Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135784599> ?p ?o ?g. }
- W3135784599 abstract "Abstract Operational Arctic sea ice forecasts are of crucial importance to science and to society in the Arctic region. Currently, statistical and numerical climate models are widely used to generate the Arctic sea ice forecasts at weather time-scales. Numerical models require near real-time input of relevant environmental conditions consistent with the model equations and they are computationally expensive. In this study, we propose a deep learning approach, namely Convolutional Long Short Term Memory Networks (ConvLSTM), to forecast sea ice in the Barents Sea at weather to sub-seasonal time scales. This is an unsupervised learning approach. It makes use of historical records and it exploits the covariances between different variables, including spatial and temporal relations. With input fields from reanalysis data, we demonstrate that ConvLSTM is able to learn the variability of the Arctic sea ice and can forecast regional sea ice concentration skillfully at weekly to monthly time scales. It preserves the physical consistency between predictors and predictands, and generally outperforms forecasts with climatology, persistence and a statistical model. Based on the known sources of predictability, sensitivity tests with different climate fields as input for learning were performed. The impact of different predictors on the quality of the forecasts are evaluated and we demonstrate that the surface energy budget components have a large impact on the predictability of sea ice at weather time scales. This method is promising to enhance operational Arctic sea ice forecasting in the near future." @default.
- W3135784599 created "2021-03-15" @default.
- W3135784599 creator A5007838729 @default.
- W3135784599 creator A5011984210 @default.
- W3135784599 creator A5052914395 @default.
- W3135784599 creator A5060587774 @default.
- W3135784599 date "2021-03-10" @default.
- W3135784599 modified "2023-10-16" @default.
- W3135784599 title "Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks" @default.
- W3135784599 cites W1485009520 @default.
- W3135784599 cites W1500365110 @default.
- W3135784599 cites W1501513608 @default.
- W3135784599 cites W1859706942 @default.
- W3135784599 cites W1922566919 @default.
- W3135784599 cites W1967722715 @default.
- W3135784599 cites W1991173872 @default.
- W3135784599 cites W2006726025 @default.
- W3135784599 cites W2017093411 @default.
- W3135784599 cites W2038838351 @default.
- W3135784599 cites W2056764457 @default.
- W3135784599 cites W2060172488 @default.
- W3135784599 cites W2064675550 @default.
- W3135784599 cites W2075428128 @default.
- W3135784599 cites W2101926813 @default.
- W3135784599 cites W2105321292 @default.
- W3135784599 cites W2109380865 @default.
- W3135784599 cites W2115421472 @default.
- W3135784599 cites W2121745948 @default.
- W3135784599 cites W2130715829 @default.
- W3135784599 cites W2137235251 @default.
- W3135784599 cites W2144937136 @default.
- W3135784599 cites W2156739270 @default.
- W3135784599 cites W2172807610 @default.
- W3135784599 cites W2175578730 @default.
- W3135784599 cites W2185702922 @default.
- W3135784599 cites W2290960045 @default.
- W3135784599 cites W2342323825 @default.
- W3135784599 cites W2471266319 @default.
- W3135784599 cites W2500487046 @default.
- W3135784599 cites W2518564917 @default.
- W3135784599 cites W2560370080 @default.
- W3135784599 cites W2606554264 @default.
- W3135784599 cites W2607773684 @default.
- W3135784599 cites W2765327719 @default.
- W3135784599 cites W2767264170 @default.
- W3135784599 cites W2774481058 @default.
- W3135784599 cites W2785583251 @default.
- W3135784599 cites W2799323237 @default.
- W3135784599 cites W2890615274 @default.
- W3135784599 cites W2890730486 @default.
- W3135784599 cites W2907362079 @default.
- W3135784599 cites W2910171846 @default.
- W3135784599 cites W2913323966 @default.
- W3135784599 cites W2917158815 @default.
- W3135784599 cites W2919115771 @default.
- W3135784599 cites W2921208939 @default.
- W3135784599 cites W2932744463 @default.
- W3135784599 cites W2942436852 @default.
- W3135784599 cites W2945471725 @default.
- W3135784599 cites W2945951547 @default.
- W3135784599 cites W2951266961 @default.
- W3135784599 cites W2962894061 @default.
- W3135784599 cites W2965187616 @default.
- W3135784599 cites W2973731563 @default.
- W3135784599 cites W2974527409 @default.
- W3135784599 cites W2988687230 @default.
- W3135784599 cites W3003764585 @default.
- W3135784599 cites W3101766586 @default.
- W3135784599 cites W55092961 @default.
- W3135784599 doi "https://doi.org/10.1175/mwr-d-20-0113.1" @default.
- W3135784599 hasPublicationYear "2021" @default.
- W3135784599 type Work @default.
- W3135784599 sameAs 3135784599 @default.
- W3135784599 citedByCount "7" @default.
- W3135784599 countsByYear W31357845992022 @default.
- W3135784599 countsByYear W31357845992023 @default.
- W3135784599 crossrefType "journal-article" @default.
- W3135784599 hasAuthorship W3135784599A5007838729 @default.
- W3135784599 hasAuthorship W3135784599A5011984210 @default.
- W3135784599 hasAuthorship W3135784599A5052914395 @default.
- W3135784599 hasAuthorship W3135784599A5060587774 @default.
- W3135784599 hasBestOaLocation W31357845991 @default.
- W3135784599 hasConcept C105795698 @default.
- W3135784599 hasConcept C111368507 @default.
- W3135784599 hasConcept C127313418 @default.
- W3135784599 hasConcept C134097258 @default.
- W3135784599 hasConcept C136894858 @default.
- W3135784599 hasConcept C149767477 @default.
- W3135784599 hasConcept C153294291 @default.
- W3135784599 hasConcept C154945302 @default.
- W3135784599 hasConcept C161798024 @default.
- W3135784599 hasConcept C170061395 @default.
- W3135784599 hasConcept C194520297 @default.
- W3135784599 hasConcept C197640229 @default.
- W3135784599 hasConcept C205649164 @default.
- W3135784599 hasConcept C2776436953 @default.
- W3135784599 hasConcept C33923547 @default.
- W3135784599 hasConcept C39432304 @default.
- W3135784599 hasConcept C41008148 @default.
- W3135784599 hasConcept C49204034 @default.