The Study Based On The Deep Learning For Indian Ocean Dipole (IOD) Index Predication

Indian Ocean Dipole (IOD) is a large-scale physical ocean phenomenon occurring in the Indian Ocean basin. IOD is of great help to predict El Niño-Southern Oscillation (ENSO). Predicting the occurrence of IOD is of great significance to the study of climate change and other major marine phenomena. Generally, the occurrence of IOD is judged by calculating the IOD index. In this paper, the Convolutional Long Short-Term Memory(convLSTM) neural network is used to build the model. The purpose is to combine the prior knowledge of physical ocean and Deep Learning to complete the prediction of IOD. The experimental results show that the fitting degree of the predicted IOD index time series to the real IOD index time series is 81.48%, and the fitting degree is 82.84% after adding the wind field data, and the accuracy is improved after adding the wind field data. IOD index line graph can generally fit the real trend of IOD index, which has a profound impact on the study of IOD phenomenon.