Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data
Abstract 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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-12167-8 |
| _version_ | 1811256756124254208 |
|---|---|
| author | Andreas Holm Nielsen Alexandros Iosifidis Henrik Karstoft |
| author_facet | Andreas Holm Nielsen Alexandros Iosifidis Henrik Karstoft |
| author_sort | Andreas Holm Nielsen |
| collection | DOAJ |
| description | Abstract 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 1–15 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. |
| first_indexed | 2024-04-12T17:46:08Z |
| format | Article |
| id | doaj.art-5755b551cbce4e54b4067db86786c400 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T17:46:08Z |
| publishDate | 2022-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5755b551cbce4e54b4067db86786c4002022-12-22T03:22:40ZengNature PortfolioScientific Reports2045-23222022-05-0112111210.1038/s41598-022-12167-8Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate dataAndreas Holm Nielsen0Alexandros Iosifidis1Henrik Karstoft2Department of Electrical and Computer Engineering, Aarhus UniversityDepartment of Electrical and Computer Engineering, Aarhus UniversityDepartment of Electrical and Computer Engineering, Aarhus UniversityAbstract 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 1–15 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.https://doi.org/10.1038/s41598-022-12167-8 |
| spellingShingle | Andreas Holm Nielsen Alexandros Iosifidis Henrik Karstoft Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data Scientific Reports |
| title | 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_short | 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 |
| url | https://doi.org/10.1038/s41598-022-12167-8 |
| work_keys_str_mv | AT andreasholmnielsen forecastinglargescalecirculationregimesusingdeformableconvolutionalneuralnetworksandglobalspatiotemporalclimatedata AT alexandrosiosifidis forecastinglargescalecirculationregimesusingdeformableconvolutionalneuralnetworksandglobalspatiotemporalclimatedata AT henrikkarstoft forecastinglargescalecirculationregimesusingdeformableconvolutionalneuralnetworksandglobalspatiotemporalclimatedata |