The habitat suitability model generated in Maxent showed areas that might be possibly occupied by this species in Sierra Nevada de Santa Marta and in serrania de Perija. However, we do not have knowledge of any records from those areas and believe they must be excluded at the moment from the potential distribution map of the species.
There are two records used in modelling the distribution of this species that may be likely misplaced, one in extreme east Casanare and another in Santander. These records did not affect the robust modelling performed by Maxent.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 60,769 km2, which corresponds to a loss of 65 % of its potential original distribution due to deforestation.
Regularized training gain is 1.726, training AUC is 0.944, unregularized training gain is 2.021.
Algorithm converged after 680 iterations (18 seconds).
The follow settings were used during the run:
45 presence records used for training.
10045 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: 0.207, categorical: 0.250, threshold: 1.550, hinge: 0.500
Feature types used: linear quadratic hinge
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.133-0.178-Fractional predicted area
0.133-0.089-Training omission rate