Table 1 Variable weightings indicating the importance in final boosted regression tree models for tracking and observer data.

Bathymetry and temperature were reliably the two most important predictors in modeling habitat. Bold numbers highlight the three most important factors for each model. NA, not applicable.

ObserverTracking
SwordfishBlue sharkBlue sharkLeatherbackSea lion
Bottom depth32.947.215.614.649.1
SST mean18.08.049.334.714.3
SSHa10.38.24.711.25.4
Chl-a7.92.711.08.912.2
y-wind5.73.74.46.11.9
Lunar phase5.53.5NANANA
Bottom roughness5.45.54.211.43.0
SST SD5.36.73.25.12.8
SSHa SD5.110.24.3NA6.0
EKE3.94.43.46.15.3