Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.09536 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908363536728064 |
|---|---|
| author | Ji, Kangyu Sheng, Fang Liu, Tianran Das, Basita Buonassisi, Tonio |
| author_facet | Ji, Kangyu Sheng, Fang Liu, Tianran Das, Basita Buonassisi, Tonio |
| contents | Classifying a crystalline solid's phase using X-ray diffraction (XRD) is a challenging endeavor, first because this is a poorly constrained problem as there are nearly limitless candidate phases to compare against a given experimental spectrum, and second because experimental signals are confounded by overlapping peaks, preferred orientations, and phase mixtures. To address this challenge, we develop Chem-XRD, a multimodal framework based on vision transformer (ViT) architecture with two defining features: (i) crystallographic data is constrained by elemental priors and (ii) phase is classified according to probabilities (not absolutes). Elemental information can be extracted from pre-synthesis precursors or post-synthesis elemental analysis. By combining structural and elemental modalities, Chem-XRD simultaneously predicts both the number and identity of phases of lead-halide perovskite materials and their decomposition products. Through integrated gradient calculations, we show that the model can adeptly adjust the contributions of structural and elemental modalities toward the final prediction of phase identification, achieving a level of interpretability beyond what self-attention mechanisms can achieve. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09536 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multimodal transformers with elemental priors for phase classification of X-ray diffraction spectra Ji, Kangyu Sheng, Fang Liu, Tianran Das, Basita Buonassisi, Tonio Applied Physics Classifying a crystalline solid's phase using X-ray diffraction (XRD) is a challenging endeavor, first because this is a poorly constrained problem as there are nearly limitless candidate phases to compare against a given experimental spectrum, and second because experimental signals are confounded by overlapping peaks, preferred orientations, and phase mixtures. To address this challenge, we develop Chem-XRD, a multimodal framework based on vision transformer (ViT) architecture with two defining features: (i) crystallographic data is constrained by elemental priors and (ii) phase is classified according to probabilities (not absolutes). Elemental information can be extracted from pre-synthesis precursors or post-synthesis elemental analysis. By combining structural and elemental modalities, Chem-XRD simultaneously predicts both the number and identity of phases of lead-halide perovskite materials and their decomposition products. Through integrated gradient calculations, we show that the model can adeptly adjust the contributions of structural and elemental modalities toward the final prediction of phase identification, achieving a level of interpretability beyond what self-attention mechanisms can achieve. |
| title | Multimodal transformers with elemental priors for phase classification of X-ray diffraction spectra |
| topic | Applied Physics |
| url | https://arxiv.org/abs/2505.09536 |