The habitat suitability model generated in Maxent showed extensively areas that are suitable in climatic terms for this species east of the Pacific slope of the Western Andes. These areas are not known to be occupied by the species and were excluded from the potential distribution map of this guan.
There are three records from Valle del Cauca placed in its geographic centre that were removed previous to modelling the distribution of this species. Similarly, we removed all records with coordinates laying down in sites with estimated elevations above 2,000 m. Otherwise, there is one record from Boca Cajambre (Valle del Cauca), with coordinates that apparently lay down at an elevation lower than the actual place where the specimens were collected, since it is just one locality we believe the model is robust enough in its predictions although this locality was included.
Assuming that the distribution of the species may have filled the complete climatic model generated, its distribution today in remnants of forest is about 51,714 km2, which corresponds to a loss of 45 % of its potential original distribution due to deforestation.
Regularized training gain is 1.957, training AUC is 0.967, unregularized training gain is 2.457.
Algorithm converged after 540 iterations (15 seconds).
The follow settings were used during the run:
19 presence records used for training.
10019 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: 0.462, categorical: 0.250, threshold: 1.810, 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:
0.105-0.141-Fractional predicted area
0.105-0-Training omission rate