Genetic algorithms (GA) are artificial intelligence techniques based on the theory of evolution that through the process of natural selection evolve formulae to solve problems or develop control strategies. We designed a GA to examine relationships between stream physical characteristics and trout distribution data for 3rd-, 5th-, and 7th-order stream sites in the Cascade Mountains, Oregon. Although traditional multivariate statistical techniques can perform this particular task, GAs are not constrained by assumptions of independence and linearity and therefore provide a useful alternative. To help gauge the effectiveness of the GA, we compared GA results with results from proportional trout distributions and multiple linear regression equations. The GA was a more effective predictor of trout distributions (paired t test, P < 0.05) than other methods and also provided new insights into relationships between stream geomorphology and trout distributions. Most importantly, GA equations emphasized the nonindependence of stream channel units by revealing that (i) the factors that influence trout distributions change along a downstream continuum, and (ii) channel unit sequence can be critical. Superior performance of the GA, along with the new information it provided, indicates that genetic algorithms may provide a useful alternative or supportive method to statistical techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.