Learning from the mistakes of others: How female elk (Cervus elaphus) adjust behaviour with age to avoid hunters

Abstract

In animal behaviour, there is a dichotomy between innate behaviours (e.g., temperament or personality traits) versus those behaviours shaped by learning. Innate personality traits are supposedly less evident in animals when confounded by learning acquired with experience through time. Learning might play a key role in the development and adoption of successful anti-predator strategies, and the related adaptation has the potential to make animals that are more experienced less vulnerable to predation. We carried out a study in a system involving a large herbivorous mammal, female elk, Cervus elaphus, and their primary predator, i.e., human hunters. Using fine-scale satellite telemetry relocations, we tested whether differences in behaviour depending on age were due solely to selection pressure imposed by human hunters, meaning that females that were more cautious were more likely to survive and become older. Or whether learning also was involved, meaning that females adjusted their behaviour as they aged. Our results indicated that both human selection and learning contributed to the adoption of more cautious behavioural strategies in older females. Whereas human selection of behavioural traits has been shown in our previous research, we here provide evidence of additive learning processes being responsible for shaping the behaviour of individuals in this population. Female elk are indeed almost invulnerable to human hunters when older than 9-10 y.o., confirming that experience contributes to their survival. Female elk monitored in our study showed individually changing behaviours and clear adaptation as they aged, such as reduced movement rates (decreased likelihood of encountering human hunters), and increased use of secure areas (forest and steeper terrain), especially when close to roads. We also found that elk adjusted behaviours depending on the type of threat (bow and arrow vs. rifle hunters). This fine-tuning by elk to avoid hunters, rather than just becoming more cautious during the hunting season, highlights the behavioural plasticity of this species. Selection on behavioural traits and/or behavioural shifts via learning are an important but often-ignored consequence of human exploitation of wild animals. Such information is a critical component of the effects of human exploitation of wildlife populations with implications for improving their management and conservation.

Fig 1. Movement rate (step-length, i.e., distance in meters travelled every 2 hours, log-transformed) in female elk as a function of age (range 1–20 years old) and hunting regime (no-hunting, bow, and rifle) as predicted by the linear mixed effect model.

Ninety-five percent marginal confidence intervals are shown as shaded areas [sample size: n = 49 female elk, each of them contributing with telemetry relocations collected over 2 consecutive years].

Fig 2. Use of terrain ruggedness (in meters) in female elk as a function of age (range 1–20 years old) and hunting regime (no-hunting, bow, and rifle) as predicted by the linear mixed effect model.

Ninety-five percent marginal confidence intervals are shown as shaded areas [sample size: n = 49 female elk, each of them contributing with telemetry relocations collected over 2 to 5 consecutive years].

Fig 3. Use of terrain ruggedness (in meters) in female elk as a function of age (range 1–20 years old) and distance to road (distance higher or lower than 500 meters) as predicted by the linear mixed effect model.

Ninety-five percent marginal confidence intervals are shown as shaded areas [sample size: n = 49 female elk, each of them contributing with telemetry relocations collected over 2 to 5 consecutive years].

Fig 4. Use of terrain ruggedness (in meters) in female elk as a function of age (range 1–20 years old) and time of the day (night, dawn, day, and dusk) as predicted by the linear mixed effect model.

Ninety-five percent marginal confidence intervals are shown as shaded areas [sample size: n = 49 female elk, each of them contributing with telemetry relocations collected over 2 to 5 consecutive years].

Fig 5. Use of forest (0 = no forest, 1 = forest) in female elk as a function of age (range 1–20 years old) and distance to road (distance higher or lower than 500 meters) as predicted by the generalized linear mixed effect model.

Ninety-five percent marginal confidence intervals are shown as shaded areas [sample size: n = 49 female elk, each of them contributing with telemetry relocations collected over 2 to 5 consecutive years].