Preprints
https://doi.org/10.5194/egusphere-2024-1346
https://doi.org/10.5194/egusphere-2024-1346
21 May 2024
 | 21 May 2024

Weather Type Reconstruction using Machine Learning Approaches

Lucas Pfister, Lena Wilhelm, Yuri Brugnara, Noemi Imfeld, and Stefan Brönnimann

Abstract. Weather types are used to characterise large–scale synoptic weather patterns over a region. Long–standing records of weather types hold important information about day–to–day variability and changes of atmospheric circulation and the associated effects on the surface. However, most weather type reconstructions are restricted in their temporal extent as well as in the accuracy of the used methods. In our study, we assess various machine learning approaches for station–based weather type reconstruction over Europe based on the CAP9 weather type classification. With a common feedforward neural network performing best in this model comparison, we reconstruct a daily CAP9 weather type series back to 1728. The new reconstructions constitute the longest daily weather type series available. A detailed validation shows considerably better performance compared to previous statistical approaches and good agreement with the reference series for various climatological analyses. Our approach may serve as a guide for other weather type classifications.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Lucas Pfister, Lena Wilhelm, Yuri Brugnara, Noemi Imfeld, and Stefan Brönnimann

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-1346', Anonymous Referee #1, 04 Aug 2024
  • RC2: 'Comment on egusphere-2024-1346', Anonymous Referee #2, 07 Aug 2024
  • RC3: 'Comment on egusphere-2024-1346', Anonymous Referee #3, 09 Aug 2024
Lucas Pfister, Lena Wilhelm, Yuri Brugnara, Noemi Imfeld, and Stefan Brönnimann

Data sets

Weather Type Reconstruction using Machine Learning Approaches Lucas Pfister https://boris.unibe.ch/id/eprint/195666

Model code and software

Weather Type Reconstruction using Machine Learning Approaches Lucas Pfister https://boris.unibe.ch/id/eprint/195666

Lucas Pfister, Lena Wilhelm, Yuri Brugnara, Noemi Imfeld, and Stefan Brönnimann

Viewed

Total article views: 689 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
414 153 122 689 44 15 16
  • HTML: 414
  • PDF: 153
  • XML: 122
  • Total: 689
  • Supplement: 44
  • BibTeX: 15
  • EndNote: 16
Views and downloads (calculated since 21 May 2024)
Cumulative views and downloads (calculated since 21 May 2024)

Viewed (geographical distribution)

Total article views: 671 (including HTML, PDF, and XML) Thereof 671 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 05 Dec 2024
Download
Short summary
Our work compares different machine learning approaches for creating long-term classifications of daily atmospheric circulation patterns using input data from surface meteorological observations. Our comparison reveals a so-called feedforward neural network to perform best in this task. Using this model, we present a daily reconstruction of the CAP9 weather type classification for Central Europe back to 1728.