Alan Huang

Extended Bradley-Terry models for head-to-head competitions

Bradley-Terry models with multivariate latent skill parameters for modelling non-transitive relationships between teams in head-to-head competitions. Applications to NBA, NRL and cricket data.

Models for counts

Count data often exhibit deviations from a nominal Poisson distribution. This project will look at ways to handle such deviations, both parametrically and non-parametrically.

Are pesticide concentrations increasing or decreasing in rivers that discharge to the Great Barrier Reef?

Project description

Monitoring of up to 86 pesticides has been conducted in rivers that discharge to the Great Barrier Reef for over 12 years. The crucial question of whether concentrations of individual pesticides are increasing or decreasing in these rivers has only been answered for one insecticide, imidacloprid and is currently being addressed for diuron. In this desktop project you will use trend analysis to determine if pesticide concentrations are changing over time. You will work with scientists from the Queensland Department of Environment and Science. Your project will generate results that will inform future management actions and policies that aim to improve the quality of water entering the Great Barrier Reef lagoon. It is expected that the results will be publishable. There is a $5 000 scholarship associated with this project.

Relevant Fields

Pollution Science, Water Quality, Data Analysis, Pesticides

Supervisors

Assoc. Prof. Michael Warne (SEES), Dr Ryan Turner (SEES), Dr Alan Huang (School of Mathematics and Physics), Catherine Neelamraju and Dr Reinier Mann (Queensland Department of Environment and Science)

Fingerprinting water

We have spectral sensor probes in 56 rivers that discharge to the Great Barrier Reef (GBR) lagoon. Every fifteen minutes they each generate a spectra of the water passing the probe to estimate nitrate concentrations. In this project you will analyse the spectra and traditional laboratory-based measurements of pollutants (86 pesticides, suspended sediment and nine forms of nitrogen and phosphorus) to determine if there are statistically significant relationships that can accurately predict pollutant concentrations. If they are sufficiently accurate, they will be used to predict the concentrations of pollutants in waterways without pollutant data. Successful relationships would be of immense interest to the Queensland Department of Environment and Science and would be extremely useful in efforts to improve the quality of water entering the GBR lagoon. It is expected that the results will be publishable. There is a $5 000 scholarship associated with this project.

Relevant Fields

Pollution Science, Water Quality, Predicting water quality, Water quality monitoring

Supervisors

Dr Ryan Turner (SEES), Assoc. Prof. Michael Warne (SEES), Dr Alan Huang (School of Mathematics and Physics)