WildfireGenome: Interpretable Machine Learning Reveals Local Drivers of Wildfire Risk and Their Cross-County Variation

TL;DR

WildfireGenome introduces an interpretable machine learning framework that combines multiple wildfire indicators to identify local risk drivers and their variation across counties, aiding targeted wildfire management strategies.

Contribution

It develops a novel, interpretable approach integrating PCA, Random Forest, and SHAP analyses for local wildfire risk assessment at decision scales.

Findings

Models achieve high accuracy (up to 0.878) and agreement (up to 0.951) across diverse counties.

Needleleaf forest cover and elevation are key risk drivers, with sharp risk increases at 30-40% needleleaf coverage.

Transferability is reliable among ecologically similar regions but limited across dissimilar contexts.

Abstract

Current wildfire risk assessments rely on coarse hazard maps and opaque machine learning models that optimize regional accuracy while sacrificing interpretability at the decision scale. WildfireGenome addresses these gaps through three components: (1) fusion of seven federal wildfire indicators into a sign-aligned, PCA-based composite risk label at H3 Level-8 resolution; (2) Random Forest classification of local wildfire risk; and (3) SHAP and ICE/PDP analyses to expose county-specific nonlinear driver relationships. Across seven ecologically diverse U.S. counties, models achieve accuracies of 0.755-0.878 and Quadratic Weighted Kappa up to 0.951, with principal components explaining 87-94% of indicator variance. Transfer tests show reliable performance between ecologically similar regions but collapse across dissimilar contexts. Explanations consistently highlight needleleaf forest cover and elevation as dominant drivers, with risk rising sharply at 30-40% needleleaf coverage. WildfireGenome advances wildfire risk assessment from regional prediction to interpretable, decision-scale analytics that guide vegetation management, zoning, and infrastructure planning.