# Deep Learning Methods for Daily Wildfire Danger Forecasting

arXiv: https://arxiv.org/abs/2111.02736 · HTML: https://mlsanity.com/paper/2111.02736/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 19 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 3 of 3)

- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [A review of machine learning applications in wildfire science and management](https://mlsanity.com/paper/2003.00646/) (2020)

## Built on by (most cited first, 17 of 17)

- [Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean](https://mlsanity.com/paper/2306.05144/) (2023)
- [Deep Learning for Global Wildfire Forecasting](https://mlsanity.com/paper/2211.00534/) (2022)
- [Hephaestus: A large scale multitask dataset towards InSAR understanding](https://mlsanity.com/paper/2204.09435/) (2022)
- [Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting](https://mlsanity.com/paper/2212.08208/) (2022)
- [Causal Graph Neural Networks for Wildfire Danger Prediction](https://mlsanity.com/paper/2403.08414/) (2024)
- [FireCastNet: Earth-as-a-Graph for Seasonal Fire Prediction](https://mlsanity.com/paper/2502.01550/) (2025)
- [Probabilistic Machine Learning for Noisy Labels in Earth Observation](https://mlsanity.com/paper/2504.03478/) (2025)
- [A General Purpose Neural Architecture for Geospatial Systems](https://mlsanity.com/paper/2211.02348/) (2022)
- [Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting](https://mlsanity.com/paper/2509.25017/) (2025)
- [Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks](https://mlsanity.com/paper/2404.06437/) (2024)
- [Rapid Deforestation and Burned Area Detection using Deep Multimodal Learning on Satellite Imagery](https://mlsanity.com/paper/2307.04916/) (2023)
- [IberFire -- a detailed creation of a spatio-temporal dataset for wildfire risk assessment in Spain](https://mlsanity.com/paper/2505.00837/) (2025)
- [Wildfire spread forecasting with Deep Learning](https://mlsanity.com/paper/2505.17556/) (2025)
- [NumS: Scalable Array Programming for the Cloud](https://mlsanity.com/paper/2206.14276/) (2022)
- [Comparing Next-Day Wildfire Predictability of MODIS and VIIRS Satellite Data](https://mlsanity.com/paper/2503.08580/) (2025)
- [Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space](https://mlsanity.com/paper/2510.12916/) (2025)
- [PyroAdapt: Adapting Wildfire Prediction under Spatial Heterogeneity and Temporal Shift](https://mlsanity.com/paper/2605.12435/) (2026)

## Abstract (arXiv)

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.