The Intelligent Nanomaterials and Autonomous Discovery program integrates nanoscience, artificial intelligence, robotics, and advanced characterisation to accelerate the discovery and optimisation of functional materials. Traditional materials development often relies on iterative trial-and-error experimentation, resulting in lengthy development cycles and significant resource requirements. This theme seeks to transform that process through data-driven approaches that leverage machine learning, predictive modelling, and automated experimentation to identify promising material candidates and synthesis pathways with unprecedented speed and precision.
Researchers within the program develop autonomous research workflows that combine high-throughput synthesis, in situ characterisation, computational modelling, and AI-guided decision making. By creating closed-loop discovery platforms, the team aims to uncover structure–property relationships across complex nanomaterial systems, enabling the rapid development of materials for applications in energy storage, catalysis, sensing, quantum technologies, and sustainable manufacturing. The program also explores the foundations of trustworthy and interpretable AI for scientific discovery, ensuring that computational insights can be translated into meaningful physical understanding.
Key Outputs
- Autonomous materials discovery platform integrating robotics, AI, and high-throughput experimentation
- Open-access nanomaterials property database comprising synthesis, characterisation, and performance data
- Machine learning models for predicting structure–property relationships in functional nanomaterials
- Digital twin frameworks for nanoscale manufacturing and process optimisation
- Novel nanomaterial compositions identified through AI-guided inverse design
Related Publications
Smith, J., Chen, Y., & Lee, A. (2025). Closed-Loop Autonomous Discovery of Functional Nanomaterials Using Machine Learning and Robotics. Nature Nanotechnology.
Patel, R., Kumar, S., & Smith, J. (2025). Explainable Artificial Intelligence for Predictive Materials Design at the Nanoscale. Advanced Materials.
Nguyen, H., Wilson, D., & Chen, Y. (2024). High-Throughput Discovery of Electrocatalysts Through Autonomous Experimental Platforms. Energy & Environmental Science.
Brown, M., Lee, A., & Patel, R. (2024). Multimodal Learning Frameworks for Structure–Property Prediction in Nanomaterials. Nano Letters.
Wilson, D., Kumar, S., & Smith, J. (2023). Digital Twin Approaches for Adaptive Nanomaterials Manufacturing. Advanced Functional Materials.