Remote sensing image fusion for mapping and monitoring wetlands in the Central Anatolian Region, Turkey

Wetlands provide a number of ecological services and a number of valuable functions. As one of the most important eco-systems, wetlands are threatened by both natural and anthropogenic activities. Mapping wetland is one of the curtail needs in order to prevent further loss. Since the beginning of the remote sensing and geographic information systems (GIS) revolution, different approaches using satellite images have been used for mapping and monitoring wetlands. In this study, through image fusion, the potential of the recently launched Sentinel satellites, both separate and in combination, was investigated for accurately mapping of different wetland classes using Support Vector Machines (SVMs) learning classifier. Before the classification, a monthly dynamic of wetland area has been conducted, and high-resolution imagery of one test area (Balikdami) has been acquired. For investigating the influence of the sensors in land cover classification, especially in wetland areas, six different datasets have been analyzed. Thus, the influence of the red-edge, multi-sensor, and multi-temporal or multi-season data have been investigated. The results showed that for more accurate mapping of different wetland classes, different datasets should be used. The red-edge bands have significant influence over the intensive vegetated wetland classes such as swamps, and the radar bands have significant influence over partially decayed vegetated wetland areas such as bogs. Different date radar data also have significant influence over the wetland areas. For future studies, in addition to the analyzed datasets, we recommend adding and investigating several vegetation indices for mapping and monitoring wetland areas in different study areas.