Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211717525> ?p ?o ?g. }
- W3211717525 endingPage "13167" @default.
- W3211717525 startingPage "13149" @default.
- W3211717525 abstract "Abstract Data assimilation techniques are widely used to predict complex dynamical systems with uncertainties, based on time-series observation data. Error covariance matrices modeling is an important element in data assimilation algorithms which can considerably impact the forecasting accuracy. The estimation of these covariances, which usually relies on empirical assumptions and physical constraints, is often imprecise and computationally expensive, especially for systems of large dimensions. In this work, we propose a data-driven approach based on long short term memory (LSTM) recurrent neural networks (RNN) to improve both the accuracy and the efficiency of observation covariance specification in data assimilation for dynamical systems. Learning the covariance matrix from observed/simulated time-series data, the proposed approach does not require any knowledge or assumption about prior error distribution, unlike classical posterior tuning methods. We have compared the novel approach with two state-of-the-art covariance tuning algorithms, namely DI01 and D05, first in a Lorenz dynamical system and then in a 2D shallow water twin experiments framework with different covariance parameterization using ensemble assimilation. This novel method shows significant advantages in observation covariance specification, assimilation accuracy, and computational efficiency." @default.
- W3211717525 created "2021-11-22" @default.
- W3211717525 creator A5003086539 @default.
- W3211717525 creator A5032850530 @default.
- W3211717525 date "2021-12-20" @default.
- W3211717525 modified "2023-10-01" @default.
- W3211717525 title "Observation error covariance specification in dynamical systems for data assimilation using recurrent neural networks" @default.
- W3211717525 cites W1920122307 @default.
- W3211717525 cites W2003191279 @default.
- W3211717525 cites W2009121338 @default.
- W3211717525 cites W2030774493 @default.
- W3211717525 cites W2032968562 @default.
- W3211717525 cites W2037416330 @default.
- W3211717525 cites W2064675550 @default.
- W3211717525 cites W2071453418 @default.
- W3211717525 cites W2086178219 @default.
- W3211717525 cites W2094746776 @default.
- W3211717525 cites W2099072159 @default.
- W3211717525 cites W2107878631 @default.
- W3211717525 cites W2113986884 @default.
- W3211717525 cites W2122801340 @default.
- W3211717525 cites W2126858228 @default.
- W3211717525 cites W2149205139 @default.
- W3211717525 cites W2151701120 @default.
- W3211717525 cites W2156453633 @default.
- W3211717525 cites W2157098139 @default.
- W3211717525 cites W2165889544 @default.
- W3211717525 cites W2166317254 @default.
- W3211717525 cites W2170791744 @default.
- W3211717525 cites W2172819965 @default.
- W3211717525 cites W2563710438 @default.
- W3211717525 cites W2604331540 @default.
- W3211717525 cites W2740686118 @default.
- W3211717525 cites W2766677625 @default.
- W3211717525 cites W2766736793 @default.
- W3211717525 cites W2773505103 @default.
- W3211717525 cites W2886967127 @default.
- W3211717525 cites W2890955732 @default.
- W3211717525 cites W2900304936 @default.
- W3211717525 cites W2963816767 @default.
- W3211717525 cites W2964398453 @default.
- W3211717525 cites W2987451530 @default.
- W3211717525 cites W3005984531 @default.
- W3211717525 cites W3023176188 @default.
- W3211717525 cites W3028069279 @default.
- W3211717525 cites W3039903604 @default.
- W3211717525 cites W3080969264 @default.
- W3211717525 cites W3090859965 @default.
- W3211717525 cites W3093625747 @default.
- W3211717525 cites W3109183328 @default.
- W3211717525 cites W3112787034 @default.
- W3211717525 cites W3123384867 @default.
- W3211717525 cites W3128140182 @default.
- W3211717525 cites W3131584643 @default.
- W3211717525 cites W3133002925 @default.
- W3211717525 cites W3166728214 @default.
- W3211717525 cites W3170825342 @default.
- W3211717525 cites W3177046878 @default.
- W3211717525 cites W4233734028 @default.
- W3211717525 cites W4241542937 @default.
- W3211717525 doi "https://doi.org/10.1007/s00521-021-06739-4" @default.
- W3211717525 hasPublicationYear "2021" @default.
- W3211717525 type Work @default.
- W3211717525 sameAs 3211717525 @default.
- W3211717525 citedByCount "8" @default.
- W3211717525 countsByYear W32117175252022 @default.
- W3211717525 countsByYear W32117175252023 @default.
- W3211717525 crossrefType "journal-article" @default.
- W3211717525 hasAuthorship W3211717525A5003086539 @default.
- W3211717525 hasAuthorship W3211717525A5032850530 @default.
- W3211717525 hasBestOaLocation W32117175251 @default.
- W3211717525 hasConcept C105795698 @default.
- W3211717525 hasConcept C11413529 @default.
- W3211717525 hasConcept C119857082 @default.
- W3211717525 hasConcept C121332964 @default.
- W3211717525 hasConcept C137250428 @default.
- W3211717525 hasConcept C151406439 @default.
- W3211717525 hasConcept C153294291 @default.
- W3211717525 hasConcept C178650346 @default.
- W3211717525 hasConcept C185142706 @default.
- W3211717525 hasConcept C24552861 @default.
- W3211717525 hasConcept C33923547 @default.
- W3211717525 hasConcept C41008148 @default.
- W3211717525 hasConcept C62520636 @default.
- W3211717525 hasConcept C79379906 @default.
- W3211717525 hasConcept C83042196 @default.
- W3211717525 hasConceptScore W3211717525C105795698 @default.
- W3211717525 hasConceptScore W3211717525C11413529 @default.
- W3211717525 hasConceptScore W3211717525C119857082 @default.
- W3211717525 hasConceptScore W3211717525C121332964 @default.
- W3211717525 hasConceptScore W3211717525C137250428 @default.
- W3211717525 hasConceptScore W3211717525C151406439 @default.
- W3211717525 hasConceptScore W3211717525C153294291 @default.
- W3211717525 hasConceptScore W3211717525C178650346 @default.
- W3211717525 hasConceptScore W3211717525C185142706 @default.
- W3211717525 hasConceptScore W3211717525C24552861 @default.
- W3211717525 hasConceptScore W3211717525C33923547 @default.
- W3211717525 hasConceptScore W3211717525C41008148 @default.