Data Intensive Science School

Participants will:

• Gain practical experience with modern data science tools
• Learn directly from experts in AI and computational science
• Build skills in scalable computing and scientific software development
• Explore emerging trends in agentic AI and open-source science
• Network with researchers across disciplines

• Apache Spark Workshop (4 hours) – Learn scalable data processing and distributed computing techniques for handling large scientific datasets.
• Machine Learning: Data Collection & Preparatio (4 hours) – Explore the foundations of building robust ML pipelines, from data acquisition to preprocessing and feature engineering.
• Agentic AI for Data Analysis (1 hour talk) Discover how autonomous AI agents are reshaping data analysis, scientific workflows, and research productivity.
• Git Workshop (2 hours) Develop essential version control skills for collaborative coding, reproducible research, and software development.
• Open Source Science (1 hour talk) Examine the growing importance of open-source ecosystems in accelerating scientific innovation and collaboration.
• PyAutoFit Workshop (2 hours) Introduction to probabilistic modelling and automated model fitting using PyAutoFit for scientific applications.
• Publishing Code (2 hours) Learn best practices for sharing, documenting, packaging, and publishing scientific software and research code.
• Real World Challenges Session (2 hours) – Apply your skills to practical scientific and data-driven problems inspired by current research challenges.
• How Not to Make NumPy Slow (2 hours) Improve performance and efficiency in scientific Python workflows through optimisation strategies and vectorised computation.