Ecological Modelling 120 (1999) 141–156
pH modelling by neural networks.
Application of control
and validation data series in the Middle Loire river
Florentina Moatar a,
*, Franc¸oise Fessant b
, Alain Poirel c
a
LTHE, UMR 5564,...
More
Ecological Modelling 120 (1999) 141–156
pH modelling by neural networks.
Application of control
and validation data series in the Middle Loire river
Florentina Moatar a,
*, Franc¸oise Fessant b
, Alain Poirel c
a
LTHE, UMR 5564, CNRS-INPG-ORSTOM-UJF, BP 53, 38041, Grenoble Cedex 9, France
b
INRETS-MAIA, 2 a6enue du General Malleret Join6ille, 94114, Arcueil, France
c
EDF-Di6ision Technique Ge´ne´rale, 21, a6enue de l’Europe, BP 41, 38 040, Grenoble Cedex 9, France
Abstract
Artificial neural networks (ANNs) are applied as a new type of model to estimate the daily pH of the Middle Loire
river.
The model is used for pH measurement screening, error detection (abnormal values, discontinuities and
recording drifts) and validating the collected data.
The measured values of pH are compared with the values estimated
by the ANN model using statistical tests to verify homogeneity and stationarity.
River water pH is affected by
numerous processes: biological, physical and g
Less