ESRI Land Cover ve Dynamic World arazi örtüsü verilerinin karşılaştırılması: Kıbrıs Adası örneği

Monitoring of Land Use/Land Cover (LU/LC) and determination of changes are very important in terms of understanding the relationship between human and the environment.With the development of remote sensing technologies, it has become easier to monitor LU/LC at local and global scales.However, many classification algorithms and methods have been developed and continue to be developed in the classification of remote sensing data.Classification algorithms and methods have advantages and disadvantages against each other.However, the detection of LULC can be used locally and globally.In this study, ESRI Land Cover and Dynamic World data, which are freely available on a global scale, were compared.Both of these data utilise Sentinel-2 imagery for classification and provide 10 m resolution LU/LC data.Cyprus island, an important island in the Mediterranean Sea, is considered in the comparison.For the comparison, firstly the consistency between the two data was analysed.Then, error matrices were created with the control points and their overall accuracy was analysed.There is 95% similarity in the water class, 78% in the crops class, 79% in the built area class, 97% in the trees class, 85% in the bare ground class, and 50% in the flooded vegetation class.Considering the general accuracy, ESRI Land Cover data gave an accuracy of 83.5% while Dynamic World data gave an accuracy of 84.5%.When the results are analysed, it is seen that both data can be used in the monitoring of LULC of the Cyprus island.