New Research Shows How African Elephants Can Be Counted From Space

Raw image in homogenous area compared with CNN detections (green boxes) and ground truth labels (red boxes). Worldview-3 Satellite images || Maxar Technologies

Research led by Isla Duporge of the University of Oxford Wildlife Conservation Research Unit and Machine Learning Research Group has shown that Elephants can be tracked and counted using satellite data, with more accuracy than humans. The research titled “Using very high-resolution satellite imagery and deep learning to detect and count African elephants in heterogeneous landscapes” was published in September 2020, with Olga Isupova, Steven Reece, David W. Macdonald, and Tiejun Wang. 

According to the research, satellites allow large-scale surveys to be conducted in short periods with repeat surveys possible in less than 24hrs. Therefore, the study used very high-resolution satellite imagery to detect and count some wildlife species in open, homogeneous landscapes and seascapes where target animals strongly 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.

The research used the highest resolution satellite imagery currently available –WorldView-3 and 4 satellite data. The team then applied a Convolution Neural Network (CNN) model to automatically detect and count African elephants in a woodland savanna ecosystem in South Africa. The team then trained and tested the model on eleven images from 2014-2019, comparing the performance accuracy of the CNN against human accuracy. Additionally, the model was applied on a coarser resolution satellite image (GeoEye-1) captured in Kenya to test if the algorithm can generalise to an elephant population outside of the training area.

The results showed that the CNN performed 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 generalise to detect elephants in a different geographical location and from a lower resolution satellite.

The research’s success will help protect the African elephants’ delining population, which have been victims of poaching, retaliatory killing from crop-raiding and habitat fragmentation. According to the researchers, the research results have demonstrated the feasibility of using high-resolution satellite imagery as a promising new wildlife surveying technique. 

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.