December 9, 2022

Deep learning enhanced individual nuclear-spin detection

Deep learning enhanced individual nuclear-spin detection General procedure for identifying hyperfine parameters of 13C nuclear spins

The detection of nuclear spins using individual electron spins has enabled diverse opportunities in quantum sensing and quantum information processing.

Proof-of-principle experiments have demonstrated atomic-scale imaging of nuclear-spin samples and controlled multi-qubit registers. However, to image more complex samples and to realize larger-scale quantum processors, computerized methods that efficiently and automatically characterize spin systems are required.

Scientists have realized a deep learning model for automatic identification of nuclear spins using the electron spin of single Nitrogen-Vacancy (NV) centers in diamond as a sensor.

Based on neural network algorithms, they developed noise recovery procedures and training sequences for highly non-linear spectra. They applied these methods to experimentally demonstrate the fast identification of 31 nuclear spins around a single NV center and accurately determine the hyperfine parameters.

Individual spin signature identification by hyperfine parameter classifier (HPC) deep learning model.
Individual spin signature identification by hyperfine parameter classifier (HPC) deep learning model.

These methods can be extended to larger spin systems and are applicable to a wide range of electron-nuclear interaction strengths.

Multiple nuclear spin detection from experimental data.
Multiple nuclear spin detection from experimental data.

These results pave the way towards efficient imaging of complex spin samples and automatic characterization of large spin-qubit registers.

The paper has been published in npj quantum information.