circuit board

Our expertise

LIV.INNO’s Research and Development (R&D) is structured around three main research areas which directly address key data science challenges.

1. Monte Carlo (MC) and High Performance Computing (HPC)

Both techniques are powerful tools for everything from modelling the birth and evolution of the universe to performing the numerical integrals needed to calculate cross sections for particle interactions.

MC is used extensively across LIV.INNO: LJMU has pioneered the use of Monte Carlo techniques in the analysis of Supernova spectra, whilst experts at the University of Liverpool have developed GENIE, the world's most widely-used neutrino Monte Carlo generator.

In the mathematics department, theoretical calculation of properties of quantum chromodynamics and related quantum field theories rests on extensive MC simulation using HPC. These techniques are also widely used by professionals in finance, healthcare, energy, manufacturing, engineering, research and development, insurance, oil & gas, transportation and the environment.

2. Artificial Intelligence (AI) and Machine Learning (ML)

Optimisation techniques that can exploit deep structures and race-tuned implementation of Deep Learning on GPUs (Graphics Processing Units) have resulted in pervasive and successful application of machine learning across the big data arena; our researchers are at the forefront of this research.

Coupled to growing volumes of data encountered in STFC science and challenges faced when hand-crafting algorithms for each specific new data source, AI and ML presents a potentially game-changing opportunity to transform STFC’s ability to do new science in several areas.

Deep learning enabled AI technology is also widely used in industry to recognise images, process natural languages, play games better than humans, and drive cars.

3. Data analysis

As organisations continue to generate enormous amounts of data, they recognise the importance of data analytics to make key business decisions. The development of efficient Monte Carlo techniques provide optimal design, scheduling, and control of industrial systems, the development and analysis of new materials and structures and the risk analysis of large portfolios of financial products.

Back to: Centre for Doctoral Training for Innovation in Data Intensive Science