To elaborate our model we removed uncertain localities such as 'Bogota skins' and all records with coordinates laying down in sites with estimated elevations above 636 m. Also eight records in BioMap and one in DatAves from Valle del Cauca, which clearly represent corrupted data, were removed previously to modelling.
The habitat suitability model generated in Maxent showed areas suitable in climatic terms for this species extensively west of the Andes in the biogeographic Choco and the mid to mid-high Magdalena Valley. These areas are not known to be occupied by the species and were excluded from the potential distribution map.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 463,601 km2, which corresponds to a loss of 9 % of its potential original distribution due to deforestation just in the Amazonian Region of Colombia.
Regularized training gain is 0.458, training AUC is 0.819, unregularized training gain is 0.663.
Algorithm converged after 160 iterations (1 seconds).
The follow settings were used during the run:
11 presence records used for training.
10011 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: 0.757, categorical: 0.464, threshold: 1.890, 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:
0.193-0.633-Fractional predicted area
0.182-0.000-Training omission rate