Conservation biology, a branch of applied ecology, aims at protecting biodiversity from erosion and extinction. Efficient conservation policy requires accurate monitoring and sampling techniques sensing natural environments over large spatio-temporal scales. Ecoacoustics offers recent alternative to traditional techniques as visual observation or trapping. At the crossroads of ecology, acoustics and computer science, ecoacoustics takes advantage of affordable and easy-to-use passive acoustic recording devices increasing spatio-temporal resolution, reducing operation cost, and relaxing the need of human expertise. Ecoacoustics can conduct long-term surveys at a large spatio-temporal scale by recording the presence of vocalizing animal species such as birds, insects or amphibians. So far ecoacoustics has been successflly applied to a broad range of applications, including monitoring human impact on natural environment. However, ecoacoustics has not yet been involved in the validation of habitat restoration programs, that is conservation actions that aim at recovering the initial state of a natural environment after a strong perturbation. Here, we will develop ecoacoustic methods to track the dynamics of animal populations and communities recolonizing a natural environment in restoration. A platform developed by the MIT (Cambridge, Massachusetts, USA) offers a unique opportunity to monitor biodiversity restoration of a freswater wetland. An important dataset has already been collected by a large network of acoustic and environmental sensors opening a challenge for AI. The first objective of the PhD consists in adapting AI supervised methods to automatically detect and identify vocalizations. The second obective is based on unsupervised methods to detect novelty or anomaly events (e.g. arrival of new (unknown) species) directly from the raw audio dataset. The last and third objective aims at describing, discovering and predicting (unexpected) spatio-temporal patterns and spatial species distribution. The expected results should help to inventory, monitor and preserve natural environments using non-invasive and expert free methods, providing AI techniques to citizens and managers. 

 

PhD student: Félix Michaud

PhD supervisor: Jérôme Sueur

Research laboratory: ISYEB - Institut de Systématique, Evolution et Biodiversité

 

Photo: Cyndi Jackson