Weather type reconstruction using machine learning approaches

<p>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 in atmospheric circulation and the associated effects on the surface. However, most weather...

Full description

Saved in:
Bibliographic Details
Main Authors: L. Pfister, L. Wilhelm, Y. Brugnara, N. Imfeld, S. Brönnimann
Format: Article
Language:English
Published: Copernicus Publications 2025-05-01
Series:Weather and Climate Dynamics
Online Access:https://wcd.copernicus.org/articles/6/571/2025/wcd-6-571-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850270445799997440
author L. Pfister
L. Pfister
L. Wilhelm
L. Wilhelm
Y. Brugnara
Y. Brugnara
Y. Brugnara
N. Imfeld
N. Imfeld
S. Brönnimann
S. Brönnimann
author_facet L. Pfister
L. Pfister
L. Wilhelm
L. Wilhelm
Y. Brugnara
Y. Brugnara
Y. Brugnara
N. Imfeld
N. Imfeld
S. Brönnimann
S. Brönnimann
author_sort L. Pfister
collection DOAJ
description <p>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 in atmospheric circulation and the associated effects on the surface. However, most weather type reconstructions are restricted in their temporal extent and suffer from methodological limitations. In our study, we assess various machine learning approaches for station-based weather type reconstruction over Europe based on the nine-class cluster analysis of principal components (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. This new reconstruction constitutes the longest daily weather type series available. 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.</p>
format Article
id doaj-art-da58b2ac6b8c45b48bde74bb95b99ad3
institution OA Journals
issn 2698-4016
language English
publishDate 2025-05-01
publisher Copernicus Publications
record_format Article
series Weather and Climate Dynamics
spelling doaj-art-da58b2ac6b8c45b48bde74bb95b99ad32025-08-20T01:52:38ZengCopernicus PublicationsWeather and Climate Dynamics2698-40162025-05-01657159410.5194/wcd-6-571-2025Weather type reconstruction using machine learning approachesL. Pfister0L. Pfister1L. Wilhelm2L. Wilhelm3Y. Brugnara4Y. Brugnara5Y. Brugnara6N. Imfeld7N. Imfeld8S. Brönnimann9S. Brönnimann10Oeschger Centre for Climate Change Research, University of Bern, Bern 3012, SwitzerlandInstitute of Geography, University of Bern, Bern 3012, SwitzerlandOeschger Centre for Climate Change Research, University of Bern, Bern 3012, SwitzerlandInstitute of Geography, University of Bern, Bern 3012, SwitzerlandOeschger Centre for Climate Change Research, University of Bern, Bern 3012, SwitzerlandInstitute of Geography, University of Bern, Bern 3012, Switzerlandnow at: Empa, Dübendorf 8600, SwitzerlandOeschger Centre for Climate Change Research, University of Bern, Bern 3012, SwitzerlandInstitute of Geography, University of Bern, Bern 3012, SwitzerlandOeschger Centre for Climate Change Research, University of Bern, Bern 3012, SwitzerlandInstitute of Geography, University of Bern, Bern 3012, Switzerland<p>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 in atmospheric circulation and the associated effects on the surface. However, most weather type reconstructions are restricted in their temporal extent and suffer from methodological limitations. In our study, we assess various machine learning approaches for station-based weather type reconstruction over Europe based on the nine-class cluster analysis of principal components (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. This new reconstruction constitutes the longest daily weather type series available. 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.</p>https://wcd.copernicus.org/articles/6/571/2025/wcd-6-571-2025.pdf
spellingShingle L. Pfister
L. Pfister
L. Wilhelm
L. Wilhelm
Y. Brugnara
Y. Brugnara
Y. Brugnara
N. Imfeld
N. Imfeld
S. Brönnimann
S. Brönnimann
Weather type reconstruction using machine learning approaches
Weather and Climate Dynamics
title Weather type reconstruction using machine learning approaches
title_full Weather type reconstruction using machine learning approaches
title_fullStr Weather type reconstruction using machine learning approaches
title_full_unstemmed Weather type reconstruction using machine learning approaches
title_short Weather type reconstruction using machine learning approaches
title_sort weather type reconstruction using machine learning approaches
url https://wcd.copernicus.org/articles/6/571/2025/wcd-6-571-2025.pdf
work_keys_str_mv AT lpfister weathertypereconstructionusingmachinelearningapproaches
AT lpfister weathertypereconstructionusingmachinelearningapproaches
AT lwilhelm weathertypereconstructionusingmachinelearningapproaches
AT lwilhelm weathertypereconstructionusingmachinelearningapproaches
AT ybrugnara weathertypereconstructionusingmachinelearningapproaches
AT ybrugnara weathertypereconstructionusingmachinelearningapproaches
AT ybrugnara weathertypereconstructionusingmachinelearningapproaches
AT nimfeld weathertypereconstructionusingmachinelearningapproaches
AT nimfeld weathertypereconstructionusingmachinelearningapproaches
AT sbronnimann weathertypereconstructionusingmachinelearningapproaches
AT sbronnimann weathertypereconstructionusingmachinelearningapproaches