2022-04-25 NITheCS Colloquium:
Devis Tuia (Ecole Polytechnique Fédérale de Lausanne)
Machine learning supporting ecology supporting machine learning
Abstract: We live in an age full of data. In all areas of society, digital data is now abundant, but also unstructured and pretty much unexploited. Animal ecology is no exception and the last years have seen an increase in the use of digital sensing to observe and understand the animal realm. In this talk, I will present some success stories at the interface of machine learning and conservation, where camera traps and drone data were used to support censing, population estimation and a general understanding of animal behaviour. I will then sketch a number of points of synergetic action necessary to strengthen such an interface, a necessary step to jointly tackling the biodiversity crisis.