Classification of breeding bird communities along an urbanization gradient using an unsupervised artificial neural network

An unsupervised artificial neural network known as self-organizing mapping (SOM) was used to examine the influence of urbanization on the assembly patterns of breeding birds. From late March until mid June 2004, we monitored 52 breeding bird species at 367 sites and analyzed their assembly patterns by their environment (impervious, water, and vegetative areas; number of deciduous trees and coniferous trees; and volume of deadwood) in Seongnam City, South Korea. The data were computed with SOM, which allows two-dimensional visualization and classification of complex bird assembly patterns using a U-matrix. SOM made it possible for us to organize the study sites into five clusters according to the similarity of the breeding bird assembly patterns. Clusters IV and V had high values for total species richness, as well as the number of species in the tree canopy, cavity, and ground-nesting guilds and the tree canopy, ground, and wood-foraging guilds. These results coincide with the fact that clusters IV and V had the highest proportion of vegetative areas, the greatest number of deciduous trees, and the highest volume of deadwood. By contrast, clusters I and II had a high percentage of impervious areas (e.g. buildings and roads) and a low percentage of vegetative areas. Coincidentally, clusters I and II had lower values for total species richness and the number of species forming nesting and foraging guilds, except for building-nesting guild and water-foraging guild. Cluster III, which contained many coniferous trees and little deadwood, had fewer total species richness compared with clusters IV and V, despite the number of coniferous trees in that area, because the trees in cluster III were relatively young, having been planted after the 1970s and having been subjected to periodic thinning. The SOM allowed us to elucidate the relationships among several environmental variables and breeding bird assembly patterns. From the point of view of an urban bird researcher who deals extensively with areas undergoing urbanization, SOM appears to be a valuable tool for visualizing and analyzing a relatively large volume of data relatively easily.

[1]  R. Céréghino,et al.  Spatial analysis of stream invertebrates distribution in the Adour-Garonne drainage basin (France), using Kohonen self organizing maps , 2001 .

[2]  J. Marzluff.  Worldwide urbanization and its effects on birds , 2001 .

[3]  J. Marzluff,et al.  Avian Ecology and Conservation in an Urbanizing World , 2002, Springer US.

[4]  Uygar Özesmi,et al.  An artificial neural network approach to spatial habitat modelling with interspecific interaction , 1999 .

[5]  P. Angelstam,et al.  Deciduous forest and resident birds: the problem of fragmentation within a coniferous forest landscape , 1995, Landscape Ecology.

[6]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[7]  Young-Seuk Park,et al.  Patternizing communities by using an artificial neural network , 1996 .

[8]  S. Lek,et al.  Ecological Applications of Unsupervised Artificial Neural Networks , 2003 .

[9]  M. Kuitunen,et al.  Ranking of habitats for the assessment of ecological impact in land use planning , 1996 .

[10]  R. Blair.  Land Use and Avian Species Diversity Along an Urban Gradient , 1996 .

[11]  J. Lockwood,et al.  Biotic homogenization: a few winners replacing many losers in the next mass extinction. , 1999, Trends in ecology & evolution.

[12]  J. V. van Wijnen,et al.  Survey of feral rock doves (Columba livia) in Amsterdam, a bird-human association , 2001, Urban Ecosystems.

[13]  H. Mooney,et al.  Human Domination of Earth’s Ecosystems , 1997, Renewable Energy.

[14]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[15]  John M. Goodburn,et al.  Cavity trees and coarse woody debris in old-growth and managed northern hardwood forests in Wisconsin and Michigan , 1998 .

[16]  Young-Seuk Park,et al.  Conservation Strategies for Endemic Fish Species Threatened by the Three Gorges Dam , 2003 .

[17]  D. Botkin,et al.  Cities as environments , 1997, Urban Ecosystems.

[18]  S. Lek,et al.  Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters , 2003 .

[19]  B. Altman,et al.  A habitat-based point-count protocol for terrestrial birds, emphasizing Washington and Oregon. , 2000 .

[20]  C. W. Kim,et al.  Illustrated flora and fauna of Korea , 1976 .

[21]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[22]  M. Ihse,et al.  Biotope patterns in urban areas: a conceptual model integrating biodiversity issues in spatial planning , 2002 .

[23]  S. Beissinger,et al.  Effects of Urbanization on Avian Community Organization , 1982 .

[24]  S. Matsuoka,et al.  The Role of Snags in the Life of Woodpeckers and Snag Management in a Forest:A Review , 1999 .

[25]  L. Carrascal,et al.  Urban influence on birds at a regional scale: A case study with the avifauna of northern Madrid province , 2006 .

[26]  S. M. Glenn,et al.  Urban Bird Diversity and Landscape Complexity: Species- environment Associations Along a Multiscale Habitat Gradient , 2003 .