Log in

SSA NSW Branch: May Meeting - Dr Ian Renner

  • 10 May 2019 12:33 AM
    Message # 7331407

    Date: Wed, 15th May 2019

    6:00pm - 6:30pm: Refreshments
    6:30pm - 7:30pm: Talk
    7.30pm: Dinner at a nearby restaurant. Please RSVP here if you would like to join for dinner.

    Venue: Level 9, Conference Room 2, Peter Shergold Building, Parammatta, University of Western Sydney

    Dr Ian Renner

    Senior Lecturer at The University of New Castle

    Latest developments in species distribution modelling

    My research focuses on species distribution modelling, in which data collected on the presence of species is used to predict the distribution of species as a function of the environment. As simple as this sounds, there is a lot of active research in species distribution modelling to address difficulties that arise with various aspects of the model. In this talk, I will present the most recent developments I have been working on in this area:

    * Increasingly, species data from different sources are available to be used in fitting species distribution models, such as presence-only data and presence-absence data or presence-only data and occupancy data. We extend recent methodological developments in combined likelihood formulations by introducing lasso-type penalties to address potential overfitting and area-interaction models that accommodate spatial dependence, making the proposed combined penalised likelihood approach more flexible and useful for realistic data settings.
    * In some cases, species records may have uncertain species labels. This can happen if, for instance, taxonomy changes for a group of species, rendering observations made before the taxonomic change confounded. In such cases, can we make use of the confounded data to improve fitted species distributions? We present new methods that make use of mixture modelling and machine learning techniques to investigate this question.


    Renner, I.R., Louvrier, J., and Gimenez, O.G. (2019) Combining multiple data sources in species distribution models while accounting for spatial dependence and overfitting with combined penalised likelihood maximisation. Submitted to Methods in Ecology & Evolution. Preprint available at

    Guilbault, E., Renner, I.W., Mahoney, M, and Beh, E. (2019) Classification of unlabelled observations in Species Distribution Modelling using Point Process Models. Submitted to Methods in Ecology & Evolution.

    Ian Renner earned his PhD in 2013 from the University of New South Wales, and continued in a post-doctorate position there before assuming a position as a lecturer with the University of Newcastle. His research interests currently focus on species distribution models for presence-only data, a fast-advancing field. He unified the literature by establishing the equivalence of two methods: point process models and MAXENT. Leveraging off of this equivalence, he proposed an approach called PPM-LASSO, which inherits the clarity of interpretation and implementation, the flexibility, and the ability to critically evaluate model fits from point process models, and extends the benefits of predictive performance gained from affixing LASSO penalties, which have contributed to MAXENT's popularity. He maintains the R package ppmlasso to fit such models.

Powered by Wild Apricot Membership Software