Explainable GeoAI for urban wildfire structure loss: vegetation and built environment in the 2025 Palisades Fire
Abstract
Urban wildfire resilience depends on interactions among built form, vegetation condition, and extreme fire weather, yet city-scale risk models often overlook whether predictive skill transfers across neighborhoods. We developed a spatially validated GeoAI workflow for the January 2025 Palisades Fire, linking 12,081 CAL FIRE damage inspections to pre-fire Sentinel-2 vegetation indices, Landsat surface temperature, LANDFIRE fuels, terrain, and OpenStreetMap buildings and roads. Among 9,883 inspected residential structures, 5,566 were destroyed. Random cross-validation yielded ROC-AUC 0.92 for the integrated XGBoost model, but 1 km spatial block validation reduced performance to 0.75; logistic regression performed similarly and was better calibrated. Building count within 100 m was the strongest predictor, with destruction odds increasing 4.12-fold per standard deviation. Vegetation moisture and greenness showed opposing conditional associations: NDMI at 100-300 m was protective (OR 0.52), whereas NDVI at 30-100 m was positively associated with destruction after accounting for moisture (OR 1.74). Predictive information was concentrated at the 100-300 m neighborhood scale. A separate post-fire track mapped burn severity and vegetation recovery without leakage. The results support neighborhood-scale susceptibility screening, moisture-aware vegetation management, and spatial block validation as a minimum standard for single-event urban wildfire modeling.
Versions
Related
- Wildfire risk for main vegetation units in a biodiversity hotspot: modelling approach in New-Caledonia, South Pacific.
- Ecological compression of vegetation information in wildfire spread prediction: a case study of the 2020 Brattain Fire
- Nighttime Light and Thermal Environment Jointly Affect Urban Vegetation Phenology.
- Fixed-ground multisensor monitoring resolves longitudinal vegetation condition and fuel-state structure in Southern California chaparral and oak scenes
- Improved permafrost soil representation in a dynamic global vegetation model enhances simulations of carbon dynamics and vegetation structure in boreal forests of Northeast China
BibTeX
@misc{farajpoor2026explainable,
title = {{Explainable GeoAI for urban wildfire structure loss: vegetation and built environment in the 2025 Palisades Fire}},
author = {Parastoo Farajpoor and Mohammadreza Narimani},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.22293},
eprint = {2608.22293},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.22293},
}
RIS
TY - UNPB
TI - Explainable GeoAI for urban wildfire structure loss: vegetation and built environment in the 2025 Palisades Fire
AU - Parastoo Farajpoor
AU - Mohammadreza Narimani
PY - 2026
DA - 2026/10/24
PB - arXiv
DO - 10.48550/arxiv.2608.22293
UR - https://arxiv.org/abs/2608.22293
AB - Urban wildfire resilience depends on interactions among built form, vegetation condition, and extreme fire weather, yet city-scale risk models often overlook whether predictive skill transfers across neighborhoods. We developed a spatially validated GeoAI workflow for the January 2025 Palisades Fire, linking 12,081 CAL FIRE damage inspections to pre-fire Sentinel-2 vegetation indices, Landsat surface temperature, LANDFIRE fuels, terrain, and OpenStreetMap buildings and roads. Among 9,883 inspected residential structures, 5,566 were destroyed. Random cross-validation yielded ROC-AUC 0.92 for the integrated XGBoost model, but 1 km spatial block validation reduced performance to 0.75; logistic regression performed similarly and was better calibrated. Building count within 100 m was the strongest predictor, with destruction odds increasing 4.12-fold per standard deviation. Vegetation moisture and greenness showed opposing conditional associations: NDMI at 100-300 m was protective (OR 0.52), whereas NDVI at 30-100 m was positively associated with destruction after accounting for moisture (OR 1.74). Predictive information was concentrated at the 100-300 m neighborhood scale. A separate post-fire track mapped burn severity and vegetation recovery without leakage. The results support neighborhood-scale susceptibility screening, moisture-aware vegetation management, and spatial block validation as a minimum standard for single-event urban wildfire modeling.
ER -