Spatiotemporal forecasting of water change trends in Urmia Lake through to 2030, using STC-based models

Abstract

The purpose of this paper is to forecast the spatiotemporal water change trends in Urmia Lake through 2030. Three space-time cube-based models were applied. The Forest-based forecast model with a mean of 0.14 forecast RMSE and 0.39 validation RMSE, had a better performance. According to the model’s results, the peripheral parts of the lake will mainly stay completely arid with a 42.5% extension in the entire period, 21.7% in spring, and a 27% reduction in winter. In the middle parts, the aridity will increase by 121% in summer, 93% in fall, and 38% in spring. Eventually, the centric areas will not be completely arid, however, the water patterns extent will decrease by 53.46% in fall, 34.6% in spring, and 28.5% in summer. Additionally, southern, eastern, western, and northern areas will experience worse conditions, respectively. The findings can be used for water resource management and water restoration plans for the lake.