Dr Maciej Cytowski1, Mike Lynch2, Glen Charlton3, Dr Rui Yang4, Anselm Motha5
1Pawsey Supercomputing Research Centre, Perth, Australia, 2The University of Sydney, Sydney, Australia, 3Intersect Australia, Sydney, Australia, 4National Computational Infrastructure, Canberra, Australia, 5University of Technology Sydney, Sydney, Australia
Biography:
Maciej Cytowski:
Maciej Cytowski is a computational scientist and expert in high-performance computing and data science. He specialises in designing and implementing computational strategies for complex scientific problems, particularly in fields like computational physics, computational biology, weather, climate, and artificial intelligence. His background is mathematics, and he holds a PhD in computational science. Currently, he is the Head of Scientific Services at the Pawsey Supercomputing Research Centre in Perth, Western Australia.
Mike Lynch:
Mike Lynch is a data science group lead at the Sydney Informatics Hub, with expertise in research data management, open standards for research data and the application of modern IT development and deployment practices to research software. In his current role he leads a team of software engineers and research compute specialists working to enable researchers to best utilise national cloud compute and the University’s GPU cluster.
Glen Charlton:
Glen is the Lead Data Scientist for the Advanced Analytics & AI (3AI) Platform at Intersect Australia. The 3AI team empowers researchers with data science and AI through hands-on support and the transfer of knowledge to improve the efficiency and increase the capability of researchers to conduct novel and practically relevant research. Glen actively promotes the novel and responsible adoption of AI for both research and operational purposes within members, partners and internally within Intersect.
Rui Yang:
Rui works as a Senior HPC Specialist at the National Computational Infrastructure (NCI), where he leads the Software and Data Modernisation team. The team provides dedicated support to multiple domain research communities by maintaining specialised computing environments, optimising performance for scientific models, and supporting collaborative projects. Rui led initiatives in deploying and evaluating state-of-the-art AI/ML models on HPC systems, maintaining ML-ready datasets and co-develop AI workflows with research groups to meet domain-specific needs.
Anselm Motha:
Anselm is the Specialist Research Technology Manager at the University of Technology Sydney (UTS). He leads a team that drives engagement with the research community at UTS. The team support a traditional queue based HPC system along with an interactive HPC system specialised for engineering workloads. Anselm strives for a collaborative IT environment for research at UTS, he works closely with other team within the IT Unit to ensure that research projects are closely aligned with the polices at UTS.
Abstract:
Situation
With developments in Artificial Intelligence (AI), scientific research increasingly relies on complex computational workflows that integrate diverse applications, data sources, and infrastructure. Supporting these workflows requires a deep understanding of both domain-specific needs and evolving technologies. Additionally, the diversity of applications and tools used by researchers grows exponentially with the development of new approaches in High Performance Computing (HPC) and AI.
Task
This session invites practitioners, researchers, and support professionals to share and discuss best practices, challenges, and strategies for enabling robust, scalable, and reproducible scientific workflows. We will explore approaches to workflow design, automation, and optimization across a range of disciplines, with a focus on practical and scalable support models, user engagement, and cross-institutional collaboration. Topics may include workflow management systems, reproducibility and containerization, GPU porting and optimisation, data management and storage, application enabling and integration with HPC, cloud, and hybrid environments.
Action
This session aims to foster a collaborative dialogue around what works, what doesn’t, and what’s next in supporting scientific applications and workflows. The session will begin with short presentations from leading institutions in Australia, focusing on changes and challenges in scientific applications and workflows support over the last couple of years. We will then switch to discussion in subgroups to focus on requirements of specific domains and selected aspects of the support ecosystem.
Result
We hope that participants will leave with actionable insights and new connections to strengthen and improve services (providers) and leverage or integrate with existing services (researchers).