Chemistry and Materials Machine Learning School 2027

📅 Dates: 5-9 April 2027
📍 Venue: STFC Daresbury Laboratory, United Kingdom
💷 Fee: £250 (includes 4 nights’ accommodation & catering)
👉 Website / Apply here: spring2027.camml.ac.uk

The Chemical and Materials Machine Learning School (CaMMLs) is a five-day intensive training course designed for PhD students (and a limited number of industrial applicants) working in the field of materials and molecular simulations who have coding experience but are not yet highly experienced with machine learning (ML). The school is organised by Physical Sciences Data Infrastructure (PSDI) in collaboration with AIchemy, and supported by STFC‑SCD, CCP5, CCP9 and CECAM.

Participants will explore the latest ML methods for atomistic simulation of materials and molecules through a combination of talks, hands-on practical sessions and poster presentations. Topics include fundamentals of machine learning, interatomic potentials and graph neural networks.

By the end of the school, participants will:

• Gain awareness of state-of-the-art ML methods for atomistic and molecular simulations

• Gain practical experience applying ML techniques in real-world research contexts

• Application deadline: 26 November 2026

• Notification of acceptance: 17 December 2026

• Payment deadline: 13 February 2027

This school is aimed primarily at PhD students in materials & molecular simulation who already code but are new to machine learning. A limited number of places may be available for industrial applicants. Places are limited to 40 and, in the event of oversubscription, we will prioritise a diverse cohort of participants.

Visit https://spring2027.camml.ac.uk/registration/ to complete your application via cvent. Payment of the course fee must be made by 13 February 2027 upon acceptance. Fee includes accommodation, breakfast, lunches, coffee breaks, school bbq and poster session refreshments.

For any enquiries please contact Alin M Elena at [email protected]. We encourage you to share this opportunity with colleagues and students who may be interested.