Satellites allow large‐scale surveys to be conducted in short time periods with repeat surveys possible at intervals of <24 h. Very‐high‐resolution satellite imagery has been successfully used to detect and count a number of wildlife species in open, homogeneous landscapes and seascapes where target animals have a strong contrast with their environment. However, no research to date has detected animals in complex heterogeneous environments or detected elephants from space using very‐high‐resolution satellite imagery and deep learning. In this study, we apply a Convolution Neural Network (CNN) model to automatically detect and count African elephants in a woodland savanna ecosystem in South Africa. We use WorldView‐3 and 4 satellite data –the highest resolution satellite imagery commercially available. We train and test the model on 11 images from 2014 to 2019. We compare the performance accuracy of the CNN against human accuracy. Additionally, we apply the model on a coarser resolution satellite image (GeoEye‐1) captured in Kenya, without any additional training data, to test if the algorithm can generalize to an elephant population outside of the training area. Our results show that the CNN performs with high accuracy, comparable to human detection capabilities. The detection accuracy (i.e., F2 score) of the CNN models was 0.78 in heterogeneous areas and 0.73 in homogenous areas. This compares with the detection accuracy of the human labels with an averaged F2 score 0.77 in heterogeneous areas and 0.80 in homogenous areas. The CNN model can generalize to detect elephants in a different geographical location and from a lower resolution satellite. Our study demonstrates the feasibility of applying state‐of‐the‐art satellite remote sensing and deep learning technologies for detecting and counting African elephants in heterogeneous landscapes. The study showcases the feasibility of using high resolution satellite imagery as a promising new wildlife surveying technique. Through creation of a customized training dataset and application of a Convolutional Neural Network, we have automated the detection of elephants in satellite imagery with accuracy as high as human detection capabilities. The success of the model to detect elephants outside of the training data site demonstrates the generalizability of the technique.

Virtually nothing in nature is uniform. Observed at the right scale, most entities are clustered rather than evenly distributed, spatially and temporally, and this applies across domains from the distribution of matter in the universe, to habitats across theEarth's surface, and to energy in the landscape. Patchiness means organisms cannot carve out even territories. Instead, their shape and size depends on the dispersion of materials needed for survival and reproduction. This fundamental feature of life is intrinsically understood in ecology, for example, in the ideal free distribution and optimal foraging theory, and is represented in the anatomy as well as behaviour of organisms via the structures and strategies for moving, finding and capturing these patchy resources. But perhaps most striking of all is the role of patchiness in facilitating the formation of social groups – of societies. The resource dispersion hypothesis (RDH) suggests that where resources are dispersed and rich enough, multiple individuals can collapse into groups that share the same space at little cost to each other. Cooperation may be absent, but sociality is favoured nevertheless. Thirty years after the origin of the hypothesis, we review the accumulating models, critiques, evidence and experiments, concluding thatRDHis a pervasive feature of animal spacing patterns across a wide range of species, taxonomic groups and ecosystems. In the spirit of the original objective of theHuxleyReviews to ‘suggest and inspire research that will improve our knowledge in the future’, we also take the opportunity to consider wider implications of theRDH. If we live and evolved on a patchwork planet, then we should expect broader effects. Indeed, we suggest that theRDHhas played an important role in the evolution of cooperation, biodiversity, behaviour and, not least, in the social organization of humans in our evolutionary past and today.

Conservation of large carnivores, such as the African lion, requires preservation of extensive core habitat areas, linkages between them, and mitigation of human-wildlife conflict. However, there are few rigorous examples of efforts that prioritized conservation actions for all three of these critical components. We used an empirically optimized resistance surface to calculate resistant kernel and factorial least cost path predictions of population connectivity and conflict risk for lions across the Kavango-Zambezi Transfrontier Conservation Area (KAZA) and surrounding landscape. We mapped and ranked the relative importance of (1) lion dispersal areas outside National Parks, (2) corridors between the key areas, and (3) areas of highest human-lion conflict risk. Spatial prioritization of conservation actions is critical given extensive land use redesignations that are reducing the extent and increasing the fragmentation of lion populations. While our example focuses on lions in southern Africa, it provides a general approach for rigorous, empirically based comprehensive conservation planning based on spatial prioritization.