Webinar: Statistical Machine Learning for Spatio-Temporal Forecasting

The Statistical Society of Australia is pleased to announce the following webinar:

Statistical Machine Learning for Spatio-Temporal Forecasting

About this webinar

Conventional spatio-temporal statistical models are well-suited for modelling and forecasting using data collected over short time horizons. However, they are generally time-consuming to fit, and often do not realistically encapsulate temporally-varying dynamics. Here, we tackle these two issues by using a deep convolution neural network (CNN) in a hierarchical statistical framework, where the CNN is designed to extract process dynamics from the process' most recent behaviour. Once the CNN is fitted, probabilistic forecasting can be done extremely quickly online using an ensemble Kalman filter with no requirement for repeated parameter estimation. We conduct an experiment where we train the model using 13 years of daily sea-surface temperature data in the North Atlantic Ocean. Forecasts are seen to be accurate and calibrated. A key advantage of the approach is that the CNN provides a global prior model for the dynamics that is realistic, interpretable, and computationally efficient to forecast with. We show the versatility of the approach by successfully producing 10-minute nowcasts of weather radar reflectivities in Sydney using the same model that was trained on daily sea-surface temperature data in the North Atlantic Ocean. This is joint work with Christopher Wikle, University of Missouri.

About the presenter

Andrew Zammit-Mangion is an Australian Research Council (ARC) Discovery Early Career Research Award (DECRA) Senior Research Fellow with the School of Mathematics and Applied Statistics at the University of Wollongong, Australia. His key interests lie in spatio-temporal models and the inferential tools that enable them. He was awarded a Best Doctoral Dissertation Prize by the Institute of Engineers and Technology (IET) in 2012, and the Cozzarelli Prize (Best PNAS paper in Engineering and Applied Sciences) by the National Academy of Sciences of the US on the topic in 2013. He is currently a member of NASA's Orbiting Carbon Observatory-2 (OCO-2), and in 2019 he published a co-authored book with Christopher Wikle and Noel Cressie on spatio-temporal modelling with R.

To register

This event is for members of SSA only. It is free, but you will need to register. After registering, you will receive a confirmation email containing information about joining the meeting. 

If you have any questions, please contact Marie-Louise Rankin. 

Would you please note that the times stated are AEDT.