Elephants and algorithms: a review of the current and future role of AI in elephant monitoring

Artificial intelligence (AI) and machine learning (ML) present revolutionary opportunities to enhance our understanding of animal behaviour and conservation strategies. Using elephants, a crucial species in Africa and Asia's protected areas, as our focal point, we delve into the role of AI and ML in their conservation. Given the increasing amounts of data gathered from a variety of sensors like cameras, microphones, geophones, drones and satellites, the challenge lies in managing and interpreting this vast data. New AI and ML techniques offer solutions to streamline this process, helping us extract vital information that might otherwise be overlooked. This paper focuses on the different AI-driven monitoring methods and their potential for improving elephant conservation. Collaborative efforts between AI experts and ecological researchers are essential in leveraging these innovative technologies for enhanced wildlife conservation, setting a precedent for numerous other species.

Testing the Effectiveness of the "Smelly" Elephant Repellent in Controlled Experiments in Semi-Captive Asian and African Savanna Elephants

Crop-raiding by elephants is one of the most prevalent forms of human-elephant conflict and is increasing with the spread of agriculture into wildlife range areas. As the magnitude of conflicts between people and elephants increases across Africa and Asia, mitigating and reducing the impacts of elephant crop-raiding has become a major focus of conservation intervention. In this study, we tested the responses of semi-captive elephants to the "smelly" elephant repellent, a novel olfactory crop-raiding mitigation method. At two trial sites, in Zambia and Thailand, African elephants (Loxodonta africana) and Asian elephants (Elephas maximus) were exposed to the repellent, in order to test whether or not they entered an area protected by the repellent and whether they ate the food provided. The repellent elicited clear reactions from both study groups of elephants compared to control conditions. Generalised linear models revealed that the elephants were more alert, sniffed more, and vocalised more when they encountered the repellent. Although the repellent triggered a response, it did not prevent elephants from entering plots protected by the repellent or from eating crops, unlike in trials conducted with wild elephants. Personality played a role in responses towards the repellent, as the elephants that entered the experimental plots were bolder and more curious individuals. We conclude that, although captive environments provide controlled settings for experimental testing, the ecological validity of testing human-elephant conflict mitigation methods with captive wildlife should be strongly considered. This study also shows that understanding animal behaviour is essential for improving human-elephant coexistence and for designing deterrence mechanisms. Appreciating personality traits in elephants, especially amongst "problem" elephants who have a greater propensity to crop raid, could lead to the design of new mitigation methods designed to target these individuals.

Current and Future Approaches to Mitigate Conflict between Humans and Asian Elephants: The Potential Use of Aversive Geofencing Devices

Asian elephants are a principal cause of human-wildlife conflict. This results in the death/injury of elephants and humans and large-scale crop and property damage. Most current human-elephant conflict (HEC) mitigation tools lack the flexibility to accommodate the ecological needs of elephants and are ineffective at reducing HEC in the long-term. Here we review common HEC mitigation tools used in Asia and the potential of Aversive Geofencing Devices (AGDs) to manage problem elephants. AGDs can be configured to monitor animal movements in real-time and deliver auditory warnings followed by electric stimuli whenever animals attempt to move across user-specified virtual boundaries. Thus, AGDs are expected to condition elephants to avoid receiving shocks and keep them away from virtually fenced areas, while providing alternative routes that can be modified if required. Studies conducted using AGDs with other species provide an overview of their potential in conditioning wild animals. We recommend that the efficacy and welfare impact of AGDs be evaluated using captive elephants along with public perception of using AGDs on elephants as a means of addressing the inherent deficiencies of common HEC mitigation tools. If elephants could be successfully conditioned to avoid virtual fences, then AGDs could resolve many HEC incidents throughout Asia.