To elaborate our model we removed uncertain localities such as localities with no coordinates and all records with coordinates laying down in sites with estimated elevations below 289 m and above 3,200 m.
The habitat suitability model generated in Maxent showed areas suitable in climatic terms for this species in Sierra Nevada de Santa Marta, Serrania del Perija, Serrania del Baudo and Serrania de San Lucas. These areas are not known to be occupied by the species and were excluded from the potential distribution map of this hummingbird. Nevertheless, it is important to highlight that Perija, Baudo and San Lucas are connected to the main Andean ranges or very close to them. Apparently the species has not filled those potential areas of its climatic 'fundamental niche'. There is no replacement geographically with other species of the genus in those areas, and therefore, it is intriguing the reason why it is not present in those areas.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 97,361 km2, which corresponds to a loss of 61 % of its potential original distribution due to deforestation. Nonetheless, this species favours edges and secondary vegetation and therefore possibly deforestation has not negatively affected greatly its populations.
Regularized training gain is 1.575, training AUC is 0.944, unregularized training gain is 1.911.
Algorithm terminated after 2000 iterations (82 seconds).
The follow settings were used during the run:
121 presence records used for training.
10120 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:
0.123-0.208-Fractional predicted area
0.124-0.041-Training omission rate