FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140418716> ?p ?o ?g. }

• W3140418716 abstract "Coupled climate simulations that span several hundred years cannot be run at a high-enough spatial resolution to resolve mesoscale ocean dynamics. Recently, several studies have considered Deep Learning to parameterize subgrid forcing within macroscale ocean equations using data from ocean-only simulations with idealized geometry. We present a stochastic Deep Learning parameterization that is trained on data generated by CM2.6, a high-resolution state-of-the-art coupled climate model. We train a Convolutional Neural Network for the subgrid momentum forcing using macroscale surface velocities from a few selected subdomains with different dynamical regimes. At each location of the coarse grid, rather than predicting a single number for the subgrid momentum forcing, we predict both the mean and standard deviation of a Gaussian probability distribution. This approach requires training our neural network to minimize a negative log-likelihood loss function rather than the Mean Square Error, which has been the standard in applications of Deep Learning to the problem of parameterizations. Each estimate of the conditional mean subgrid forcing is thus associated with an uncertainty estimate–the standard deviation—which will form the basis for a stochastic subgrid parameterization. Offline tests show that our parameterization generalizes well to the global oceans and a climate with increased levels without further training. We then implement our learned stochastic parameterization in an eddy-permitting idealized shallow water model. The implementation is stable and improves some statistics of the flow. Our work demonstrates the potential of combining Deep Learning tools with a probabilistic approach in parameterizing unresolved ocean dynamics." @default.
• W3140418716 created "2021-04-13" @default.
• W3140418716 creator A5032073724 @default.
• W3140418716 creator A5089428149 @default.
• W3140418716 date "2021-09-01" @default.
• W3140418716 modified "2023-10-16" @default.
• W3140418716 title "Stochastic‐Deep Learning Parameterization of Ocean Momentum Forcing" @default.
• W3140418716 cites W1413993273 @default.
• W3140418716 cites W1517713824 @default.
• W3140418716 cites W1903029394 @default.
• W3140418716 cites W1965246719 @default.
• W3140418716 cites W1969534246 @default.
• W3140418716 cites W1987259268 @default.
• W3140418716 cites W1988868855 @default.
• W3140418716 cites W1991467573 @default.
• W3140418716 cites W2000152887 @default.
• W3140418716 cites W2012119251 @default.
• W3140418716 cites W2013380149 @default.
• W3140418716 cites W2018925825 @default.
• W3140418716 cites W2021047795 @default.
• W3140418716 cites W2044901812 @default.
• W3140418716 cites W2050962398 @default.
• W3140418716 cites W2062712788 @default.
• W3140418716 cites W2064000876 @default.
• W3140418716 cites W2072699218 @default.
• W3140418716 cites W2074447412 @default.
• W3140418716 cites W2100353119 @default.
• W3140418716 cites W2103137128 @default.
• W3140418716 cites W2103757834 @default.
• W3140418716 cites W2109005173 @default.
• W3140418716 cites W2112584277 @default.
• W3140418716 cites W2147087715 @default.
• W3140418716 cites W2148927104 @default.
• W3140418716 cites W2151268634 @default.
• W3140418716 cites W2157935243 @default.
• W3140418716 cites W2165849387 @default.
• W3140418716 cites W2167470758 @default.
• W3140418716 cites W2176979713 @default.
• W3140418716 cites W2237826530 @default.
• W3140418716 cites W2342125189 @default.
• W3140418716 cites W2515622298 @default.
• W3140418716 cites W2585005339 @default.
• W3140418716 cites W2601369622 @default.
• W3140418716 cites W2747354436 @default.
• W3140418716 cites W2892142020 @default.
• W3140418716 cites W2897763799 @default.
• W3140418716 cites W2908155528 @default.
• W3140418716 cites W2919728436 @default.
• W3140418716 cites W2966184765 @default.
• W3140418716 cites W2973091672 @default.
• W3140418716 cites W2974527409 @default.
• W3140418716 cites W3007927169 @default.
• W3140418716 cites W3040129451 @default.
• W3140418716 cites W3047626512 @default.
• W3140418716 cites W3048932873 @default.
• W3140418716 cites W3082908155 @default.
• W3140418716 cites W3092043406 @default.
• W3140418716 cites W3095163478 @default.
• W3140418716 cites W3105945687 @default.
• W3140418716 cites W3133270374 @default.
• W3140418716 cites W4231178963 @default.
• W3140418716 doi "https://doi.org/10.1029/2021ms002534" @default.
• W3140418716 hasPublicationYear "2021" @default.
• W3140418716 type Work @default.
• W3140418716 sameAs 3140418716 @default.
• W3140418716 citedByCount "24" @default.
• W3140418716 countsByYear W31404187162021 @default.
• W3140418716 countsByYear W31404187162022 @default.
• W3140418716 countsByYear W31404187162023 @default.
• W3140418716 crossrefType "journal-article" @default.
• W3140418716 hasAuthorship W3140418716A5032073724 @default.
• W3140418716 hasAuthorship W3140418716A5089428149 @default.
• W3140418716 hasBestOaLocation W31404187161 @default.
• W3140418716 hasConcept C10138342 @default.
• W3140418716 hasConcept C105795698 @default.
• W3140418716 hasConcept C111368507 @default.
• W3140418716 hasConcept C119857082 @default.
• W3140418716 hasConcept C121332964 @default.
• W3140418716 hasConcept C127313418 @default.
• W3140418716 hasConcept C132651083 @default.
• W3140418716 hasConcept C153294291 @default.
• W3140418716 hasConcept C154945302 @default.
• W3140418716 hasConcept C162324750 @default.
• W3140418716 hasConcept C163716315 @default.
• W3140418716 hasConcept C168754636 @default.
• W3140418716 hasConcept C187599188 @default.
• W3140418716 hasConcept C197115733 @default.
• W3140418716 hasConcept C22679943 @default.
• W3140418716 hasConcept C33923547 @default.
• W3140418716 hasConcept C40382383 @default.
• W3140418716 hasConcept C41008148 @default.
• W3140418716 hasConcept C49204034 @default.
• W3140418716 hasConcept C49937458 @default.
• W3140418716 hasConcept C50644808 @default.
• W3140418716 hasConcept C60718061 @default.
• W3140418716 hasConcept C62520636 @default.
• W3140418716 hasConcept C7228185 @default.
• W3140418716 hasConceptScore W3140418716C10138342 @default.
• W3140418716 hasConceptScore W3140418716C105795698 @default.
• W3140418716 hasConceptScore W3140418716C111368507 @default.

• next