Progress and Prospect of AI in ARPES Workflow
Abstract
Artificial intelligence (AI) is becoming an increasingly useful tool across the experimental sciences, including angle-resolved photoemission spectroscopy (ARPES), which routinely produces large, multidimensional datasets of electronic structure. Recent advances in AI and machine learning (ML) have opened new opportunities across the entire ARPES workflow, from automated sample preparation and real-time data acquisition to post-experiment data analysis and comparison with theoretical calculations. Despite this progress, a comprehensive review of ML applications, their capabilities, and reliability across the different stages of ARPES workflow is still lacking. In this review, we first introduce ML methods that are most relevant to experimentalists working in condensed matter physics and materials science. We then follow the ARPES workflow, reviewing existing ML applications at each step and discussing their advantages, limitations and potential for future development. We also examine the current ARPES data landscape, where several open databases are available but remain relatively small and fragmented compared with large, shared datasets such as ImageNet. Given these limitations, we suggest that the community focus on sharing pretrained models that can be further trained, adapted to specific tasks, and redistributed, while working toward a larger and standardized open ARPES dataset repository. Finally, we discuss our perspectives on the future of AI within the ARPES workflow using a six-level framework of laboratory automation, highlighting the opportunities and challenges in moving toward a fully autonomous, self-driving ARPES laboratory.
Related
- The role of A in ARPES
- Search prospect for electrophilic bosons at the μTRISTAN
- Nano-ARPES observation of a flat band at the \bar{M} point in 2.4° twisted bilayer graphene
- Phonon-Dressed Quasiparticles in Epitaxial Scandium Nitride Resolved by Soft X-ray ARPES
- Probing the electronic structure of UTe2 with ARPES and high-energy spectroscopy
BibTeX
@misc{ekahana2026progress,
title = {{Progress and Prospect of AI in ARPES Workflow}},
author = {Sandy Adhitia Ekahana and Aalok Tiwari and Pratik Saud and Aaron Bostwick and Chris Jozwiak and Eli Rotenberg and Jyoti Katoch},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10140},
eprint = {2610.10140},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10140},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Progress and Prospect of AI in ARPES Workflow
AU - Sandy Adhitia Ekahana
AU - Aalok Tiwari
AU - Pratik Saud
AU - Aaron Bostwick
AU - Chris Jozwiak
AU - Eli Rotenberg
AU - Jyoti Katoch
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.10140
UR - https://arxiv.org/abs/2610.10140
AB - Artificial intelligence (AI) is becoming an increasingly useful tool across the experimental sciences, including angle-resolved photoemission spectroscopy (ARPES), which routinely produces large, multidimensional datasets of electronic structure. Recent advances in AI and machine learning (ML) have opened new opportunities across the entire ARPES workflow, from automated sample preparation and real-time data acquisition to post-experiment data analysis and comparison with theoretical calculations. Despite this progress, a comprehensive review of ML applications, their capabilities, and reliability across the different stages of ARPES workflow is still lacking. In this review, we first introduce ML methods that are most relevant to experimentalists working in condensed matter physics and materials science. We then follow the ARPES workflow, reviewing existing ML applications at each step and discussing their advantages, limitations and potential for future development. We also examine the current ARPES data landscape, where several open databases are available but remain relatively small and fragmented compared with large, shared datasets such as ImageNet. Given these limitations, we suggest that the community focus on sharing pretrained models that can be further trained, adapted to specific tasks, and redistributed, while working toward a larger and standardized open ARPES dataset repository. Finally, we discuss our perspectives on the future of AI within the ARPES workflow using a six-level framework of laboratory automation, highlighting the opportunities and challenges in moving toward a fully autonomous, self-driving ARPES laboratory.
ER -