Table 1 Predictor variables included in the random forests modeling and the scales retained in the univariate scaling step of sloth bears in Bandhavgarh Tiger Reserve
From: Using machine learning to predict habitat suitability of sloth bears at multiple spatial scales
Variable type | Variables | Optimal scale (m) | Abbreviations |
|---|---|---|---|
Topographic | Elevation | 2000 | elevation2km |
Terrain ruggedness index | 6000 | rug6km | |
River density | 1000 | river1km | |
Cover | NDVI in summer season | 5000 | ndvisum5km |
NDVI in winter season | 6000 | ndviwin6km | |
NDVI in wet season | 8000 | ndviwet8km | |
Habitat composition | Dry deciduous forests | 1000 | drydec1km |
Moist deciduous forests | 4000 | moistdec4km | |
Sal-dominated forests | 5000 | sal5km | |
Disturbance | Degraded habitat patches | 8000 | degraded8km |
Farmland | 9000 | farmland9km | |
Road density | 1000 | road1km | |
Human settlements | 6000 | settlement6km |