thumbnail

Application of neural networks to prediction of fish diversity and salmonid production in the Lake Ontario basin

Transactions of the American Fisheries Society

By:
DOI: 10.1577/FT04-044.1

Links

Abstract

Diversity and fish productivity are important measures of the health and status of aquatic systems. Being able to predict the values of these indices as a function of environmental variables would be valuable to management. Diversity and productivity have been related to environmental conditions by multiple linear regression and discriminant analysis, but such methods have several shortcomings. In an effort to predict fish species diversity and estimate salmonid production for streams in the eastern basin of Lake Ontario, I constructed neural networks and trained them on a data set containing abiotic information and either fish diversity or juvenile salmonid abundance. Twenty percent of the original data were retained as a test data set and used in the training. The ability to extend these neural networks to conditions throughout the streams was tested with data not involved in the network training. The resulting neural networks were able to predict the number of salmonids with more than 84% accuracy and diversity with more than 73% accuracy, which was far superior to the performance of multiple regression. The networks also identified the environmental variables with the greatest predictive power, namely, those describing water movement, stream size, and water chemistry. Thirteen input variables were used to predict diversity and 17 to predict salmonid abundance.

Additional Publication Details

Publication type:
Article
Publication Subtype:
Journal Article
Title:
Application of neural networks to prediction of fish diversity and salmonid production in the Lake Ontario basin
Series title:
Transactions of the American Fisheries Society
DOI:
10.1577/FT04-044.1
Volume
134
Issue:
1
Year Published:
2005
Language:
English
Publisher:
Taylor & Francis
Publisher location:
London, UK
Contributing office(s):
Great Lakes Science Center
Description:
16 p.
Larger Work Type:
Article
Larger Work Subtype:
Journal Article
First page:
28
Last page:
43
Number of Pages:
16