Investigating the surface changes of Urmia Lake using the integration of Landsat-8 and Sentinel-2 satellite data
Subject Areas : Applications in water resources managementAmir Ghayebi 1 * , Ahmad Ahmadi 2 , Behnaz Bigdeli 3
1 - Civil Engineering/Faculty of Civil Engineering/Shahroud University of Technology/Shahroud/Iran
2 - Dept of Civil Engineering, Shahrood University of Technology, Shahrood, Iran
3 - Dept of Civil Engineering, Shahrood University of Technology
Keywords: Supervised classification, Data Fusion, Surface water, Urmia Lake, Change detection, remote sensing,
Abstract :
Among environmental changes, water plays a very vital role in the political, social and economic issues of countries, which can be used as one of the most practical sources of water supply available to humans and animals. Investigating the fluctuations of the water level of the lakes in terms of the importance, location and nature of these water bodies has become especially important in recent years. Lake Urmia with an area of 51200 square kilometers is of special importance as the largest internal lake of Iran and the 20th lake in the world. Landsat-8 and Sentinel-2 satellite data for the years 2013 to 2021 were used to investigate and evaluate changes in the water level of Lake Urmia, vegetation and soil around it. First, radiometric and atmospheric corrections were made on the images, and then, while using Gram Schmidt and LMVM integrators to increase spatial resolution, NDWI, AWEI, WI2015 and NDVI indices were extracted in order to differentiate the lake water level from non-water. paid. Finally, by combining the indicators with each other and by sampling the training and test samples, in order to classify the images, supervised classifiers such as Maximum Likelihood, Support Vector Machine, Neural Network and Minimum Distance to Mean were used. Also, in order to improve the results, the output of the classifiers was merged using the majority voting method. The results of the research showed that the majority voting method was chosen as the most suitable classification method with the highest level of accuracy. The water level of Lake Urmia, the vegetation and soil around it have also undergone significant changes during the years 2013 to 2021, so that in 2021, compared to 2020, the water level decreased by 29.89%, and the vegetation increased by 16.08%. And the soil has increased by 17.50%.
_||_