Akademik Veri Yönetim Sistemi
Turkish Journal of Remote Sensing, cilt.6, sa.1, ss.12-25, 2024 (Hakemli Dergi)
The effects of irregular population growth, migration mobility, and vegetation dynamics
by humans can lead to changes in Land Use and Land Cover (LULC). Changes in LULC are
particularly significant in coastal areas associated with industrial activities. The
southeastern Marmara region, which is one of Turkey's industrial coastal areas, is also
affected by the surrounding changes. The study area was selected to determine LULC
change and classification accuracy using Sentinel-2 vegetation indices combinations. In
the study area, the Gemlik-Bursa Northern Interchange Investments Area and TOGG
(Turkey's Automobile Initiative Group) factory are located. The study area was
determined by creating a 5-km buffer zone from the coast to the mainland covering
Armutlu district of Yalova province and Osmangazi, Mudanya, and Gemlik districts of
Bursa province. Random Forest (RF) classification technique was applied both to the
original bands and to 21 new band combinations that are derived from Sentinel-2
multispectral satellite imagery for 3 seasons in 2016 and 2020. The new band
combinations used for classification were created by adding the normalized vegetation
indices, the original bands and the bands obtained from the simple ratio formula. In
2016, the highest accuracy results for the winter, spring, and summer seasons were
observed for the OI12 (82.93%), ORF (84.44%), and ORF (84.67%) indices, while in 2020
were observed for the OI5 (85.89%), ORF (84.75%), and OI6 (84.63%) indices. In
Southeast Marmara, investment decisions taken at national level have led to population
growth in the region. Although it was observed that there was no significant change in
classification accuracy with the addition of spectral features to the original bands such
as NDVI and SR, we believe that future testing of the data with different statistical and
machine learning methods provide higher accuracy