Abstract
Abstract
To solve the problem of the difficulty in selecting multi-parameter features of the ocean and the lack of power of traditional time-series prediction models in predicting ocean data, an ocean time-series prediction GRU model based on the Borutashap algorithm, and a hybrid multivariate empirical modal decomposition is proposed to predict multivariate in this paper. The feature selection of multi-feature ocean data is carried out by the Borutashap algorithm based on the XG-boost model, then the selected data are decomposed by multi-modal decomposition, and the data are reconstructed to get the high-frequency and low-frequency components, and the trend term components by Permutation Entropy, and finally the high-frequency and low-frequency components and the trend term are respectively brought into the GRU network and the prediction is summed up to get the final result. In this paper, the model’s effectiveness is verified by ablation experiments and compared with other feature selection models and classical time series prediction models, the results show that the model has a better prediction effect.
Funder
Hebei Natural Science Foundation
National Natural Science Foundation of China
S&T Program of Hebei
Reference26 articles.
1. Researching progress and application status of eutrophication evaluation method of seawater;Xiaojuan;Advances in Earth Science,2018
2. Temporal and spatial distribution of red tide outbreaks in the Yangtze River Estuary and adjacent waters, China;Liu;Marine Pollution Bulletin,2013
3. Dissolved organic matter (DOM) released by phytoplankton in the contemporary and future ocean;Thornton;Eur. J. Phycol.,2014