Machine‐Learning Spectral Indicators of Topology
Topological materials discovery has emerged as an important frontier in condensed matter physics. While theoretical classification frameworks have been used to identify thousands of candidate topological materials, experimental determination of materials' topology often poses significant techni...
| Main Authors: | , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147614 |
| _version_ | 1811084160645726208 |
|---|---|
| author | Andrejevic, Nina Andrejevic, Jovana Bernevig, B Andrei Regnault, Nicolas Han, Fei Fabbris, Gilberto Nguyen, Thanh Drucker, Nathan C Rycroft, Chris H Li, Mingda |
| author2 | Massachusetts Institute of Technology. Department of Nuclear Science and Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Nuclear Science and Engineering Andrejevic, Nina Andrejevic, Jovana Bernevig, B Andrei Regnault, Nicolas Han, Fei Fabbris, Gilberto Nguyen, Thanh Drucker, Nathan C Rycroft, Chris H Li, Mingda |
| author_sort | Andrejevic, Nina |
| collection | MIT |
| description | Topological materials discovery has emerged as an important frontier in condensed matter physics. While theoretical classification frameworks have been used to identify thousands of candidate topological materials, experimental determination of materials' topology often poses significant technical challenges. X-ray absorption spectroscopy (XAS) is a widely used materials characterization technique sensitive to atoms' local symmetry and chemical bonding, which are intimately linked to band topology by the theory of topological quantum chemistry (TQC). Moreover, as a local structural probe, XAS is known to have high quantitative agreement between experiment and calculation, suggesting that insights from computational spectra can effectively inform experiments. In this work, computed X-ray absorption near-edge structure (XANES) spectra of more than 10 000 inorganic materials to train a neural network (NN) classifier that predicts topological class directly from XANES signatures, achieving F1 scores of 89% and 93% for topological and trivial classes, respectively is leveraged. Given the simplicity of the XAS setup and its compatibility with multimodal sample environments, the proposed machine-learning-augmented XAS topological indicator has the potential to discover broader categories of topological materials, such as non-cleavable compounds and amorphous materials, and may further inform field-driven phenomena in situ, such as magnetic field-driven topological phase transitions. |
| first_indexed | 2024-09-23T12:45:51Z |
| format | Article |
| id | mit-1721.1/147614 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:45:51Z |
| publishDate | 2023 |
| publisher | Wiley |
| record_format | dspace |
| spelling | mit-1721.1/1476142023-01-21T03:26:10Z Machine‐Learning Spectral Indicators of Topology Andrejevic, Nina Andrejevic, Jovana Bernevig, B Andrei Regnault, Nicolas Han, Fei Fabbris, Gilberto Nguyen, Thanh Drucker, Nathan C Rycroft, Chris H Li, Mingda Massachusetts Institute of Technology. Department of Nuclear Science and Engineering Topological materials discovery has emerged as an important frontier in condensed matter physics. While theoretical classification frameworks have been used to identify thousands of candidate topological materials, experimental determination of materials' topology often poses significant technical challenges. X-ray absorption spectroscopy (XAS) is a widely used materials characterization technique sensitive to atoms' local symmetry and chemical bonding, which are intimately linked to band topology by the theory of topological quantum chemistry (TQC). Moreover, as a local structural probe, XAS is known to have high quantitative agreement between experiment and calculation, suggesting that insights from computational spectra can effectively inform experiments. In this work, computed X-ray absorption near-edge structure (XANES) spectra of more than 10 000 inorganic materials to train a neural network (NN) classifier that predicts topological class directly from XANES signatures, achieving F1 scores of 89% and 93% for topological and trivial classes, respectively is leveraged. Given the simplicity of the XAS setup and its compatibility with multimodal sample environments, the proposed machine-learning-augmented XAS topological indicator has the potential to discover broader categories of topological materials, such as non-cleavable compounds and amorphous materials, and may further inform field-driven phenomena in situ, such as magnetic field-driven topological phase transitions. 2023-01-20T18:10:00Z 2023-01-20T18:10:00Z 2022 2023-01-20T18:05:10Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/147614 Andrejevic, Nina, Andrejevic, Jovana, Bernevig, B Andrei, Regnault, Nicolas, Han, Fei et al. 2022. "Machine‐Learning Spectral Indicators of Topology." Advanced Materials, 34 (49). en 10.1002/ADMA.202204113 Advanced Materials Creative Commons Attribution NonCommercial License 4.0 https://creativecommons.org/licenses/by-nc/4.0/ application/pdf Wiley Wiley |
| spellingShingle | Andrejevic, Nina Andrejevic, Jovana Bernevig, B Andrei Regnault, Nicolas Han, Fei Fabbris, Gilberto Nguyen, Thanh Drucker, Nathan C Rycroft, Chris H Li, Mingda Machine‐Learning Spectral Indicators of Topology |
| title | Machine‐Learning Spectral Indicators of Topology |
| title_full | Machine‐Learning Spectral Indicators of Topology |
| title_fullStr | Machine‐Learning Spectral Indicators of Topology |
| title_full_unstemmed | Machine‐Learning Spectral Indicators of Topology |
| title_short | Machine‐Learning Spectral Indicators of Topology |
| title_sort | machine learning spectral indicators of topology |
| url | https://hdl.handle.net/1721.1/147614 |
| work_keys_str_mv | AT andrejevicnina machinelearningspectralindicatorsoftopology AT andrejevicjovana machinelearningspectralindicatorsoftopology AT bernevigbandrei machinelearningspectralindicatorsoftopology AT regnaultnicolas machinelearningspectralindicatorsoftopology AT hanfei machinelearningspectralindicatorsoftopology AT fabbrisgilberto machinelearningspectralindicatorsoftopology AT nguyenthanh machinelearningspectralindicatorsoftopology AT druckernathanc machinelearningspectralindicatorsoftopology AT rycroftchrish machinelearningspectralindicatorsoftopology AT limingda machinelearningspectralindicatorsoftopology |