The habitat suitability model generated in Maxent showed extensive areas that are suitable in climatic terms for this species west of the Andes. It is well known these areas are not occupied by this species and they were excluded from its potential distribution map. Interestingly, the model also predicted more areas than expected in the Orinoco region and in the extreme southwest Amazon region.
Assuming the distribution of the species may have filled the complete climatic model generated in the Amazon region of Colombia, its distribution today in remnants of forest is potentially about 468,402 km2, which corresponds to a loss of 9 % of its potential original distribution in the region due to deforestation. Interestingly, this figure is even smaller when its distribution is restricted to suitable and highly suitable areas, and those areas in the Trapecio and extreme SEsw were trimmed from the potential distribution. In such a case, its distribution today in remnants of forest is potentially about 225,875 km2, which corresponds to a loss of ≈ 1.7 % of its potential original distribution in the region due to deforestation.
Regularized training gain is 0.508, training AUC is 0.878, unregularized training gain is 0.861.
Algorithm converged after 140 iterations (1 seconds).
The follow settings were used during the run:
5 presence records used for training.
10005 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: 0.575, threshold: 1.950, hinge: 0.500
Feature types used: linear
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.2-0.602-Fractional predicted area
0.2-0-Training omission rate