Effects of the training dataset characteristics on the performance of nine species distribution models: application to Diabrotica virgifera virgifera

0365160 - BÚ 2012 RIV US eng J - Journal Article
Dupin, A. - Reynaud, P. - Jarošík, Vojtěch - Baker, R. - Brunel, S. - Eyre, D. - Pergl, Jan - Makowski, D.
Effects of the training dataset characteristics on the performance of nine species distribution models: application to Diabrotica virgifera virgifera.
PLoS ONE. Roč. 6, 6:e230957 (2011), s. 1-11. ISSN 1932-6203. E-ISSN 1932-6203
R&D Projects: GA ČR GA206/09/0563; GA MŠMT LC06073
Institutional research plan: CEZ:AV0Z60050516
Keywords : geographical distribution * biological invasions * envelope models
Subject RIV: EF - Botanics
Impact factor: 4.092, year: 2011

Model performance was highly sensitive to the geographical area used for calibration; most of the models performed poorly when fitted to a restricted area corresponding to an early stage of the invasion. Our results also showed that Principal Component Analysis was useful in reducing the number of model input variables for the models that performed poorly with 19 input variables. DOMAIN, Environmental Distance, MAXENT, and Envelope Score were the most accurate models but all the models tested in this study led to a substantial rate of mis-classification.
Permanent Link: http://hdl.handle.net/11104/0200467