Back to search

Cornell University

Artificial Neural Networks As Watershed Nutrient Loading Models

Abstract

dc:description.abstract

Artificial neural network (ANN) is a computing architecture in the area of artificial intelligence. The present study aims at the wider use of ANN in the watershed loading prediction. An important aspect of these initiatives is the accurate forecasting nutrient load in runoff water. Accurate prediction of watershed loading has been recognized as an important measure for effective water management strategy. This study compares Haith's Generalized Watershed Loading Function (GWLF) and Arnold's Soil and Water Assessment Tool (SWAT) to multilayer artificial neural networks for monthly/daily watershed load forecast modeling. The comparison splits into two different parts; 1) performance of the ANN calibrated to the observed data; 2) performance of the ANN calibrated to simulated data. The first part includes comparison of model estimates from both the ANN and the GWLF to the collected observations from West Branch Delaware River watershed. The second part evaluates the performance of calibrated ANN model using simulated output using the SWAT. Feed-forward networks with one hidden layer of sigmoid nodes followed by an output layer of linear nodes were created for both comparisons. The model performances were evaluated using various statistical indices. For each of the ANN models, different numbers of nodes were tested in order to create the optimal structure. The modeling results indicate that calibrated feed-forward ANN models were found to provide reasonable prediction accuracy as the GWLF and the SWAT in most of the nutrient categories. With its flexibility and computation efficiency, the ANN is anticipated as a useful tool to obtain a quick preliminary assessment of nutrient loading variations.

Degree

thesis:*
Name thesis:degree_name
M.S., Civil and Environmental Engineering
Level thesis:degree_level
Master of Science
Discipline thesis:degree_discipline
Civil and Environmental Engineering
Grantor
Cornell University
Year dc:date.issued
2011

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kim, Raymond
Chair dc:contributor.chair
  • Loucks, Daniel Peter
Committee member dc:contributor.committeemember
  • Bisogni Jr, James John

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
7745378

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kim, Raymond. Artificial Neural Networks As Watershed Nutrient Loading Models. Master of Science thesis, Cornell University, 2011. https://hdl.handle.net/1813/29469