Physics Informed Machine Learning for Rapid Defect Characterization of crystalline materials
Wagle, Kamal, Pokharel, Reeju · 2026
Read Physics Informed Machine Learning for Rapid Defect Characterization of crystalline materials by Wagle, Kamal, Pokharel, Reeju (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/doe-osti-3029207-physics-informed-machine-learning-for-ra.txt.
Description
Kamal Wagle and Reeju Pokharel of Los Alamos National Laboratory presented these slides on April 10, 2026. The deck is a background-and-goal outline rather than a full report. Its problem: diffraction experiments record intensity but lose phase. Recovering a crystal's structure means solving a nonlinear inverse problem, usually by phase retrieval. The answer is generative machine learning for Bragg coherent diffraction imaging, which learns the inverse problem. Ground truth comes from molecular dynamics snapshots whose diffraction patterns are simulated to teach the model, aiming at defect checks in crystals.
Catalog record
| CREATOR | Wagle, Kamal, Pokharel, Reeju |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| LICENSE | Public Domain |
| RIGHTS | PUBLIC DOMAIN |
| SOURCE | DOE OSTI |