Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Limitations of runoff models to accurately predict floods due to the non-linearity of rainfallrunoff process and the complex nature of hydroclimatological processes make them less desirable for some applications. Black box models such as the artificial neural network (ANN) provide a mathematically flexible structure to identify complex non-linear relationship between inputs and outputs without attempting to explain the nature of the phenomena. A multilayer perceptron ANN technique with an error back propagation algorithm was applied to a multi-time scale prediction of the stage of a hydrologically closed lake, Devils Lake (DL) and discharge of Red River of the North at Grand Forks station (RR-GF) in North Dakota. The modeling exercise used 1 year (2002), 5 years (1998-2002), and 27 years (1975-2002) hydrometeorological data for the daily, weekly and monthly predictions, respectively, for both basins with portion of data for training (calibration) and the remaining for testing (verification). Implementation of the model using antecedent precipitation, stage/discharge in addition to current precipitation and air temperature improved the prediction. Comparison of the model output with the observed values showed average testing prediction efficiency (E) of 86% and 45% for DL and RR-GF basins, respectively with higher efficiency for the daily than monthly simulations.