CanadaFireSat: Toward high-resolution wildfire forecasting with multiple modalities

TL;DR

This paper introduces CanadaFireSat, a high-resolution wildfire forecasting benchmark using multi-modal satellite data and deep learning, significantly improving prediction accuracy over existing coarse-resolution models.

Contribution

It presents a new high-resolution dataset and baseline methods for 100m wildfire prediction across Canada, leveraging multi-modal satellite data and deep learning architectures.

Findings

Multi-modal inputs outperform single-modal inputs in wildfire prediction.

Achieved 60.3% F1 score in 2023 wildfire season prediction.

High-resolution models demonstrate potential for continental-scale wildfire forecasting.

Abstract

Canada experienced in 2023 one of the most severe wildfire seasons in recent history, causing damage across ecosystems, destroying communities, and emitting large quantities of CO2. This extreme wildfire season is symptomatic of a climate-change-induced increase in the length and severity of the fire season that affects the boreal ecosystem. Therefore, it is critical to empower wildfire management in boreal communities with better mitigation solutions. Wildfire probability maps represent an important tool for understanding the likelihood of wildfire occurrence and the potential severity of future wildfires. The massive increase in the availability of Earth observation data has enabled the development of deep learning-based wildfire forecasting models, aiming at providing precise wildfire probability maps at different spatial and temporal scales. A main limitation of such methods is their reliance on coarse-resolution environmental drivers and satellite products, leading to wildfire occurrence prediction of reduced resolution, typically around $\sim 0.1${\deg}. This paper presents a benchmark dataset: CanadaFireSat, and baseline methods for high-resolution: 100 m wildfire forecasting across Canada, leveraging multi-modal data from high-resolution multi-spectral satellite images (Sentinel-2 L1C), mid-resolution satellite products (MODIS), and environmental factors (ERA5 reanalysis data). Our experiments consider two major deep learning architectures. We observe that using multi-modal temporal inputs outperforms single-modal temporal inputs across all metrics, achieving a peak performance of 60.3% in F1 score for the 2023 wildfire season, a season never seen during model training. This demonstrates the potential of multi-modal deep learning models for wildfire forecasting at high-resolution and continental scale.