Mapping the Floristic Dynamics of the Dried Aral Sea Bed using Artificial Intelligence and Remote Sensing Technologies

The desiccation of the Aral Sea has given rise to new ecological landscapes, demanding modern approaches for monitoring and managing emergent ecosystems. This study applies remote sensing and artificial intelligence (AI) methods to map and assess the vegetation cover across the exposed seabed. Using NDVI and LAI indices derived from Landsat satellite imagery, combined with ground surveys and AI-based classification algorithms, we created a dynamic and spatially referenced vegetation database. Results show an increase in hardy halophytic species in specific zones, influenced by soil salinity, microclimatic conditions, and landform types. GIS and convolutional neural networks were integrated to detect and map species patterns, supporting long-term biodiversity monitoring and restoration efforts. The approach lays a foundation for scalable, data-driven ecological monitoring of one of the world’s most extreme anthropogenic deserts.