FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224993707> ?p ?o ?g. }

• W4224993707 endingPage "1991" @default.
• W4224993707 startingPage "1977" @default.
• W4224993707 abstract "Abstract Remote sensing data play a critical role in improving numerical weather prediction (NWP). However, the physical principles of radiation dictate that data voids frequently exist in physical space (e.g., subcloud area for satellite infrared radiance or no-precipitation region for radar reflectivity). Such data gaps impair the accuracy of initial conditions derived from data assimilation (DA), which has a negative impact on NWP. We use the barotropic vorticity equation to demonstrate the potential of deep learning augmented data assimilation (DDA), which involves reconstructing spatially complete pseudo-observation fields from incomplete observations and using them for DA. By training a convolutional autoencoder (CAE) with a long simulation at a coarse “forecast” resolution (T63), we obtained a deep learning approximation of the “reconstruction operator,” which maps spatially incomplete observations to a model state with full spatial coverage and resolution. The CAE was applied to an incomplete streamfunction observation (∼30% missing) from a high-resolution benchmark simulation and demonstrated satisfactory reconstruction performance, even when only very sparse (1/16 of T63 grid density) observations were used as input. When only spatially incomplete observations are used, the analysis fields obtained from ensemble square root filter (EnSRF) assimilation exhibit significant error. However, in DDA, when EnSRF takes in the combined data from the incomplete observations and CAE reconstruction, analysis error reduces significantly. Such gains are more pronounced with sparse observation and small ensemble size because the DDA analysis is much less sensitive to observation density and ensemble size than the conventional DA analysis, which is based solely on incomplete observations. Significance Statement Data assimilation plays a critical role in improving the skills of modern numerical weather prediction by establishing accurate initial conditions. However, unobservable regions are common in observation data, particularly those derived from remote sensing. The nonlinear relationship between data from observable regions and the physical state of unobservable regions may impede DA efficiency. As a result, we propose that deep learning be used to improve data assimilation in such cases by reconstructing a spatially complete first guess of the physical state with deep learning and then applying data assimilation to the reconstructed field. Such deep learning augmentation is found effective in improving the accuracy of data assimilation, especially for sparse observation and small ensemble size." @default.
• W4224993707 created "2022-04-28" @default.
• W4224993707 creator A5029525859 @default.
• W4224993707 creator A5043773772 @default.
• W4224993707 creator A5071969820 @default.
• W4224993707 creator A5088319420 @default.
• W4224993707 date "2022-08-01" @default.
• W4224993707 modified "2023-10-01" @default.
• W4224993707 title "Deep Learning Augmented Data Assimilation: Reconstructing Missing Information with Convolutional Autoencoders" @default.
• W4224993707 cites W1970847893 @default.
• W4224993707 cites W2030774493 @default.
• W4224993707 cites W2038418888 @default.
• W4224993707 cites W2079854164 @default.
• W4224993707 cites W2113453022 @default.
• W4224993707 cites W2122853097 @default.
• W4224993707 cites W2135114661 @default.
• W4224993707 cites W2147119488 @default.
• W4224993707 cites W2160174901 @default.
• W4224993707 cites W2169888267 @default.
• W4224993707 cites W2174784159 @default.
• W4224993707 cites W2179860363 @default.
• W4224993707 cites W2180946617 @default.
• W4224993707 cites W2769078202 @default.
• W4224993707 cites W2789462704 @default.
• W4224993707 cites W2911349806 @default.
• W4224993707 cites W2917360514 @default.
• W4224993707 cites W2946188186 @default.
• W4224993707 cites W3004495293 @default.
• W4224993707 cites W3021602575 @default.
• W4224993707 cites W3039903604 @default.
• W4224993707 cites W3045384300 @default.
• W4224993707 cites W3091960939 @default.
• W4224993707 cites W3099724835 @default.
• W4224993707 cites W3102846047 @default.
