To elaborate our model we removed uncertain localities such as those localities with no coordinates and all records with coordinates laying down in sites with estimated elevations below 2,300 m and above 4,000 m.
The habitat suitability model generated in Maxent showed a few areas suitable in climatic terms for this species in isolated areas further south than the known range in the Eastern Andes and further north than the known range in the Central Andes. Also a very few pixels were predicted as presence in Sierra Nevada de Santa Marta. Those areas are not known to be occupied by the species and were excluded from the potential distribution map of this hummingbird.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 8,345 km2, which corresponds to a loss of 80 % of its potential original distribution due to deforestation. Nonetheless, this species favours edges, secondary vegetation and gardens and therefore possibly deforestation has not negatively affected greatly its populations.
Regularized training gain is 3.060, training AUC is 0.987, unregularized training gain is 3.308.
Algorithm converged after 1640 iterations (53 seconds).
The follow settings were used during the run:
156 presence records used for training.
10152 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
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.034-0.047-Fractional predicted area
0.032-0.013-Training omission rate