Ensemble nitrogen-vacancy (NV) centers in diamond enable robust vector magnetometry in unshielded environments, yet deployment remains bottlenecked by complex calibration and a reliance on external data references. Conventional statistical machine learning requires an exorbitantly large volume of training data and suffers from severe simulation-to-reality mismatches. To address this, we introduce a physics-guided hybrid machine learning framework that embeds the Zeeman splitting directly into the learning pipeline. Our physics-guided model significantly reduces the average tracking error demonstrating a 372-fold precision improvement over purely statistical baselines. Furthermore, our hybrid architecture pairs a sparse physical measurement with scalable synthetic data generation, seamlessly incorporating real-world hardware non-idealities. When deployed to decode uncalibrated, raw experimental ODMR data, our framework delivers exceptional predictive accuracy for the scalar magnetic field. This work paves the way toward self-calibrated sensors while establishing a machine learning training method applicable to other data-scarce physical systems
Ensemble nitrogen-vacancy (NV) centers in diamond enable robust vector magnetometry in unshielded environments, yet deployment remains bottlenecked by complex calibration and a reliance on external data references. Conventional statistical machine learning requires an exorbitantly large volume of training data and suffers from severe simulation-to-reality mismatches. To address this, we introduce a physics-guided hybrid machine learning framework that embeds the Zeeman splitting directly into the learning pipeline. Our physics-guided model significantly reduces the average tracking error demonstrating a 372-fold precision improvement over purely statistical baselines. Furthermore, our hybrid architecture pairs a sparse physical measurement with scalable synthetic data generation, seamlessly incorporating real-world hardware non-idealities. When deployed to decode uncalibrated, raw experimental ODMR data, our framework delivers exceptional predictive accuracy for the scalar magnetic field. This work paves the way toward self-calibrated sensors while establishing a machine learning training method applicable to other data-scarce physical systems
Nitrogen-vacancy (NV) centers in diamond are a versatile quantum sensing platform for high sensitivity measurements of magnetic fields, temperature and strain with nanoscale spatial resolution. A common bottleneck is the analysis of optically detected magnetic resonance (ODMR) spectra, where target quantities are encoded in resonance features. Conventional nonlinear fitting is often computationally expensive, sensitive to initialization, and prone to failure at low signal-to-noise ratio (SNR). Here we introduce a robust, efficient machine learning (ML) framework for real-time ODMR analysis based on a one-dimensional convolutional neural network (1D-CNN). The model performs direct parameter inference without initial guesses or iterative optimization, and is naturally parallelizable on graphics processing units (GPU) for high-throughput processing. We validate the approach on both synthetic and experimental datasets, showing improved throughput, accuracy and robustness than standard nonlinear fitting, with the largest gains in the low-SNR regime. We further validate our methods in two representative sensing applications: diagnosing intracellular temperature changes using nanodiamond probes and widefield magnetic imaging of superconducting vortices in a high-temperature superconductor. This deep-learning inference framework enables fast and reliable extraction of physical parameters from complex ODMR data and provides a scalable route to real-time quantum sensing and imaging.
Precise characterization of the local spin environment of single diamond nitrogen-vacancy (NV) centers is crucial for advancing quantum sensing, quantum networking, and the optimization of quantum materials. However, single NV center fluorescence measurements requires long averaging times to obtain clean data that is suitable for conventional model fitting, and that constitutes a key experimental bottleneck for high-throughput characterization. To address this, we introduce \textsc{NVRNet}, a physics-informed simulation-to-reality machine learning pipeline that maps minimal-sweep, noisy Ramsey data to a denoised waveform while directly estimating the hyperfine coupling to proximal 13C nuclear spins. The pipeline's denoiser utilizes a two-stage time-frequency U-Net and an attention-augmented time-domain U-Net, pretrained on Hamiltonian-based spin-dynamics simulations with experimentally calibrated noise. To effectively bridge the simulation-to-reality gap, parameter-efficient adapters are attached to the backbone and fine-tuned on targeted experimental data. Across three distinct NV centers, this experimentally fine-tuned model reduces the median reconstruction error on held-out, few-sweep traces to 0.44-0.67× of the raw experimental noise level. Subsequently, a transformer-based estimator extracts the underlying hyperfine parameters. Forward reconstructions derived from these inferred parameters faithfully reproduce the dominant experimental time- and frequency-domain features, yielding representative normalized fast Fourier transform (FFT) reconstruction errors of 0.10-0.19. By reducing both the required data volume and acquisition time, \textsc{NVRNet} enables up to ∼40× acceleration of the measurement process, establishing a fast, hardware-compatible pathway for robust hyperfine inference and autonomous qubit characterization.
