INFOTERRA: A global network for environmental information

INFOTERRA, the International Referral System for Sources of Environmental Information, is a component of EARTHWATCH, UNEP's programme for the critical assessment of the global environment. One of the first three programme activity centres set up to implement the EARTHWATCH concept, INFOTERRA was established to facilitate the exchange of environmental information within and between nations. The system became fully operational in January 1977, when the first edition of the International Directory of Sources of Environmental Information was published.Since then, INFOTERRA has processed over 3000 environmental queries around the world through its network of 101 participating countries. As the network enters its fourth year of operations, its partners are exploring ways of improving the flow of information to decision makers around the world and have begun a preliminary evaluation of the effectiveness of the system. The following report describes the basic features of INFOTERRA and the services it provides and discusses the results of studies undertaken to measure the effectiveness of this unique international cooperative effort in the field of environmental information exchange.     

Leveraging social media and deep learning to detect rare megafauna in video surveys

Deep learning has become a key tool for the automated monitoring of animal populations with video surveys. However, obtaining large numbers of images to train such models is a major challenge for rare and elusive species because field video surveys provide few sightings. We designed a method that takes advantage of videos accumulated on social media for training deep-learning models to detect rare megafauna species in the field. We trained convolutional neural networks (CNNs) with social media images and tested them on images collected from field surveys. We applied our method to aerial video surveys of dugongs (Dugong dugon) in New Caledonia (southwestern Pacific). CNNs trained with 1303 social media images yielded 25% false positives and 38% false negatives when tested on independent field video surveys. Incorporating a small number of images from New Caledonia (equivalent to 12% of social media images) in the training data set resulted in a nearly 50% decrease in false negatives. Our results highlight how and the extent to which images collected on social media can offer a solid basis for training deep-learning models for rare megafauna detection and that the incorporation of a few images from the study site further boosts detection accuracy. Our method provides a new generation of deep-learning models that can be used to rapidly and accurately process field video surveys for the monitoring of rare megafauna.