期刊名称：International Journal of Environment and Geoinformatics
电子版ISSN：2148-9173
出版年度：2021
卷号：8
期号：4
页码：529-536
语种：English
出版社：IJEGEO
摘要：Global warming threatens ecosystems through rising temperatures, increasing sea levels, drought, and extreme weather conditions.The natural balance of seas and oceans is also at stake with recent outbreaks of mucilage events all over the world. The mucilagephenomenon, which has been frequently observed in the Adriatic and Tyrrhenian seas, has taken place the second time in the Sea ofMarmara in Spring 2021. The Sea of Marmara dividing the Asian and European parts of Turkey is an important inland sea withheavy maritime traffic, hosting many industrial zones and surrounded by highly populated cities. This study aims to determine themucilage formations that were observed intensely all around the Sea of Marmara, focusing on the coasts of Istanbul, Kocaeli, Yalova,and Bursa through classifying Sentinel-2A images dated 19 and 24 May 2021, when the peak period of mucilage bloom, using a newparadigm of object-based image analysis (OBIA) approach. To create representative and homogenous image objects, multi-resolutionsegmentation was applied, and its result was inputted into a classification process using Random Forest (RF) classifier to generatethematic maps. The produced results were compared with pixel-based classification and a high correlation was estimated. Objectbased classification was found effective for the determination of mucilage-covered areas (> 90% overall accuracy) for bothconsidered dates. More specifically, areas covered with mucilage aggregates were computed as 56.15 km² and 67.51 km² for 19 Mayand 24 May 2021, respectively, indicating rapid growth in only 5-day period. The resulting thematic maps revealed that mucilagewas heavily distributed in the gulfs of Gemlik and Izmit and along the coasts of Darica, Tuzla and Pendik.
