FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313397958> ?p ?o ?g. }

• W4313397958 abstract "Abstract. We introduce a scalable approach to parametrise the unresolved subgrid-scale of sea-ice dynamics with deep learning techniques. We apply this data-driven approach to a regional sea-ice model that accounts exclusively for dynamical processes with a Maxwell-Elasto-Brittle rheology. Our channel-like model setup is driven by a wave-like wind forcing, which generates examples of sharp transitions between unfractured and fully-fractured sea ice. Using a convolutional U-Net architecture, the parametrising neural network extracts multiscale and anisotropic features and, thus, includes important inductive biases needed for sea-ice dynamics. The neural network is trained to correct all nine model variables at the same time. With the initial and forecast state as input into the neural network, we cast the subgrid-scale parametrisation as model error correction, needed to correct unresolved model dynamics. We test the here-proposed approach in twin experiments, where forecasts of a low-resolution forecast model are corrected towards high-resolution truth states for a forecast lead time of about 10 min. At this lead time, our approach reduces the forecast errors by more than 75 %, averaged over all model variables. The neural network learns hereby a physically-explainable input-to-output relation. Furthermore, cycling the subgrid-scale parametrisation together with the geophysical model improves the short-term forecast up to one hour. We consequently show that neural networks can parametrise the subgrid-scale for sea-ice dynamics. We therefore see this study as an important first step towards hybrid modelling to forecast sea-ice dynamics on an hourly to daily timescale." @default.
• W4313397958 created "2023-01-06" @default.
• W4313397958 creator A5017148161 @default.
• W4313397958 creator A5018511252 @default.
• W4313397958 creator A5018870567 @default.
• W4313397958 creator A5038930505 @default.
• W4313397958 creator A5071447945 @default.
• W4313397958 creator A5073908622 @default.
• W4313397958 creator A5087494328 @default.
• W4313397958 date "2023-01-02" @default.
• W4313397958 modified "2023-10-16" @default.
• W4313397958 title "Deep learning of subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell-Elasto-Brittle rheology" @default.
• W4313397958 doi "https://doi.org/10.5194/egusphere-2022-1342" @default.
• W4313397958 hasPublicationYear "2023" @default.
• W4313397958 type Work @default.
• W4313397958 citedByCount "1" @default.
• W4313397958 countsByYear W43133979582023 @default.
• W4313397958 crossrefType "posted-content" @default.
• W4313397958 hasAuthorship W4313397958A5017148161 @default.
• W4313397958 hasAuthorship W4313397958A5018511252 @default.
• W4313397958 hasAuthorship W4313397958A5018870567 @default.
• W4313397958 hasAuthorship W4313397958A5038930505 @default.
• W4313397958 hasAuthorship W4313397958A5071447945 @default.
• W4313397958 hasAuthorship W4313397958A5073908622 @default.
• W4313397958 hasAuthorship W4313397958A5087494328 @default.
• W4313397958 hasBestOaLocation W43133979581 @default.
• W4313397958 hasConcept C121332964 @default.
• W4313397958 hasConcept C127313418 @default.
• W4313397958 hasConcept C136894858 @default.
• W4313397958 hasConcept C153294291 @default.
• W4313397958 hasConcept C154945302 @default.
• W4313397958 hasConcept C2778755073 @default.
• W4313397958 hasConcept C41008148 @default.
• W4313397958 hasConcept C49204034 @default.
• W4313397958 hasConcept C50644808 @default.
• W4313397958 hasConcept C62520636 @default.
• W4313397958 hasConcept C8058405 @default.
• W4313397958 hasConceptScore W4313397958C121332964 @default.
• W4313397958 hasConceptScore W4313397958C127313418 @default.
• W4313397958 hasConceptScore W4313397958C136894858 @default.
• W4313397958 hasConceptScore W4313397958C153294291 @default.
• W4313397958 hasConceptScore W4313397958C154945302 @default.
• W4313397958 hasConceptScore W4313397958C2778755073 @default.
• W4313397958 hasConceptScore W4313397958C41008148 @default.
• W4313397958 hasConceptScore W4313397958C49204034 @default.
• W4313397958 hasConceptScore W4313397958C50644808 @default.
• W4313397958 hasConceptScore W4313397958C62520636 @default.
• W4313397958 hasConceptScore W4313397958C8058405 @default.
• W4313397958 hasFunder F4320316572 @default.
• W4313397958 hasFunder F4320326256 @default.
• W4313397958 hasLocation W43133979581 @default.
• W4313397958 hasOpenAccess W4313397958 @default.
• W4313397958 hasPrimaryLocation W43133979581 @default.
• W4313397958 hasRelatedWork W1569164921 @default.
• W4313397958 hasRelatedWork W1973272087 @default.
• W4313397958 hasRelatedWork W2173370015 @default.
• W4313397958 hasRelatedWork W2183136027 @default.
• W4313397958 hasRelatedWork W2362200898 @default.
• W4313397958 hasRelatedWork W2386387936 @default.
• W4313397958 hasRelatedWork W2603367389 @default.
• W4313397958 hasRelatedWork W2748952813 @default.
• W4313397958 hasRelatedWork W2899084033 @default.
• W4313397958 hasRelatedWork W3095329480 @default.
• W4313397958 isParatext "false" @default.
• W4313397958 isRetracted "false" @default.
• W4313397958 workType "article" @default.