Abstract In this paper, the China’s first global ocean Climate Data Records (CDRs) are used to analyze and predict the sea level changes in the Yellow Sea with obvious seasonal changes. Based on the singular spectrum analysis (SSA) method, the spatiotemporal and time series of sea level anomalies (SLAs) in the Yellow Sea are decomposed and de-noised. Then the long short-term memory (LSTM) neural network is combined with the SSA to establish the SSA-LSTM combined model to predict the sea level trends of the Yellow Sea. Compared with the traditional methods, the prediction accuracy of SSA-LSTM combined model is significantly improved with minimum 35.04 mm RMSE values for the SLA time series prediction. For the one-year prediction of spatiotemporal series of SLA, the minimum RMSE values are only 19.68 mm. The law of spatial and temporal differentiation of the sea level change in the Yellow Sea is also analyzed by temporal empirical orthogonal function. It is found that the sea level trend of the Yellow Sea is highly consistent and significantly related to the season and latitude. According to the SSA-LSTM combined model, the sea level rise rate of the Yellow Sea will remain at 3.65 ± 0.79 mm/year in the next ten years.
Regional sea level changes prediction integrated with singular spectrum analysis and long-short-term memory network
Advances in Space Research ; 68 , 11 ; 4534-4543
2021-08-12
10 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
A Short-Term Traffic Flow Prediction Method Based on Long Short-Term Memory Network
British Library Conference Proceedings | 2019
|ANALYSIS AND COMPARISON OF LONG SHORT-TERM MEMORY NETWORKS SHORT-TERM TRAFFIC PREDICTION PERFORMANCE
DOAJ | 2020
|Transportation Research Record | 2022
|Long short term memory for driver intent prediction
IEEE | 2017
|