Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2602.20959 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912923286241280 |
|---|---|
| author | Slagle, Ian Alamgir, Faisal Fung, Victor |
| author_facet | Slagle, Ian Alamgir, Faisal Fung, Victor |
| contents | Determining atomic structure from spectroscopic data is central to materials science but remains restricted to a limited set of techniques and material classes, largely due to the computational cost and complexity of structural refinement. Here we introduce ActiveStructOpt, a general framework that integrates graph neural network surrogate models with active learning to efficiently determine candidate structures that reproduce target spectra with minimal computational expenditure. Benchmarking with X-ray pair distribution function data, and with the more computationally demanding simulations of X-ray absorption near-edge spectra (XANES) and extended X-ray absorption fine structure (EXAFS), demonstrate that ActiveStructOpt reliably determines structures that match closely in spectra across diverse materials classes. Under equivalent computational budgets, ActiveStructOpt outperforms existing structure determination methods. By enabling data-efficient, multi-objective structural refinement across a broad range of computable spectroscopic techniques, ActiveStructOpt provides a flexible and extensible approach to atomic structure determination in complex materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20959 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Determining Atomic Structure from Spectroscopy via an Active Learning Framework Slagle, Ian Alamgir, Faisal Fung, Victor Materials Science Determining atomic structure from spectroscopic data is central to materials science but remains restricted to a limited set of techniques and material classes, largely due to the computational cost and complexity of structural refinement. Here we introduce ActiveStructOpt, a general framework that integrates graph neural network surrogate models with active learning to efficiently determine candidate structures that reproduce target spectra with minimal computational expenditure. Benchmarking with X-ray pair distribution function data, and with the more computationally demanding simulations of X-ray absorption near-edge spectra (XANES) and extended X-ray absorption fine structure (EXAFS), demonstrate that ActiveStructOpt reliably determines structures that match closely in spectra across diverse materials classes. Under equivalent computational budgets, ActiveStructOpt outperforms existing structure determination methods. By enabling data-efficient, multi-objective structural refinement across a broad range of computable spectroscopic techniques, ActiveStructOpt provides a flexible and extensible approach to atomic structure determination in complex materials. |
| title | Determining Atomic Structure from Spectroscopy via an Active Learning Framework |
| topic | Materials Science |
| url | https://arxiv.org/abs/2602.20959 |