English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Classifying the state of the atmosphere into a finite number of large-scalecirculation regimes is a popular way of investigating teleconnections, thepredictability of severe weather events, and climate change. Here, weinvestigate a supervised machine learning approach based on deformableconvolutional neural networks (deCNNs) and transfer learning to forecast theNorth Atlantic-European weather regimes during extended boreal winter for 1 to15 days into the future. We apply state-of-the-art interpretation techniquesfrom the machine learning literature to attribute particular regions ofinterest or potential teleconnections relevant for any given weather clusterprediction or regime transition. We demonstrate superior forecastingperformance relative to several classical meteorological benchmarks, as well aslogistic regression and random forests. Due to its wider field of view, we alsoobserve deCNN achieving considerably better performance than regularconvolutional neural networks at lead times beyond 5-6 days. Finally, we findtransfer learning to be of paramount importance, similar to previousdata-driven atmospheric forecasting studies.

Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data