Olfactory Enrichment of Captive Pygmy Hippopotamuses with Applied Machine Learning

TL;DR

This study explores how scents can improve the welfare of pygmy hippopotamuses in captivity and uses machine learning to track their behaviors automatically.

Contribution

The study introduces scent-based enrichment for pygmy hippos and validates automated behavioral tracking using SLEAP software.

Findings

Olfactory enrichment increased environmental engagement and reduced inactivity in pygmy hippos.

SLEAP software showed strong agreement with manual tracking for most behaviors.

Automation can complement traditional methods in monitoring animal welfare.

Abstract

Zoologists and researchers commonly study animals by observing their behavior, enclosure use, and activity levels to gain insights into their engagement with the environment and their level of stimulation. Traditionally, this has been done by watching them directly, but such methods are time-consuming and often influenced by personal judgment. This study investigates the effects of scents as an enrichment on three individual pygmy hippopotamuses. Furthermore, we examined whether the software SLEAP (v1.4.1a2) could automate the tracking of the animals. Overall, the results indicated that the scents encouraged the hippos to explore more, and the software gave similar results to manual observations for most behaviors. This means that scent-based enrichment can be useful for pygmy hippopotamuses, and technology can help zoological institutions with monitoring animal welfare more easily.

The pygmy hippopotamus (Choeropsis liberiensis, Morton, 1849) is classified as Endangered by the International Union for the Conservation of Nature (IUCN). Compared to other large, threatened mammals, this species remains relatively understudied and new findings indicate potential welfare concerns, emphasizing the need for further research on the species welfare in zoological institutions. One approach to improving welfare in captivity is through environmental enrichment. This study investigated the effects of olfactory enrichment on three individual pygmy hippopotamuses through behavioral analysis and heat-map visualization. Using continuous focal sampling, several behaviors were influenced by the stimuli, with results showing a general decrease in inactivity and an increase in environmental engagement and interaction, particularly through scenting behavior. To further enhance behavioral quantification, machine learning techniques were applied to video data, comparing manual and automated behavior classification using the pose estimation program SLEAP. Four behaviors Standing, Locomotion, Feeding/Foraging, and Lying Down were compared. A confusion matrix, time budgets, and Kendall’s Coefficient of Concordance (W) were used to assess agreement between methods. The results showed a strong and moderate agreement between manual and automated annotations, for the female and calf, respectively. This demonstrates the potential of automation to complement behavioral observations in future welfare monitoring.

Figures