Deterministic nanoassembly may enable unique integrated on-chip quantum photonic devices. Such integration requires a careful large-scale selection of nanoscale building blocks such as solid-state single-photon emitters by means of optical characterization. Second-order autocorrelation is a cornerstone measurement that is particularly time-consuming to realize on a large scale. Supervised machine learning-based classification of quantum emitters as “single” or “not-single” is implemented based on their sparse autocorrelation data. The method yields a classification accuracy of 95% within an integration time of less than a second, realizing roughly a 100-fold speedup compared to the conventional Levenberg–Marquardt fitting approach. It is anticipated that machine learning-based classification will provide a unique route to enable rapid and scalable assembly of quantum nanophotonic devices.

We report results on multiband observations from radio to gamma-rays of the two radio-loud narrow-line Seyfert 1 (NLSy1) galaxies PKS 2004-447 and J1548+3511. Both sources show a core-jet structure on parsec scale, while they are unresolved at the arcsecond scale. The high core dominance and the high variability brightness temperature make these NLSy1 galaxies good gamma-ray source candidates. Fermi-Large Area Telescope detected gamma-ray emission only from PKS 2004-447, with a gamma-ray luminosity comparable to that observed in blazars. No gamma-ray emission is observed for J1548+ 3511. Both sources are variable in X-rays. J1548+ 3511 shows a hardening of the spectrum during high activity states, while PKS 2004-447 has no spectral variability. A spectral steepening likely related to the soft excess is hinted below 2 keV for J1548+ 3511, while the X-ray spectra of PKS 2004-447 collected by XMM-Newton in 2012 are described by a single power law without significant soft excess. No additional absorption above the Galactic column density or the presence of an Fe line is detected in the X-ray spectra of both sources.