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

2026-01-04

arXiv.org

AI Summary

Wildfire risk prediction faces significant challenges due to the stochastic nature of ignition and spread processes, as well as complex nonlinear interactions among multiple drivers, which often undermine the reliability and interpretability of data-driven models. This work proposes the first trustworthy prediction framework that integrates multi-scale temporal modeling, uncertainty quantification, and SHAP-based interpretability to effectively fuse heterogeneous driving factors and uncover their spatiotemporal influence mechanisms. Evaluated during the 2023–2024 wildfire seasons in western Canada, the model achieves an F1 score of 0.90 and a PR-AUC of 0.98 at low computational cost, revealing key insights such as the dominant role of temperature in overall risk and the pronounced spatial heterogeneity in humidity effects.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• wildfire risk prediction
• data-driven models
• predictive uncertainty
• model interpretability
• nonlinear interactions

Innovation

• trustworthy AI
• wildfire risk prediction
• uncertainty quantification
• multi-scale temporal modeling
• SHAP interpretability