On 2 April 2026, AIchemy Hub and the Institute of Physics (IOP) and brought together a vibrant community of over 100 researchers, spanning experimental and computational materials science, for a focused mini-symposium on machine learning (ML) for experimental materials data.
The event highlighted how AI is transforming the way we analyse, interpret, and act on increasingly complex datasets across scattering, microscopy, tomography, and spectroscopy.
The symposium featured a diverse and engaging line-up of speakers, showcasing cutting-edge applications of machine learning across experimental materials science:
- Austin Mroz (Imperial College London) — Remembering the lab in computational materials discovery
- Robert Palgrave (University College London) — Machine Learning Approaches to X-ray Photoelectron Spectroscopy Data Analysis
- Sam Cooper (Imperial College London) — Small Features, Big Impact: Designing at the Microscale with Generative AI
- Sarah Haigh (University of Manchester) — Application of AI to Advance Quantitative Atomic Scale Transmission Electron Microscopy
- Shelly Conroy (Imperial College London) — AI for Emergent Polar Topologies: Opportunities and Pitfalls in Electron Microscopy Data
- Antony Vamvakeros (Finden Ltd) — AI Methods for Data-Intensive Chemical Characterisation in Industry
- Andrew McCluskey (University of Bristol) — Bayesian Model Selection Provides a Robust Tool for Experimental Analysis
- Shijing Sun (University of Cambridge) — From Data to Decisions: Learning Efficiently from Robotic Experiments
A lively panel discussion highlighted key shared challenges, including data quality, interpretability, and integrating ML into experimental workflows. The day also included a poster session and ended with networking and informal discussions over drinks
We thank all speakers and attendees for making this event such a success and look forward to continuing these conversations through the AIchemy hub.