Improving extreme hydrologic events forecasting using a new criterion for artificial neural network selection

Authors

  • Paulin Coulibaly,

    Corresponding author
    1. NSERC/Hydro-Quebec/Alcan Chair in Statistical Hydrology, Institut National de la Recherche Scientifique (INRS-Eau), Sainte-Foy, Qc, Canada G1V 4C7
    • NSERC/Hydro-Quebec/Alcan Chair in Statistical Hydrology, Institut National de la Recherche Scientifique (INRS-Eau), Sainte-Foy, Qc, Canada G1V 4C7
    Search for more papers by this author
  • Bernard Bobée,

    1. NSERC/Hydro-Quebec/Alcan Chair in Statistical Hydrology, Institut National de la Recherche Scientifique (INRS-Eau), Sainte-Foy, Qc, Canada G1V 4C7
    Search for more papers by this author
  • François Anctil

    1. Department of Civil Engineering, Centre de Recherche Géomatique, Université Laval, Sainte-Foy, QC, Canada G1K 7P4
    Search for more papers by this author

Abstract

The issue of selecting appropriate model input parameters is addressed using a peak and low flow criterion (PLC). The optimal artificial neural network (ANN) models selected using the PLC significantly outperform those identified with the classical root-mean-square error (RMSE) or the conventional Nash–Sutcliffe coefficient (NSC) statistics. The comparative forecast results indicate that the PLC can help to design an appropriate ANN model to improve extreme hydrologic events (peak and low flow) forecast accuracy. Copyright © 2001 John Wiley & Sons, Ltd.

Ancillary