Sentinel-2 Remote Sensing for Forest Fire Mapping and Climate Resilience: Operational Solutions for Mediterranean Ecosystems in Northern Algeria

Forest fires are an accelerating, climate-driven threat to Mediterranean ecosystems along the Silk Road, and Northern Algeria is experiencing increasingly severe episodes. This paper presents an operationally validated methodology for mapping burned areas from free Sentinel-2 imagery (Copernicus), combining multi-temporal preprocessing, NDVI, NBR and the differenced Normalized Burn Ratio (dNBR) with a four-class fire severity classification. Applied to a coastal forest zone in the wilaya of El Tarf, it mapped 3,815 ha of burned area, 64.2% of which was of high or very high severity. Validation against 120 ground control points yielded an overall accuracy of 87.4% (Cohen's Kappa = 0.81). The optimal detection window is 10–30 days after the fire, with vegetation regeneration over 4–6 months. Sentinel-1 SAR integration, machine-learning automation and institutional transfer to civil protection services are outlined as routes to operational scaling and transboundary early warning across the Silk Road.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-15
DOI
https://doi.org/10.5281/zenodo.24262917
Primary Topic
Fire effects on ecosystems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Sentinel-2 Remote Sensing for Forest Fire Mapping and Climate Resilience: Operational Solutions for Mediterranean Ecosystems in Northern Algeria

Seyfallah Bouraoui
Zenodo (CERN European Organization for Nuclear Research)
Fire effects on ecosystems
article

Sentinel-2 Remote Sensing for Forest Fire Mapping and Climate Resilience: Operational Solutions for Mediterranean Ecosystems in Northern Algeria

Seyfallah Bouraoui
article en

Abstract

Forest fires are an accelerating, climate-driven threat to Mediterranean ecosystems along the Silk Road, and Northern Algeria is experiencing increasingly severe episodes. This paper presents an operationally validated methodology for mapping burned areas from free Sentinel-2 imagery (Copernicus), combining multi-temporal preprocessing, NDVI, NBR and the differenced Normalized Burn Ratio (dNBR) with a four-class fire severity classification. Applied to a coastal forest zone in the wilaya of El Tarf, it mapped 3,815 ha of burned area, 64.2% of which was of high or very high severity. Validation against 120 ground control points yielded an overall accuracy of 87.4% (Cohen's Kappa = 0.81). The optimal detection window is 10–30 days after the fire, with vegetation regeneration over 4–6 months. Sentinel-1 SAR integration, machine-learning automation and institutional transfer to civil protection services are outlined as routes to operational scaling and transboundary early warning across the Silk Road.

Zenodo (CERN European Organization for Nuclear Research)
University of Sciences and Technology Houari Boumediene (DZ)
Fire effects on ecosystems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon