Preprints
https://doi.org/10.5194/wcd-2021-27
https://doi.org/10.5194/wcd-2021-27

  25 May 2021

25 May 2021

Review status: this preprint is currently under review for the journal WCD.

Automated detection and classification of synoptic scale fronts from atmospheric data grids

Stefan Niebler1, Annette Miltenberger2, Bertil Schmidt1, and Peter Spichtinger2 Stefan Niebler et al.
  • 1Institut für Informatik, Johannes Gutenberg Universität Mainz, Staudingerweg 7, 55128 Mainz, Germany
  • 2Institut für Physik der Atmosphäre, Johannes Gutenberg Universität Mainz, Becherweg 21, 55128 Mainz, Germany

Abstract. Automatic determination of fronts from atmospheric data is an important task for weather prediction. In this paper we introduce a deep neural network to detect and classify fronts from multi-level ERA5 reanalysis data. Model training and prediction is evaluated using two different regions covering Europe and North America. We apply label deformation within our loss function which removes the need for skeleton operations or other complicated post processing steps as observed in other work, to create the final output. We observe good prediction scores with CSI higher than 62.9 % and a Object Detection Rate of more than 73 %. Frontal climatologies of our network are highly correlated (greater than 79.6 %) to climatologies created from weather service data. Evaluated cross sections further show that our networks classification is physical plausible. Comparison with a well-established baseline method (ETH Zurich) shows a better performance of our network classification.

Stefan Niebler et al.

Status: open (until 06 Jul 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wcd-2021-27', Peter Düben, 24 Jun 2021 reply

Stefan Niebler et al.

Model code and software

Front Detection Network Code Stefan Niebler https://doi.org/10.5281/zenodo.4770096

Video supplement

Front Detection Results January 2016 - 1 hour resolution Stefan Niebler https://doi.org/10.5446/53399

Stefan Niebler et al.

Viewed

Total article views: 303 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
213 84 6 303 16 5 3
  • HTML: 213
  • PDF: 84
  • XML: 6
  • Total: 303
  • Supplement: 16
  • BibTeX: 5
  • EndNote: 3
Views and downloads (calculated since 25 May 2021)
Cumulative views and downloads (calculated since 25 May 2021)

Viewed (geographical distribution)

Total article views: 292 (including HTML, PDF, and XML) Thereof 292 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 Jun 2021
Download
Short summary
We use machine learning to create a network that detects and classifies four types of synoptic scale weather fronts from ERA5 atmospheric reanalysis data. Our work can be used to reduce the amount of manual work previously needed for this task. Additionally our results show that multiple sources of training data are necessary to perform well on different regions, implying differences within those regions. Qualitative evaluation shows that the results are physically plausible.