PSDI launched a new webinar series entitled “From Project to Platform: New Resources on PSDI”. This series aims to showcase the high-quality tools and resources developed through the funding call 2025, introduce them to a broader community, and foster engagement with relevant user groups.
On 30th April 2026, PSDI hosted the first session of the new webinar series titled “AI‑driven materials discovery” .
-
- Universal Hyper-Active Learning for Machine Learning Interatomic Potentials – Professor James Kermode (University of Warwick)
- MOFevaluator: A Cloud-Based Platform for Process-Informed Discovery of MOF for Carbon Capture and Beyond – Dr Peter McCallum and Professor Susana Garcia (Heriot-Watt University)
For those who missed the live session or wish to revisit the discussion, the full webinar is available on our YouTube channel.
The slides are available on zenodo:
Stay tuned for future PSDI webinars by subscribing to our PSDI YouTube Channel.
Abstract: This webinar is a joint session.
-
- Professor James Kermode (University of Warwick) presented ase-uhal, a tool that uses “Universal” Hyper-Active Learning to intelligently accelerate training dataset generation for machine learning interatomic potentials, with support for fine-tuning foundation models.
- Dr Peter McCallum and Professor Susana Garcia (Heriot-Watt University) introduced MOFevaluator, a cloud-based platform for process-informed discovery of Metal–Organic Frameworks (MOFs), enabling efficient screening for carbon capture and other applications through an interactive web interface and API.
