Machine Learning in Ecosystem Informatics (invited lecture for DS 2007) Author: Thomas G. Dietterich Affiliation: School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA. Abstract. Ecosystem Informatics (EI) brings together mathematical and computational tools to address fundamental scientific and application problems in the ecosystem sciences. This talk will describe two on-going research efforts in EI at Oregon State University: (a) the application of machine learning and computer vision for automated arthropod population counting and (b) the application of linear Gaussian dynamic Bayesian networks for automated cleaning of data from environmental sensor networks. The talk will also briefly describe our experience at OSU with an interdisciplinary graduate program in Ecosystem Informatics. ©Copyright 2007 Author