Assessment of the January 2025 Los Angeles County wildfires: A multi-modal analysis of impact, response, and population exposure

TL;DR

The paper addresses the multi-faceted challenge of wildfire impact assessment by introducing Chebyshev-KAN (Cheby-KAN), a neural network framework applied to Sentinel-2 imagery for precise burned-area mapping across four January 2025 LA County fires. It integrates WorldPop demographics, NLCD land cover, PAD-US, and building footprints to deliver a comprehensive impact framework that covers land cover changes, infrastructure damage, jurisdictional complexity, and population exposure. The approach achieves high accuracy (overall 0.9868, kappa 0.9714, F1 0.9817) and quantifies burn extents totaling 17,042.85 ha, with shrubland ecosystems consistently driving burn patterns (57.4–75.8%). Findings highlight significant urban-wildland interface impacts and diverse agency coordination needs, offering actionable guidance for targeted wildfire management and gender- and age-conscious emergency planning in fire-prone landscapes.

Abstract

This study presents a comprehensive analysis of four significant California wildfires: Palisades, Eaton, Kenneth, and Hurst, examining their impacts through multiple dimensions, including land cover change, jurisdictional management, structural damage, and demographic vulnerability. Using the Chebyshev-Kolmogorov-Arnold network model applied to Sentinel-2 imagery, the extent of burned areas was mapped, ranging from 315.36 to 10,960.98 hectares. Our analysis revealed that shrubland ecosystems were consistently the most affected, comprising 57.4-75.8% of burned areas across all events. The jurisdictional assessment demonstrated varying management complexities, from singular authority (98.7% in the Palisades Fire) to distributed management across multiple agencies. A structural impact analysis revealed significant disparities between urban interface fires (Eaton: 9,869 structures; Palisades: 8,436 structures) and rural events (Kenneth: 24 structures; Hurst: 17 structures). The demographic analysis showed consistent gender distributions, with 50.9% of the population identified as female and 49.1% as male. Working-age populations made up the majority of the affected populations, ranging from 53.7% to 54.1%, with notable temporal shifts in post-fire periods. The study identified strong correlations between urban interface proximity, structural damage, and population exposure. The Palisades and Eaton fires affected over 20,000 people each, compared to fewer than 500 in rural events. These findings offer valuable insights for the development of targeted wildfire management strategies, particularly in wildland urban interface zones, and emphasize the need for age- and gender-conscious approaches in emergency response planning.

Figures (10)

• Figure 1: Geographic location of the four major wildfire events in Los Angeles County, California.
• Figure 2: Workflow for burned area detection using Sentinel-2 imagery and KAN model.
• Figure 3: Multi-criteria framework for fire impact assessment.
• Figure 4: Burned area mapping results obtained using the Kolmogorov-Arnold Network (KAN) model, applied to Sentinel-2 imagery. The map highlights burned areas (red) and unburned areas (green), with coastal boundaries marked in blue dashed lines. The masking of noisy label pixels in unburned regions enhanced the accuracy and reliability of the results.
• Figure 5: Burned land cover and land use distribution for four fire events: (a) Hurst Fire, (b) Eaton Fire, (c) Kenneth Fire, and (d) Palisades Fire.