Ensemble Empirical Mode Decomposition with Adaptive Noise with Convolution Based Gated Recurrent Neural Network: A New Deep Learning Model for South Asian High Intensity Forecasting

Abstract

The intensity variation of the South Asian high (SAH) plays an important role in the formation and extinction of many kinds of mesoscale systems, including tropical cyclones, southwest vortices in the Asian summer monsoon (ASM) region, and the precipitation in the whole Asia Europe region, and the SAH has a vortex symmetrical structure; its dynamic field also has the symmetry form. Not enough previous studies focus on the variation of SAH daily intensity. The purpose of this study is to establish a day-to-day prediction model of the SAH intensity, which can accurately predict not only the interannual variation but also the day-to-day variation of the SAH. Focusing on the summer period when the SAH is the strongest, this paper selects the geopotential height data between 1948 and 2020 from NCEP to construct the SAH intensity datasets. Compared with the classical deep learning methods of various kinds of efficient time series prediction model, we ultimately combine the Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method, which has the ability to deal with the nonlinear and unstable single system, with the Permutation Entropy (PE) method, which can extract the SAH intensity feature of IMF decomposed by CEEMDAN, and the Convolution-based Gated Recurrent Neural Network (ConvGRU) model is used to train, test, and predict the intensity of the SAH. The prediction results show that the combination of CEEMDAN and ConvGRU can have a higher accuracy and more stable prediction ability than the traditional deep learning model. After removing the redundant features in the time series, the prediction accuracy of the SAH intensity is higher than that of the classical model, which proves that the method has good applicability for the prediction of nonlinear systems in the atmosphere.

Polar Vortex Multi-Day Intensity Prediction Relying on New Deep Learning Model: A Combined Convolution Neural Network with Long Short-Term Memory Based on Gaussian Smoothing Method

“…With the renewal and iteration of the neural networks, many spatiotemporal prediction models are constantly proposed and applied to the prediction of various systems in the atmosphere [76][77][78][79][80][81][82][83]. The ensemble DL model is one of the most typical cases.…”

“…Previous studies also have shown that adding mathematical processing methods to the machine learning model will improve the stability and fitting effect of the model to a certain extent. For example, Peng et al [79] investigated that the CEEMDAN + ConvGRU method can accurately predict the intensity of the South Asian high (SAH) and achieved better stability than the traditional machine learning method. The ensemble empirical mode decomposition (EEMD) combined with CNN + LSTM method proposed by [90] also can predict the El Niño index more accurately and stably.…”