Publications

Understanding the behaviour of animals in their natural habitats is critical to ecology and conservation. Camera traps are a powerful tool to collect such data with minimal disturbance. They however produce a very large quantity of images, which can make human-based annotation cumbersome or even impossible. While automated species identification with artificial intelligence has made impressive progress, the automatic classification of animal behaviours in camera trap images remains a developing field. Here, we explore the potential of foundation models, specifically vision-language models (VLMs), to perform this task without the need to first train a model, which would require some level of human-based annotation. Using two datasets, of alpine and African fauna, we investigate the zero-shot capabilities of different kinds of recent VLMs to predict behaviours and estimate behaviour-specific diel activity patterns in three ungulate species. By comparing our predictions to behaviours annotated by participatory science, our results show that using these automatic methods, it is possible to achieve F1-score as high as 86.39% in behaviour classification and produce activity patterns that closely align with those derived from participatory science data (overlap indexes between 84% and 90%). These findings demonstrate the potential of foundation models and vision-language models in ecological research. Ecologists are encouraged to adopt these new methods and leverage their full capabilities to facilitate ecological studies.

In large herbivores, the timing of births often coincides with the seasonal peak of food resources availability, likely to improve juvenile survival and reduce reproduction costs. Some species, however, breed year-round, even in seasonal environments. Demographic processes, such as to what extent being born during the lean season reduces survival of juveniles and reproductive females, remain understudied in large mammals inhabiting tropical ecosystems. We investigated survival rates in plains zebras (Equus quagga) in Hwange National Park (Zimbabwe), a highly seasonal savanna ecosystem. We used capture-recapture models to analyse long-term demographic data (2008-2019). We investigated the effect of seasonality as a categorical (wet versus dry season) and continuous (duration of the dry season) variable on survival. We found little variability in early juvenile survival (φ = 0.458 ± 0.044 SE, < 6 m.o.), whereas late juvenile and yearling survivals were higher and decreased with increasing length of the dry season (from 0.850 ± 0.095 SE to 0.480 ± 0.120 SE). Female survival was high (> 0.703 ± 0.057 SE and up to 0.995 ± 0.006 SE) but decreased with exposure to the dry season in non-reproductive females. The probability of females becoming reproductive in the following year was not affected by the length of the dry season (0.423 and 0.420 for reproductive and non-reproductive females, respectively). Our results highlight the importance of individual quality in reproductive performance, as reproductive females seem to buffer the effect of environmental variability on their own survival and that of their foal.