Skip to main content

Table 2 Performance metrics of hypervolumes in the geographic space

From: Transmission risk of Oropouche fever across the Americas

Environmental predictors

Model calibration region

Mean performance in G (SD)

Total suitable pixels

OC-SVM

Convex hulls

OC-SVM

Convex hulls

PCs prop. = 95%

Centroid based buffer

0.49 (0.17)

0.54 (0.17)

96,335.5

83,375.5

PCs prop. = 95%

South America

0.48 (0.16)

0.56 (0.18)

91,830

80,161

PCs prop. = 96%

Americas

0.63 (0.17)

0.45 (0.19)

122,456

79,344

Climates

Centroid based buffer

0.62 (0.16)

0.44 (0.17)

114,231

107,553.5

Climates

South America

0.60 (0.17)

0.48 (0.20)

114,917

105,012

Climates

Americas

0.58 (0.20)

0.51 (0.18)

122,851

120,561

  1. Performance metrics of one-class support vector machines (OC-SVM) and convex hulls hypervolumes were measured in the geographical (G) space using three different model calibration regions and two categories of environmental predictors. Best performing model in bold. SD Standard deviation, PCs Principal components, Prop. Cumulative proportion of the three principal components used for model calibration