ACEMS Research Briefs

These are short summary descriptions of our latest, just-published research.

ACEMS Research Briefs Projects

Advanced Bayesian approaches for state-space models with a case study on soil carbon sequestration

The methods presented in this paper are useful for farmers and landowners in estimating carbon stocks in agricultural production systems.

Inclusion of features derived from a mixture of time window sizes improved classification accuracy of machine learning algorithms for sheep grazing behaviours

What if farmers could tell if one of their livestock was sick, without even being around the animal? Farmers are now using inertial motion sensors to study grazing behaviour. But the challenge is interpreting all the data those sensors provide. New research led by ACEMS PhD candidate Shuwen Hu reveals which machine learning methods are best suited to handle the problem.

Multivariate Bayesian meta‑analysis: joint modelling of multiple cancer types using summary statistics

This research provides a tool so that people can use readily available data from online cancer atlases, and understand patterns for multiple cancer types together.

Elucidating user behaviours in a digital health surveillance system to correct prevalence estimates

ACEMS researchers at The University of Adelaide develop a statistical model to get a better estimate of the spread of influenza-like-illness, accounting for human behaviour in online health surveillance systems.

Particle Methods for Stochastic Differential Equation Mixed Effects Models

ACEMS Researchers at QUT and UNSW introduce three novel parameter estimation methods for stochastic differential equation mixed effects models (SDEMEMs).

Stochastic spatial random forest (SS-RF) for interpolating probabilities of missing land cover data

How do you measure something you can’t see?

That’s the aim of new research just published by ACEMS’ researchers in the Journal of Big Data. Led by Jacinta Holloway Brown from ACEMS at QUT, the researchers developed a new statistical method to predict forest cover in satellite images where portions of the image are blocked by cloud cover. Not only that, the new method also calculates a probability to show how confident the prediction is.

Forecasting intensifying disturbance effects on coral reefs

ACEMS research combines state-of-art methodologies for coral reef data collection, remote sensing and statistical modelling to predict the future ecological status of the reefs within the Great Barrier Reef as the incidence of multiple disturbances continues to increase.

Monitoring through many eyes: Integrating datasets to improve monitoring of the Great Barrier Reef

Enormous effort is invested in monitoring the Great Barrier Reef (GBR), but data collection is currently fragmented over dozens of publicly and privately funded organisations, with data collected using different methods and for different purposes. As a result, the data are rarely analysed together.

A population of bang-bang switches of defective interfering particles makes within-host dynamics of dengue virus controllable

Viral pathogens pose a continuous and shifting biological threat to military readiness and national security overall in the form of infectious disease with pandemic potential. Today’s limited vaccines and other antivirals are often circumvented by quickly mutating viruses that evolve to develop resistance to treatments that are carefully formulated to act only specific strains of a virus.

A Feature‐Based Procedure for Detecting Technical Outliers in Water‐Quality Data From In Situ Sensors

Water-quality sensors are exposed to changing environments and extreme weather conditions and thus are prone to errors, including failure. These technical errors make data unreliable and untrustworthy and affect performance of any subsequent data analysis. ACEMS researchers, led by Priyanga Dilini Talagala, have proposed a feature based procedure, named oddwater, for detecting technical outliers in water-quality data derived from in situ sensors.

Welcome to the ACEMS Reportal

All contributors should enter data on all of the Centre’s reportable key performance indicators (KPIs).

These are short summary descriptions of our latest, just-published research.