To elaborate our model we removed uncertain localities such as 'Bogota skins'. Also two records in BioMap from Cundinamarca and Tolima in the western slope of the Eastern Andes that seem odd. Although it is important to note that both records appear in other external databases in the same fashion as in BioMap.
The habitat suitability model generated in Maxent showed areas suitable in climatic terms for this species west of the Andes, particularly in the Pacific slope of the Western Andes. These 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 18,770 km2, which corresponds to a loss of 54 % of its potential original distribution due to deforestation. Although this species uses edges and possibly secondary vegetation it is important to note that it is an uncommon species distributed locally and therefore its populations in Colombia may be relatively small. Possibly it deserves certain attention in conservation if it is intended to be protected in Colombia, although is important to note that its global population is not threatened.
Regularized training gain is 2.179, training AUC is 0.988, unregularized training gain is 3.165.
Algorithm converged after 660 iterations (24 seconds).
The follow settings were used during the run:
16 presence records used for training.
10015 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: 0.543, categorical: 0.286, threshold: 1.840, hinge: 0.500
Feature types used: hinge linear quadratic
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.058-0.113-Fractional predicted area
0.062-0.000-Training omission rate