Detecting Thermodynamic Phase Transition via Explainable Machine Learning of Photoemission Spectroscopy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909577367257088 |
|---|---|
| author | Chen, Xu Sun, Yuanjie Hruska, Eugen Dixit, Vivek Yang, Jinming He, Yu Wang, Yao Liu, Fang |
| author_facet | Chen, Xu Sun, Yuanjie Hruska, Eugen Dixit, Vivek Yang, Jinming He, Yu Wang, Yao Liu, Fang |
| contents | Identifying thermodynamic signatures of electronic phases, such as superconductivity, is challenging in low-dimensional materials due to strong fluctuations and low probing volume. Spectroscopic methods are often used to identify new bulk phases, but their main measurable quantity -- electronic energy gaps -- is no longer an effective order parameter in low-dimensional and fluctuating systems. Combining angle-resolved photoemission with a domain-adversarial neural network, we report a data-driven method to identify thermodynamic phase transitions solely based on single-particle spectra. We demonstrate 97.6$\%$ accuracy in cuprate superconductor Bi$_2$Sr$_2$CaCu$_2$O$_{8+δ}$ with strong superconducting fluctuations. This model notably compensates for the scarcity of experimental data by leveraging virtually inexhaustible simulated data. Further, its explainability reveals the crucial role of in-gap spectral weight in detecting phase fluctuations and thermodynamic transitions. Our work pinpoints the spectroscopic signatures of fluctuating orders and enables using spectroscopy for machine-learning-assisted material discovery for low-dimensional and strong coupling systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04445 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting Thermodynamic Phase Transition via Explainable Machine Learning of Photoemission Spectroscopy Chen, Xu Sun, Yuanjie Hruska, Eugen Dixit, Vivek Yang, Jinming He, Yu Wang, Yao Liu, Fang Superconductivity Strongly Correlated Electrons Identifying thermodynamic signatures of electronic phases, such as superconductivity, is challenging in low-dimensional materials due to strong fluctuations and low probing volume. Spectroscopic methods are often used to identify new bulk phases, but their main measurable quantity -- electronic energy gaps -- is no longer an effective order parameter in low-dimensional and fluctuating systems. Combining angle-resolved photoemission with a domain-adversarial neural network, we report a data-driven method to identify thermodynamic phase transitions solely based on single-particle spectra. We demonstrate 97.6$\%$ accuracy in cuprate superconductor Bi$_2$Sr$_2$CaCu$_2$O$_{8+δ}$ with strong superconducting fluctuations. This model notably compensates for the scarcity of experimental data by leveraging virtually inexhaustible simulated data. Further, its explainability reveals the crucial role of in-gap spectral weight in detecting phase fluctuations and thermodynamic transitions. Our work pinpoints the spectroscopic signatures of fluctuating orders and enables using spectroscopy for machine-learning-assisted material discovery for low-dimensional and strong coupling systems. |
| title | Detecting Thermodynamic Phase Transition via Explainable Machine Learning of Photoemission Spectroscopy |
| topic | Superconductivity Strongly Correlated Electrons |
| url | https://arxiv.org/abs/2406.04445 |