Workshop Report
The Optimisation and Machine Learning Workshop brought together engineers, researchers, and stakeholders to explore cutting-edge computational approaches for metamaterials design. Focused on capability-building, the event provided practical insight into how optimisation techniques and machine learning can accelerate innovation in the development of multiscale architected materials.
Event Overview
Led by Dr Panesar, Co-Lead of the Theory, Modelling and AI Special Interest Group (SIG), and supported by the UK Metamaterials Network (UKMMN) team, the workshop delivered a focused and hands-on learning experience. The event aimed to equip participants with the skills and tools needed to apply advanced computational methods in their own research and engineering practice.
Attendees represented a broad cross-section of the community, including academic researchers, industry engineers, and government stakeholders. This diversity enabled valuable knowledge exchange between theory, application, and policy perspectives.
Key Themes and Content
The workshop explored how topology optimisation and machine learning can be leveraged to design high-performance metamaterials across multiple scales. Sessions addressed both the theoretical foundations and practical implementation of these approaches, highlighting their potential to unlock new material functionalities and efficiencies.
Key areas of discussion included:
- The integration of optimisation algorithms in metamaterial design workflows
- The application of machine learning techniques to accelerate discovery and improve predictive modelling
- Strategies for bridging scales in the design of architected materials
- The role of computational tools in enabling rapid prototyping and innovation
To support continued learning and adoption, a suite of computational resources and code examples were made available to participants via the IDEA Lab platform.
Engagement and Feedback
The workshop was met with overwhelmingly positive feedback from attendees, particularly in its in-person delivery format. Participants highlighted the practical relevance of the content and the accessibility of the tools provided.
The event also generated strong visibility beyond the immediate audience, with attendees sharing their experiences and key takeaways professional networks such as LinkedIn, amplifying its impact across the wider community.
Outcomes and Impact
A significant indicator of the workshop’s success is the initiation of two new collaborative projects, directly arising from interactions during the event. These collaborations highlight the workshop’s effectiveness in connecting participants and translating knowledge into tangible research outcomes.
The event also sparked interest across the UKMMN community, with additional Special Interest Groups expressing a desire to collaborate on future editions. This cross-SIG engagement reflects the growing importance of computational approaches within the metamaterials field and the demand for further training opportunities.
Next Steps
Building on this success, plans are already underway to deliver a follow-up workshop in July 2027 in Durham. The next iteration is expected to expand in scope, incorporating contributions from additional SIGs and reinforcing interdisciplinary collaboration.
Conclusion
The Optimisation and Machine Learning Workshop successfully advanced skills development and collaboration within the metamaterials community. By combining technical training with opportunities for networking and idea exchange, the event has contributed to strengthening the UK’s capability in computational materials design and laid the foundation for sustained collaboration and future innovation.