A machine-learning approach to high-throughput spatially resolved ARPES measurements
Abstract
Spatially resolved angle-resolved photoemission spectroscopy (ARPES) is a powerful technique for mapping local electronic structures, but it requires long measurement times to achieve sufficient signal-to-noise ratio (SNR) at each spatial point. This constraint limits beamtime efficiency and exacerbates sample degradation. In samples with domain structures, however, similar spectra are repeatedly measured across spatial positions, creating substantial redundancy in spatially resolved ARPES datasets. Here we systematically evaluate how SNR degradation from reduced acquisition times affects unsupervised domain classification. PCA-based dimensionality reduction maintained high agreement with the high-SNR reference classification even under low-SNR conditions, whereas direct clustering of spectral vectors showed rapid degradation beginning at a relatively high-SNR regime. Because dimensionality reduction is applied solely for domain classification, the representative spectrum of each domain is obtained as a direct average of the measured data. These results demonstrate that combining short-acquisition measurements with intra-domain spectral averaging through the co-addition of spectra within each classified domain can substantially accelerate spatially resolved ARPES while preserving classification accuracy.
Related
- UniFFBench: evaluating universal machine learning force fields against experimental measurements
- Machine Learning for High-Throughput Reaction Yield Prediction in DNA-Encoded Library Synthesis
- Dual-comb spectroscopy for spatially resolved hydrogen combustion diagnostics over a wide temperature range
- Pathway-Resolved Observable Memory Reveals Hidden Mediation from Sparse Conformational Measurements
- Spatially resolved 3D aging model linking interdependent degradation mechanisms to knee and end-of-life prediction
BibTeX
@article{imamura2026machinelearning,
title = {{A machine-learning approach to high-throughput spatially resolved ARPES measurements}},
author = {Masaki Imamura and Daijiro Koga and Kazutoshi Takahashi},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75986-z},
url = {https://www.nature.com/articles/s41598-026-75986-z},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A machine-learning approach to high-throughput spatially resolved ARPES measurements
AU - Masaki Imamura
AU - Daijiro Koga
AU - Kazutoshi Takahashi
PY - 2026
DA - 2026/10/23
JO - Scientific Reports
DO - 10.1038/s41598-026-75986-z
UR - https://www.nature.com/articles/s41598-026-75986-z
AB - Spatially resolved angle-resolved photoemission spectroscopy (ARPES) is a powerful technique for mapping local electronic structures, but it requires long measurement times to achieve sufficient signal-to-noise ratio (SNR) at each spatial point. This constraint limits beamtime efficiency and exacerbates sample degradation. In samples with domain structures, however, similar spectra are repeatedly measured across spatial positions, creating substantial redundancy in spatially resolved ARPES datasets. Here we systematically evaluate how SNR degradation from reduced acquisition times affects unsupervised domain classification. PCA-based dimensionality reduction maintained high agreement with the high-SNR reference classification even under low-SNR conditions, whereas direct clustering of spectral vectors showed rapid degradation beginning at a relatively high-SNR regime. Because dimensionality reduction is applied solely for domain classification, the representative spectrum of each domain is obtained as a direct average of the measured data. These results demonstrate that combining short-acquisition measurements with intra-domain spectral averaging through the co-addition of spectra within each classified domain can substantially accelerate spatially resolved ARPES while preserving classification accuracy.
SN - 2045-2322
ER -