Random forest modelling of multi‐scale, multi‐species habitat associations within KAZA transfrontier conservation area using spoor data

As landscape‐scale conservation models grow in prominence, assessments of how wildlife utilise multiple‐use landscapes are required to inform effective conservation and management planning. Such efforts should incorporate multi‐species perspectives to maximise value for conservation, and should account for scale to accurately capture species‐environment relationships. We show that the random forest machine learning algorithm can be used to model large‐scale sign‐based data in a multi‐scale framework. We used this method to investigate scale‐dependent habitat associations for 16 mammal species of high conservation importance across the southern Kavango Zambezi (KAZA) Transfrontier Conservation Area in Botswana and Zimbabwe. Our findings revealed substantial variation in factors shaping habitat use across species, and illustrate that different species often have divergent responses to the same environmental and anthropogenic factors, and differ in the scales at which they respond to them. For all variables across all species, scale optimisation most often selected our largest scale. Precipitation, soil nutrients, and vegetation appeared to be the most important factors determining mammal distributions, likely through their associations with food resources for herbivores and, in turn, prey availability for carnivores. Anthropogenic pressures also had an important influence, with many species selecting against areas with high cattle density. The variety of relationships with human density indicated that species vary in their tolerance of humans. We found a consistent positive relationship with areas under high protection, and negative relationship with unprotected and less‐strictly protected areas. Policy implications. Through a novel application of random forest modelling to spoor data from 16 mammal species, this study highlights the importance of adopting a multi‐scale, multi‐species approach for decision‐making processes that depend on understanding wildlife distributions and habitat associations, such as protected area and corridor prioritisation. The findings identify changing rainfall patterns and increasing livestock numbers as emerging trends that may impact wildlife distributions, both within sub‐Saharan Africa and on a global scale. Wildlife management authorities should use modelling exercises and adaptive management to ensure that protected area networks remain fit for purpose under anticipated changes in rainfall under climate change, and explore initiatives that promote coexistence of wildlife and livestock.