Artificial Neural Networks (ANNs) are now widely used in many areas of science, medicine, finance and engineering. Analysis and prediction of time series of hydrological/and meteorological data is one such application. Problems that still exist in the application of ANN's are the lack of transparency and the expertise needed for training. An evolutionary algorithm-based method to train a type of neural networks called Product Units Based Neural Networks (PUNN) has been proposed in a 2006 study. This study investigates the applicability of this type of neural networks to hydrological time series prediction. The technique, with a few small changes to improve the performance, is applied to some benchmark time series as well as to a real hydrological time series for prediction. The results show that evolutionary PUNN produce more transparent models compared to widely used multilayer perceptron (MLP) neural network models. It is also seen that training of PUNN models requires less expertise compared to MLPs.
Evolutionary product unit based neural networks for hydrological time series analysis
Dulakshi S. K. Karunasingha, A. W. Jayawardena, W. K. Li; Evolutionary product unit based neural networks for hydrological time series analysis. Journal of Hydroinformatics 1 October 2011; 13 (4): 825–841. doi: https://doi.org/10.2166/hydro.2010.099
Download citation file:
Close
Dulakshi S. K. Karunasingha, A. W. Jayawardena, W. K. Li; Evolutionary product unit based neural networks for hydrological time series analysis. Journal of Hydroinformatics 1 October 2011; 13 (4): 825–841. doi: https://doi.org/10.2166/hydro.2010.099
Download citation file:
Close
Impact Factor 1.728
CiteScore 3.5 • Q2
Cited by
Subscribe to Open
This paper is Open Access via a Subscribe to Open model. Individuals can help sustain this model by contributing the cost of what would have been author fees. Find out more here.