Drivers of extinction risk in African mammals: the interplay of distribution state, human pressure, conservation response and species biology

Although conservation intervention has reversed the decline of some species,our success is outweighed by a much larger number of species movingtowards extinction. Extinction risk modelling can identify correlates of riskand species not yet recognized to be threatened. Here, we use machine learningmodels to identify correlates of extinction risk in African terrestrialmammals using a set of variables belonging to four classes: species distributionstate, human pressures, conservation response and species biology.We derived information on distribution state and human pressure from satellite-borne imagery. Variables in all four classes were identified as importantpredictors of extinction risk, and interactions were observed among variablesin different classes (e.g. level of protection, human threats, species distributionranges). Species biology had a key role in mediating the effect ofexternal variables. The model was 90% accurate in classifying extinction riskstatus of species, but in a few cases the observed and modelled extinctionrisk mismatched. Species in this condition might suffer from an incorrectclassification of extinction risk (hence require reassessment). An increasedavailability of satellite imagery combined with improved resolution and classificationaccuracy of the resulting maps will play a progressively greater role inconservation monitoring.JRC.H.5-Land Resources Managemen