Tropospheric zenith wet delay prediction with a new hybrid ANN-Gorilla troops optimizer algorithm

Abstract

In recent years, machine learning techniques, especially artificial neural networks (ANN), have been widely applied for engineering problems since they have proven to be a good predictor, especially in accurate weather forecasting applications. The study aims to evaluate the prediction capability of the novel hybrid ANN-GTO (Gorilla Troops Optimizer), which is not applied for predicting the zenith wet delay (ZWD) in the earlier literature, and the developed ANN-GTO has been compared with two training algorithms, namely Levenberg-Marquardt and Bayesian Regularization, the performance of the ANN-GTO has also been compared with improved ANN methods to illustrate the efficiency of ANN-GTO. The results of all the developed models have been compared via performance criteria. Three inputs, such as pressure, temperature, and water vapour pressure (WVP) have been employed for model training and testing purposes. The analysis outcomes have disclosed that all the ANN enhanced with GTO have overachieved the classic ANN and other hybrid ANN models in predicting ZWD.(c) 2023 COSPAR. Published by Elsevier B.V. All rights reserved.