Estuarine flood modelling using artificial neural networks

Prediction of water levels at estuaries poses a significant challenge for modelling of floods due to the influence of tidal effects. In this study, a two-stage forecasting system is proposed. In the first stage, the tidal portion of the available records is used to develop a tidal prediction system. The predictions of the first stage are used for flood modelling in the second. Experimental results suggest that the proposed flood modelling approach is advantageous for forecasting flood levels with more than 1 hour lead times.Prediction of water levels at estuaries poses a significant challenge for modelling of floods due to the influence of tidal effects. In this study, a two-stage forecasting system is proposed. In the first stage, the tidal portion of the available records is used to develop a tidal prediction system. The predictions of the first stage are used for flood modelling in the second. Experimental results suggest that the proposed flood modelling approach is advantageous for forecasting flood levels with more than 1 hour lead times.
View less >

Conference Title

PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

DOI

https://doi.org/10.1109/IJCNN.2014.6889704

Subject

Other environmental sciences not elsewhere classified

Publication URI

http://hdl.handle.net/10072/157503

Collection

Conference outputs