Trustworthy Data-Driven Wildfire Risk Prediction and Understanding in Western Canada

TL;DR

This paper introduces a trustworthy, uncertainty-aware data-driven model for wildfire risk prediction in western Canada, outperforming existing methods and providing interpretability of key risk drivers during record-breaking fire seasons.

Contribution

It presents a novel multi-scale temporal modeling framework that explicitly quantifies uncertainty and offers process-level interpretability for wildfire risk prediction.

Findings

Model achieved F1 score of 0.90 and PR-AUC of 0.98.

Uncertainty analysis revealed spatial and seasonal patterns in wildfire risk.

Temperature is the dominant risk driver, with moisture constraints influencing spatial variations.

Abstract

In recent decades, the intensification of wildfire activity in western Canada has resulted in substantial socio-economic and environmental losses. Accurate wildfire risk prediction is hindered by the intrinsic stochasticity of ignition and spread and by nonlinear interactions among fuel conditions, meteorology, climate variability, topography, and human activities, challenging the reliability and interpretability of purely data-driven models. We propose a trustworthy data-driven wildfire risk prediction framework based on long-sequence, multi-scale temporal modeling, which integrates heterogeneous drivers while explicitly quantifying predictive uncertainty and enabling process-level interpretation. Evaluated over western Canada during the record-breaking 2023 and 2024 fire seasons, the proposed model outperforms existing time-series approaches, achieving an F1 score of 0.90 and a PR-AUC of 0.98 with low computational cost. Uncertainty-aware analysis reveals structured spatial and seasonal patterns in predictive confidence, highlighting increased uncertainty associated with ambiguous predictions and spatiotemporal decision boundaries. SHAP-based interpretation provides mechanistic understanding of wildfire controls, showing that temperature-related drivers dominate wildfire risk in both years, while moisture-related constraints play a stronger role in shaping spatial and land-cover-specific contrasts in 2024 compared to the widespread hot and dry conditions of 2023. Data and code are available at https://github.com/SynUW/mmFire.