Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data
Abstract Glass formation is frequently observed in metallic alloys. Machine learning has been applied to discover new metallic glasses. However, the incomplete understanding of glass formation hinders descriptor selection and material property representation. Here, we use X-ray diffraction spectra,...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-025-01753-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849343379098304512 |
|---|---|
| author | Weijie Xie Yitao Sun Chao Wang Mingxing Li Fucheng Li Yanhui Liu |
| author_facet | Weijie Xie Yitao Sun Chao Wang Mingxing Li Fucheng Li Yanhui Liu |
| author_sort | Weijie Xie |
| collection | DOAJ |
| description | Abstract Glass formation is frequently observed in metallic alloys. Machine learning has been applied to discover new metallic glasses. However, the incomplete understanding of glass formation hinders descriptor selection and material property representation. Here, we use X-ray diffraction spectra, the essential tool for identifying amorphous structure, as an intermediate link. By representing spectra as images, we train generative models to produce high-fidelity spectra for all alloys in multicomponent alloy systems. Training with spectra from a tiny fraction of the total alloys is sufficient for accurate spectra generation, enabling the identification of compositional regions with a high probability of glass formation. The shift from numerical to image-based representation unlocks the potential of machine learning in the design of glass-forming alloys. Furthermore, our approach is applicable to a wide range of materials and spectroscopic techniques. We anticipate that this strategy will accelerate materials discovery across previously unexplored compositional and processing spaces. |
| format | Article |
| id | doaj-art-2b667a99776248af9542b0d6bf4feeda |
| institution | Kabale University |
| issn | 2057-3960 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj-art-2b667a99776248af9542b0d6bf4feeda2025-08-20T03:43:01ZengNature Portfolionpj Computational Materials2057-39602025-08-011111810.1038/s41524-025-01753-9Artificial intelligence can recognize metallic glasses in vast compositional space with sparse dataWeijie Xie0Yitao Sun1Chao Wang2Mingxing Li3Fucheng Li4Yanhui Liu5Institute of Physics, Chinese Academy of SciencesInstitute of Physics, Chinese Academy of SciencesInstitute of Physics, Chinese Academy of SciencesInstitute of Physics, Chinese Academy of SciencesInstitute of Physics, Chinese Academy of SciencesInstitute of Physics, Chinese Academy of SciencesAbstract Glass formation is frequently observed in metallic alloys. Machine learning has been applied to discover new metallic glasses. However, the incomplete understanding of glass formation hinders descriptor selection and material property representation. Here, we use X-ray diffraction spectra, the essential tool for identifying amorphous structure, as an intermediate link. By representing spectra as images, we train generative models to produce high-fidelity spectra for all alloys in multicomponent alloy systems. Training with spectra from a tiny fraction of the total alloys is sufficient for accurate spectra generation, enabling the identification of compositional regions with a high probability of glass formation. The shift from numerical to image-based representation unlocks the potential of machine learning in the design of glass-forming alloys. Furthermore, our approach is applicable to a wide range of materials and spectroscopic techniques. We anticipate that this strategy will accelerate materials discovery across previously unexplored compositional and processing spaces.https://doi.org/10.1038/s41524-025-01753-9 |
| spellingShingle | Weijie Xie Yitao Sun Chao Wang Mingxing Li Fucheng Li Yanhui Liu Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data npj Computational Materials |
| title | Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data |
| title_full | Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data |
| title_fullStr | Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data |
| title_full_unstemmed | Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data |
| title_short | Artificial intelligence can recognize metallic glasses in vast compositional space with sparse data |
| title_sort | artificial intelligence can recognize metallic glasses in vast compositional space with sparse data |
| url | https://doi.org/10.1038/s41524-025-01753-9 |
| work_keys_str_mv | AT weijiexie artificialintelligencecanrecognizemetallicglassesinvastcompositionalspacewithsparsedata AT yitaosun artificialintelligencecanrecognizemetallicglassesinvastcompositionalspacewithsparsedata AT chaowang artificialintelligencecanrecognizemetallicglassesinvastcompositionalspacewithsparsedata AT mingxingli artificialintelligencecanrecognizemetallicglassesinvastcompositionalspacewithsparsedata AT fuchengli artificialintelligencecanrecognizemetallicglassesinvastcompositionalspacewithsparsedata AT yanhuiliu artificialintelligencecanrecognizemetallicglassesinvastcompositionalspacewithsparsedata |