ALBERT

Description: Sudden stratospheric warmings are prominent examples of dynamical wave–mean flow interactions in the Arctic stratosphere during Northern Hemisphere winter. They are characterized by a strong temperature increase on time scales of a few days and a strongly disturbed stratospheric vortex. This work investigates a wide class of supervised learning methods with respect to their ability to classify stratospheric warmings, using temperature anomalies from the Arctic stratosphere and atmospheric forcings such as ENSO, the quasi-biennial oscillation (QBO), and the solar cycle. It is demonstrated that one representative of the supervised learning methods family, namely nonlinear neural networks, is able to reliably classify stratospheric warmings. Within this framework, one can estimate temporal onset, duration, and intensity of stratospheric warming events independently of a particular pressure level. In contrast to classification methods based on the zonal-mean zonal wind, the approach herein distinguishes major, minor, and final warmings. Instead of a binary measure, it provides continuous conditional probabilities for each warming event representing the amount of deviation from an undisturbed polar vortex. Additionally, the statistical importance of the atmospheric factors is estimated. It is shown how marginalized probability distributions can give insights into the interrelationships between external factors. This approach is applied to 40-yr and interim ECMWF (ERA-40/ERA-Interim) and NCEP–NCAR reanalysis data for the period from 1958 through 2010.