CBRI/SysGen Seminar – Jane Elith – 7th October 2016
Species distribution models
I work on statistical and machine learning methods for modelling the response of species to their environments. These are static models, usually some form of regression. Species distribution models are very popular, and are one of the leading research fronts internationally in ecology and environmental sciences. I will present an overview of the models, outline why they are popular, and give some examples of typical complexities in the data and in applications that make this an interesting area for collaboration between ecologists, statisticians and computer scientists.
Jane Elith is an Associate Professor in the School of BioSciences, and part of the Quantitative Ecology group (qaeco.com). She started undergraduate life in Agricultural Science, spent 12 years away from work, raising children, and completed a PhD in environmental science here at the University of Melbourne in 2003. She has been an ARC Future Fellow, and now has an ongoing appointment. Species distribution models are used by both academics and practitioners, and Jane has been particularly interested in the methods and their appropriateness for the data and questions to which they are often applied. Her research has applied significance because distribution modelling is key in many aspects of species management, including understanding current distributions of threatened species, predicting how distributions might change in the future, supporting threat management, and controlling invasive species.