Description du projet
L’intelligence artificielle aide à prévoir les phénomènes météorologiques extrêmes
Les cyclones tropicaux, les vagues de chaleur et les sécheresses extrêmes sont des exemples de phénomènes climatiques extrêmes difficiles à prévoir. Le changement climatique a accru la probabilité et la gravité de ces événements, et il est essentiel mais difficile de prévoir leur survenue. Le projet CLINT, financé par l’UE, s’appuiera sur les données recueillies par le Service Copernicus concernant le changement climatique et sur les récentes avancées en matière d’intelligence artificielle (IA). En appliquant un cadre d’IA composé de techniques et d’algorithmes d’apprentissage automatique, il traitera de grands ensembles de données climatiques pour améliorer la science du climat en termes de détection, de causalité et d’attribution des événements extrêmes. CLINT couvrira également les impacts de la quantification des événements extrêmes sur divers secteurs socio‑économiques à l’échelle paneuropéenne et à l’échelle locale dans différents types de zones sensibles au changement climatique.
Objectif
Weather and climate extremes pose challenges for adaptation and mitigation policies as well as disaster risk management, emphasizing the value of Climate Services in supporting strategic decision-making. Today Climate Services can benefit from an unprecedented availability of data, in particular from the Copernicus Climate Change Service, and from recent advances in Artificial Intelligence (AI) to exploit the full potential of these data. The main objective of CLINT is the development of an AI framework composed of Machine Learning (ML) techniques and algorithms to process big climate datasets for improving Climate Science in the detection, causation and attribution of Extreme Events, including tropical cyclones, heatwaves and warm nights, and extreme droughts, along with compound events and concurrent extremes. Specifically, the framework will support (1) the detection of spatial and temporal patterns, and evolutions of climatological fields associated with Extreme Events, (2) the validation of the physically based nature of causality discovered by ML algorithms, and (3) the attribution of past and future Extreme Events to emissions of greenhouse gases and other anthropogenic forcing. The framework will also cover the quantification of the Extreme Events impacts on a variety of socio-economic sectors under historical, forecasted and projected climate conditions by developing innovative and sectorial AI-enhanced Climate Services. These will be demonstrated across different spatial scales, from the pan European scale to support EU policies addressing the Water-Energy-Food Nexus to the local scale in three types of Climate Change Hotspots. Finally, these services will be operationalized into Web Processing Services, according to most advanced open data and software standards by Climate Services Information Systems, and into a Demonstrator to facilitate the uptake of project results by public and private entities for research and Climate Services development.
Champ scientifique
Mots‑clés
Programme(s)
Régime de financement
RIA - Research and Innovation actionCoordinateur
20133 Milano
Italie