Monitoring and Prediction of the Urmia Lake Drying Trend Based on Time-Series Remotely Sensed Images and Artificial Neural Networks

Urmia Lake, which is the second largest permanent hypersaline lake in world, shrinking recent decades. Since accurate spatial information about essential to managing current and emerging crises of lake, this study used Lake satellite images time-series investigate drought trends by analyzing via Artificial Neural Networks (ANN). The proposed approach comprising following four steps. First, yearly Landsat (2000-2022) are corrected geometrically radiometrically. Then, 2000-2020 classified into five land cover classes, including; deep water, shallow salt, soil, vegetation. In third step, ANN trained for 2000-2019 as input tested 2020 an output. Finally, predict future covers (for 2021 2022 years). order evaluate model, predicted maps were compared with their corresponding ground truth quantitative criteria calculated. overall accuracy prediction equal 92.75% 90.62%, respectively, indicates high capability method modeling predicting changes its shores.