Sürdürülebilir Kalkınma Amaçları

• 2
• 1
• 1
• 1

Yazarlar

• Bjelotomić Oršulić, Olga(1)
• Günen, Mehmet Akif(1)
• Türk, Salih(1)
• Yalvac, Sefa(1)

• MakaleAçık Erişim2026Scopus SJRQ1/r/gumushane/13897
  Severity-Based Mapping of Land-Subsidence Hazard Zones and Critical Hotspots Using SBAS-InSAR and Spatial Statistics: The Konya Metropolitan Area, Turkey

  Yalvac, Sefa; Bjelotomić Oršulić, Olga

  Land subsidence induced by excessive groundwater withdrawal has become one of the most significant geohazards affecting the Konya Closed Basin, Turkey. Although previous studies have successfully monitored ground deformation using geodetic and remote sensing techniques, limited attention has been devoted to transforming deformation measurements into quantitative, spatially classified hazard information. This study presents a severity-based framework for delineating land-subsidence hazard zones and critical hotspots in the Konya metropolitan area by integrating SBAS-InSAR observations and spatial statistical analyses. A total of 82 Sentinel-1 SAR acquisitions (41 ascending and 41 descending images) acquired between January 2023 and May 2026 were processed using the Small Baseline Subset (SBAS) technique. Ascending and descending line-of-sight deformation measurements were combined to derive vertical deformation rates, which were integrated with spatial statistical indicators and a composite severity index to quantify deformation clustering and classify subsidence severity. Hazard zones and critical hotspot areas were delineated through severity-based classification and spatial connectivity analyses. The results reveal a continuous north–south-oriented subsidence deformation belt extending across the eastern Konya. Maximum vertical subsidence rates exceeded 230 mm/yr, while spatial statistical analyses confirmed strongly clustered and statistically significant deformation patterns. Severity-based hazard zonation identified four hazard classes and a continuous high-hazard corridor. Clustering analysis further identified a dominant hotspot belt covering approximately 160 km2, with mean subsidence rates of approximately 142 mm/yr. A sensitivity analysis of the composite severity index weighting scheme, the spatial statistical neighborhood distance, the DBSCAN clustering parameters, and the number of Jenks severity classes confirmed that the resulting hazard zones and critical hotspot belt are robust to reasonable parameter variations. The findings demonstrate that land subsidence in Konya is organized as a spatially continuous regional-scale deformation system rather than a collection of isolated subsidence centers. The proposed framework transforms InSAR-derived deformation measurements into quantitative, decision-support hazard information and provides a transferable methodology for land-subsidence hazard assessment in groundwater-stressed urban environments.

  • 
  • 
  • 
  İncele
• MakaleYalnız künye2026Scopus SJRQ3/r/gumushane/13713
  Burned area detection using Sentinel-1 and Sentinel-2 features and analysis of ensemble models with explainable AI

  Günen, Mehmet Akif; Türk, Salih

  Wildfires are serious environmental disasters that threaten ecosystem sustainability, reduce biodiversity, and disrupt the global carbon cycle. This study aimed to improve the accuracy and interpretability of burned area mapping in the Bodrum, Köyceğiz, and Marmaris districts of Muğla province, Türkiye, by integrating multi-sensor satellite data with ensemble machine learning and explainable artificial intelligence (XAI). Sentinel-1 and Sentinel-2 imagery were processed to derive 50 optical and radar-based features, which were classified using four ensemble methods: AdaBoost.M1, Random Forest, GentleBoost, and RUSBoost. The SHapley Additive exPlanations framework was applied to quantify the contribution of each feature and guide feature selection. Results indicated that Sentinel-2 spectral indices, particularly NBR, NBRSWIR, and bands B12 and B8, were the most decisive variables for burned area classification, while Sentinel-1 features contributed less strongly overall but the IVH_ratio variable emerged as the most informative radar-based indicator. Among the classifiers, AdaBoost.M1 achieved the most stable and accurate performance, Random Forest showed strong sensitivity to spectral variability, GentleBoost performed effectively with reduced feature sets, and RUSBoost addressed class imbalance but showed weaker spatial continuity. Importantly, classification accuracy saturated after approximately 15 features, demonstrating that high accuracy can be achieved with fewer inputs and lower computational demand. Moreover, McNemar’s statistical test confirmed that the observed differences among classifiers were significant, highlighting GentleBoost’s clear superiority over other methods. Overall, the integration of optical and radar data with XAI provides a transparent, efficient, and replicable framework for operational burned area monitoring in Mediterranean ecosystems.

  • 
  • 
  AtıfScopus2·WoS3·OpenAlex2

  İncele