Assessment of Chimpanzee Nest Detectability in Drone-Acquired Images

Abstract

Abstract:As with other species of great apes, chimpanzee numbers have declined over the past decades. Proper conservation of the remaining chimpanzees requires accurate and frequent data on their distribution and density. In Tanzania, 75% of the chimpanzees live at low densities on land outside national parks and little is known about their distribution, density, behavior or ecology. Given the sheer scale of chimpanzee distribution across western Tanzania (>20,000 km 2 ), we need new methods that are time and cost efficient while providing precise and accurate data across broad spatial scales. Scientists have recently demonstrated the usefulness of drones for detecting wildlife, including apes. Whilst direct observation of chimpanzees is unlikely given their elusiveness, we investigated the potential of drones to detect chimpanzee nests in the Issa valley, western Tanzania. Between 2015 and 2016, we tested and compared the capabilities of two fixed-wing drones. We surveyed twenty-two plots (50 × 500 m) in gallery forests and miombo woodlands to compare nest observations from the ground with those from the air. We performed mixed-effects logistic regression models to evaluate the impact of image resolution, seasonality, vegetation type, nest height and color on nest detectability. An average of 10% of the nests spotted from the ground were detected from the air. From the factors tested, only image resolution significantly influenced nest detectability in drone-acquired images. We discuss the potential, but also the limitations, of this technology for determining chimpanzee distribution and density and to provide guidance for future investigations on the use of drones for ape population surveys. Combining traditional and novel technological methods of surveying allows more accurate collection of data on animal distribution and habitat connectivity that has important implications for ape conservation in an increasingly anthropogenically-disturbed landscape.

Importance of machine learning for enhancing ecological studies using information-rich imagery

“…for elusive species), which is important for species where documenting actual individuals is difficult, including threatened species, such as sea turtles, crocodilians and various bird species (e.g. Schofield et al 2017, Bonnin et al 2018, and (4) 'feature size,' when the focus was on detecting clusters of dense vegetation or aggregated invertebrates in which individuals are difficult to distinguish from each other (e.g. seagrass, moss and aquatic vegetation beds, coral reefs, stromatolites, mussel beds or homogeneous sections of habitat).…”

“…It might be easier to manually process imagery data over implementing a machinelearning model for rare and elusive species for which only a small amount of data are available (e.g. Schofield et al 2017, Bonnin et al 2018). However, as machine learning becomes more accessible and programs become available that can be adapted for different species, this tool will be invaluable for regular and repeated surveys of large geographical areas, or when the number of individuals is very large (Chabot et al 2015, Bonnin et al 2018, Hodgson et al 2018).…”

“…Schofield et al 2017, Bonnin et al 2018). However, as machine learning becomes more accessible and programs become available that can be adapted for different species, this tool will be invaluable for regular and repeated surveys of large geographical areas, or when the number of individuals is very large (Chabot et al 2015, Bonnin et al 2018, Hodgson et al 2018). In addition, recent and successful attempts to detect endangered species using machine-learning algo rithms (e.g.…”

“…baited remote underwater video stations [BRUVs] and remotely operated underwater vehicles [ROVs]) and in the air (unmanned aerial vehicles [UAVs] and unmanned aerial systems [UASs]), are providing a completely new perspective of wildlife and the ecosystems in which they live (Mallet & Pelletier 2014, Christie et al 2016. For example, UAVs are being used to map habitats (Kaneko et al 2014, Szantoi et al 2017 as well as monitor the abundance, behaviour and health of wildlife (Barasona et al 2014, Chabot et al 2015, Schofield et al 2017, Bonnin et al 2018. In particular, UAVs provide an opportunity to monitor elusive animals, including vulnerable and endangered species for which data remain limited, facilitating improved conservation actions, including serving as an antipoaching tool , Olivares-Mendez et al 2015, Christie et al 2016.…”

Editorial of Special Issue “Drones for Biodiversity Conservation and Ecological Monitoring”

“…Three of the published articles have addressed the main issues and opportunities in wildlife detection and mapping, and in both cases applied to protected species. Bonnin et al [1] used fixed-wing drones by means of in line transects and grid missions to locate Chimpanzee nests in Tanzania. Potential unknown nests were identified although many nests located in the middle of tree crowns could not be detected.…”