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 1,514 m. Also three records in BioMap, two from Barbacoas (Nariño) and one from Isla Santa Sofia (Amazonas), which represent corrupted data, were removed previously to modelling.
The habitat suitability model generated in Maxent showed areas suitable in climatic terms for this species in the far east, the Cauca Valley and in Nariño. These areas are not known to be occupied by the species and were excluded from the potential distribution map. Nevertheless, it is important to highlight that there are two records from the Cauca Valley; one is in BioMap from Cunday, Tolima, which is misplaced and its coordinates must fall in the Magdalena Valley and the other is in DatAves from Risaralda, which may be corrupted data. Ebird (2016) has one record in the area near Buenaventura. These data needs further verification. It is possible that the species has entered the Cauca River Valley in recent years following deforestation, but this is uncertain at present time.
Regularized training gain is 1.331, training AUC is 0.938, unregularized training gain is 1.798.
Algorithm terminated after 2000 iterations (67 seconds).
The follow settings were used during the run:
131 presence records used for training.
10130 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: 0.050, categorical: 0.250, threshold: 1.000, hinge: 0.500
Feature types used: hinge product linear threshold quadratic
'Equal Training Sensitivity and Specificity' and 'Equate Entropy of Thresholded and Original Distributions' thresholds and omission rates:
0.140-0.266-Fractional predicted area
0.137-0.038-Training omission rate