Abstract
Understanding the mechanisms of habitat selection is fundamental to the construction of proper conservation and management plans for many avian species. Habitat changes caused by human beings increase the landscape complexity and thus the complexity of data available for explaining species distribution. New techniques that assume no linearity and capable to extrapolate the response variables across landscapes are needed for dealing with difficult relationships between habitat variables and distribution data. We used a random forest algorithm to study breeding-site selection of herons and egrets in a human-influenced landscape by analyzing land use around their colonies. We analyzed the importance of each land-use variable for different scales and its relationship to the probability of colony presence. We found that there exist two main spatial scales on which herons and egrets select their colony sites: medium scale (4 km) and large scale (10–15 km). Colonies were attracted to areas with large amounts of evergreen forests at the medium scale, whereas avoidance of high-density urban areas was important at the large scale. Previous studies used attractive factors, mainly foraging areas, to explain bird-colony distributions, but our study is the first to show the major importance of repellent factors at large scales. We believe that the newest non-linear methods, such as random forests, are needed when modelling complex variable interactions when organisms are distributed in complex landscapes. These methods could help to improve the conservation plans of those species threatened by the advance of highly human-influenced landscapes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Battin J, Lawler JJ (2006) Cross-scale correlations and the design and analysis of avian habitat selection studies. Condor 108:59–70
Boisteau B, Marion L (2007) Habitat use by the grey heron (Ardea cinerea) in eastern France. CR Biol 330:629–634
Breiman L (1996) Bagging predictors. Mach Learn 24:123–140
Breiman L (2001) Random forests. Mach Learn 45:5–32
Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth International Group, Belmont
Bustamante J (1997) Predictive models for lesser krestel Falco naumanni distribution, abundance and extintion in southern Spain. Biol Conserv 80:153–160
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88:2783–2792
Environmental Agency of Japan (1994) Distribution and population status of colonies and communal roosts of 22 bird species from 1990 to 1992. Wild Bird Society of Japan and the Environmental Agency of Japan, Tokyo
Fasola M, Alieri R (1992) Conservation of heronry Ardeidae sites in North Italian agricultural landscapes. Biol Conserv 62:219–228
Fasola M, Canova L (1991) Colony site selection by eight species of gulls and terns breeding in the ≪Valli di Comacchio≫ (Italy). Italian J Zool 658:261–266
Friedman J (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
Fuller RJ (2012) Birds and habitat: relationships in changing landscapes. Cambridge University Press, Cambridge
Gibbs J, Kinkel L (1997) Determinants of the size and location of great blue heron colonies. Colonial Waterbirds 20:1–7
Gill F (2007) Ornithology. Freeman and Company, New York
Hastie T, Tibshirani R, Friedman J, Franklin J (2005) The elements of statistical learning: data mining, inference and prediction. Math Intell 27:83–85
Heinänen S, Rönkä M, Numers MV (2008) Modelling the occurrence and abundance of a colonial species, the arctic tern Sterna paradisaea in the archipelago of SW Finland. Ecography 31:601–611
Hijmans RJ, van Etten J (2012) Raster: geographic analysis and modeling with raster data. R package version 2.1-25
Keating K, Cherry S (2004) Use and interpretation of logistic regression in habitat selection studies. J Wild Manag 68:774–789
Kelly J, Stralberg D, Etienne K, McCaustland M (2008) Landscape influence on the quality of heron and egret colony sites. Wetlands 28:257–275
Lane S, Fujioka M (1998) The impact of changes in irrigation practices on the distribution of foraging egrets and herons (Ardeidae) in the rice fields of central Japan. Biol Conserv 83:221–230
Lauver CL, Busby WH, Whistler JL (2002) Testing a GIS model of habitat suitability for a declining grassland bird. Environ Manag 30:88–97
Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2:18–22
Mashiko M, Toquenaga Y (2013) Increasing variation in population size and species composition ratio in mixed-species heron colonies in Japan. Forktail 29:71–77
Myrtveit I, Stensrud E, Shepperd M (2005) Reliability and validity in comparative studies of software prediction models. IEEE Trans Softw Eng 31:380–391
Narusue M (1992) Changes in the distribution and extent of breeding colonies of egrets in Saitama Prefecture. Strix 11:189–209
Orians G, Wittenberger J (1991) Spatial and temporal scales in habitat selection. Am Nat 137:S29–S49
Parkes ML, Mora MA, Feagin RA (2012) Using scale, cover type and GIS to evaluate nuisance cattle egret colony site selection. Waterbirds 35:56–63
Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9:181–199
Seppelt R, Voinov A (2002) Optimization methodology for land use patterns using spatially explicit landscape models. Ecol Model 151:125–142
R Development Core Team (2011) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna
Tojo H (1996) Habitat selection, foraging behavior and prey of five heron species in Japan. Jpn J Ornithol 45:141–158
Tourenq C, Benhamou S, Sadoul N, Sandoz A, Mesleard F, Martin J, Hafner H (2004) Spatial relationships between tree-nesting heron colonies and rice fields in the Camargue, France. Auk 121:193–202
Wiens JA, Milne BT (1989) Scaling of ‘landscapes’ in landscape ecology, or, landscape ecology from a beetle’s perspective. Landsc Ecol 3:87–96
Acknowledgments
We thank S. Ikeno, M. Seido, and K. Takeda for supplying information about the location of some colonies. We also thank K. Ohashi and members of the Population Ecology laboratory for helpful discussions. This study was supported in part by Grant-in-Aids for Scientific Research (13740433 and 19570014) to YT from the MEXT and JSPS. Additional financial support was provided through a Monbukagakusho scholarship to L. Carrasco from MEXT.
Author information
Authors and Affiliations
Corresponding author
Appendix: Range and correlations between land use variables
Appendix: Range and correlations between land use variables
In order to examine the range of each explanatory variable used in the samples of this study models, we compared the percentages of the land use coverage of the whole study area with the average of the percentages of the land use variables for the buffer areas surrounding the colonies for the most important scales (Table 1).
For examining colinearity between land use variables, we calculated the Pearson’s correlation coefficients between them for the most important scales (Tables 2, 3).
About this article
Cite this article
Carrasco, L., Mashiko, M. & Toquenaga, Y. Application of random forest algorithm for studying habitat selection of colonial herons and egrets in human-influenced landscapes. Ecol Res 29, 483–491 (2014). https://doi.org/10.1007/s11284-014-1147-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11284-014-1147-0