Selecting thresholds of occurrence in the prediction of species distributions
Tóm tắt
Transforming the results of species distribution modelling from probabilities of or suitabilities for species occurrence to presences/absences needs a specific threshold. Even though there are many approaches to determining thresholds, there is no comparative study. In this paper, twelve approaches were compared using two species in Europe and artificial neural networks, and the modelling results were assessed using four indices: sensitivity, specificity, overall prediction success and Cohen's kappa statistic. The results show that prevalence approach, average predicted probability/suitability approach, and three sensitivity‐specificity‐combined approaches, including sensitivity‐specificity sum maximization approach, sensitivity‐specificity equality approach and the approach based on the shortest distance to the top‐left corner (0,1) in ROC plot, are the good ones. The commonly used kappa maximization approach is not as good as the afore‐mentioned ones, and the fixed threshold approach is the worst one. We also recommend using datasets with prevalence of 50% to build models if possible since most optimization criteria might be satisfied or nearly satisfied at the same time, and therefore it's easier to find optimal thresholds in this situation.
Từ khóa
Tài liệu tham khảo
Berry P. M., 2001, Climate change and nature conservation in the Britain and Ireland: modelling natural resource responses to climate change (the MONARCH project), 43
Berry P. M., 2002, Modelling potential impacts of climate change on the bioclimatic envelope of species in Britain and Ireland, Global Ecol. Biogeogr., 11, 453, 10.1111/j.1466-8238.2002.00304.x
Fielding A. H., 1995, Testing the generality of bird‐habitat models, Conserv. Biol., 9, 1446, 10.1046/j.1523-1739.1995.09061466.x
Nahm U. Y., 2000, Using information extraction to aid the discovery of prediction rules from text, 51
Schapire R. E., 1998, Boosting and Rocchio applied to text filtering, 215