EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An interpretable remote sensing–machine learning framework for wildfire soil burn severity prediction in the northwestern United States

Subhankar Das, Mariana Dobre, Roger Lew, Sarah A. Lewis, Erin S. Brooks, Peter R. Robichaud, Anurag Srivastava, Mary Ellen Miller, Alex M. Watanabe, Marta Basso

International Journal of Wildland Fire · 21.08.2026 · 35 (8)

DOI: 10.1071/wf25295 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Wildland Fire, online erschienen am 04.08.2026. Verfasst von Subhankar Das und 9 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 128 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Aeronautics and Space Administration.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Although soil burn severity (SBS) is traditionally mapped post-fire, pre-fire predictive approaches remain limited despite their potential to identify areas at risk of soil degradation, runoff and erosion.

Aim

To develop a large-scale model for predicting post-fire SBS from pre-fire conditions at ~30 m spatial resolution.

Methods

A harmonized dataset of 62 wildfires (2018–2024) was used to build machine learning (ML) frameworks based on Random Forest, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), using pre-fire vegetation, climate, soil–terrain and anthropogenic predictors. Performance was evaluated using five-fold cross-validation (CV), leave-one-fire-out (LOFO) validation and independent testing on 2025 fires. Key Results All models showed similar CV overall accuracy (OA ~0.58), but LOFO performance varied. LightGBM maintained more consistent OA (0.51–0.58) across fire size classes, whereas XGBoost and Random Forest exhibited comparable performance. Key predictors included vegetation biomass (Normalized Difference Moisture Index, Enhanced Vegetation Index), fuel stress (Evaporative Stress Index, Evapotranspiration), elevation and soil moisture. High SBS was associated with dry conditions and high biomass availability, with region-specific controls modulating these patterns.

Conclusion

ML models using pre-fire environmental data enable proactive SBS prediction.

Implications

This framework supports fuel management planning, potential post-fire hydrological impact assessment and the prediction of SBS from pre-fire conditions.

Förderung

  • National Aeronautics and Space Administration

Zitieren

APA

Das, S., Dobre, M., Lew, R., Lewis, S. A., Brooks, E. S., Robichaud, P. R., Srivastava, A., Miller, M. E., Watanabe, A. M., & Basso, M. (2026). An interpretable remote sensing–machine learning framework for wildfire soil burn severity prediction in the northwestern United States. International Journal of Wildland Fire, 35(8). https://doi.org/10.1071/wf25295

Vancouver

Das S, Dobre M, Lew R, Lewis SA, Brooks ES, Robichaud PR, et al. An interpretable remote sensing–machine learning framework for wildfire soil burn severity prediction in the northwestern United States. International Journal of Wildland Fire. 2026;35(8). doi:10.1071/wf25295

BibTeX
@article{Das2026,
  author = {Das, Subhankar and Dobre, Mariana and Lew, Roger and Lewis, Sarah A. and Brooks, Erin S. and Robichaud, Peter R. and Srivastava, Anurag and Miller, Mary Ellen and Watanabe, Alex M. and Basso, Marta},
  title = {An interpretable remote sensing–machine learning framework for wildfire soil burn severity prediction in the northwestern United States},
  journal = {International Journal of Wildland Fire},
  year = {2026},
  volume = {35},
  number = {8},
  doi = {10.1071/wf25295}
}
Kostenlos starten →