Data visualisation uses a combination of hardware and software to explore patterns and relationships in research data, giving researchers greater understanding of their projects and potential outcomes.
It’s used at all stages of research: from conception, planning, data gathering and quality control, to analysis, presentation and publication. In this era of big data traditional approaches to visualisation are being challenged.
New opportunities exist in the form of large-format two- and three-dimensional (stereoscopic) displays, tiled display walls, virtual reality headsets, and the use of cloud-based virtual desktop infrastructure.
The Advanced Visualisation Lab works with Swinburne Research Institutes and centres to:
support, enhance and extend the use of advanced visualisation
build capability in data visualisation
research, design, develop and implement new solutions, with an emphasis on accelerating the rate of discovery.
The Advanced Visualisation Lab supports a range of Swinburne supercomputing projects. See more projects on the OzSTAR website.
Seeing Stars: Tera-scale Astronomical Data Analysis and Visualisation (GraphTIVA)
The sheer volume of data that requires sifting and analysis is a challenge for contemporary science, whether it’s on the cellular level for bio medicinal research or on the cosmic level in the field of astronomy.
‘Big data’ describes datasets too large for traditional methods of analysis, and it’s becoming the norm, particularly with advances in astronomical observation and simulation. The ability to perform the fundamental tasks of analysis, processing and visualisation is becoming a key factor for competition and scientific discovery.
To support knowledge discovery and deeper research, Swinburne University of Technology has designed and built the Tera-scale interactive visualisation and data analysis framework (GraphTIVA). GraphTIVA is a high-performance, graphics processing unit (GPU)-based framework for the efficient analysis and visualisation of Tera-scale 3-dimensional data cubes.
The computing power of GraphTIVA is approaching one teravoxel per second. (A voxel is a 3D analogue of a pixel.) The results are 10–100 times faster than the best possible performance with traditional single-node, multi-core CPU implementations. The framework can scale to volumes of 1 terabyte (TB) and larger, and other, parallel algorithms can be added to provide further analytical tools.
GraphTIVA’s scalability and ability to use parallel algorithms for analysis will allow the framework to meet the image analysis and visualisation requirements of next-generation telescopes, including the forthcoming Square Kilometre Array pathfinder radio telescopes.
The Advanced Visualisation Lab has access to a range of facilities and equipment: