Abstract
Wildfire forecasting is of paramount importance for disaster risk reduction and environmental sustainability. We approach daily fire danger prediction as a machine learning task, using historical Earth observation data from the last decade to predict next-day’s fire danger. To that end, we collect, pre-process and harmonize an open-access datacube, featuring a set of covariates that jointly affect the fire occurrence and spread, such as weather conditions, satellite-derived products, topography features and variables related to human activity. We implement a variety of Deep Learning (DL) models to capture the spatial, temporal or spatio-temporal context and compare them against a Random Forest (RF) baseline. We find that either spatial or temporal context is enough to surpass the RF, while a ConvLSTM that exploits the spatio-temporal context performs best with a test Area Under the Receiver Operating Characteristic of 0.926. Our DL-based proof-of-concept provides national-scale daily fire danger maps at a much higher spatial resolution than existing operational solutions.
Add the full text or supplementary notes for the publication here using Markdown formatting.
Ioannis Prapas
PhD Candidate
My research interests include Deep Learning, Earth Observation, Wildfire Forecasting, Modeling Earth System Dynamics.
Spyros Kondylatos
PhD Candidate
My research interests include Deep Learning, Bayesian Deep Learning, Earth Observation, Natural Hazards, Wildfires Forecasting
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