Machine-learning-enhanced NV-center quantum sensing

Nitrogen-vacancy (NV) centers in diamond are known for their precise and robust probing of various physical properties, including magnetic field, electric field, temperature, and pressure. Their spin-dependent photoluminescence (PL) allows optical readout of the environmental parameters through optically detected magnetic resonance (ODMR). Here, we introduce machine learning (ML) techniques to further enhance the performance and enable multimodal operations of NV-based sensing. We apply ML algorithms on PL and ODMR spectra collected by a fiber-coupled NV-thermometer. Our results show improved accuracy of NV-thermometry with both all-optical and ODMR measurements. We also implement ML methods on vector magnetic field reconstruction and pressure sensing with NV centers. These approaches pave the way toward ML-assisted high-precision multimodal NV quantum sensors.