Non-linear vector ANN predictor for Earth rotation parameters forecast

TL;DR

This paper introduces a long-term vector prediction method for Earth rotation parameters using an artificial neural network, addressing error growth and enhancing accuracy with nonlinear correction techniques.

Contribution

It presents a novel neural network-based approach for long-term Earth rotation parameter forecasting, utilizing Taken's algorithm and nonlinear correction to improve prediction stability.

Findings

Effective long-term prediction of Earth rotation parameters

Reduction in exponential error growth during forecasting

Enhanced accuracy with nonlinear correction methods

Abstract

Many approaches are developed for the forecasting of the Earth rotation pa-rameters. In this work, we consider long-term vector prediction scheme realized on the artificial neural network. Learning set is formed on basis of the Taken' algorithm. Our approach allows us to obtain the vector of the parameter values and escape the expo-nential growth of the prediction errors. The versions of the prediction enhancement based on the using for nonlinear corrector are discussed.