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 1,793 m and above 4,500 m. Also one record in BioMap from Cundinamarca, which represents corrupted information in the database.
The habitat suitability model generated in Maxent showed a few pixels suitable in climatic terms for this species in the eastern slope of the Eastern Andes in southeastern Norte de Santander. 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 1,587 km2, which corresponds to a loss of 57 % of its potential original distribution due to deforestation. This proportion may be slightly overestimated since in some areas of its distribution this species includes Paramo.
This Colombian Endemic from Sierra Nevada de Santa Marta has lost great extent of its original habitat and remnants are heavily fragmented and the quality of it is believed being impacted by human disturbance. Despite it uses borders and has been registered in gardens and Eucalyptus its small and fragmented range puts it under the category Endangered (EN).
Regularized training gain is 5.473, training AUC is 0.999, unregularized training gain is 6.087.
Algorithm converged after 180 iterations (1 seconds).
The follow settings were used during the run:
10 presence records used for training.
10010 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: 0.800, categorical: 0.500, threshold: 1.900, hinge: 0.500
Feature types used: linear quadratic
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.003-0.004-Fractional predicted area
0.000-0.000-Training omission rate