Project title: Understanding amorphous oxides for solar cell applications using generative machine learning
PI: Volker Deringer
Amorphous oxides play a critical role in sustainable energy production using solar cells. Understanding their microscopic structural features is essential for improving the performance of next-generation solar cell technologies. Generative AI has recently revolutionised fields such as chemistry, biology, and materials science by combining advanced machine learning techniques with deep domain expertise. A notable example is the recently published AlphaFold 3, serving as a revolutionary engine for protein folding prediction. In addition, generative modelling is increasingly applied to the discovery of new crystal structures, leading to a significant advancement in AI-assisted materials design. However, the application of generative models to amorphous oxides remains largely unexplored. The primary challenges stem from the complex disordered nature of amorphous networks and the limited integration of domain-specific knowledge in AI methods.
In this project, we will address these challenges by integrating state-of-the-art machine learning interatomic potentials with advanced generative AI techniques to develop robust, predictive models for amorphous oxides. By combining generative AI with our expertise in amorphous materials, we aim to create physically meaningful models that can be used to guide the design of next-generation solar cells with improved efficiency and sustainability.
