Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157723780> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3157723780 endingPage "012029" @default.
- W3157723780 startingPage "012029" @default.
- W3157723780 abstract "Abstract Sea Surface Temperature (SST) plays an important role in marine ecology. SST prediction raises considerable attention in ocean-related fields. Recently, deep learning models are widely used in SST prediction, but it is not easy to obtain optimal prediction results using historical observation data directly. More than temporal information, SST data also contains other features, such as trend, periodicity and disturbance. In this paper, we proposed a Multi-Channel LSTM (MC-LSTM) model to improve SST prediction. Firstly, a wavelet transform is used to decompose time-sequence data into multiple sequences representing trend, period and disturbance respectively. Secondly, we use multiple LSTM channels to train these data in parallel, and then obtain the combined prediction results. MC-LSTM can predict Sea surface temperature only by historical SST data, without the help of other spatial and climatic information, so it is easy to get the data. Compared with the direct use of LSTM for prediction, MC-LSTM can improve the prediction accuracy by 26%." @default.
- W3157723780 created "2021-05-10" @default.
- W3157723780 creator A5046728432 @default.
- W3157723780 creator A5059331441 @default.
- W3157723780 date "2021-04-01" @default.
- W3157723780 modified "2023-10-11" @default.
- W3157723780 title "A Multi-Channel LSTM Model for Sea Surface Temperature Prediction" @default.
- W3157723780 cites W1985864871 @default.
- W3157723780 cites W2064675550 @default.
- W3157723780 cites W2132984323 @default.
- W3157723780 cites W2594584909 @default.
- W3157723780 cites W2778580105 @default.
- W3157723780 cites W3001611209 @default.
- W3157723780 cites W3093070619 @default.
- W3157723780 doi "https://doi.org/10.1088/1742-6596/1880/1/012029" @default.
- W3157723780 hasPublicationYear "2021" @default.
- W3157723780 type Work @default.
- W3157723780 sameAs 3157723780 @default.
- W3157723780 citedByCount "1" @default.
- W3157723780 countsByYear W31577237802023 @default.
- W3157723780 crossrefType "journal-article" @default.
- W3157723780 hasAuthorship W3157723780A5046728432 @default.
- W3157723780 hasAuthorship W3157723780A5059331441 @default.
- W3157723780 hasBestOaLocation W31577237801 @default.
- W3157723780 hasConcept C127162648 @default.
- W3157723780 hasConcept C127313418 @default.
- W3157723780 hasConcept C134097258 @default.
- W3157723780 hasConcept C153180895 @default.
- W3157723780 hasConcept C154945302 @default.
- W3157723780 hasConcept C2778112365 @default.
- W3157723780 hasConcept C31258907 @default.
- W3157723780 hasConcept C41008148 @default.
- W3157723780 hasConcept C49204034 @default.
- W3157723780 hasConcept C54355233 @default.
- W3157723780 hasConcept C86803240 @default.
- W3157723780 hasConceptScore W3157723780C127162648 @default.
- W3157723780 hasConceptScore W3157723780C127313418 @default.
- W3157723780 hasConceptScore W3157723780C134097258 @default.
- W3157723780 hasConceptScore W3157723780C153180895 @default.
- W3157723780 hasConceptScore W3157723780C154945302 @default.
- W3157723780 hasConceptScore W3157723780C2778112365 @default.
- W3157723780 hasConceptScore W3157723780C31258907 @default.
- W3157723780 hasConceptScore W3157723780C41008148 @default.
- W3157723780 hasConceptScore W3157723780C49204034 @default.
- W3157723780 hasConceptScore W3157723780C54355233 @default.
- W3157723780 hasConceptScore W3157723780C86803240 @default.
- W3157723780 hasIssue "1" @default.
- W3157723780 hasLocation W31577237801 @default.
- W3157723780 hasOpenAccess W3157723780 @default.
- W3157723780 hasPrimaryLocation W31577237801 @default.
- W3157723780 hasRelatedWork W1991420611 @default.
- W3157723780 hasRelatedWork W2020822748 @default.
- W3157723780 hasRelatedWork W2100280008 @default.
- W3157723780 hasRelatedWork W2112284452 @default.
- W3157723780 hasRelatedWork W2118811314 @default.
- W3157723780 hasRelatedWork W2149938466 @default.
- W3157723780 hasRelatedWork W2353357840 @default.
- W3157723780 hasRelatedWork W3081257409 @default.
- W3157723780 hasRelatedWork W4285010679 @default.
- W3157723780 hasRelatedWork W4382288843 @default.
- W3157723780 hasVolume "1880" @default.
- W3157723780 isParatext "false" @default.
- W3157723780 isRetracted "false" @default.
- W3157723780 magId "3157723780" @default.
- W3157723780 workType "article" @default.