Deep learning enhanced noise spectroscopy of a spin qubit environment

TL;DR

This paper demonstrates that neural networks significantly improve noise spectral density reconstruction in quantum systems, enabling more accurate and efficient noise spectroscopy for NV center-based qubits.

Contribution

The study introduces a deep learning approach to noise spectroscopy that surpasses traditional methods in accuracy and efficiency for quantum noise characterization.

Findings

Neural networks outperform standard dynamical decoupling techniques in spectral density reconstruction.

Deep learning models require fewer sequences for accurate noise characterization.

Enhanced noise spectroscopy improves qubit coherence protection.

Abstract

The undesired interaction of a quantum system with its environment generally leads to a coherence decay of superposition states in time. A precise knowledge of the spectral content of the noise induced by the environment is crucial to protect qubit coherence and optimize its employment in quantum device applications. We experimentally show that the use of neural networks can highly increase the accuracy of noise spectroscopy, by reconstructing the power spectral density that characterizes an ensemble of carbon impurities around a nitrogen-vacancy (NV) center in diamond. Neural networks are trained over spin coherence functions of the NV center subjected to different Carr-Purcell sequences, typically used for dynamical decoupling (DD). As a result, we determine that deep learning models can be more accurate than standard DD noise-spectroscopy techniques, by requiring at the same time a much smaller number of DD sequences.