Materials-Discovery

This reposiztory is dedicated to the use of AI for the acceleration of materials discovery. The first project under this repo would be a replication of key methodologies of the paper 'Merchant, A., Batzner, S., Schoenholz, S.S. et al. Scaling deep learning for materials discovery. https://doi.org/10.1038/s41586-023-06735-9' From microchips to batteries and photovoltaics, discovery of inorganic crystals has been bottlenecked by expensive trial-and-error approaches. Concurrently, deep-learning models for language, vision and biology have showcased emergent predictive capabilities with increasing data and computation12,13,14. Here we show that graph networks trained at scale can reach unprecedented levels of generalization, improving the efficiency of materials discovery by an order of magnitude