Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376279928> ?p ?o ?g. }
- W4376279928 endingPage "119106" @default.
- W4376279928 startingPage "119106" @default.
- W4376279928 abstract "El Niño-Southern Oscillation (ENSO) has a profound impact on global climate, and the ability to forecast it effectively over the long term is essential. In recent years, deep learning methods have demonstrated superior prediction outcomes compared to conventional numerical models. However, due to limited observational data, most of these deep learning methods learn information from simulation data derived from physical models, and ensuring the quality of such simulation data can prove challenging. As a result, the models in CMIP5/6 were recombined using genetic algorithms (GAs) to create our training dataset. A deep learning model was then used to learn features from the output of these combined CMIP models so that these physical numerical models can complement each other. To address the issue of inadequate spatiotemporal feature extraction present in many deep learning methods, we devised an ENSO deep learning regression model. An improved self-attention mechanism was introduced into the convolutional LSTM (long short-term memory) network to enable our model to better extract local and global spatiotemporal features. With our method and model, we were able to obtain less erroneous forecast results, and our method surpassed other state-of-the-art deep learning methods in terms of its capability for long-term forecasting." @default.
- W4376279928 created "2023-05-13" @default.
- W4376279928 creator A5016393348 @default.
- W4376279928 creator A5048817987 @default.
- W4376279928 creator A5066102428 @default.
- W4376279928 date "2023-09-01" @default.
- W4376279928 modified "2023-10-11" @default.
- W4376279928 title "Forecasting ENSO using convolutional LSTM network with improved attention mechanism and models recombined by genetic algorithm in CMIP5/6" @default.
- W4376279928 cites W1522985918 @default.
- W4376279928 cites W1665721417 @default.
- W4376279928 cites W1977552403 @default.
- W4376279928 cites W1984788530 @default.
- W4376279928 cites W1985114715 @default.
- W4376279928 cites W1993131108 @default.
- W4376279928 cites W2064675550 @default.
- W4376279928 cites W2081871596 @default.
- W4376279928 cites W2084542919 @default.
- W4376279928 cites W2092497323 @default.
- W4376279928 cites W2157807748 @default.
- W4376279928 cites W2164655924 @default.
- W4376279928 cites W2193503481 @default.
- W4376279928 cites W2308199225 @default.
- W4376279928 cites W2416755734 @default.
- W4376279928 cites W2551911289 @default.
- W4376279928 cites W2560557936 @default.
- W4376279928 cites W2604162004 @default.
- W4376279928 cites W2623586299 @default.
- W4376279928 cites W2768820243 @default.
- W4376279928 cites W2967059064 @default.
- W4376279928 cites W2968862935 @default.
- W4376279928 cites W2973731563 @default.
- W4376279928 cites W2999039443 @default.
- W4376279928 cites W2999484584 @default.
- W4376279928 cites W3025111165 @default.
- W4376279928 cites W3038541442 @default.
- W4376279928 cites W3094067205 @default.
- W4376279928 cites W3095957783 @default.
- W4376279928 cites W3106966053 @default.
- W4376279928 cites W3115080100 @default.
- W4376279928 cites W3122200694 @default.
- W4376279928 cites W3150575809 @default.
- W4376279928 cites W3160192749 @default.
- W4376279928 cites W3162017678 @default.
- W4376279928 cites W3163961661 @default.
- W4376279928 cites W3168685493 @default.
- W4376279928 cites W3192951112 @default.
- W4376279928 cites W3193349278 @default.
- W4376279928 cites W4225288501 @default.
- W4376279928 cites W4287448984 @default.
- W4376279928 cites W4288048318 @default.
- W4376279928 cites W55193983 @default.
- W4376279928 cites W3161934848 @default.
- W4376279928 doi "https://doi.org/10.1016/j.ins.2023.119106" @default.
- W4376279928 hasPublicationYear "2023" @default.
- W4376279928 type Work @default.
- W4376279928 citedByCount "2" @default.
- W4376279928 countsByYear W43762799282023 @default.
- W4376279928 crossrefType "journal-article" @default.
- W4376279928 hasAuthorship W4376279928A5016393348 @default.
- W4376279928 hasAuthorship W4376279928A5048817987 @default.
- W4376279928 hasAuthorship W4376279928A5066102428 @default.
- W4376279928 hasConcept C104317684 @default.
- W4376279928 hasConcept C108583219 @default.
- W4376279928 hasConcept C112313634 @default.
- W4376279928 hasConcept C11413529 @default.
- W4376279928 hasConcept C119857082 @default.
- W4376279928 hasConcept C127716648 @default.
- W4376279928 hasConcept C132651083 @default.
- W4376279928 hasConcept C138885662 @default.
- W4376279928 hasConcept C154945302 @default.
- W4376279928 hasConcept C168754636 @default.
- W4376279928 hasConcept C185592680 @default.
- W4376279928 hasConcept C188082640 @default.
- W4376279928 hasConcept C18903297 @default.
- W4376279928 hasConcept C2776401178 @default.
- W4376279928 hasConcept C41008148 @default.
- W4376279928 hasConcept C41895202 @default.
- W4376279928 hasConcept C55493867 @default.
- W4376279928 hasConcept C81363708 @default.
- W4376279928 hasConcept C86803240 @default.
- W4376279928 hasConceptScore W4376279928C104317684 @default.
- W4376279928 hasConceptScore W4376279928C108583219 @default.
- W4376279928 hasConceptScore W4376279928C112313634 @default.
- W4376279928 hasConceptScore W4376279928C11413529 @default.
- W4376279928 hasConceptScore W4376279928C119857082 @default.
- W4376279928 hasConceptScore W4376279928C127716648 @default.
- W4376279928 hasConceptScore W4376279928C132651083 @default.
- W4376279928 hasConceptScore W4376279928C138885662 @default.
- W4376279928 hasConceptScore W4376279928C154945302 @default.
- W4376279928 hasConceptScore W4376279928C168754636 @default.
- W4376279928 hasConceptScore W4376279928C185592680 @default.
- W4376279928 hasConceptScore W4376279928C188082640 @default.
- W4376279928 hasConceptScore W4376279928C18903297 @default.
- W4376279928 hasConceptScore W4376279928C2776401178 @default.
- W4376279928 hasConceptScore W4376279928C41008148 @default.
- W4376279928 hasConceptScore W4376279928C41895202 @default.
- W4376279928 hasConceptScore W4376279928C55493867 @default.
- W4376279928 hasConceptScore W4376279928C81363708 @default.