Paper Info
Title
Selection of smoothing parameter estimators for general regression neural networks - Applications to hydrological and water resources modelling
Abstract
Multi-layer perceptron artificial neural networks are used extensively in hydrological and water resources modelling. However, a significant limitation with their application is that it is difficult to determine the optimal model structure. General regression neural networks (GRNNs) overcome this limitation, as their model structure is fixed. However, there has been limited investigation into the best way to estimate the parameters of GRNNs within water resources applications. In order to address this shortcoming, the performance of nine different estimation methods for the GRNN smoothing parameter is assessed in terms of accuracy and computational efficiency for a number of synthetic and measured data sets with distinct properties. Of these methods, five are based on bandwidth estimators used in kernel density estimation, and four are based on single and multivariable calibration strategies. In total, 5674 GRNN models are developed and preliminary guidelines for the selection of GRNN parameter estimation methods are provided and tested.
Year
DOI
Venue
2014
10.1016/j.envsoft.2014.05.010
Environmental Modelling & Software
Keywords
Field
DocType
general regression neural networks,smoothing parameter estimators,artificial neural networks,multi-layer perceptrons,hydrology and water resources,extreme and average events
Multivariable calculus,Regression,Computer science,Smoothing,Artificial intelligence,Estimation theory,Artificial neural network,Perceptron,Machine learning,Estimator,Kernel density estimation
Journal
Volume
Issue
ISSN
59
1
1364-8152
Citations 
PageRank 
References 
8
0.60
13
Authors
3
Name
Order
Citations
PageRank
Xuyuan Li1191.93
Aaron C. Zecchin21168.85
Holger R. Maier373872.97