Machine Learning Analysis of high-dimensional ARPES Data for Nd_1-xSr_xNiO₃

Angle-resolved photoemission spectroscopy (ARPES) is a powerful technique for probing the electronic properties of quantum materials, providing unique insights into the high-dimensional electronic structure in momentum and energy space. However, traditional methods for extracting material parameters from ARPES data face significant challenges, due to a complex material parameter dependence, the vast momentum-energy configurational space, and inherent experimental noise etc. In this talk, I will present our recent advancements in leveraging high-throughput simulations and cutting-edge AI tools, specifically neural implicit representations, to effectively extract material parameters from high-resolution ARPES spectra on perovskite nickelates. Our work opens a new direction in applying AI to bridge the gap between theory and high-dimensional ARPES measurement, enhancing the investigation of emergent properties in quantum materials.