DocumentCode
2456523
Title
Interactive spatial evolutionary computation based predictive modeling of rare plant species occurrences
Author
Garagic, Denis ; Rhodes, Bradley J. ; Abramiuk, Marc A.
Author_Institution
BAE Syst. Adv. Inf. Technol., Burlington, MA, USA
fYear
2011
fDate
19-21 Oct. 2011
Firstpage
472
Lastpage
475
Abstract
In this paper, a habitat suitability model for rare plant species is developed by combining spatial predictive modeling techniques and an evolutionary computation method known as Interactive Evolution (IE). The interactive spatial evolutionary computation based predictive modeling enables an analyst to combine advanced mathematical geospatial and pattern recognition modeling techniques, conceptual knowledge, available empirical data, and expert-interactive dynamic data visualization techniques to predict species distributions. This methodology represents a step toward identifying regions where species are likely located to base argument for appropriate stratification in applying culturally relative conservation strategies to protect them and promote overall enhanced ecological integrity to the region. The model accuracy was assessed statistically by testing for independence between predicted occurrence and actual occurrence using cross-validation tests.
Keywords
biology computing; botany; data visualisation; ecology; evolutionary computation; interactive systems; learning (artificial intelligence); pattern recognition; vegetation mapping; advanced mathematical geospatial technique; conceptual knowledge; conservation strategy; ecological integrity; expert-interactive dynamic data visualization technique; habitat suitability model; interactive spatial evolutionary computation based predictive modeling; pattern recognition modeling technique; rare plant species occurrence; region identification; supervised learning; Adaptation models; Biological system modeling; Computational modeling; Data models; Mathematical model; Predictive models; Probabilistic logic; Interactive evolutionary computation; habitat suitability model; neural networks; spatial predictive modeling; supervised learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Nature and Biologically Inspired Computing (NaBIC), 2011 Third World Congress on
Conference_Location
Salamanca
Print_ISBN
978-1-4577-1122-0
Type
conf
DOI
10.1109/NaBIC.2011.6089634
Filename
6089634
Link To Document