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 1,331 m.
The habitat suitability model generated in Maxent showed areas suitable in climatic terms for this species in the high Magdalena valley and to the east and north in the slopes of the Eastern Andes, serrania del Perija, Sierra Nevada de Santa Marta and in the far east Amazon in the Rio Negro region and south. These areas are not known to be occupied by the species and were excluded from the potential distribution map of this hummingbird. A relatively small area in the northern Pacific and extreme southwestern lowlands (likely suitable) were unpredicted and were noted as such in our maps. Also, lowland areas north of the Western and Central Andes between Uraba and serrania de San Lucas are in this same category. Some sections of the slopes above the Cauca Valley were predicted as suitable. Apparently, there are local records in this zone, which has been largely deforested.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 82,428 km2, which corresponds to a loss of 52 % of its potential original distribution due to deforestation.
Regularized training gain is 1.777, training AUC is 0.949, unregularized training gain is 2.070.
Algorithm converged after 1140 iterations (33 seconds).
The follow settings were used during the run:
76 presence records used for training.
10074 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: 0.119, categorical: 0.250, threshold: 1.240, 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:
19.483 10.09 Cumulative threshold
0.277 0.135 Logistic threshold
0.105 0.169 Fractional predicted area
0.105 0.066 Training omission rate