The habitat suitability model generated in Maxent showed extensive areas that might be possibly occupied by this species west of the Andes. Nevertheless, it is well known the species is just present east of the Andes and therefore these were removed from the potential distribution map of this species.
It is necessary to bear in mind that this model was elaborated using just three point localities, from where this species is known in Colombia. The model is useful in the sense that can give an indication of the potential areas where the species may be looked for in the country. The distribution of this rare and local species is extremely unknown in Colombia. Additionally, we added four other points from where the species is known in Venezuela and Ecuador (EBIRD) and produce a minimum convex polygon as a general guidance of the most likely areas where the species may be in Colombia within our model.
Regularized training gain is 0.208, training AUC is 0.824, unregularized training gain is 0.459.
Algorithm converged after 720 iterations (2 seconds).
The follow settings were used during the run:
3 presence records used for training.
10003 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: 1.000, categorical: 0.605, threshold: 1.970, hinge: 0.500
Feature types used: linear
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.225-0.815-Fractional predicted area
0.333-0-Training omission rate