To elaborate our model we removed uncertain localities such as 'Bogota skins', those localities with no coordinates and all records with coordinates laying down in sites with estimated elevations above 2,000 m.
The habitat suitability model generated in Maxent showed areas suitable in climatic terms for this species west of the Andes. These areas are not known to be occupied by the species and were excluded from the potential distribution map of this hummingbird. Also is important to note that extensive areas were not predicted as suitable by our model in the southern Amazon and far east Amazon in the region of Rio Negro, these areas were noted as such in our maps.
Distribution of specimens according to BioMap suggest a zone of intergradation between subspecies caribaeus and phoeopygus in the region of serrania de La Macarena and nearby zones, which needs further revision and study.
Assuming that the distribution of the species may have filled the complete climatic model generated in the Amazon region, its distribution today in remnants of forest is about 473,114 km2, which corresponds to a loss of 9 % of its potential original distribution due to deforestation in that region.
Regularized training gain is 1.347, training AUC is 0.943, unregularized training gain is 1.982.
Algorithm terminated after 2000 iterations (66 seconds).
The follow settings were used during the run:
113 presence records used for training.
10112 points used to determine the Maxent distribution (background points and presence points).
Environmental layers used (all continuous): bio10co bio11co bio12co bio13co bio14co bio15co bio16co bio17co bio18co bio19co bio1co bio2co bio3co bio4co bio5co bio6co bio7co bio8co bio9co
Regularization values: linear/quadratic/product: 0.050, categorical: 0.250, threshold: 1.000, hinge: 0.500
Feature types used: hinge product linear threshold quadratic
'Fixed Cumulative Value of 1%', Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.672-0.115-0.260-Fractional predicted area
0.000-0.115-0.071-Training omission rate