Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean

Abstract

We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean. Mesogeos integrates variables representing wildfire drivers (meteorology, vegetation, human activity) and historical records of wildfire ignitions and burned areas for 17 years (2006-2022). It is designed as a cloud-friendly spatio-temporal dataset, namely a datacube, harmonizing all variables in a grid of 1km x 1km x 1-day resolution. The datacube structure offers opportunities to assess machine learning (ML) usage in various wildfire modeling tasks. We extract two ML-ready datasets that establish distinct tracks to demonstrate this potential: (1) short-term wildfire danger forecasting and (2) final burned area estimation given the point of ignition. We define appropriate metrics and baselines to evaluate the performance of models in each track. By publishing the datacube, along with the code to create the ML datasets and models, we encourage the community to foster the implementation of additional tracks for mitigating the increasing threat of wildfires in the Mediterranean.

Spyros Kondylatos

PhD Candidate

My research interests include Deep Learning, Bayesian Deep Learning, Earth Observation, Natural Hazards, Wildfires Forecasting

Ioannis Prapas

PhD Candidate

My research interests include Deep Learning, Earth Observation, Wildfire Forecasting, Modeling Earth System Dynamics.

Ioannis Papoutsis

Head of Orion Lab
Assistant Professor of Artificial Intelligence for Earth Observation @ NTUA
Adjunct Researcher @ NOA

Earth Observation, Machine Learning, Natural Hazard Monitoring