Fire hazard forecasting in the Mediterranean

Climate change is playing an increasing role in determining wildfire regimes, with future climate variability expected to enhance the risk and severity of wildfires in many biomes including Southern Europe, while global warming greater than 1.5°C could lead to a 40% increase in Mediterranean burned area. This DeepCube Use Case aims to increase the preparedness and emergency response capacity of civil protection authorities and fire brigades with fire hazard forecasting systems using Artificial Intelligence on big EO and non-EO data.

Specifically, DeepCube will examine – among others – the climatic and vegetation status and the anthropogenic drivers that impact fire proneness based on multivariate historical data analysis, the burned area trends in Mediterranean ecosystems, the modeling of fire hazard to make more accurate future predictions using Earth Observation data time-series analysis, and the impact of vegetation recovery dynamics on inter-seasonal fire risk.

We aim to research a hybrid modelling approach, coupling physical models with data-driven Machine Learning, create robust fire hazard forecasts at large scales, and enhance our understanding of fire dynamics in complex ecosystems.

The use case will be co-designed with the support and contribution of the Hellenic Fire Service.

This is the first time that the full historical Mediterranean burned areas will be used to analyse fire patterns and trends vis-a-vis heterogeneous fire drivers, by training an explainable Deep Learning model conditioned by a physical Terrestrial Ecosystem Model, to deliver fire risk prognosis.

Use Case Leader
National Observatory of Athens

Interested in learning more? Contact us!
Dr. Ioannis Papoutsis, ipapoutsis@noa.gr