Post-Fire Burned Area Detection Using Machine Learning and Burn Severity Classification with Spectral Indices in İzmir: A SHAP-Driven XAI Approach

Basit Öğe Kaydı
dc.authorid0000-0002-0609-8032
dc.authorid0000-0002-7927-4703
dc.authorid0000-0002-5951-0107
dc.contributor.authorGündüz, Halil İbrahim
dc.contributor.authorTorun, Ahmet Tarık
dc.contributor.authorGezgin, Cemil
dc.date.accessioned2025-07-11T06:34:11Z
dc.date.available2025-07-11T06:34:11Z
dc.date.issued2025
dc.departmentMühendislik Fakültesi
dc.description.abstractThis study was conducted to precisely map burned areas in fire-prone forest regions of İzmir and analyze the spatial distribution of wildfires. Using Sentinel-2 satellite imagery, burn severity was first classified using the dNBR and dNDVI indices. Subsequently, machine learning (ML) algorithms—RF, XGBoost, LightGBM, and AdaBoost—were employed to classify burned and unburned areas. To enhance model performance, hyperparameter optimization was applied, and the results were evaluated using multiple accuracy metrics. This study found that the RF model achieved the highest performance, with an overall accuracy of 98.0% and a Kappa coefficient of 0.960. In comparison, classification based solely on spectral indices resulted in overall accuracies of 86.6% (dNBR) and 81.7% (dNDVI). A key contribution of this study is the integration of Explainable Artificial Intelligence (XAI) through SHapley Additive exPlanations (SHAP) analysis, which was used to interpret the influence of key spectral and environmental variables in burned area classification. SHAP analysis made the model decision processes transparent and identified dNBR, dNDVI, and SWIR/NIR bands as the most influential variables. Furthermore, spatial analyses confirmed that variations in spectral reflectance across fire-affected regions are critical for accurate burned area delineation, particularly in heterogeneous landscapes. This study provides a scientific framework for post-fire ecosystem restoration, fire management, and disaster strategies, offering decision-makers data-driven and effective intervention strategies.
dc.identifier.doi10.3390/fire8040121
dc.identifier.issn25716255
dc.identifier.issue4
dc.identifier.scopus105003386789
dc.identifier.urihttps://dx.doi.org/10.3390/fire8040121
dc.identifier.urihttps://hdl.handle.net/20.500.12451/13253
dc.identifier.volume8
dc.identifier.wosWOS:001475050400001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorGündüz, Halil İbrahim
dc.institutionauthorid0000-0002-0609-8032
dc.language.isoen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.relation.ispartofFire
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/embargoedAccess
dc.subjectBurn Severity
dc.subjectdNBR
dc.subjectdNDVI
dc.subjectMachine Learning
dc.subjectSentinel-2
dc.subjectSHAP
dc.subjectWildfires
dc.subjectXAI
dc.titlePost-Fire Burned Area Detection Using Machine Learning and Burn Severity Classification with Spectral Indices in İzmir: A SHAP-Driven XAI Approach
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
gunduz-halil ibrahim.pdf
Boyut:
6.64 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Makale Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu