Date of Award
1995
Document Type
Thesis
Publication Status
Version of Record
Submission Date
October 2026
Thesis/Dissertation Advisor [Chair]
Scarlatos, Panagiotis (Pete) D.
Abstract
An artificial neural network is used to predict the stable geometry of alluvial rivers. This knowledge is useful for the design of new channels or modification of natural rivers. Given inputs of river discharge, slope and mean particle size, an artificial neural network is trained to predict the corresponding stable channel width and depth. The network is trained using data from several alluvial canals and rivers. Various factors including training set size and composition, number of hidden layer nodes, activation function type, and data scaling method are analyzed as variables affecting network performance. These factors are studied to determine impacts on network accuracy and generalizing ability.
Extent
174 p.
Recommended Citation
Hoffman, David Carl, "Artificial neural network prediction of alluvial river geometry" (1995). Electronic Theses and Dissertations 1990 - 1999. 713.
https://digitalcommons.fau.edu/etd_general_4/713
Identifier
FADT15179
Comments
College of Engineering and Computer Science|FAU Electronic Theses and Dissertations Collection|Thesis (M.S.)--Florida Atlantic University, 1995.|College of Engineering and Computer Science