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 below 1,796 m and above 3,600 m. Also four records in BioMap allegedly collected by Lehman in Popayan, which are doubtful were deleted. Those records need confirmation, in case are correct they will extend the known distribution to the north.
The habitat suitability model generated in Maxent showed extensive areas suitable in climatic terms for this species farther north from the Andes of Nariño in the three cordilleras. Those areas are not known to be occupied by this species and were deleted from our final potential distribution map. It is possible that because records from 'La Planada; are slightly low the overall range of the species has been slightly overestimated in case the georeferences were placed with a degree of error.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 2,977 km2, which corresponds to a loss of 71 % of its potential original distribution due to deforestation.
Regularized training gain is 2.371, training AUC is 0.987, unregularized training gain is 3.276.
Algorithm converged after 160 iterations (1 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:
0.033-0.093-Fractional predicted area
0.000-0.000-Training omission rate