Seasonal reservoir inflow forecasting with low-frequency climatic indices: a comparison of data-driven methods

Abstract This paper investigates the potential of using data-driven methods, namely Bayesian neural networks (BNN), recurrent multi-layer perceptrons (RMLP), time-lagged feed-forward networks (TLFN), and conventional multi-layer perceptrons (MLP) to forecast seasonal reservoir inflows of the Churchill Falls watershed in northeastern Canada. A climate variability indicator (the El Niño-Southern Oscillation, ENSO) is used as additional information to historical inflow time series in order to predict seasonal reservoir inflows. The prediction results showed that the Bayesian neural network model was best able to capture the additional information provided by the ENSO series, and provided improved predictions in spring and summer seasons relative to the same model using only reservoir inflows. Similarly, time-lagged feed-forward networks and recurrent multi-layer perceptrons showed some improved forecast skill in spring when the ENSO index series are used but generally provided superior performance overall. The conventional multi-layer perceptron appears unable to capture relevant information from the ENSO series regardless of the season. However, when only historical flow series are used, all the selected data-driven methods provide very competitive forecast performances.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Ashutosh Kumar Singh,et al.  Coupled oceanic‐atmospheric variability and U.S. streamflow , 2005 .

[3]  R Govindaraju,et al.  ARTIFICIAL NEURAL NETWORKS IN HYDROLOGY: II, HYDROLOGIC APPLICATIONS , 2000 .

[4]  Francis H. S. Chiew,et al.  Seasonal streamflow forecasting in eastern Australia and the El Niño–Southern Oscillation , 1998 .

[5]  Elfatih A. B. Eltahir,et al.  El Niño and the Natural Variability in the Flow of the Nile River , 1996 .

[6]  Paulin Coulibaly,et al.  A recurrent neural networks approach using indices of low-frequency climatic variability to forecast regional annual runoff. , 2000 .

[7]  S. Islam,et al.  The El Niño southern oscillation and long‐range forecasting of flows in the Ganges , 2001 .

[8]  A. Barnston,et al.  Long-Lead Forecasts of Seasonal Precipitation in Africa Using CCA , 1996 .

[9]  Bernard Bobée,et al.  Neural Network‐Based Long‐Term Hydropower Forecasting System , 2000 .

[10]  B. Bobée,et al.  Multivariate Reservoir Inflow Forecasting Using Temporal Neural Networks , 2001 .

[11]  Paulin Coulibaly,et al.  Wavelet analysis of variability in annual Canadian streamflows , 2004 .

[12]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[13]  Orazio Giustolisi,et al.  Improving generalization of artificial neural networks in rainfall–runoff modelling / Amélioration de la généralisation de réseaux de neurones artificiels pour la modélisation pluie-débit , 2005 .

[14]  B. Bobée,et al.  Improving extreme hydrologic events forecasting using a new criterion for artificial neural network selection , 2001 .

[15]  Guiling Wang,et al.  Use of ENSO information in medium- and long-range forecasting of the Nile floods , 1999 .

[16]  Paulin Coulibaly,et al.  Bayesian neural network for rainfall‐runoff modeling , 2006 .

[17]  A. Barnston,et al.  Skill of Seasonal Climate Forecasts in Canada Using Canonical Correlation Analysis , 1996 .

[18]  Jose C. Principe,et al.  Neural and adaptive systems : fundamentals through simulations , 2000 .

[19]  Dimitri P. Solomatine,et al.  On the encapsulation of numerical-hydraulic models in artificial neural network , 1999 .

[20]  Bernard Bobée,et al.  Prévision hydrologique par réseaux de neurones artificiels : état de l'art , 1999 .

[21]  Christian W. Dawson,et al.  Hydrological modelling using artificial neural networks , 2001 .

[22]  Jouko Lampinen,et al.  Bayesian approach for neural networks--review and case studies , 2001, Neural Networks.

[23]  Thomas C. Piechota,et al.  Long Range Streamflow Forecasting Using El Nino-Southern Oscillation Indicators , 1999 .

[24]  M. Cane,et al.  Annual river discharge in southeastern Australia related to El Nino‐Southern Oscillation forecasts of sea surface temperatures , 1993 .

[25]  Paulin Coulibaly,et al.  Spatial and Temporal Variability of Canadian Seasonal Streamflows , 2005 .

[26]  Prediction of summer inflows to lakes in the Southern Alps, New Zealand, using the spring Southern Oscillation Index , 1996 .

[27]  E. Rasmusson,et al.  Variations in Tropical Sea Surface Temperature and Surface Wind Fields Associated with the Southern Oscillation/El Niño , 1982 .