Rydberg-atom sensors have emerged as a promising quantum technology for broadband radio-frequency detection owing to their intrinsic calibration, wide frequency coverage, and high sensitivity. However, their potential for intelligent identification of real-world wireless signals remains largely unexplored. Here, we demonstrate a quantum-enabled framework for mobile signal classification based on Rydberg electromagnetically induced transparency spectroscopy and deep learning. Three types of wireless emissions, including cellular voice call, Wi-Fi, and 5G signals from three commercial smartphone brands, are measured to construct a spectral-fingerprint dataset. A convolutional neural network trained on this dataset achieves an initial baseline classification accuracy of 93.44\%. To compensate for spectral drifts induced by temporal and environmental variations, a progressive fine-tuning strategy is employed to continuously adapt the pretrained model, enabling robust classification across diverse deployment scenarios. Furthermore, continuous real-time monitoring is demonstrated under dynamically varying wireless conditions, including cellular voice call, Wi-Fi, and their coexistence. The proposed system achieves an overall frame-level recognition accuracy of 87.67\% over a 60-s measurement. These results establish a pathway toward intelligent quantum radio-frequency sensing and highlight the potential of Rydberg-atom platforms for real-time wireless signal awareness and spectrum monitoring.
AI Summary
Can Rydberg-atom RF sensors identify practical wireless signals from their optical responses, including under measurement drift and changing signal conditions? This paper combines rubidium Rydberg electromagnetically induced transparency (EIT) spectroscopy with a one-dimensional convolutional neural network to classify smartphone emissions.
An antenna collects signals and routes them to a vapor cell interrogated through the $58D_{5/2}$ Rydberg state. Off-resonant RF fields produce time-dependent ac Stark shifts; scanning the probe detuning maps these shifts into distortions of the EIT transmission profile. A time-dependent density-matrix model describes this encoding. More than 10,000 measured fingerprints cover nine categories: cellular voice calls, Wi-Fi, and 5G data from three smartphone brands. With a stratified random 80:20 training–validation split, the CNN achieves 93.44% validation accuracy after 100 training epochs.
Sequential supervised fine-tuning addresses five increasingly distorted measurement scenarios. In the most distorted scenario, reported accuracy improves from 69.33% to 89.44%; final accuracies in two less severe scenarios are 96.78% and 92.44%. A separate 60-second continuous measurement switches among voice calls, Wi-Fi, and their coexistence, yielding 87.67% frame-level recognition accuracy, with more errors near transitions and during coexistence.
The stated remaining challenges include testing scalability across more communication standards and transmitter configurations, reducing reliance on labeled calibration data for adaptation, and developing faster optical interrogation and low-latency inference hardware for autonomous operation.
Central claim may not hold: The reported 93.44% baseline accuracy comes from validation data also used for training decisions and model selection, with no independent test evaluation reported.
The deployment-robustness claim relies on sequential fine-tuning across inadequately specified distortion scenarios without a documented separation between adaptation and evaluation data.
The claimed real-time demonstration reports 87.67% accuracy over 60 seconds but does not establish acquisition throughput, end-to-end latency, or concurrent online inference.
Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.
Rydberg-atom sensors have emerged as a promising quantum technology for broadband radio-frequency detection owing to their intrinsic calibration, wide frequency coverage, and high sensitivity. However, their potential for intelligent identification of real-world wireless signals remains largely unexplored. Here, we demonstrate a quantum-enabled framework for mobile signal classification based on Rydberg electromagnetically induced transparency spectroscopy and deep learning. Three types of wireless emissions, including cellular voice call, Wi-Fi, and 5G signals from three commercial smartphone brands, are measured to construct a spectral-fingerprint dataset. A convolutional neural network trained on this dataset achieves an initial baseline classification accuracy of 93.44%. To compensate for spectral drifts induced by temporal and environmental variations, a progressive fine-tuning strategy is employed to continuously adapt the pretrained model, enabling robust classification across diverse deployment scenarios. Furthermore, continuous real-time monitoring is demonstrated under dynamically varying wireless conditions, including cellular voice call, Wi-Fi, and their coexistence. The proposed system achieves an overall frame-level recognition accuracy of 87.67% over a 60-s measurement. These results establish a pathway toward intelligent quantum radio-frequency sensing and highlight the potential of Rydberg-atom platforms for real-time wireless signal awareness and spectrum monitoring.
