Taejun Sung

In wildfire burn severity assessment, change detection approaches based on satellite-derived burn severity indices (BSIs) have emerged as effective alternatives to traditional field-based methods such as the Composite Burn Index (CBI). However, previous studies have primarily focused on improving model performance using carefully curated datasets, while paying relatively limited attention to a fundamental limitation—the phenological consistency between pre- and post-fire imagery. This study proposes an automated burn severity analysis framework that incorporates phenology detrending to address this limitation. The proposed framework integrates hotspot-based automatic extraction of regions of interest, acquisition of valid pre- and post-fire imagery free from cloud contamination, and a vegetation phenology adjustment procedure to generate analysis-ready BSI datasets. By introducing the adjusted differenced BSI (adBSI) as a core component, the framework substantially increases the number of usable image pairs and enhances the stability and reliability of burn severity estimates. Validation against CBI plots and burn area data from the Monitoring Trends in Burn Severity (MTBS) program across the contiguous United States demonstrates that adBSI consistently achieves performance comparable to or better than conventional differenced BSI (dBSI). The improvement is particularly pronounced under phenologically mismatched pre- and post-fire conditions, especially when phenology-sensitive indices such as the normalized difference vegetation index (NDVI) are applied to vegetation types with strong seasonal variability, including deciduous forests. Time-series analyses further confirm that adBSI effectively suppresses seasonal fluctuations, yielding more stable and robust results than conventional dBSI. The developed framework was successfully applied to the 2025 wildfire events in the Los Angeles region, demonstrating its practical applicability. Overall, this study presents a simple yet powerful solution to a long-standing challenge in change detection–based burn severity analysis. Future work will focus on incorporating additional environmental variables and nonlinear modeling approaches to further enhance performance and extend the applicability of the proposed framework beyond wildfire burn severity analysis to a broader range of change detection applications.

Taejun Sung, Garyung Lee, Doeun Kim, Woohyeok Kim, Seyoung Yang, Jungho Im. Korean J. Remote Sens. 2026;42:165. https://doi.org/10.7780/kjrs.2026.42.1.12

Taejun Sung, Garyung Lee, Doeun Kim, Woohyeok Kim, Seyoung Yang, Jungho Im. Korean J. Remote Sens. 2025;41:565-80. https://doi.org/10.7780/kjrs.2025.41.3.6

Satellite-based wildfire detection models provide real-time data that is essential for effective management of wildfires, whose frequency and intensity are increasing. However, conventional temperature anomaly-based contextual algorithms fail to incorporate environmental and structural information, resulting in poor generalization capabilities across various environmental conditions and wildfire intensities. This study developed a novel machine learning-based wildfire detection model incorporating advanced contextual features to fulfill the deficiencies of conventional contextual (CC) algorithms. Specifically, two advanced contextual features—considering the baseline environment (ACE) and structural similarity (ACS)—were introduced, and their effectiveness was assessed relative to CC features. The integration of ACE and ACS significantly enhanced the performance of all the evaluated machine learning algorithms, with the light gradient boosting machine (LGBM) model, considering ACE and ACS as input variables, achieving the highest accuracy (precision: 98.56%; recall: 97.78%; F1-score: 98.17%). Owing to its heightened detection sensitivity, the LGBM model identified additional wildfires that the GEO-KOMPSAT-2A forest fire products had failed to detect. The variations in the environmental heterogeneity and wildfire intensity significantly diminished the effectiveness of conventional temperature anomaly-based algorithms. ACE and ACS effectively mitigated performance deterioration attributable to environmental heterogeneity and intensity variations, respectively. This investigation analyzed the potential error sources in conventional satellite-based wildfire detection models and applied a novel methodology to refine them, ultimately proposing a model that can be generalized across varied environmental conditions and wildfire intensities.