Abstract
In this study, artificial neural network model was constructed in order to predict the water level. The target stream is the main stream between Yongdam Dam and Daecheong Dam in the Geum river Basin, and as input data at the upstream, the observation water level at the Sutong and the Hotan observatory and the water level at the Songcheon observatory, which is a tributary, are considered as input data. As an output value, an artificial neural network model was constructed to predict the water level of the Okcheon station at the downstream with 3 hours and 6 hours lead time. The artificial neural network model was constructed around a single hidden layer, and the sensitivity to the prediction accuracy of three learning variables was analyzed: Epoch number, Batch size, and Learning rate. For training, testing, and validation of artificial neural networks, learning was conducted using observed water level data for 13 years from 2000 to 2012, and water level data for two years from 2013 to 2014. The optimal model was selected through the used test. In addition, water level prediction from 2015 to 2016 was performed using the selected optimal model.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Crisis and Emergency Management: Theory and Praxis
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.
