| Details: |
Semiconductors nanocrystals with uniform morphology and composition are expected to exhibit consistent responses during light-matter interactions. However, microscopy reveals stark variations in their photoluminescence blinking patterns, even under identical experimental conditions. This discrepancy arises from differences in the nature and density of crystal defects and nonradiative trap states. Consequently, heterogeneous blinking patterns serve as valuable indicators of material quality, capable of uncovering concealed features through statistical analysis of large datasets. This approach requires efficient segregation of numerous blinking trajectories, which is currently encumbered by laborious calculations, computational bottlenecks, and manual intervention. We present a robust (un)supervised machine learning (ML) module that automatically clusters real-time high-dimensional microscopy signals and perform class-wise power spectral density calculation. This workflow is explicitly tested for wide-field fluorescence image analysis of semiconductor nanocrystals, while simultaneously beneficial for scanning tunnelling spectroscopy. We additionally demonstrate the impact of data-preprocessing on the clustering efficiency. As a programmed interface, the ML-PSD technology can advance contemporary (micro)spectroscopy by enabling rapid analytics of big-data to achieve instant optical characterization of semiconductor nanocrystals. |