Optimizing burn area mapping with Sentinel-2: A comparative evaluation of spectral indices for accurate and efficient post-fire delineation
Loading...
Files
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
DOI
Abstract
This study evaluates Sentinel-2 imagery for wildfire detection and post-fire assessment by comparing spectral indices (NDVI, BAI, BAIS2, CSI, NBR) using the separability index and accuracy metrics validated with PlanetScope data. The differenced Normalized Burn Ratio (dNBR) was most effective, achieving 90.7% accuracy and a Kappa of 0.8. Future research should explore machine learning methods, test indices across ecosystems, assess temporal stability, develop field validation databases, and integrate Sentinel-2 with other sensors like SAR and UAVs to improve fire mapping and overcome cloud cover issues.
Description
Keywords
Citation
Collections
Endorsement
Review
Supplemented By
Referenced By
Rights and licensing
Hozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.