BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk Prediction

TL;DR

This paper introduces a comprehensive 25-year wildfire dataset with multimodal data for British Columbia, enabling long-term modeling and benchmarking of deep learning methods for boreal wildfire risk prediction.

Contribution

It provides a large-scale, multimodal dataset and evaluates multiple deep learning models, addressing the scarcity of long-term, high-resolution wildfire data for risk prediction.

Findings

Transformer models outperform CNNs in wildfire prediction

Position embedding improves model accuracy

Fuel and weather factors are most influential

Abstract

Wildfire risk prediction remains a critical yet challenging task due to the complex interactions among fuel conditions, meteorology, topography, and human activity. Despite growing interest in data-driven approaches, publicly available benchmark datasets that support long-term temporal modeling, large-scale spatial coverage, and multimodal drivers remain scarce. To address this gap, we present a 25-year, daily-resolution wildfire dataset covering 240 million hectares across British Columbia and surrounding regions. The dataset includes 38 covariates, encompassing active fire detections, weather variables, fuel conditions, terrain features, and anthropogenic factors. Using this benchmark, we evaluate a diverse set of time-series forecasting models, including CNN-based, linear-based, Transformer-based, and Mamba-based architectures. We also investigate effectiveness of position embedding and the relative importance of different fire-driving factors. The dataset and the corresponding code can be found at https://github.com/SynUW/mmFire