Artificial intelligence for climate prediction of extremes: State of the art, challenges, and future perspectives

Искусственный интеллект для климатического прогнозирования экстремальных явлений: современное состояние, проблемы и перспективы
Stefano Materia, Lluís Palma, Chiem van Straaten, O Sungmin, Antonios Mamalakis, Leone Cavicchia, Dim Coumou, Paolo De Luca, Marlene Kretschmer, Markus G. Donat
2024-09-03

artificial intelligencecausal discoveryclimate predictionexplainable AIextreme event prediction
Abstract Extreme events such as heat waves and cold spells, droughts, heavy rain, and storms are particularly challenging to predict accurately due to their rarity and chaotic nature, and because of model limitations. However, recent studies have shown that there might be systemic predictability that is not being leveraged, whose exploitation could meet the need for reliable predictions of aggregated extreme weather measures on timescales from weeks to decades ahead. Recently, numerous studies have been devoted to the use of artificial intelligence (AI) to study predictability and make climate predictions. AI techniques have shown great potential to improve the prediction of extreme events and uncover their links to large‐scale and local drivers. Machine and deep learning have been explored to enhance prediction, while causal discovery and explainable AI have been tested to improve our understanding of the processes underlying predictability. Hybrid predictions combining AI, which can reveal unknown spatiotemporal connections from data, with climate models that provide the theoretical foundation and interpretability of the physical world, have shown that improving prediction skills of extremes on climate‐relevant timescales is possible. However, numerous challenges persist in various aspects, including data curation, model uncertainty, generalizability, reproducibility of methods, and workflows. This review aims at overviewing achievements and challenges in the use of AI techniques to improve the prediction of extremes at the subseasonal to decadal timescale. A few best practices are identified to increase trust in these novel techniques, and future perspectives are envisaged for further scientific development. This article is categorized under: Climate Models and Modeling > Knowledge Generation with Models The Social Status of Climate Change Knowledge > Climate Science and Decision Making
1
Causal discovery and explainable AI can help identify and interpret the processes underlying predictability.
2
Extreme-event prediction is difficult because such events are rare, chaotic, and constrained by limitations in existing climate models.
3
Hybrid approaches combining AI with physically grounded climate models have demonstrated the potential to improve prediction skill on climate-relevant timescales.
4
Key unresolved challenges include data curation, model uncertainty, generalizability, reproducibility, and trustworthy scientific workflows.
5
Machine learning and deep learning can improve extreme-event prediction and reveal links between extremes and large-scale or local drivers.
6
Recent research indicates that systemic predictability of extremes exists and could support reliable aggregated predictions from subseasonal to decadal timescales.

Extreme climate and weather events, including heat waves, cold spells, droughts, heavy rain, and storms

Their predictability and prediction on subseasonal-to-decadal timescales, including links to large-scale and local drivers and the underlying processes

Publication Details
Publication Date
2024-09-03
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Stefano Materia
Lluís Palma
Chiem van Straaten
O Sungmin
Antonios Mamalakis
Leone Cavicchia
Dim Coumou
Paolo De Luca
Marlene Kretschmer
Markus G. Donat
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%