SeasFire Cube

The SeasFire Cube is an open access scientific datacube for seasonal fire forecasting around the globe. Apart from seasonal fire forecasting, which is the aim of the SeasFire project, the datacube can be used for several other tasks. For example, it can be used to model teleconnections and memory effects in the earth system. Additionally, it can be used to model emissions from wildfires and the evolution of wildfire regimes.

It contains 21 years of data (2001-2021) in an 8-days time resolution and 0.25 degrees grid resolution. It has a diverse range of seasonal fire drivers. It expands from atmospheric and climatological ones to vegetation variables, socioeconomic and the target variables related to wildfires such as burned areas, fire radiative power, and wildfire-related CO2 emissions.

All versions are available for download on Zenodo.

SeasFire Cube v0.3:

SeasFire Cube v0.2:

SeasFire Cube v0.1:


Are you interested in learning how to use the SeasFire Cube? We have created a simple walkthrough to open the dataset, filter it based on location and time, and visualise its features.

Python tutorials:

Julia tutorial:

ESA Φ-Lab Workshop on AI for Natural Hazard Management

Recordings: Part 1 | Part 2

Akanksha Ahuja, National Observatory of AthensGraph Neural Networks for Remote Sensing
Dr. Nuno Carvalhais, Max Planck Institute for BiogeochemistryBridging statistical learning and process-based modeling of the Earth system
Prof. Gustau Camps-Valls, Universitat de ValènciaCausal Inference for Disaster Management
Spyros Kondylatos, National Observatory of AthensProbabilistic Machine Learning for Disaster Management
Prof. Dimitrios Michail, Harokopeio University of AthensGraph Neural Networks for Remote Sensing
Dr. Ioannis Papoutsis, National Observatory of AthensEarly Warning: Volcanic unrest detection
Dr. Michele Ronco, Universitat de València
Cristiano De Nobili, Johanna Strebl, Giovanni Paolini, Pi School of AI
Explainable AI for Wildfire Forecasting
Ioannis Prapas, National Observatory of AthensDeep Learning for Rapid Landslide Detection
Ioannis Prapas, National Observatory of AthensDeep Learning for Wildfire Danger Forecasting at Different Spatiotemporal Scales
Prof. Raúl Ramos, Universidad de AntioquiaDeep Learning Data Pipelines for Rapid Emergency Response