Neural Networks in the Ice-Correction of Discharge Observations: Paper presented at the Nordic Hydrological Conference (Akureyri, Iceland–August 1996)

• Published in: Hydrology research Vol. 28; no. 4-5; p. 283
• Main Authors: Huttunen, Markus, Vehviläinen, Bertel, Ukkonen, Esko
• Format: Journal Article
• Language: English
• Published: Copenhagen IWA Publishing 01.08.1997
• Subjects: Backwater effect; Backwaters; Discharge; Error correction; Hydrology; Ice; Ice effects; Mathematical models; Modelling; Neural networks; Parameters

We have applied three models, a neural network, a conceptual model and a combination of these two a hybrid model, to model the backwater effect of ice in a river. The neural network is a black-box model. It is based mainly on observed data and it lacks the expert knowledge of the system. The concept...