Articles | Volume 3, issue 4
Weather Clim. Dynam., 3, 1157–1182, 2022
https://doi.org/10.5194/wcd-3-1157-2022
Weather Clim. Dynam., 3, 1157–1182, 2022
https://doi.org/10.5194/wcd-3-1157-2022
Research article
19 Oct 2022
Research article | 19 Oct 2022

Identification of high-wind features within extratropical cyclones using a probabilistic random forest – Part 1: Method and case studies

Lea Eisenstein et al.

Model code and software

RAMEFI (RAndom-forest based MEsoscale wind Feature Identification) Lea Eisenstein, Benedikt Schulz, Ghulam A. Qadir, Joaquim G. Pinto, and Peter Knippertz https://doi.org/10.5281/zenodo.6541303

RAMEFI Lea Eisenstein, Benedikt Schulz, Ghulam A. Qadir, Joaquim G. Pinto, and Peter Knippertz https://gitlab.physik.uni-muenchen.de/Lea.Eisenstein/ramefi

Video supplement

Objective identification of high-wind features within extratropical cyclones using a probabilistic random forest (RAMEFI). Part I: Method and illustrative case studies - Video Supplement Lea Eisenstein, Benedikt Schulz, Ghulam A. Qadir, Joaquim G. Pinto, and Peter Knippertz https://doi.org/10.5281/zenodo.6541277

Download
Short summary
Mesoscale high-wind features within extratropical cyclones can cause immense damage. Here, we present RAMEFI, a novel approach to objectively identify the wind features based on a probabilistic random forest. RAMEFI enables a wide range of applications such as probabilistic predictions for the occurrence or a multi-decadal climatology of these features, which will be the focus of Part 2 of the study, with the goal of improving wind and, specifically, wind gust forecasts in the long run.