Can Rydberg-atom RF sensors identify practical wireless signals from their optical responses, including under measurement drift and changing signal conditions? This paper combines rubidium Rydberg electromagnetically induced transparency (EIT) spectroscopy with a one-dimensional convolutional neural network to classify smartphone emissions.
An antenna collects signals and routes them to a vapor cell interrogated through the 58D5/2 Rydberg state. Off-resonant RF fields produce time-dependent ac Stark shifts; scanning the probe detuning maps these shifts into distortions of the EIT transmission profile. A time-dependent density-matrix model describes this encoding. More than 10,000 measured fingerprints cover nine categories: cellular voice calls, Wi-Fi, and 5G data from three smartphone brands. With a stratified random 80:20 training–validation split, the CNN achieves 93.44% validation accuracy after 100 training epochs.
Sequential supervised fine-tuning addresses five increasingly distorted measurement scenarios. In the most distorted scenario, reported accuracy improves from 69.33% to 89.44%; final accuracies in two less severe scenarios are 96.78% and 92.44%. A separate 60-second continuous measurement switches among voice calls, Wi-Fi, and their coexistence, yielding 87.67% frame-level recognition accuracy, with more errors near transitions and during coexistence.
The stated remaining challenges include testing scalability across more communication standards and transmitter configurations, reducing reliance on labeled calibration data for adaptation, and developing faster optical interrogation and low-latency inference hardware for autonomous operation.
The broadband characteristic of Rydberg atoms renders them suitable for spectrum monitoring in high-frequency and multi-band joint wireless communication systems. We demonstrate a cross-band spectrum monitoring system, integrating atomic sensing with intelligent recognition. The cross-band signals resonate with different Rydberg transitions, and are coherently mapped to a unified intermediate-frequency channel via atomic superheterodyne detection. This scheme enables simultaneous multi-band reception with no observable inter-band crosstalk. The system achieves real-time modulation recognition directly from atomically-sensed streams, using a lightweight automatic modulation recognition model on an embedded platform. We demonstrate that the system enables low error-vector-magnitude reception of high-order modulated signals. Moreover, the system maintains a recognition accuracy above 80% with low latency over a signal-to-noise ratio range from -15 dB to 20 dB. This unified framework provides a viable route toward scalable, quantum-enhanced intelligent sensing in complex electromagnetic environments.
In recent years, the Rydberg-atom sensor has attracted significant attention due to its high sensitivity, wide dynamic range, and miniaturization capabilities. However, noise from laser power fluctuations, frequency drift, and environment is introduced alongside the intrinsic quantum noise of Rydberg atoms, significantly degrading system performance for microwave sensing. This study tries to reduce the noise impact by combining the Rydberg-atom sensor with the convolutional neural network (CNN)-transformer model. The CNN module captures local temporal features of the signals, while the transformer module extracts global correlations within these features. We apply it to the following classification tasks of atomic microwave sensing: multifrequency microwave recognition, broadband spectrum monitoring, and automatic modulation recognition. We demonstrate that the CNN-transformer model achieves high accuracy across the three tasks and can effectively reduce the noise impact, which holds significant potential for applications in radar detection and wireless communication.
Partial discharge originates from microscopic insulation imperfections in high-voltage apparatus and is widely considered a critical marker of incipient deterioration. Conventional partial discharge detection methods are typically constrained by limited bandwidth and often rely on predefined feature extraction, which impedes reliable recognition of broadband transient signals. In this work, we employ a Rydberg atomic sensor to directly capture time-domain responses of partial discharge emissions and construct distinctive spectral fingerprints for different types. A 1D ResNet deep learning model is then applied to recognize these fingerprints from time-domain signals without manual feature engineering. Under increased source-antenna distances, where spectral features are significantly attenuated, the model attains a recognition accuracy of approximately 94\% across four partial discharge categories, demonstrating robustness to attenuation and noise. We further validate the approach in a simulated early-warning scenario, where partial discharge signals mixed with noise are analyzed and the model successfully generates predictive alarms. These results underscore the potential of integrating Rydberg-based broadband sensing with data-driven analysis for non-invasive, high-sensitivity diagnostics of electrical insulation systems.
