Physics-informed diffusion models for extrapolating crystal structures beyond known motifs
This work addresses the challenge of discovering new materials with unreported crystal frameworks for materials science, offering an incremental improvement by enhancing the efficiency of crystal structure prediction through generative models.
The paper tackled the problem of generating novel crystal structures beyond known motifs by developing a physics-informed diffusion method that embeds descriptors for compactness and local environment diversity, resulting in 67% of generated structures being outside the 100 most common prototypes and 66% of low-energy frameworks not matching any known prototypes.
Discovering materials with previously unreported crystal frameworks is key to achieving transformative functionality. Generative artificial intelligence offers a scalable means to propose candidate crystal structures, however existing approaches mainly reproduce decorated variants of established motifs rather than uncover new configurations. Here we develop a physics-informed diffusion method, supported by chemically grounded validation protocol, which embeds descriptors of compactness and local environment diversity to balance physical plausibility with structural novelty. Conditioning on these metrics improves generative performance across architectures, increasing the fraction of structures outside 100 most common prototypes up to 67%. When crystal structure prediction (CSP) is seeded with generative structures, most candidates (97%) are reconstructed by CSP, yielding 145 (66%) low-energy frameworks not matching any known prototypes. These results show that while generative models are not substitutes for CSP, their chemically informed, diversity-guided outputs can enhance CSP efficiency, establishing a practical generative-CSP synergy for discovery-oriented exploration of chemical space.