Deciphering Majorana Zero Modes in Topological Superconductor FeTe0.55Se0.45 with Machine-Learning-Assisted Spectral Deconvolution
This study developed a data-driven workflow combining spectral deconvolution and machine learning to distinguish genuine Majorana zero modes (MZMs) from trivial in-gap states in FeTe0.55Se0.45. By analyzing spatially resolved local density of states, the method successfully identified specific vortex cores exhibiting signatures consistent with MZMs, providing a reproducible way to isolate these crucial topological features.