English

Deep Learning Methods for Daily Wildfire Danger Forecasting

Machine Learning 2021-11-05 v1 Artificial Intelligence Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.2111.02736,
  title  = {Deep Learning Methods for Daily Wildfire Danger Forecasting},
  author = {Ioannis Prapas and Spyros Kondylatos and Ioannis Papoutsis and Gustau Camps-Valls and Michele Ronco and Miguel-Ángel Fernández-Torres and Maria Piles Guillem and Nuno Carvalhais},
  journal= {arXiv preprint arXiv:2111.02736},
  year   = {2021}
}

Comments

Accepted to the workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

R2 v1 2026-06-24T07:25:48.396Z