Amorphous materials—the disordered solids found in everything from smartphone glass to optical fibres—have long resisted computational design because their atomic structures are too complex for standard simulations. Most computer-driven materials discovery relies on quantum-mechanical simulations of crystals, which have orderly, repeating atomic patterns. Amorphous materials lack this order, making them nearly impossible to model with existing methods. This has left a vast class of technologically important substances—including many glasses, polymers, and thin films—outside the reach of predictive design. The researcher proposes to overcome this barrier by developing machine learning algorithms that can "learn" the structural rules of amorphous materials. One strand of work will create databases that train interatomic potentials to simulate these disordered systems with the same realism now reserved for crystals. Another will build a deep-learning model to predict nuclear magnetic resonance (NMR) shifts—a key experimental fingerprint—from simulated structures. If successful, the project would open amorphous materials to computational discovery for the first time. This is fundamental science: it aims to establish a methodology, not to deliver a specific product. But the payoff could be substantial—enabling the rational design of stronger, lighter, or more transparent glasses, better optical fibres, or more durable coatings, without the trial-and-error that currently governs their development.
View original technical description
The discovery and design of new technologically relevant materials is a major research goal in the physical sciences. Quantum-mechanical simulations on large supercomputers have brought the computational design of materials within reach: identifying suitable compositions, searching for stable crystal structures, guiding and inspiring experimental discoveries. However powerful, this progress has been largely limited to crystalline materials with long-range structural order and relatively small unit cells. In contrast, the amorphous (non-crystalline) state has been a long-standing challenge for predictive atomistic simulations, which has severely restricted the range of new materials to be discovered. I here propose to overcome this important challenge: by developing machine learning (ML) driven approaches for the atomic-scale modelling, optimisation, and design of multicomponent amorphous materials with desired properties. This ambitious project will leverage the power of both supervised and unsupervised ML algorithms to "learn" and navigate structural space. The first objective is to develop methodology with which to create universally applicable fitting databases for ML interatomic potentials - thereby making multicomponent amorphous materials amenable to realistic atomistic modelling, on par with how crystalline solids are treated today. The second objective is to develop a novel deep learning model, here to be used for predicting solid-state NMR shifts, but with more general implications for ML-based property prediction. Finally, the methodology will be used in computational practice and applied to key materials systems. This project will open up a new degree of realism in the structural modelling and understanding of the amorphous state, provide a wealth of openly available research data, and ultimately enable the computationally driven design of new amorphous materials.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know