Rydberg atomic quantum receivers (RAQRs) are emerging quantum precision sensing platforms designed for receiving radio frequency (RF) signals. It relies on the creation of Rydberg atoms from normal atoms by exciting one or more electrons to a very high energy level, thereby making the atom sensitive to RF signals. RAQRs realize RF-to-optical conversions based on atom-light interactions relying on the so-called electromagnetically induced transparency (EIT) and Autler- Townes splitting (ATS) so that the desired RF signal can be read out optically. The large dipole moments of Rydberg atoms associated with rich choices of Rydberg states facilitate an ultra-high sensitivity (~nv⁄cm/√Hz) and an ultra-broadband tunability (direct-current to Terahertz). RAQRs also exhibit compelling scalability and lend themselves to the construction of innovative, compact receivers. Initial experimental studies have demonstrated their capabilities in classical wireless communications and sensing. To fully harness their potential in a wide variety of applications, we commence by outlining the underlying fundamentals of Rydberg atoms, followed by the principles and schemes of RAQRs. Then, we overview the state-of-the-art studies from both physics and communication societies. Furthermore, we conceive Rydberg atomic quantum single-input single-output (RAQ-SISO) and multiple-input multiple- output (RAQ-MIMO) schemes to facilitate the integration of RAQRs with classical wireless systems. Finally, we conclude with a set of potent research directions.
Rydberg atoms have emerged as a versatile and efficient platform for high-sensitivity quantum sensing of free-space electric fields, with remarkable progress in detecting low-frequency signals. To date, low-frequency Rydberg receivers have relied on a constant bias field, typically realized via intra-cell electrodes or Rydberg plasmas generated by photoelectric effects or inter-atomic interactions. While these approaches improve sensitivity, they suffer from inherent challenges in calibration, long-term stability, and robustness, hindering practical deployment. Here, we propose, design, and experimentally demonstrate a quantum sensing scheme for low-frequency electric signals using modulated auxiliary fields in Rydberg atoms. Unlike conventional methods that employ external DC electric fields that are often fully shielded by adsorbed atom layers on the cell walls, we introduce an AC-field modulation strategy. The incoming low-frequency signal mixes with the auxiliary field, and together they induce Stark shifts of the Rydberg level. These shifts are mapped onto the probe laser via electromagnetically induced transparency (EIT), in a manner analogous to heterodyne detection. We demonstrate a sensitivity of 7.5±2.6μV/(cm⋅Hz1/2) at 5 kHz and a minimal detectable field of 0.26±0.04μV/cm with an integration time of 1000 s. Furthermore, we extend this approach to systematically analyze the performance of generalized auxiliary fields containing multiple frequency components. By virtue of modulated auxiliary field and quantum frequency mixing, our results establish a robust and systematic framework for quantum sensing of low-frequency electric fields with Rydberg atoms, offering improved sensitivity, stability, and immunity to environmental drifts.
Rydberg atoms are neutral atoms excited to high principal quantum number states, which endows them with exaggerated properties such as large electric dipole moments, long lifetimes, and extreme sensitivity to external electromagnetic fields. These characteristics form the foundation of Rydberg atom-based sensors, an emerging class of quantum devices capable of optically detecting electric fields across frequencies from DC to the terahertz regime. Rydberg-based electrometry operates through both Autler–Townes (AT) splitting of resonant Rydberg transitions and Stark-shift measurements for high-frequency or far-detuned fields, enabling broadband field sensing from DC to the THz regime. Using ladder-type electromagnetically induced transparency (EIT) and AT splitting, these sensors enable non-invasive, SI-traceable measurements of field amplitude, frequency, phase, and polarization. Recent developments have demonstrated broadband electric field probes, voltage calibration standards, and compact RF receivers based on thermal vapor cells and integrated photonic architectures. Furthermore, innovations in multi-photon EIT, superheterodyne readout, and multi wave mixing have expanded the dynamic range and bandwidth of Rydberg-based electrometry. Despite challenges related to environmental perturbations, linewidth broadening, and laser stabilization, ongoing advances in atomic control, hybrid photonic integration, and EIT-based readout promise scalable, chip-compatible sensors. This review summarizes the physical principles, experimental progress, and emerging applications of Rydberg atom-based sensing, emphasizing their potential for next generation quantum metrology, wireless communication, and precision field mapping.