Akademik Veri Yönetim Sistemi
SHIPS AND OFFSHORE STRUCTURES, cilt.1, sa.1, ss.1-23, 2026 (SCI-Expanded, Scopus)
Hydrographic surveys are essential for safe navigation and coastal management; however, conventional vessel-based methods are fuel-intensive and produce significant carbon emissions. This study assesses the carbon footprint of hydrographic surveys in Türkiye and evaluates Satellite-Derived Bathymetry (SDB) combined with machine learning as a low-carbon alternative. Annual emissions from the hydrographic fleet of Istanbul University’s Institute of Marine Sciences and Management are estimated at 3850 tCO₂e. Bathymetric data derived from Sentinel-2 imagery were processed using machine learning models including KNN, RF, SVM, and LR. Case studies in Samsun (Black Sea), Izmir Bay (Aegean Sea), and Iskenderun Bay (Mediterranean Sea) showed strong agreement between SDB outputs and in situ measurements (R² ≥ 0.98; RMSE: 0.55–0.89 m). Results confirm compliance with IHO S-44 standards and demonstrate that SDB is cost-effective and significantly less carbon-intensive than traditional methods, supporting sustainable hydrography.