Multivariate analysis and self-organizing mapping applied to analysis of nest-site selection in Black-tailed Gulls

摘要: Abstract The factors affecting nest-site selection and breeding success of Black-tailed Gulls (Larus crassirostris) were studied in Hongdo Island Korea during the seasons 2002 2003. Two analyzing methods, Principal Component Analysis (PCA) Self-Organizing Map (SOM) – an unsupervised learning method artificial neural networks, applied to multivariable datasets characterizing nest-sites gulls. Both methods provided insights on major trends by Gulls. PCA showed that variables regarding “wall” effect such as rock cover nest-wall (positively), nearest distance between neighbors (negatively) related SOM confirmed ordination sample sites efficiently classified according environmental condition for breeding. Grouping based was more finely revealed subdivision slope neighbors. use techniques ecological informatics would be efficient tool data behavior birds.