Mesoscale vortex trajectory stationary sequence extraction and recurrent neural network prediction method

Abstract

The invention discloses a mesoscale vortex trajectory stationary sequence extraction and recurrent neural network prediction method. The method comprises the following steps: collecting related data and carrying out mathematical statistics; introducing variational mode decomposition applying correlation entropy, searching optimal parameters, and decomposing non-stationary mesoscale vortex propagation trajectory data into K stationary subsequences; establishing an improved multi-step prediction network model based on a double-stage attention recurrent neural network; constructing an improved regularization strategy training model; sequentially sending the decomposed stationary sub-sequence and the multi-feature variable sequence into a multi-step prediction network model, training the model through an improved regularization strategy, respectively predicting the sub-sequences, and finally obtaining a target prediction result. According to the method, prediction research of mesoscale vortex trajectory data is assisted through a satellite height measurement observation technology from the perspective of machine learning, and accurate prediction of mesoscale vortexes has important scientific and application values for understanding propagation and evolution characteristics of the mesoscale vortexes and improving the simulation capability of climate changes.

Description

technical field [0001] The invention relates to a method for extracting a smooth sequence of a mesoscale vortex trajectory and predicting a cyclic neural network, and belongs to the technical field of intelligent information processing and target prediction. Background technique [0002] Mesoscale eddies are ubiquitous in the world's oceans and are an important ocean physical phenomenon. Due to the improvement in temporal availability, resolution and coverage of satellite altimetry data, more and more studies have been conducted on the temporal and spatial distribution and motion characteristics of mesoscale eddies. However, there are few prediction studies based on mesoscale eddy trajectory data. In recent years, research on the prediction of mesoscale eddy propagation trajectory has been gradually carried out. Simulation capabilities are of great scientific and practical significance. [0003] In general, the main methods used for ocean mesoscale forecasting can be divid...

AI Technical Summary

Problems solved by technology

[0004] In the task of multivariate time series prediction, deep learning technology provides an effective, novel and reliable method to improve the prediction accuracy. Challenges: First, multivariate time series data has high dimensions and complex spatial relationships. How to deal with spatial relationships at the same time and at different times is a problem that needs to be solved

Second, multiple time series, some or all of which are correlated to some extent, how to discover and exploit the long-term dependence of the temporal relationship between them is a difficult point

Third, many classical methods mostly solve the single-step forecasting problem, however, in real life, single-step time series forecasting usually does not help because it is difficult to predict what will happen after the multi-step condition

At the same time, in multi-step forecasting, the error will increase with the number of forecast steps, which is more complicated than single-step forecasting

Fourth, the oceanic mesoscale vortex is evolving in both time and space, and is highly unstable, with obvious nonlinear and non-stationary characteristics, which greatly increases the difficulty of prediction

Finally, the difficulty of prediction is that the mesoscale vortex has no significant periodicity, and the moving speed and self-transformation are not fixed, which is also a challenge for the deep learning model of fixed connections.

Images