Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.23181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911315906265088 |
|---|---|
| author | Vasylenko, Andrij Ottomano, Federico Collins, Christopher M. Savani, Rahul Dyer, Matthew S. Rosseinsky, Matthew J. |
| author_facet | Vasylenko, Andrij Ottomano, Federico Collins, Christopher M. Savani, Rahul Dyer, Matthew S. Rosseinsky, Matthew J. |
| contents | Discovering materials with new structural chemistry is key to achieving transformative functionality. Generative artificial intelligence offers a scalable route to propose candidate crystal structures. We introduce a reliable low-cost proxy for structural novelty as a conditioning property to steer generation towards novel yet physically plausible structures. We then develop a physics-informed diffusion model that embeds this descriptor of local environment diversity together with compactness as a stability metric to balance physical plausibility with structural novelty. Conditioning on these metrics improves generative performance across diffusion models, shifting generation away from structural motifs that dominate the training data. A chemically grounded validation protocol isolates those candidates that combine plausibility with structural novelty for physics-based calculation of energetic stability. Both the stability and the novelty of candidates emerging from this workflow can however change when the full potential energy surface at a candidate composition is evaluated with crystal structure prediction (CSP). This suggests a practical generative-CSP synergy for discovery-oriented exploration, where AI targets physically viable yet structurally distinct regions of chemical space for detailed physics-based assessment of novelty and stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Introducing physics-informed generative models for targeting structural novelty in the exploration of chemical space Vasylenko, Andrij Ottomano, Federico Collins, Christopher M. Savani, Rahul Dyer, Matthew S. Rosseinsky, Matthew J. Materials Science Machine Learning Discovering materials with new structural chemistry is key to achieving transformative functionality. Generative artificial intelligence offers a scalable route to propose candidate crystal structures. We introduce a reliable low-cost proxy for structural novelty as a conditioning property to steer generation towards novel yet physically plausible structures. We then develop a physics-informed diffusion model that embeds this descriptor of local environment diversity together with compactness as a stability metric to balance physical plausibility with structural novelty. Conditioning on these metrics improves generative performance across diffusion models, shifting generation away from structural motifs that dominate the training data. A chemically grounded validation protocol isolates those candidates that combine plausibility with structural novelty for physics-based calculation of energetic stability. Both the stability and the novelty of candidates emerging from this workflow can however change when the full potential energy surface at a candidate composition is evaluated with crystal structure prediction (CSP). This suggests a practical generative-CSP synergy for discovery-oriented exploration, where AI targets physically viable yet structurally distinct regions of chemical space for detailed physics-based assessment of novelty and stability. |
| title | Introducing physics-informed generative models for targeting structural novelty in the exploration of chemical space |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2510.23181 |