Evaluation of synthetic and experimental training data in supervised machine learning applied to charge state detection of quantum dots

TL;DR

This study compares the effectiveness of synthetic, experimental, and combined training data in supervised machine learning models for charge state detection in quantum dot systems, highlighting the importance of realistic data for accurate predictions.

Contribution

It evaluates the generalization ability of models trained on synthetic versus experimental data and demonstrates the necessity of realistic data for reliable charge state detection.

Findings

Models trained on experimental data perform best.

Combining synthetic and experimental data does not significantly improve accuracy.

Adding noise to synthetic data does not greatly enhance model performance.

Abstract

Automated tuning of gate-defined quantum dots is a requirement for large scale semiconductor based qubit initialisation. An essential step of these tuning procedures is charge state detection based on charge stability diagrams. Using supervised machine learning to perform this task requires a large dataset for models to train on. In order to avoid hand labelling experimental data, synthetic data has been explored as an alternative. While providing a significant increase in the size of the training dataset compared to using experimental data, using synthetic data means that classifiers are trained on data sourced from a different distribution than the experimental data that is part of the tuning process. Here we evaluate the prediction accuracy of a range of machine learning models trained on simulated and experimental data and their ability to generalise to experimental charge stability diagrams in two dimensional electron gas and nanowire devices. We find that classifiers perform best on either purely experimental or a combination of synthetic and experimental training data, and that adding common experimental noise signatures to the synthetic data does not dramatically improve the classification accuracy. These results suggest that experimental training data as well as realistic quantum dot simulations and noise models are essential in charge state detection using supervised machine learning.