Fragmented tropical forests can be highly dynamic, with the spatial configuration of forest patches changing through time. Yet, the lack of longitudinal studies limits our understanding of how patch dynamics affect biodiversity, especially when there is a time lag in species extinctions (extinction debt). We assessed how temporal changes in patch size, shape complexity and isolation affect populations of the Mexican howler monkey (Alouatta palliata mexicana), hypothesizing that we would find an extinction debt in this relatively long‐lived species. We assessed patch occupancy, subpopulation size and immature‐to‐female ratio in 39 forest patches from Los Tuxtlas, Mexico, in both 2001 and 2013. To identify time‐lag responses to habitat disturbance, we related demographic attributes in 2013 to patch metrics in 2001 and 2013 and tested whether primate subpopulations were better predicted by current or historical patch characteristics. We also assessed how changes in patch metrics affected each demographic attribute between 2001 and 2013. Patch size and shape complexity increased over time, whereas isolation decreased. These positive spatial changes were accompanied by a 1.6‐fold increase in mean subpopulation size over the same period. In addition, occupancy and immature‐to‐female ratio were similarly related to patch attributes in both years, suggesting that there is no extinction debt. Our findings are ‘good news’, suggesting that forest recovery over a relatively short period can promote the recovery of this Critically Endangered taxon. They also highlight the importance of preventing forest loss and promoting forest regeneration in human‐modified tropical landscapes.

Segmentation of high-resolution tomographic data is often an extremely time-consuming task and until recently, has usually relied upon researchers manually selecting materials of interest slice by slice. With the exponential rise in datasets being acquired, this is clearly not a sustainable workflow. In this paper, we apply the Trainable Weka Segmentation (a freely available plugin for the multiplatform program ImageJ) to typical datasets found in archaeological and evolutionary sciences. We demonstrate that Trainable Weka Segmentation can provide a fast and robust method for segmentation and is as effective as other leading-edge machine learning segmentation techniques.