We present a novel method for full vector magnetometry using nitrogen-vacancy (NV) centers. In contrast to conventional optically detected magnetic resonance techniques, our method employs two distinct broadband microwave pulses and measures them after transmission through the NV sensor medium, thus capturing the line splitting of the ground state triplet due to the Zeeman effect. Two orthogonally polarized microwave pulses allow resolving all magnetic field components independently by reading out differently oriented NV centers. Simulated data is analyzed using deep neural networks, whose efficacy we expect to translate very well to experiments. Our method yields sensitivities between 5pT/Hz and 100pT/Hz across different magnetic field vector components, while achieving approximately nT accuracy at a signal-to-noise (SNR) ratio of 70dB. By being capable of accurately measuring magnetic fields down to 25μT, the need for a bias field beyond Earth's magnetic field is eliminated.
Ensemble nitrogen-vacancy (NV) diamond magnetometers combine high sensitivity with vector-field reconstruction, but practical deployment is limited by errors arising from high-frequency laser noise during short-duration operations and slow-varying gain fluctuations and offset drift during long-term operation. Here, we present an integrated digital architecture for achieving NV magnetometry stability across distinct timescales. A dynamic differential readout continuously balances fluorescence and reference channels to suppress correlated laser noise. Second-derivative Lorentzian lineshape tracking enables in-situ correction of slope variations arising from slow changes in gain and optical excitation. We further identify temperature-induced bias-magnet fluctuations as a dominant source of long-term drift and introduce a magnetic eigenvector transformation that uses the intrinsic response of NV resonances to eliminate these variations. We show, under unshielded ambient conditions, that this architecture achieves an off-resonance noise factor of 1.0 ± 0.1, matching the fundamental limit with ten-fold suppression of long-term drift, enabling stable, field-ready quantum magnetometry.
Nitrogen-vacancy (NV) centers in diamond can serve as highly sensitive solid-state quantum sensors for high-sensitivity magnetometry. However, in the noisy intermediate-scale quantum (NISQ) era, extracting reliable information from noisy, finite-shot, and measurement-limited sensing data remains a considerable challenge. Whereas, quantum machine learning (QML) offers a potential path to improve parameter estimation by learning nonlinear relationships between quantum-sensing data and the underlying physical signal. In this work, we investigate the role of QML in magnetic-field estimation within an NV center-inspired magnetometry setting. We formulated magnetic field sensing as a supervised regression task. We compared the performance of several classical machine learning models trained on measurement-based classical data with that of quantum kernel-based models trained on pre-measurement coherent quantum states. Our objective is to isolate the impact of measurement-induced information loss and therefore provide a theoretical upper bound on the sensing performance. The upper bound is achievable only when coherent quantum information is directly available to the learning model. Our results show that QML-based sensing performance improves significantly with coherent quantum-state information, and not much with changes in model complexity or learning paradigm. This observation underscores the importance of learning pipelines that tightly integrate quantum sensors and QML models to enhance magnetic field sensing under realistic constraints.
Quantum sensors based on nitrogen vacancy (NV) centers in diamond have been a central topic in the sensing community for more than a decade. The extraordinary properties at room temperature of the spin system in diamond have made it one of the most prominent quantum platforms for the development of commercial quantum sensors. In particular, the sensitivity of the electronic spin in NV centers has made diamond-based magnetic sensors of special interest for their potential application in medical, industrial or navigation solutions. However, the use of these sensors for universal vector magnetometry was constrained by the need for previous knowledge on the field being measured to fully exploit their benefits. In this work, we show a method to perform unconditional vector magnetometry without the need of external information on the magnetic field, based only on the spatial arrangement of the diamond and the microwave antenna combination. While previous NV-based vector magnetometry methods require partial knowledge of the magnetic field (e.g. a calibrated bias field), we exploit the possibilities of selecting particular directions of the spins in the diamond with elliptically polarized microwave fields. We prove that our method allows to estimate both magnitude and direction of external magnetic fields without further assumptions or constraints.