A GNSS-based weather forecasting approach using Nonlinear Auto Regressive Approach with Exogenous Input (NARX)

Abstract

The rapid variation of precipitation that occurs in the troposphere potentially affects weather conditions. Using GNSS-derived precipitable water vapour (PWV) and external input of rainfall data is useful and beneficial for the prediction of rapid changes of PWV which eventually leads to rainfall prediction in near real time. A nonlinear autoregressive approach with exogenous input (NARX) is an effective approach to statistical forecasting which is used in weather forecasting studies. Furthermore, choosing the most effective algorithm between the Levenberg Marquardt regularization and Bayesian Regularization may be ideal for predicting rainfall. Ten GNSS stations from the Malaysia real-time kinematic network (MyRTKnet) were selected. The selected GNSS stations cover Perak states in Malaysia from 1 January to 31 December 2013. While Obtained results from linear regression model show only 1% correlation between rainfall data and GNSS-derived PWV, comparing the predicted values by NARX networks and actual data show a significant improvement. Addition of GNSS-derived PWV along with daily rainfall data collected from meteorological stations significantly improves the prediction results between 30% and 59% correlation for Bayesian and Levenberg Marquardt regularization, respectively. Furthermore, the Levenberg Marquardt training algorithm may be the most accurate model among the forms of ANN used. Such a significant improvement is favourable to use NARX networks for near real time prediction.