Nowcasting Extreme Weather with Machine Learning Techniques Applied to Different Input Datasets

Abstract

Predicting extreme weather events in a short time period and developing in localized areas, is a challenge. The nowcasting of severe and extreme weather events is an issue for the air traffic management and control because it affects the aviation safety, it determines delays, diversions and higher costs. This work is part of a larger study devoted to nowcast rain and wind speed in the area of Malpensa airport by merging different datasets. We use as reference the weather station of Novara to develop a nowcasting machine learning algorithm which could be reusable in other locations. In this location we have the availability of ground based meteorological sensors, a GNSS receiver, a Radar and lightning detectors. Our analysis shows that the Long Short-Term Memory Encoder Decoder approach is well suited for the nowcasting of meteorological variables. The predictions are based on 4 different datasets configurations providing rain and wind speed nowcast for 1h with a time step of 10 minutes. The results are very promising with extreme wind speed probability of detection higher than 90% and false alarms lower than 2%, and good performance in extreme rain detection for the first 30 minutes.

Keywords: Nowcasting, Machine learning, weather, weather extreme