Tutorials

Tutorial 1

Overview

Title: Harnessing HPC and AI for Interactive Analysis and Visualisation of Large Scientific Datasets with the National Science Data Fabric (NSDF)

Computing resources increasingly span cloud platforms, institutional clusters, and personal laptops. Yet, scientific data is often generated remotely at experimental facilities or supercomputing centres, making data movement a challenge. Scientists need efficient ways to stream, inspect, analyse, and visualise data interactively without transferring large datasets.

This hands-on tutorial demonstrates how the National Science Data Fabric (NSDF) enables interactive, AI-augmented workflows for exploring large scientific datasets. Participants will learn how to stream data from remote public or private storage, analyse data using notebook-based environments, and deploy visualisation tools for scientific inference.

What you'll learn

• Streaming data from remote storage platforms
• Using AI methods for selective data exploration
• Visualising multidimensional scientific datasets
• Building modular and flexible scientific workflows

Prerequisites

• Bring your own laptop with Windows, macOS, or Linux
• Modern web browser, Chrome or Firefox recommended
• A GitHub account
• No software installation required; optional JupyterLab use is provided.

Target audience

• Scientists
• Researchers
• Students
• Engineers working with large datasets.

Prior HPC or AI specialisation isn't required.

Instructors

Professor Michela Taufer, University of Tennessee, Knoxville, United States of America.

Professor Valerio Pascucci, University of Utah, United States of America.

Duration

3 hours across 2 sessions.

Tutorial 2

Overview

Title: Federated Learning for Edge Computing

Edge computing has become an important paradigm for next-generation distributed systems by enabling computation close to data sources, thereby reducing latency, lowering communication overhead, and improving data privacy.

At the same time, Federated Learning has emerged as a promising approach for training models across decentralised devices without moving raw data to a central server, making it particularly attractive for edge environments.

This tutorial explores the principles, system architectures, and practical realisation of federated learning for edge computing. It reviews the basic concepts of FL and the Flower framework, and presents two demonstration settings:

• a Flower-based federated learning workflow for a Low Earth Orbit edge computing scenario
• a Raspberry Pi-based platform for lightweight federated learning.

Schedule

• Introduction: 5 minutes
• Applications of Federated Learning in Edge Computing: 10 minutes
• Architectures and Deployment Considerations for FL at the Edge: 10 minutes
• Hands-on Demo 1: Flower-based Federated Learning for a LEO Edge Computing Scenario: 30 minutes
• Hands-on Demo 2: Implementing and Visualisation of Federated Learning on Raspberry Pi: 30 minutes
• Final remarks: 5 minutes

Prerequisites

• Intermediate Python programming
• Basic cloud and edge computing
• Basic machine learning.

Intended audience: intermediate level.

Instructors

Dr Nan Yang, Western Sydney University, Australia

Associate Professor Rodrigo N. Calheiros, Western Sydney University, Australia

Professor Massimo Villari, University of Messina, Italy

Mark Gambito, University of Messina, Italy and Western Sydney University, Australia

Professor Bahman Javadi, Western Sydney University, Australia

Duration

1.5 hours in 1 session.