Abstract
Water level change of Lake Tana, the source of the Blue Nile was analyzed. Correlations between the water level change and global sea surface temperature (GSST) were calculated and teleconnections were found. Prediction of water level was performed using a recurrent artificial neural network model. First, the seasonal change of water level was divided into three phases, the rising, recession 1, and recession 2 phases. The water level increased during the rising phase, decreased rapidly during the recession 1 phase, and decreased at a uniform rate during the recession 2 phase. To find teleconnections of the water level change in the rising phase with GSST, correlations between the level change and GSST were calculated. Sea regions on the Pacific Ocean indicated significant correlations with the level change at lag 0–1 month and lag 6–7 months. There was a strongly correlated sea zone over the western Pacific Ocean at time lags of 6–7 months. To predict water level change, SST time series of the correlated zone was applied to a recurrent neural network model. Predictions of changes of the rise of the water level of Lake Tana during the rainy season from teleconnections with SSTs via the neural network model simulated the observed changes well (r = 0.795). Prediction of the changes of Lake Tana’s water level with a lead time of 6–7 months can greatly facilitate management of the lake’s water resources.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.