Using Machine Learning for Remote Behaviour Classification-Verifying Acceleration Data to Infer Feeding Events in Free-Ranging Cheetahs.

Behavioural studies of elusive wildlife species are challenging but important when they are threatened and involved in human-wildlife conflicts. Accelerometers (ACCs) and supervised machine learning algorithms (MLAs) are valuable tools to remotely determine behaviours. Here we used five captive cheetahs in Namibia to test the applicability of ACC data in identifying six behaviours by using six MLAs on data we ground-truthed by direct observations. We included two ensemble learning approaches and a probability threshold to improve prediction accuracy. We used the model to then identify the behaviours in four free-ranging cheetah males. Feeding behaviours identified by the model and matched with corresponding GPS clusters were verified with previously identified kill sites in the field. The MLAs and the two ensemble learning approaches in the captive cheetahs achieved precision (recall) ranging from 80.1% to 100.0% (87.3% to 99.2%) for resting, walking and trotting/running behaviour, from 74.4% to 81.6% (54.8% and 82.4%) for feeding behaviour and from 0.0% to 97.1% (0.0% and 56.2%) for drinking and grooming behaviour. The model application to the ACC data of the free-ranging cheetahs successfully identified all nine kill sites and 17 of the 18 feeding events of the two brother groups. We demonstrated that our behavioural model reliably detects feeding events of free-ranging cheetahs. This has useful applications for the determination of cheetah kill sites and helping to mitigate human-cheetah conflicts.

Communication hubs of an asocial cat are the source of a human-carnivore conflict and key to its solution.

Human-wildlife conflicts occur worldwide. Although many nonlethal mitigation solutions are available, they rarely use the behavioral ecology of the conflict species to derive effective and long-lasting solutions. Here, we use a long-term study with 106 GPS-collared free-ranging cheetahs (Acinonyx jubatus) to demonstrate how new insights into the socio-spatial organization of this species provide the key for such a solution. GPS-collared territory holders marked and defended communication hubs (CHs) in the core area of their territories. The CHs/territories were distributed in a regular pattern across the landscape such that they were not contiguous with each other but separated by a surrounding matrix. They were kept in this way by successive territory holders, thus maintaining this overdispersed distribution. The CHs were also visited by nonterritorial cheetah males and females for information exchange, thus forming hotspots of cheetah activity and presence. We hypothesized that the CHs pose an increased predation risk to young calves for cattle farmers in Namibia. In an experimental approach, farmers shifted cattle herds away from the CHs during the calving season. This drastically reduced their calf losses by cheetahs because cheetahs did not follow the herds but instead preyed on naturally occurring local wildlife prey in the CHs. This implies that in the cheetah system, there are "problem areas," the CHs, rather than "problem individuals." The incorporation of the behavioral ecology of conflict species opens promising areas to search for solutions in other conflict species with nonhomogenous space use.