Al Ecologist: The use of algorithms for wildlife monitoring in the Korean DMZ

This study explores the use of artificial intelligence (Al) for environmental research by developing deep-learning algorithms for wildlife monitoring in and around the Korean Demilitarized Zone (DMZ). First, it develops computer vision systems for analysing wildlife images from ecologists and trap cameras- which we call the “Al ecologist”. The algorithms can perform automated species identification of a dozen of mammal species and several crane species, while making population-count estimations of selected crane species. Second, we examines the ways in which the machine and the human intersect in the formation and operation of Al. We specifically focus on the shared but diverging epistemologies of Al ecologists and human ecologists. This involves discussions of translation, agency, and friction, which opens up the space for surprises and creativity.