Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data
Classifying the state of the atmosphere into a finite number of large-scale circulation regimes is a popular way of investigating teleconnections, the predictability of severe weather events, and climate change. Here, we investigate a supervised machine learning approach based on deformable convolut...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2022
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2202.04964 https://arxiv.org/abs/2202.04964 |
id |
ftdatacite:10.48550/arxiv.2202.04964 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2202.04964 2023-05-15T17:33:11+02:00 Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data Nielsen, Andreas Holm Iosifidis, Alexandros Karstoft, Henrik 2022 https://dx.doi.org/10.48550/arxiv.2202.04964 https://arxiv.org/abs/2202.04964 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CC-BY Machine Learning cs.LG FOS Computer and information sciences Article CreativeWork article Preprint 2022 ftdatacite https://doi.org/10.48550/arxiv.2202.04964 2022-03-10T11:44:46Z Classifying the state of the atmosphere into a finite number of large-scale circulation regimes is a popular way of investigating teleconnections, the predictability of severe weather events, and climate change. Here, we investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) and transfer learning to forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. We apply state-of-the-art interpretation techniques from the machine learning literature to attribute particular regions of interest or potential teleconnections relevant for any given weather cluster prediction or regime transition. We demonstrate superior forecasting performance relative to several classical meteorological benchmarks, as well as logistic regression and random forests. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days. Finally, we find transfer learning to be of paramount importance, similar to previous data-driven atmospheric forecasting studies. : Submitted to Nature - Scientific Reports Article in Journal/Newspaper North Atlantic DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Machine Learning cs.LG FOS Computer and information sciences |
spellingShingle |
Machine Learning cs.LG FOS Computer and information sciences Nielsen, Andreas Holm Iosifidis, Alexandros Karstoft, Henrik Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
topic_facet |
Machine Learning cs.LG FOS Computer and information sciences |
description |
Classifying the state of the atmosphere into a finite number of large-scale circulation regimes is a popular way of investigating teleconnections, the predictability of severe weather events, and climate change. Here, we investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) and transfer learning to forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. We apply state-of-the-art interpretation techniques from the machine learning literature to attribute particular regions of interest or potential teleconnections relevant for any given weather cluster prediction or regime transition. We demonstrate superior forecasting performance relative to several classical meteorological benchmarks, as well as logistic regression and random forests. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days. Finally, we find transfer learning to be of paramount importance, similar to previous data-driven atmospheric forecasting studies. : Submitted to Nature - Scientific Reports |
format |
Article in Journal/Newspaper |
author |
Nielsen, Andreas Holm Iosifidis, Alexandros Karstoft, Henrik |
author_facet |
Nielsen, Andreas Holm Iosifidis, Alexandros Karstoft, Henrik |
author_sort |
Nielsen, Andreas Holm |
title |
Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
title_short |
Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
title_full |
Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
title_fullStr |
Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
title_full_unstemmed |
Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
title_sort |
forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data |
publisher |
arXiv |
publishDate |
2022 |
url |
https://dx.doi.org/10.48550/arxiv.2202.04964 https://arxiv.org/abs/2202.04964 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.48550/arxiv.2202.04964 |
_version_ |
1766131611100774400 |