Andrew Parnell is Hamilton Professor in the Hamilton Institute at Maynooth University. His research is in statistics and machine learning for large structured data sets in a variety of application areas. He has co-authored over 75 peer-reviewed papers in journals such as Science, Nature Communications, and Proceedings of the National Academy of Sciences, and has methodological publications in journals such as Statistics and Computing, Knowledge-Based Systems, The Annals of Applied Statistics, and Journal of the Royal Statistical Society: Series C. He has been awarded over €3 million to date in direct funding as PI or Co-PI, and has been involved in grants totalling over €65 million as PI/collaborator. He has been heavily involved in the commercialisation of research through the start-up companies Prolego Scientific (CSO) and Atturos (Scientific Advisor). He is currently a principal investigator in the SFI I-Form Advanced Manufacturing Centre, and a funded investigator in the SFI Insight Centre for Data Analytics.

 

His main theoretical research interests include:

- Tree-based machine learning methods such as Bayesian Additive Regression Trees (BART) and Random Forests

- Extreme Value Theory

- Spatial statistics

- Bayesian hierarchical modelling using JAGS and Stan

- Compositional data

- Zero-inflation modelling
- Missing data analysis

 

His current list of application areas includes:

• Climatology, including sea level rise, extremes, and measuring rapid past climate changes

• Manufacturing, including anomaly detection, real-time tool wear analytics, and additive manufacturing

• Bioinformatics, including genotype by environment interaction modelling, and high dimensional *omics analysis

• Learning analytics for monitoring student progress and engagement

• Quantitative ecology especially mixing models for estimating animal diets and sediment tracing

• Radiocarbon dating and chronology modelling for archaeological and palynological applications

He enjoys collaborating with other scientists and writing non-specialist software via the open-source statistical language R.