eXtreme events : Artificial Intelligence for Detection and Attribution (XAIDA)

Description:

Climate change is modifying and enhancing extreme weather events such as heatwaves, devastating wildfires, cyclones, floods and droughts. The XAIDA project aims to characterise, detect and attribute extreme events using a novel data-driven, impact-based approach. It will use new AI techniques and bring together specialists in extreme event attribution, atmospheric dynamics, climate modelling, machine learning and causal inference. The hope is that the project findings will be able to shed light on the effect of climate change on atmospheric phenomena like cyclones and convective storms, which are not well understood or quantified. The project will also provide tools to assess the causal pathways leading to extreme events.

The “Extreme event attribution” field has recently developed in order to provide representations of future climates in terms of meaningful patterns of extreme events, which can underpin future projections in a way that is useful for adaptation, and for which a causal link between events and human influence on climate can be established or refuted. However, extreme event detection, attribution and projections studies currently face major limitations. 

The XAIDA project aims at filling these gaps. Using new artificial intelligence techniques, and strong two-way interaction with key stakeholders, it will (i) characterize, detect and attribute extreme events using a novel data-driven, impact-based approach, (ii) assess their underlying causal pathways and physical drivers using causal networks methods, and (iii) simulate high-intensity and as yet unseen events that are physically plausible in the present and future climates.

To achieve this, XAIDA brings together teams of specialists in extreme event attribution, atmospheric dynamics, climate modelling, machine learning and causal inference, to:

• Understand the effect of climate change on a variety of impacting atmospheric phenomena currently poorly understood or quantified (cyclones, convective storms, long-lived anomalies, or summer compound events), both for past and future evolutions;
• Develop, in co-design with a community of key stakeholders, a novel, broader and impacts-based attribution and projection framework which extracts causal pathways of extremes;
• Develop storylines of events of unseen intensity, based on machine learning methods;
• Provide new tools for model assessment of causal pathways leading to extreme events and investigate the causes of disagreements between models and observations;
• Develop an interaction and communication platform with stakeholders with the ambition to improve training and education on climate change and impacts and to bring these developments to future operational climate services.

Project information

Lead

CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE - CNRS

Partners

Commissariat à l’Energie Atomique et aux Energies Alternatives (France)

Vrije Universiteit Amsterdam (VU)|Netherlands

The Chancellor, Masters and Scholars of the University of Oxford (Uk)

Koninklijk Nederlands Meteorologisch Instituut-Knmi (The Netherlands)

Met Office (Uk)

Max-Planck-Gesellschaft Zur Forderung Der Wissenschaften Ev (Germany)

Universitat De Valencia (Spain)

Universitaet Leipzig  (Germany)

Deutsches Zentrum Fur Luft - Und Raumfahrt Ev(Germany)

Eidgenoessische Technische Hochschule Zuerich (Switzerland)

Helmholtz-Zentrum fur Umweltforschung Gmbh - Ufz (Germany)

The University of Reading (Uk)

UNESCO – International Centre For Theoretical Physics (Ictp)|Italy

Foundation pour l'education à la Science Dans le Sillage de la Main a la Pate (France)

Stichting International Red Cross Red Crescent Centre on Climate Change And Disaster Preparedness (The Netherlands)

Imperial College London – Grantham Institute (Icl) | United Kingdom

 

Source of funding

H2020-EU.3.5. - SOCIETAL CHALLENGES - Climate action, Environment, Resource Efficiency and Raw Materials