Artificial neural networks (ANNs) are mathematical models based on the transfer of information through a network of functional units, called neurons. Given a number of input values, entered at the basis of the network, one or more outputs are generated. Several algorithms exist for determining the inner parameters of the neural network, based on calibration data. ANNs are currently recognized as an alternative to multivariate statistics in predicting aquatic communities. Recently, several studies have been published concerning the application of neural networks in relating freshwater macroinvertebrates with their abiotic environment (e.g. WALLEY & FoNTAMA 1998, ScHLEITER et al. 1999, GABRIELS er al. 2000). The aim of this srudy was to test the potential of ANNs in predicting which taxa would occur in the sediment at a particular sampling point. For this purpose, a dataset of sediment samples from unnavigable watercourses, including abiotic variables and abundances of macroinvenebrates, was used.
[1]
W. J. Walley,et al.
Neural network predictors of average score per taxon and number of families at unpolluted river sites in Great Britain
,
1998
.
[2]
Peter Goethals,et al.
Modelling benthic macro-invertebrate communities in Flanders using artificial neural networks
,
2000
.
[3]
Ingrid M. Schleiter,et al.
Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks
,
1999
.
[4]
Geoffrey E. Hinton,et al.
Learning representations by back-propagating errors
,
1986,
Nature.
[5]
Niels De Pauw,et al.
Biotic index for sediment quality assessment of watercourses in Flanders, Belgium
,
2001,
Aquatic Ecology.