Skip to main content


Table 4 Contributions of predictor variables to the boosted regression tree models predicting physical geography variables to wet season and dry season hotspots of malaria infection on Unguja, Zanzibar

From: Mapping hotspots of malaria transmission from pre-existing hydrology, geology and geomorphology data in the pre-elimination context of Zanzibar, United Republic of Tanzania

Variable description Relative influence (%)
  Wet season Dry season
Slope angle (°) 28.7 25.6
Distance to doline (m) 25.6 35.1
Distance to stream (m) 18.2 8.7
Landcover type 13 17.4
Geology type 10.1 8.3
Elevation (m) 3.9 4.7
Soil infiltration rate 0.5 0.1
Condition of health facility 0 0