Ensemble of small models for estimating potential abundance of Caucasian grouse (Lyrurus mlokosiewiczi) in Iran

Abstract

The need to obtain information on population size to inform management actions for conservation is imperative. Despite this, reliable data on Caucasian grouse abundance is scarce in Iran. The goal of this study was to explore the potential distribution of Caucasian grouse using an ensemble of small models with outstanding performance for modelling rare species' distributions to estimate the potential population size in Iran. We fitted an ensemble of small models with generalized boosted model (GBM) and maximum entropy (MaxEnt), and then built a final ensemble prediction by averaging across these two ensembles of small models. We considered ten environmental descriptors (land-cover, anthropogenic and topographic features) which were extracted over a 70 hectare spatial extent surrounding 22 Caucasian grouse lek occurrences. The best model's prediction map was used to estimate the potential population size of Caucasian grouse in Iran. The ensemble of small models with generalized boosted model showed higher transferability performances than the two other models on both 10-fold cross-validation and a geographically independent dataset. Based on the published species' densities and our prediction map, the potential population size of Caucasian grouse for Iran was estimated to be 98-196 individuals, which is considerably less than 350 reported by previous assessments. The predicted distribution map can be used to select priority areas for conservation, and to identify survey locations for the species in areas which so far have been poorly sampled.