The CCP-NC is pleased to welcome you to the upcoming workshop on the state of Machine Learning in NMR crystallography. We will discuss the central challenges that the NMR crystallography community seeks to address with the emerging techniques and tools from the machine-learning field. The challenges and opportunities identified will be placed in the context of the current state of the art by our machine-learning experts.
Who is this for
This meeting is for you if you are
a) an ssNMR researcher wondering what ML could do for you, or if ML can solve one of your outstanding problems (e.g. of length- or timescale); or
b) a ML researcher looking for a fruitful application area that has interesting challenges and a welcoming community.
Speakers
We have an exceptional line-up of invited speakers spanning both machine learning and NMR crystallography, including:
- Sharon E. Ashbrook (University of St. Andrews) - Computational Solid-State NMR - Solid Ion Conductors under Scrutiny
- Michael A. Hope (University of Warwick)
- Gábor Csányi and Lars Schaaf (University of Cambridge) - Machine learning force fields are ready for NMR action - dynamics and property prediction
- Daniel Lee (University of Manchester) - DNP-NMR Crystallography
- Paul Hodgkinson (Durham University)
- John Griffin (Lancaster University) - Applications and Challenges for the Study of Metal-Organic Frameworks by Solid-State NMR
- Chris Pickard (University of Cambridge)
- Simone Köcher (Forschungszentrum Jülich GmbH)
- Volker Deringer (University of Oxford)
- Chris Heard (Charles University)
- Matthias Kellner (EPFL) -Advancing chemical shielding predictions in organic solids
Chris Pickard: From AI to AI and back to AI
The emphasis of the meeting will be on discussing the current challenges and opportunities and so we encourage you to bring your favourite topics. Some areas we will touch on include:
- ssNMR researchers are routinely using ab initio calculations to help interpret experimental findings. Ab initio calculations are used to i) generate structural models ii) predict NMR properties. However, there are computational bottlenecks that are currently prohibiting some projects, where ML tools can help.
- It would be interesting to hear about these problems. While ML tools are highly adaptable, they will not necessarily work out-of-the-box on a particular system and it'd be useful to know where the specific interests are.
- How would ssNMR groups use ML tools? Ab initio packages are fairly robust and there exist training events enabling experimentally focussed PhD students and postdocs to master their use. How could we facilitate a similarly accessible entry point for these new methods?
- What are the current capabilities of ML tools? How do these fit into the NMR crystallography workflow? What are the research directions relevant to the ssNMR community?
Posters
We will have posters set up throughout the two days with ample time for discussion between sessions. We encourage both early career researchers to bring their latest work as well as research group leads to bring overviews of their group's activities.
Registration fee
The registration fee is £50 which includes meals and accommodation. This is kept as low as possible to encourage a wide participation and was enabled thanks to generous funding of the CCP-NC via the UKRI DRI grant.
Travel grant resources
The CCP-NC has a bursary scheme to enable UK early career researchers to participate in events such as this. You can find out more and how to apply here:
https://www.ccpnc.ac.uk/opportunities/travel-fund
Hybrid/Recording
Unfortunately, due to the emphasis on discussion during this workshop, we cannot offer a hybrid/recording option. However, we will be publishing a report summarising some of the overarching themes on the CCP-NC website after the event.
Register By