212971657 hasConcept C24552861 @default.
• W4212971657 hasConcept C41008148 @default.
• W4212971657 hasConcept C45942800 @default.
• W4212971657 hasConcept C62520636 @default.
• W4212971657 hasConcept C79334102 @default.
• W4212971657 hasConceptScore W4212971657C11413529 @default.
• W4212971657 hasConceptScore W4212971657C119857082 @default.
• W4212971657 hasConceptScore W4212971657C119898033 @default.
• W4212971657 hasConceptScore W4212971657C121332964 @default.
• W4212971657 hasConceptScore W4212971657C153294291 @default.
• W4212971657 hasConceptScore W4212971657C154945302 @default.
• W4212971657 hasConceptScore W4212971657C157286648 @default.
• W4212971657 hasConceptScore W4212971657C158622935 @default.
• W4212971657 hasConceptScore W4212971657C205649164 @default.
• W4212971657 hasConceptScore W4212971657C206833254 @default.
• W4212971657 hasConceptScore W4212971657C24552861 @default.
• W4212971657 hasConceptScore W4212971657C41008148 @default.
• W4212971657 hasConceptScore W4212971657C45942800 @default.
• W4212971657 hasConceptScore W4212971657C62520636 @default.
• W4212971657 hasConceptScore W4212971657C79334102 @default.
• W4212971657 hasIssue "3" @default.
• W4212971657 hasLocation W42129716571 @default.
• W4212971657 hasOpenAccess W4212971657 @default.
• W4212971657 hasPrimaryLocation W42129716571 @default.
• W4212971657 hasRelatedWork W2017755194 @default.
• W4212971657 hasRelatedWork W2160343576 @default.
• W4212971657 hasRelatedWork W2179584279 @default.
• W4212971657 hasRelatedWork W2182570291 @default.
• W4212971657 hasRelatedWork W2240479891 @default.

• next