Fog Prediction for Road Traffic Safety in a Coastal Desert Region: Improvement of Nowcasting Skills by the Machine-Learning Approach

Abstract

A new model for nowcasting fog events in the coastal desert area of Dubai is presented, based on a machine-learning algorithm—decision-tree induction. In the investigated region high frequency observations from automatic weather stations were utilized as a database for the analysis of useful patterns. The induced decision trees yield for the first six forecasting hours increased prediction skill when compared to the coupled Weather Research and Forecasting (WRF) model and the PAFOG fog model (Bartok et al., Boundary-Layer Meteorol 145:485–506, 2012). The decision tree results were further improved by integrating the output of the coupled numerical fog forecasting models in the training database of the decision tree. With this treatment, the statistical quality measures, i.e. the probability of detection, the false alarm ratio, and the Gilbert’s skill score, achieved values of 0.88, 0.19, and 0.69, respectively. From these results we conclude that the best fog forecast in the Dubai region is obtained by applying for the first six forecast hours the newly-developed machine-learning algorithm, while for forecast times exceeding 6 h the coupled numerical models are the best choice.