To elaborate the habitat suitability model we removed 'Bogota skins' and all records with coordinates laying down in sites with estimated elevations out of the range within 300-2,300 m.
The habitat suitability model generated in Maxent showed a few areas that are suitable in climatic terms for this species in serrania del Baudo, serrania de San Jacinto and several low hills east of the Andes. These areas are not known to be occupied by the species and were excluded from the potential distribution map of this guan. Interestingly, several areas in the Andes below 300 m and above 2,500 m (including areas around Bogota) were predicted as climatically suitable for this species. However, it is very unlikely the species can be found at elevations outside the range between 300-2,500 m; even it is not clear if the 'Bogota' collections made of this species were taken in nearby areas below Bogota or in the 'altiplano'. Therefore, we refined our final potential distribution map for this Guan deleting areas outside this last specified range.
Assuming that the distribution of the species may have filled the complete climatic model generated (first model), its potential distribution today in remnants of forest is about 114,242 km2, which corresponds to a loss of 58 % of its potential original distribution due to deforestation.
Regularized training gain is 1.337, training AUC is 0.940, unregularized training gain is 1.842.
Algorithm converged after 740 iterations (21 seconds).
The follow settings were used during the run:
38 presence records used for training.
10038 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: 0.227, categorical: 0.250, threshold: 1.620, 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:
0.144-0.263-Fractional predicted area
0.132-0.053-Training omission rate