Open AccessForecasting tropospheric wet delay using LSTM neural network
Author(s) -
Samuel Ogunjo,
Joseph Babatunde Dada,
O.J. Ajayi
Publication year - 2022
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/993/1/012024
Subject(s) - troposphere , artificial neural network , environmental science , meteorology , term (time) , water vapor , computer science , artificial intelligence , geography , physics , quantum mechanics
Tropospheric wet delay is a critical factor in radio communication. Accurate estimation of the wet delay is difficult due to the variability in water vapour. In this study, we aim to model and predict tropospheric wet delay over four tropical locations using Long Short-Term Memory (LSTM) neural network. Results obtained in this study showed RMSE and MAE within the range 18.96–21.16 and 14.08–16.38 respectively. LSTM model was able to capture the different regimes of wet delays in each of the locations under consideration. This approach can significantly improve link budget and planning within tropical regions.