Author(s): Lekhangani Arunoda Basnayakea; Vladan Babovic
Linked Author(s): Vladan Babovic
Keywords: Flow routing; Data driven techniques; Artificial neural networks; Distributed Modelling; Cluster-based modelling
Abstract: This paper demonstrates the application of data driven models for distributed flow routing. Daily flow data of the four stations in the White River of Indiana are used in the study. In the first part of the study, single-station models are developed, firstly using the nearest upstream station data and secondly with all existing upstream flow data. Then, single-station models are sequentially applied to estimate the downstream flows. The model performance is evaluated with different data time intervals. Comparison of model results indicates that single river reach model performance can be improved with temporally refined data. In the second part of this study, cluster-based modelling is applied to improve the flow estimations. Simulation results of this preliminary analysis indicate that it is a promising method to improve the streamflow forecasts.