In recent years, species distribution models have been used to gain a better understanding of past and future range dynamics of species. Here, we focus on a keystone species of the North African forest ecosystem (Cedrus atlantica) by calculating a consensus model of the species current geographic potential distribution in North Africa, based on a weighted average method aiming to decrease uncertainty. The consensus model is obtained using seven species distribution model algorithms taking into account 24 environmental variables. The model is then applied to several past and future time slices. Past projections refer to the Middle-Holocene and the Last Glacial Maximum, whereas those of future are related to expect conditions around 2050 and 2070. We found that the current potential distribution of Cedrus atlantica is larger than its actual geographical distribution. For some explanatory variables, the analysis revealed their importance for the species current distribution. Among all obtained models, that for the Middle-Holocene showed the maximum expansion of the species potential distribution. The Last Glacial Maximum model provided new putative glacial refugia of Cedrus atlantica, not shown by other mechanistic models and palaeorecord localities. Future projections revealed a significant and fast contraction with shifting in altitude of the species range, showing more fragmented areas and even species disappearance in many North African localities. These findings can help to restore cedar forests and conserve them by ex situ strategies according to the future defined refugia in North Africa. Attention should be paid to the resolution of related output maps, the current biotic interactions, and those that may arise under climate change.
