DETERMINATION OF THE EFFECTS OF VARIOUS SPECTRAL INDEX COMBINATIONS ON SEASONAL LAND USE AND LAND COVER (LULC) CHANGES USING RANDOM FOREST (RF) CLASSIFICATION CASE STUDY: SOUTHEAST MARMARA REGION 2016-2020
Turkish Journal of Remote Sensing · 2024
DOI: 10.51489/tuzal.1395189 ↗Kurz gefasst
Fachartikel in der Zeitschrift Turkish Journal of Remote Sensing, 2024. Verfasst von Eda Aşci und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Gefördert von: This study is part of the Eda ASCI’s Master Thesis on Graduate School of Çanakkale Onsekiz Mart University, School of Graduate Studies, Department of Geographi….
Abstract (Originalsprache)
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 South-Eastern Marmara region, which is one of Turkey's important industrial coastal areas, is also affected by the surrounding changes. The study area was selected on purposes to determine LULC change and accuracy of classification using Sentinel-2 based vegetation indices combinations. In study area, the Gemlik-Bursa Northern Interchange investments area and newly construction of the 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 in the area covering the Armutlu district of Yalova province and the Osmangazi, Mudanya, and Gemlik districts of Bursa province. The RF (Random Forest) classification technique has been applied to original bands and combination of 21 new bands using indices obtained from satellite images for 3 seasons in 2016 and 2020. The highest accuracy results for the winter, spring, and summer seasons of 2016 were observed in OI12 (%82,93), ORF (%84,44), and again ORF (%84,67) indices, while in 2020, they were observed in OI5 (%85,89), ORF (%84,75), and OI6 (%84,63) indices. The main reason for changes in classification accuracy due to the influence of different bands is understood to be the interaction between the LULC on the ground in the season when the image was acquired and the characteristics in the bands. It was determined that the changes in LULC in the South-Eastern Marmara would be due to investment decisions taken in the region, resulting population growth, and pixel-based classification errors due to spectral reflections in some areas.
Förderung
- This study is part of the Eda ASCI’s Master Thesis on Graduate School of Çanakkale Onsekiz Mart University, School of Graduate Studies, Department of Geographi…
Zitieren
APA
Aşci, E., & Genç, L. (2024). DETERMINATION OF THE EFFECTS OF VARIOUS SPECTRAL INDEX COMBINATIONS ON SEASONAL LAND USE AND LAND COVER (LULC) CHANGES USING RANDOM FOREST (RF) CLASSIFICATION CASE STUDY: SOUTHEAST MARMARA REGION 2016-2020. Turkish Journal of Remote Sensing. https://doi.org/10.51489/tuzal.1395189
Vancouver
Aşci E, Genç L. DETERMINATION OF THE EFFECTS OF VARIOUS SPECTRAL INDEX COMBINATIONS ON SEASONAL LAND USE AND LAND COVER (LULC) CHANGES USING RANDOM FOREST (RF) CLASSIFICATION CASE STUDY: SOUTHEAST MARMARA REGION 2016-2020. Turkish Journal of Remote Sensing. 2024. doi:10.51489/tuzal.1395189
BibTeX
@article{Aci2024,
author = {Aşci, Eda and Genç, Levent},
title = {DETERMINATION OF THE EFFECTS OF VARIOUS SPECTRAL INDEX COMBINATIONS ON SEASONAL LAND USE AND LAND COVER (LULC) CHANGES USING RANDOM FOREST (RF) CLASSIFICATION CASE STUDY: SOUTHEAST MARMARA REGION 2016-2020},
journal = {Turkish Journal of Remote Sensing},
year = {2024},
doi = {10.51489/tuzal.1395189}
}
EUVIMED