Tree-Based Regressor Comparison for Burn Severity Mapping: Spatially Blocked Validation Within and Across Fires

초록

Highlights What are the main findings? Random Forest is strongest within-fire (spatial LOCO). Extra Trees transfers best to unseen fires (LOFO). What are the implications of the main finding? For operational mapping, use ensemble models as low-tuning defaults to produce rapid, reliable severity maps even without local field plots. Adopt spatially blocked cross-validation and maintain diverse multi-fire training libraries to improve transferability and communicate uncertainty.Highlights What are the main findings? Random Forest is strongest within-fire (spatial LOCO). Extra Trees transfers best to unseen fires (LOFO). What are the implications of the main finding? For operational mapping, use ensemble models as low-tuning defaults to produce rapid, reliable severity maps even without local field plots. Adopt spatially blocked cross-validation and maintain diverse multi-fire training libraries to improve transferability and communicate uncertainty.Abstract Accurate, timely maps of post-fire burn severity are vital for rehabilitation, hydrologic hazard assessment, and ecosystem recovery in the western United States, where large, frequent wildfires and steep environmental gradients challenge model generalization. Machine learning models, particularly tree-based regressors, are increasingly used to relate satellite-derived spectral features to ground-based severity metrics such as the Composite Burn Index (CBI). However, model generalization across spatial domains, both within and between wildfires, remains poorly characterized. In this study, we benchmarked six tree-based regression models (Decision Tree-DT, Random Forest-RF, Extra Trees-ET, Bagging, Gradient Boosting-GB, and AdaBoost-AB) for predicting wildfire severity from Landsat surface reflectance data across ten U.S. fire events. Two spatial validation strategies were applied: (i) within-fire spatial generalization via Leave-One-Cluster-Out (LOCO) and (ii) cross-fire transfer via Leave-One-Fire-Out (LOFO). Performance is assessed with R2, RMSE, and MAE under identical predictors and default hyperparameters. Results indicate that, under LOCO, variance-reduction ensembles lead: RF attains R2 = 0.679, MAE = 0.397, RMSE = 0.516, with ET statistically comparable (R2 = 0.673, MAE = 0.393, RMSE = 0.518), and Bagging close behind (R2 = 0.668, MAE = 0.402, RMSE = 0.525). Under LOFO, ET transfers best (R2 = 0.616, MAE = 0.450, RMSE = 0.571), followed by GB (R2 = 0.564, MAE = 0.479, RMSE = 0.606) and RF (R2 = 0.543, MAE = 0.490, RMSE = 0.621). These results indicate that tree ensembles, especially ET and RF, are competitive under minimal tuning for rapid severity mapping; in practice, RF is a strong choice for an individual fire with local calibration, whereas ET is preferred when model transferability to unseen fires is paramount.

키워드