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

Scientific and technological advances in numerical modelling have improvedthe quality of climate predictions over recent decades, but predictive skillremains limited in many aspects. Extreme events such as heat and cold waves,droughts, heavy rain and storms are particularly challenging to predictaccurately due to their rarity and non-linear chaotic nature, and because ofmodel limitations. However, recent studies have shown that predictive skill ofextremes can be increased when using more sophisticated approaches, indicatingthat there might be systemic predictability that is not being leveraged.Recently, numerous studies have been devoted to the exploitation of ArtificialIntelligence (AI) to study the predictability and make predictions of weatherand climate. AI techniques have shown great potential to improve the predictionof extreme events and uncover their links to large-scale and local drivers.Machine and deep learning, causal discovery, explainable AI, are only some ofthe approaches that have been tested to both improve our understanding of theprocesses underlying predictability and enhance prediction skill of extremeevents. Results are promising, especially for hybrid predictions that combinethe AI, which can reveal and exploit unknown spatio-temporal connections fromdata, and climate models, that provide the theoretical foundation andinterpretability of the physical world. On the other hand, challenges aremultiple in many aspects, from data curation to model uncertainty andgeneralizability, to the reproducibility of methods and workflows. A few bestpractices are identified to increase trust in these novel techniques, andfuture perspectives are envisaged for further scientific development.

Artificial Intelligence for Prediction of Climate Extremes: State of the art, challenges and future perspectives