Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000537280> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3000537280 endingPage "2196" @default.
- W3000537280 startingPage "2185" @default.
- W3000537280 abstract "Abstract. Over the last couple of years, machine learning parameterizations have emerged as a potential way to improve the representation of subgrid processes in Earth system models (ESMs). So far, all studies were based on the same three-step approach: first a training dataset was created from a high-resolution simulation, then a machine learning algorithm was fitted to this dataset, before the trained algorithm was implemented in the ESM. The resulting online simulations were frequently plagued by instabilities and biases. Here, coupled online learning is proposed as a way to combat these issues. Coupled learning can be seen as a second training stage in which the pretrained machine learning parameterization, specifically a neural network, is run in parallel with a high-resolution simulation. The high-resolution simulation is kept in sync with the neural network-driven ESM through constant nudging. This enables the neural network to learn from the tendencies that the high-resolution simulation would produce if it experienced the states the neural network creates. The concept is illustrated using the Lorenz 96 model, where coupled learning is able to recover the “true” parameterizations. Further, detailed algorithms for the implementation of coupled learning in 3D cloud-resolving models and the super parameterization framework are presented. Finally, outstanding challenges and issues not resolved by this approach are discussed." @default.
- W3000537280 created "2020-01-23" @default.
- W3000537280 creator A5082396379 @default.
- W3000537280 date "2020-05-08" @default.
- W3000537280 modified "2023-10-09" @default.
- W3000537280 title "Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations: general algorithms and Lorenz 96 case study (v1.0)" @default.
- W3000537280 cites W1971365200 @default.
- W3000537280 cites W2015772410 @default.
- W3000537280 cites W2034956278 @default.
- W3000537280 cites W2065339245 @default.
- W3000537280 cites W2103757834 @default.
- W3000537280 cites W2120949479 @default.
- W3000537280 cites W2162152641 @default.
- W3000537280 cites W2495412896 @default.
- W3000537280 cites W2569139521 @default.
- W3000537280 cites W2782714865 @default.
- W3000537280 cites W2802330886 @default.
- W3000537280 cites W2803408063 @default.
- W3000537280 cites W2804943168 @default.
- W3000537280 cites W2808400960 @default.
- W3000537280 cites W2809789958 @default.
- W3000537280 cites W2908155528 @default.
- W3000537280 cites W2911964244 @default.
- W3000537280 cites W2936911364 @default.
- W3000537280 cites W2947753393 @default.
- W3000537280 cites W2957147396 @default.
- W3000537280 cites W2974527409 @default.
- W3000537280 cites W2985916778 @default.
- W3000537280 cites W3007927169 @default.
- W3000537280 cites W3040929669 @default.
- W3000537280 cites W3100642145 @default.
- W3000537280 cites W3105945687 @default.
- W3000537280 cites W3122436375 @default.
- W3000537280 doi "https://doi.org/10.5194/gmd-13-2185-2020" @default.
- W3000537280 hasPublicationYear "2020" @default.
- W3000537280 type Work @default.
- W3000537280 sameAs 3000537280 @default.
- W3000537280 citedByCount "36" @default.
- W3000537280 countsByYear W30005372802020 @default.
- W3000537280 countsByYear W30005372802021 @default.
- W3000537280 countsByYear W30005372802022 @default.
- W3000537280 countsByYear W30005372802023 @default.
- W3000537280 crossrefType "journal-article" @default.
- W3000537280 hasAuthorship W3000537280A5082396379 @default.
- W3000537280 hasBestOaLocation W30005372801 @default.
- W3000537280 hasConcept C11413529 @default.
- W3000537280 hasConcept C119857082 @default.
- W3000537280 hasConcept C126042441 @default.
- W3000537280 hasConcept C154945302 @default.
- W3000537280 hasConcept C17744445 @default.
- W3000537280 hasConcept C199539241 @default.
- W3000537280 hasConcept C2776359362 @default.
- W3000537280 hasConcept C3913047 @default.
- W3000537280 hasConcept C41008148 @default.
- W3000537280 hasConcept C50644808 @default.
- W3000537280 hasConcept C76155785 @default.
- W3000537280 hasConcept C94625758 @default.
- W3000537280 hasConceptScore W3000537280C11413529 @default.
- W3000537280 hasConceptScore W3000537280C119857082 @default.
- W3000537280 hasConceptScore W3000537280C126042441 @default.
- W3000537280 hasConceptScore W3000537280C154945302 @default.
- W3000537280 hasConceptScore W3000537280C17744445 @default.
- W3000537280 hasConceptScore W3000537280C199539241 @default.
- W3000537280 hasConceptScore W3000537280C2776359362 @default.
- W3000537280 hasConceptScore W3000537280C3913047 @default.
- W3000537280 hasConceptScore W3000537280C41008148 @default.
- W3000537280 hasConceptScore W3000537280C50644808 @default.
- W3000537280 hasConceptScore W3000537280C76155785 @default.
- W3000537280 hasConceptScore W3000537280C94625758 @default.
- W3000537280 hasIssue "5" @default.
- W3000537280 hasLocation W30005372801 @default.
- W3000537280 hasLocation W30005372802 @default.
- W3000537280 hasLocation W30005372803 @default.
- W3000537280 hasOpenAccess W3000537280 @default.
- W3000537280 hasPrimaryLocation W30005372801 @default.
- W3000537280 hasRelatedWork W1561022130 @default.
- W3000537280 hasRelatedWork W1878822803 @default.
- W3000537280 hasRelatedWork W1995263003 @default.
- W3000537280 hasRelatedWork W2063547430 @default.
- W3000537280 hasRelatedWork W2234430299 @default.
- W3000537280 hasRelatedWork W2524993630 @default.
- W3000537280 hasRelatedWork W2573584392 @default.
- W3000537280 hasRelatedWork W2607244263 @default.
- W3000537280 hasRelatedWork W4206700937 @default.
- W3000537280 hasRelatedWork W1831690014 @default.
- W3000537280 hasVolume "13" @default.
- W3000537280 isParatext "false" @default.
- W3000537280 isRetracted "false" @default.
- W3000537280 magId "3000537280" @default.
- W3000537280 workType "article" @default.