Weather type reconstruction using machine learning approaches

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

doi:https://doi.org/10.5194/wcd-6-571-2025

Articles | Volume 6, issue 2

https://doi.org/10.5194/wcd-6-571-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/wcd-6-571-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 6, issue 2

Research article

|

21 May 2025

Research article |

| 21 May 2025

Weather type reconstruction using machine learning approaches

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

Supplement

https://doi.org/10.5194/wcd-6-571-2025-supplement

Data sets

Swiss Early Meteorological Observations v2.0 Yuri Brugnara https://doi.org/10.1594/PANGAEA.948258

Messstationen Tagesdaten [Measuring Stations, Daily Data] GeoSphere Austria https://doi.org/10.60669/GS6W-JD70

Weather Type Reconstruction using Machine Learning Approaches Lucas Pfister http://dx.doi.org/10.48350/195666

Model code and software

Weather Type Reconstruction using Machine Learning Approaches Lucas Pfister http://dx.doi.org/10.48350/195666

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 that a feedforward neural network performs best at this task. Using this model, we present a daily reconstruction of a commonly used weather type classification for central Europe that dates back to 1728.