Photoelectron spectroscopy serves as a prevalent characterization technique within the realm of material science. Specifically, angle-resolved photoelectron spectroscopy (ARPES) provides a direct method for determining the energy-momentum dispersion relationship and Fermi surface structure of electrons within a material system. This makes ARPES a potent tool for the investigation of many-body interactions and correlated quantum materials. The field of photoelectron spectroscopy has seen continuous advancements, with the emergence of technologies such as time-resolved ARPES and nano-ARPES. Concurrently, the evolution of synchrotron radiation devices has led to the generation of an increasing volume of high throughput and high dimension experimental data. This underscores the growing urgency for the development of more efficient and precise data processing methods, as well as the extraction of deeper physical information. In light of these developments, machine learning is poised to play an increasingly significant role across various fields, including but not limited to ARPES. This paper reviews the application of machine learning in photoelectron spectroscopy, which primarily encompasses three aspects:
1.Data Denoising: Machine learning can be utilized for denoising photoelectron spectroscopy data. The denoising process via machine learning algorithms can be bifurcated into two methods. Both of the two methods do not need for manual data annotation. The first approach involves the use of noise generation algorithms to simulate experimental noise, thereby obtaining effective low signal-to-noise ratio to high signal-to-noise ratio data pairs. Alternatively, the second approach can be employed to extract noise and clean spectral data, respectively.
2.Electronic Structure and Chemical Composition Analysis: Machine learning can be applied for the analysis of electronic structure and chemical composition. (Angle-resolved) photoelectron spectroscopy contains abundant information about material structure. Information such as energy band structure, self-energy, binding energy, and other condensed matter data can be rapidly acquired through machine learning schemes.
3.Prediction of Photoelectron Spectroscopy: the electronic structure information obtained by combining first-principles calculation can also predict the photoelectron spectroscopy. The rapid acquisition of photoelectron spectroscopy data through machine learning algorithms also holds significance for material design. Photoelectron spectroscopy holds significant importance in the study of condensed matter physics. In the context of synchrotron radiation development, the construction of an automated data acquisition and analysis system could play a pivotal role in condensed matter physics research. In addition, adding more physical constraints to the machine learning model will improve the interpretability and accuracy of the model. There exists a close relationship between photoelectron spectroscopy and first-principles calculations with respect to electronic structure properties. The integration of these two through machine learning is anticipated to significantly contribute to the study of electronic structure properties. Furthermore, as machine learning algorithms continue to evolve, the application of more advanced machine learning algorithms in photoelectron spectroscopy research is expected. By building automated data acquisition and analysis systems, designing comprehensive workflows based on machine learning and first-principles methods, and integrating new machine learning techniques, it will help accelerate the progress of photoelectron spectroscopy experiments and facilitate the analysis of electronic structure properties and microscopic physical mechanisms, which will advance the frontier research in quantum materials and condensed matter physics.