Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386594858> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4386594858 abstract "Machine learning techniques have seen a tremendous rise in popularity in weather and climate sciences. Data assimilation (DA), which combines observations and numerical models, has great potential to incorporate machine learning and artificial intelligence (ML/AI) techniques. In this paper, we use U-Net, a type of convolutional neutral network (CNN), to predict the ensemble covariances in the Ensemble Kalman Filter (EnKF) algorithm. Using a 2-layer quasi-geostrophic model, U-Nets are trained using data from existing EnKF systems. The U-Nets are then used to predict the flow-dependent covariance matrices in U-Net Kalman Filter (UNetKF) experiments, which are compared to traditional 3-dimensional variational (3DVar) and EnKF methods. The performance of UNetKF can match or exceed that of 3DVar, or EnKF with ensemble sizes up to 80. We also demonstrate that trained U-Nets can be transferred to a higher-resolution model for UNetKF, which again performs competitively to 3DVar and EnKF, particularly for small ensemble sizes." @default.
- W4386594858 created "2023-09-12" @default.
- W4386594858 creator A5014984085 @default.
- W4386594858 date "2023-09-11" @default.
- W4386594858 modified "2023-09-29" @default.
- W4386594858 title "UNetKF: Ensemble U-Net Kalman Filter" @default.
- W4386594858 doi "https://doi.org/10.22541/essoar.169447444.44778188/v1" @default.
- W4386594858 hasPublicationYear "2023" @default.
- W4386594858 type Work @default.
- W4386594858 citedByCount "0" @default.
- W4386594858 crossrefType "posted-content" @default.
- W4386594858 hasAuthorship W4386594858A5014984085 @default.
- W4386594858 hasBestOaLocation W43865948581 @default.
- W4386594858 hasConcept C105795698 @default.
- W4386594858 hasConcept C106131492 @default.
- W4386594858 hasConcept C11413529 @default.
- W4386594858 hasConcept C119857082 @default.
- W4386594858 hasConcept C119898033 @default.
- W4386594858 hasConcept C153294291 @default.
- W4386594858 hasConcept C154945302 @default.
- W4386594858 hasConcept C157286648 @default.
- W4386594858 hasConcept C178650346 @default.
- W4386594858 hasConcept C205649164 @default.
- W4386594858 hasConcept C206833254 @default.
- W4386594858 hasConcept C24552861 @default.
- W4386594858 hasConcept C31972630 @default.
- W4386594858 hasConcept C33923547 @default.
- W4386594858 hasConcept C41008148 @default.
- W4386594858 hasConcept C45942800 @default.
- W4386594858 hasConcept C79334102 @default.
- W4386594858 hasConceptScore W4386594858C105795698 @default.
- W4386594858 hasConceptScore W4386594858C106131492 @default.
- W4386594858 hasConceptScore W4386594858C11413529 @default.
- W4386594858 hasConceptScore W4386594858C119857082 @default.
- W4386594858 hasConceptScore W4386594858C119898033 @default.
- W4386594858 hasConceptScore W4386594858C153294291 @default.
- W4386594858 hasConceptScore W4386594858C154945302 @default.
- W4386594858 hasConceptScore W4386594858C157286648 @default.
- W4386594858 hasConceptScore W4386594858C178650346 @default.
- W4386594858 hasConceptScore W4386594858C205649164 @default.
- W4386594858 hasConceptScore W4386594858C206833254 @default.
- W4386594858 hasConceptScore W4386594858C24552861 @default.
- W4386594858 hasConceptScore W4386594858C31972630 @default.
- W4386594858 hasConceptScore W4386594858C33923547 @default.
- W4386594858 hasConceptScore W4386594858C41008148 @default.
- W4386594858 hasConceptScore W4386594858C45942800 @default.
- W4386594858 hasConceptScore W4386594858C79334102 @default.
- W4386594858 hasLocation W43865948581 @default.
- W4386594858 hasOpenAccess W4386594858 @default.
- W4386594858 hasPrimaryLocation W43865948581 @default.
- W4386594858 hasRelatedWork W1913800847 @default.
- W4386594858 hasRelatedWork W1965898538 @default.
- W4386594858 hasRelatedWork W2101981609 @default.
- W4386594858 hasRelatedWork W2160343576 @default.
- W4386594858 hasRelatedWork W2244214810 @default.
- W4386594858 hasRelatedWork W2386891525 @default.
- W4386594858 hasRelatedWork W2408210013 @default.
- W4386594858 hasRelatedWork W2592766532 @default.
- W4386594858 hasRelatedWork W3015434310 @default.
- W4386594858 hasRelatedWork W3137064266 @default.
- W4386594858 isParatext "false" @default.
- W4386594858 isRetracted "false" @default.
- W4386594858 workType "article" @default.