skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Adversarial autoencoder ensemble for fast and probabilistic reconstructions of few-shot photon correlation functions for solid-state quantum emitters

Journal Article · · Physical Review. B, Condensed Matter and Materials Physics

Second-order photon correlation measurements [g((2))(tau) functions] are widely used to classify single-photon emission purity in quantum emitters or to measure the multiexciton quantum yield of emitters that can simultaneously host multiple excitations - such as quantum dots - by evaluating the value of g((2))(tau = 0). Accumulating enough photons to accurately calculate this value is time consuming and could be accelerated by fitting of few-shot photon correlations. Here, we develop an uncertainty-aware, deep adversarial autoencoder ensemble (AAE) that reconstructs noise-free g((2))(tau) functions from noise-dominated, few-shot inputs. The model is trained with simulated g((2))(tau) functions that are facilely generated by Poisson sampling time bins. The AAE reconstructions are performed orders-of-magnitude faster, with reconstruction errors and estimates of g((2))(tau = 0) that are lower in variance and similar in accuracy compared to Maximum likelihood estimation and Levenberg-Marquardt least-squares fitting approaches, for simulated and experimentally measured few-shot g((2))(tau) functions (similar to 100 two-photon events) of InP/ZnS/ZnSe and CdS/CdSe/CdS quantum dots. The deep-ensemble model comprises eight individual autoencoders, allowing for probabilistic reconstructions of noise-free g((2))(tau) functions, and we show that the predicted variance scales inversely with number of shots, with comparable uncertainties to computationally intensive Markov chain Monte Carlo sampling. This work demonstrates the advantage of machine learning models to perform uncertainty-aware, fast, and accurate reconstructions of simple Poisson-distributed photon correlation functions, allowing for on-the-fly reconstructions and accelerated materials characterization of solid-state quantum emitters.

Research Organization:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Office of Science - Office of Basic Energy Sciences - Scientific User Facilities Division; Natural Sciences and Engineering Research Council of Canada (NSERC); Samsung Advanced Institute of Technology (SAIT)
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1961621
Journal Information:
Physical Review. B, Condensed Matter and Materials Physics, Vol. 106, Issue 4
Country of Publication:
United States
Language:
English

References (34)

Disentangling the effects of clustering and multi-exciton emission in second-order photon correlation experiments journal January 2013
Biexciton Quantum Yield of Single Semiconductor Nanocrystals from Photon Statistics journal March 2011
On-demand generation of indistinguishable polarization-entangled photon pairs journal February 2014
A quantum light-emitting diode for the standard telecom window around 1,550 nm journal February 2018
Optimal phase estimation in quantum networks journal June 2007
Sample-Efficient Adaptive Calibration of Quantum Networks Using Bayesian Optimization journal March 2022
Quantum astrochemical spectroscopy: Review journal June 2016
A perspective on multiparameter quantum metrology: From theoretical tools to applications in quantum imaging journal April 2020
Efficiently reconstructing compound objects by quantum imaging with higher-order correlation functions journal October 2019
Resolution-enhanced quantum imaging by centroid estimation of biphotons journal March 2019
Multicarrier Dynamics in Quantum Dots journal January 2021
Gradient CdSe/CdS Quantum Dots with Room Temperature Biexciton Unity Quantum Yield journal May 2015
Coherent single-photon emission from colloidal lead halide perovskite quantum dots journal February 2019
A highly efficient single-photon source based on a quantum dot in a photonic nanowire journal January 2010
Triggered polarization-entangled photon pairs from a single quantum dot up to 30 K journal September 2007
Highly efficient and stable InP/ZnSe/ZnS quantum dot light-emitting diodes journal November 2019
Negative Trion Auger Recombination in Highly Luminescent InP/ZnSe/ZnS Quantum Dots journal February 2021
Sustained Biexciton Populations in Nanoshell Quantum Dots journal March 2019
Quantum Shells Boost the Optical Gain of Lasing Media journal February 2022
Accelerating quantum optics experiments with statistical learning journal May 2020
Rapid Classification of Quantum Sources Enabled by Machine Learning journal September 2020
Identification of light sources using machine learning journal June 2020
Neural-network approach for identifying nonclassicality from click-counting data journal May 2020
Identifying nonclassicality from experimental data using artificial neural networks journal June 2021
Quantum State Tomography with Conditional Generative Adversarial Networks journal September 2021
Accelerating Ultrafast Spectroscopy with Compressive Sensing journal February 2021
Machine learning of two-dimensional spectroscopic data journal April 2019
Machine Learning for Vibrational Spectroscopic Maps journal October 2019
An Introduction to Variational Autoencoders journal January 2019
A simple introduction to Markov Chain Monte–Carlo sampling journal March 2016
Probabilistic programming in Python using PyMC3 journal January 2016
Markov chain Monte Carlo method and its application journal March 1998
Markov Chain Monte Carlo Sampling for Target Analysis of Transient Absorption Spectra journal March 2019
A semiconductor source of triggered entangled photon pairs journal January 2006