• W4224993707 cites W3126142687 @default.
• W4224993707 cites W3138422838 @default.
• W4224993707 cites W4230214869 @default.
• W4224993707 doi "https://doi.org/10.1175/mwr-d-21-0288.1" @default.
• W4224993707 hasPublicationYear "2022" @default.
• W4224993707 type Work @default.
• W4224993707 citedByCount "3" @default.
• W4224993707 countsByYear W42249937072022 @default.
• W4224993707 countsByYear W42249937072023 @default.
• W4224993707 crossrefType "journal-article" @default.
• W4224993707 hasAuthorship W4224993707A5029525859 @default.
• W4224993707 hasAuthorship W4224993707A5043773772 @default.
• W4224993707 hasAuthorship W4224993707A5071969820 @default.
• W4224993707 hasAuthorship W4224993707A5088319420 @default.
• W4224993707 hasBestOaLocation W42249937072 @default.
• W4224993707 hasConcept C101738243 @default.
• W4224993707 hasConcept C108583219 @default.
• W4224993707 hasConcept C11413529 @default.
• W4224993707 hasConcept C119857082 @default.
• W4224993707 hasConcept C127313418 @default.
• W4224993707 hasConcept C13280743 @default.
• W4224993707 hasConcept C147947694 @default.
• W4224993707 hasConcept C153294291 @default.
• W4224993707 hasConcept C154945302 @default.
• W4224993707 hasConcept C185798385 @default.
• W4224993707 hasConcept C205649164 @default.
• W4224993707 hasConcept C23690007 @default.
• W4224993707 hasConcept C24552861 @default.
• W4224993707 hasConcept C41008148 @default.
• W4224993707 hasConcept C62649853 @default.
• W4224993707 hasConcept C9357733 @default.
• W4224993707 hasConceptScore W4224993707C101738243 @default.
• W4224993707 hasConceptScore W4224993707C108583219 @default.
• W4224993707 hasConceptScore W4224993707C11413529 @default.
• W4224993707 hasConceptScore W4224993707C119857082 @default.
• W4224993707 hasConceptScore W4224993707C127313418 @default.
• W4224993707 hasConceptScore W4224993707C13280743 @default.
• W4224993707 hasConceptScore W4224993707C147947694 @default.
• W4224993707 hasConceptScore W4224993707C153294291 @default.
• W4224993707 hasConceptScore W4224993707C154945302 @default.
• W4224993707 hasConceptScore W4224993707C185798385 @default.
• W4224993707 hasConceptScore W4224993707C205649164 @default.
• W4224993707 hasConceptScore W4224993707C23690007 @default.
• W4224993707 hasConceptScore W4224993707C24552861 @default.
• W4224993707 hasConceptScore W4224993707C41008148 @default.
• W4224993707 hasConceptScore W4224993707C62649853 @default.
• W4224993707 hasConceptScore W4224993707C9357733 @default.
• W4224993707 hasIssue "8" @default.
• W4224993707 hasLocation W42249937071 @default.
• W4224993707 hasLocation W42249937072 @default.
• W4224993707 hasOpenAccess W4224993707 @default.
• W4224993707 hasPrimaryLocation W42249937071 @default.
• W4224993707 hasRelatedWork W1488071885 @default.
• W4224993707 hasRelatedWork W1661652877 @default.
• W4224993707 hasRelatedWork W2009506495 @default.
• W4224993707 hasRelatedWork W2025500520 @default.
• W4224993707 hasRelatedWork W2166103570 @default.
• W4224993707 hasRelatedWork W2964402443 @default.
• W4224993707 hasRelatedWork W3083734595 @default.
• W4224993707 hasRelatedWork W4230321606 @default.
• W4224993707 hasRelatedWork W48354229 @default.
• W4224993707 hasRelatedWork W833739244 @default.
• W4224993707 hasVolume "150" @default.
• W4224993707 isParatext "false" @default.

• next