A Short-term Evaporation Duct Height Prediction Method Using EMD and Parameter Optimized SVR

Abstract

Evaporation duct often appears in the near ground layer close to the sea surface, and it is an important factor affecting the performance of shore based, ship borne or low altitude airborne radar and communication systems. Mastering the information of evaporation duct in advance can effectively avoid the electromagnetic wave loss caused by the evaporation duct in the atmospheric environment. In this study, a regression algorithm based on empirical mode decomposition (EMD) and support vector regression (SVR) is proposed to solve the prediction problem of evaporation duct height (EDH). This paper introduces a method of extracting the data of EDH series, splits the data of EDH series by EMD in spectrum and trains several instances of support vector regression machine to complete the prediction of each component. In addition, particle swarm optimization (PSO) and its variants are introduced to solve the parameter optimization problem of SVR. The experimental results demonstrate that the EMD strategy and particle swarm optimization strategy are effective to improve the accuracy of the prediction results.