Advanced search
1 file | 602.82 KB

Analysis of environmental factors determining distribution pattern of Azolla filiculoides (Lam.) azollaceae in Anzali wetland, northern Iran

Author
Organization
Abstract
The first consideration in predictive ecological modelling is the selection of appropriate input variables. Numerous variables can, however, be involved whereas most of them cannot be omitted from the analysis without a significant loss of information. Therefore, rigorous methods are needed to distinguish which variables are essential from those which are not. In this paper, the use of greedy stepwise (GS) and genetic algorithms (GA) is explored to automatically select the relevant input variables to be used in classification trees (CTs) for predicting the cover percentage of Azolla filiculoides (Lam.). The database applied consisted of measurements from 7 sites in Selkeh wetland (northern Iran). Biotic and abiotic variables were collected over the 2007-2008 study period. The results showed that after variable selection, the predictive performances of the CTs had improved. GS was shown to be less efficient than GA. Optimization of GA and GS resulted in an easy interpretation of the selected variables. Both structural habitat and physico-chemical variables can affect habitat requirements of A. filiculoides in the wetland, but the dependence of this aquatic fern on structural habitat parameters was well-confirmed by the CTs after variable selection. Application of the given algorithms in combination with CTs thus proved to have a good capability in selecting the most important variables explaining the cover of A. filiculoides in Selkeh wetland.
Keywords
predictive models, wetland management, alien species

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 602.82 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Sadeghi Pasvisheh, Roghayeh, Rahmat Zarkami, Karim Sabetraftar, and Patrick Van Damme. 2014. “Analysis of Environmental Factors Determining Distribution Pattern of Azolla Filiculoides (Lam.) Azollaceae in Anzali Wetland, Northern Iran.” In Communications in Agricultural and Applied Biological Sciences, 79:199–205.
APA
Sadeghi Pasvisheh, R., Zarkami, R., Sabetraftar, K., & Van Damme, P. (2014). Analysis of environmental factors determining distribution pattern of Azolla filiculoides (Lam.) azollaceae in Anzali wetland, northern Iran. COMMUNICATIONS IN AGRICULTURAL AND APPLIED BIOLOGICAL SCIENCES (Vol. 79, pp. 199–205). Presented at the 19th National symposium on Applied Biological Sciences.
Vancouver
1.
Sadeghi Pasvisheh R, Zarkami R, Sabetraftar K, Van Damme P. Analysis of environmental factors determining distribution pattern of Azolla filiculoides (Lam.) azollaceae in Anzali wetland, northern Iran. COMMUNICATIONS IN AGRICULTURAL AND APPLIED BIOLOGICAL SCIENCES. 2014. p. 199–205.
MLA
Sadeghi Pasvisheh, Roghayeh, Rahmat Zarkami, Karim Sabetraftar, et al. “Analysis of Environmental Factors Determining Distribution Pattern of Azolla Filiculoides (Lam.) Azollaceae in Anzali Wetland, Northern Iran.” Communications in Agricultural and Applied Biological Sciences. Vol. 79. 2014. 199–205. Print.
@inproceedings{4283824,
  abstract     = {The first consideration in predictive ecological modelling is the selection of appropriate input variables. Numerous variables can, however, be involved whereas most of them cannot be omitted from the analysis without a significant loss of information. Therefore, rigorous methods are needed to distinguish which variables are essential from those which are not. In this paper, the use of greedy stepwise (GS) and genetic algorithms (GA) is explored to automatically select the relevant input variables to be used in classification trees (CTs) for predicting the cover percentage of Azolla filiculoides (Lam.). The database applied consisted of measurements from 7 sites in Selkeh wetland (northern Iran). Biotic and abiotic variables were collected over the 2007-2008 study period. The results showed that after variable selection, the predictive performances of the CTs had improved. GS was shown to be less efficient than GA. Optimization of GA and GS resulted in an easy interpretation of the selected variables. Both structural habitat and physico-chemical variables can affect habitat requirements of A. filiculoides in the wetland, but the dependence of this aquatic fern on structural habitat parameters was well-confirmed by the CTs after variable selection. Application of the given algorithms in combination with CTs thus proved to have a good capability in selecting the most important variables explaining the cover of A. filiculoides in Selkeh wetland.},
  author       = {Sadeghi Pasvisheh, Roghayeh and Zarkami, Rahmat and Sabetraftar, Karim and Van Damme, Patrick},
  booktitle    = {COMMUNICATIONS IN AGRICULTURAL AND APPLIED BIOLOGICAL SCIENCES},
  issn         = {1379-1176},
  keyword      = {predictive models,wetland management,alien species},
  language     = {eng},
  location     = {Gembloux, Belgium},
  number       = {1},
  pages        = {199--205},
  title        = {Analysis of environmental factors determining distribution pattern of Azolla filiculoides (Lam.) azollaceae in Anzali wetland, northern Iran},
  volume       = {79},
  year         = {2014},
}