Monthly streamflow forecasting using neuro-wavelet techniques and input analysis

• Published in: Hydrological sciences journal Vol. 63; no. 15-16; pp. 2060 - 2075
• Main Authors: Honorato, André Gustavo da Silva Melo, Silva, Gustavo Barbosa Lima da, Guimarães Santos, Celso Augusto
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 10-12-2018; Taylor & Francis Ltd
• Subjects: Accuracy; Artificial neural networks; Components; Forecasting; low frequency; Mathematical models; Model accuracy; monthly streamflow forecasting; Neural networks; Stream discharge; Stream flow; Streamflow forecasting; Wavelet analysis; wavelet transform
• ISSN: 0262-6667; 2150-3435
• DOI: 10.1080/02626667.2018.1552788

Combinations of low-frequency components (also known as approximations) resulting from the wavelet decomposition are tested as inputs to an artificial neural network (ANN) in a hybrid approach, and compared to classical ANN models for flow forecasting for 1, 3, 6 and 12 months ahead. In addition, the inputs are rewritten in terms of the flow, revealing what type of information was being provided to the network, in order to understand the effect of the approximations on the forecasting performance. The results show that the hybrid approach improved the accuracy of all tested models, especially for 1, 3 and 6 months ahead. The input analyses show that high-frequency components are more important for shorter forecast horizons, while for longer horizons, they may worsen the model accuracy.