Uncertainty-Aware Wildfire Hazard Assessment Using Machine Learning, Fuzzy Logic, and Remote Sensing Data

Wildfire hazard assessment increasingly relies on machine learning models trained on large-scale remote sensing and geospatial datasets. However, the limited transparency and uncertainty awareness of many data-driven approaches hinder their operational use and trustworthiness for decision-making. In this study, we propose an interpretable and uncertainty-aware wildfire hazard assessment framework that integrates fuzzy logic preprocessing, histogram-based gradient boosting (HGB), and artificial intelligence.
Multiple environmental, climatic, topographic, vegetation, geological, and anthropogenic variables derived from remote sensing and GIS sources are transformed into continuous fuzzy membership functions to explicitly represent gradual transitions and inherent uncertainties in wildfire-related drivers. The HGB model is employed to efficiently handle high-dimensional raster data and to produce probabilistic wildfire susceptibility estimates. Model interpretability is ensured using SHAP, which quantifies the contribution and direction of each predictor to wildfire probability, enabling transparent interpretation of model behaviour. In addition, predictive uncertainty is quantified through an ensemble approach, highlighting spatial patterns of confidence and disagreement among model predictions.
Results demonstrate strong discriminative performance while revealing physically meaningful relationships, with precipitation acting as the dominant suppressor of wildfire probability, and fuel availability, temperature, and wind emerging as key amplifying factors. The proposed framework enhances model transparency, interpretability, and reliability, supporting trustworthy wildfire hazard assessment and decision-making for risk mitigation and resource allocation.