Özet:

Floods are natural disasters that corrupt vegetation, cause loss of lives, and harm economies. There are many cases floods originate, sometimes natural, sometimes man-made. The use of agricultural fields unconsciously, land cover modifications, incorrect city planning can be listed as unnatural reasons. Modeling and mapping the floods, real-time monitoring with satellite are cost-efficient ways of decreasing the causes of floods and helping the authorities to give the exact decisions during or after the event. Synthetic-aperture radar (SAR) satellite imagery helps in monitoring disasters like flooding. The all-weather operating capability provides cloud-free day and night imagery, even in the worst weather conditions. In this paper, Sentinel-1 satellite imagery provided by European Space Agency (ESA) is used to investigate the flood event that happened in January 2020 in the Tarsus agricultural field (West Cukurova Region) of Mersin, Turkey. Sentinel-1 imagery for the nearest dates is collected, pre-processed, and thresholded with Otsu’s method and a flood map is obtained. Sentinel-2 satellite imagery for the same study area is used to verify the Sentinel-1 output composite. Spectral indices are applied on Sentinel-2 composite and classification is done with Random Forests, CART, Support Vector Machine (SVM) and Naive Bayes algorithms. Random Forest and SVM algorithms provided the best classification result. Finally, Sentinel-1 and Sentinel-2 products are overlaid as change management.

Anahtar Kelimeler: