Automatic Detection of Nuclear Spins at Arbitrary Magnetic Fields via Signal-to-Image AI Model

Area of Science:

• Quantum Sensing
• Diamond Quantum Technologies
• Materials Science

Background:

• Nitrogen-vacancy (NV) centers in diamond are promising quantum sensors operating at room temperature.
• Interpreting NV center signals is challenging, especially in low magnetic fields and noisy conditions.
• Current methods struggle with complex signals and require prior knowledge of the nuclear environment.

Purpose of the Study:

• To develop an automated method for characterizing the nuclear environment around NV diamond sensors.
• To infer the number of nuclear spins and their hyperfine couplings from NV sensor signals.
• To overcome limitations of traditional methods in low magnetic fields and noisy environments.

Main Methods:

• A novel signal-to-image deep learning model was developed and trained.
• The model processes complex NV center signals to extract nuclear spin information.
• Numerical simulations were used to test model performance across various scenarios.

Main Results:

• The deep learning model accurately infers the number of nuclear spins and hyperfine couplings.
• The model demonstrates effectiveness across diverse magnetic field strengths and noise levels.
• Achieved an average error of less than 2 kHz in estimating hyperfine constants.

Conclusions:

• Deep learning offers a robust solution for analyzing complex NV center quantum sensor data.
• The developed model enables fast and accurate characterization of nuclear environments.
• This approach has significant potential for real-world experimental applications in quantum sensing.