Recently, the team of academician Guo Guangcan of the University of Science and Technology of China has made new progress in multi-frequency microwave sensing, using artificial intelligence to achieve precision detection based on the multi-frequency microwave of the Reedberg atom, which is conducive to the microwave sensing and communication based on the Reedborg atom.
a is the atomic energy level diagram, b is the experimental device diagram, and c-e is the schematic diagram of the neural network layer, and the picture is from the University of Science and Technology of China
Since the Reedberg atom has a large electric dipole moment (the electric dipole moment can be used to measure the overall polarity of the charge system) and can produce a strong response to weak electric fields, it is favored as a microwave measurement system, and multi-frequency microwave electric field measurement based on The Rydberg atom has broad application prospects in microwave radar and microwave communication.
However, there are still many scientific problems in the field of microwave measurement based on Reedberg atoms that need to be solved urgently. Among them, multi-frequency microwave reception is a difficult problem, because multi-frequency microwaves in atoms can cause complex interference patterns, which seriously interfere with signal reception and recognition.
In recent years, the research group of Academician Guo Guangcan of the University of Science and Technology of China has made important progress in using the Reedberg atomic system to focus on quantum simulation and quantum precision measurement scientific research. This time, based on the rubidium atom system at room temperature, the team used the Reedberg atom as a microwave antenna and modem, and successfully detected the multi-frequency microwave field of phase modulation (that is, the binary phase shift keying signal of frequency division multiplexing, a signal transmission method widely used in digital communication) through the electromagnetic induction transparency effect, and analyzed the received modulated signal through the deep learning neural network to achieve high-fidelity demodulation of the multi-frequency microwave signal, and further tested the high robustness of the experimental scheme for microwave noise.
Image from Nature Communications
The team effectively decoded a frequency division multiplexing (FDM) phase-shift keyed signal containing a noisy QR code with an accuracy rate of 99.32%. The results show that the reedberg microwave receiver based on deep learning enhancement can allow direct decoding of 20 FDM signals at a time, without the need for multiple band-pass filters and other complex circuits. The results were published in Nature Communications.
The above work proposes and realizes the scheme of effectively detecting multi-frequency microwave electric fields without solving the main equation, which not only takes advantage of the sensitivity advantage of The Reedberg atoms, but also reduces the noise effect. This study organically combines atomic sensing with deep learning, provides an important reference for the cross-binding of precision measurement and neural networks, and can also be applied to detect multiple targets at the same time.
Machine learning decodes the results, a-c is the recovery result of the deep learning model on the transmitted signal when the training time is different, and the picture comes from the University of Science and Technology of China
Reviewers commented: "The results presented in this work are very useful to other researchers in the field of atomic and molecular photophysics, as it shows the future application of deep learning in quantum-enhanced sensing of atomic systems." ”
Liu Zongkai, a doctoral candidate at the Key Laboratory of Quantum Information of the Chinese Academy of Sciences, is the first author of the paper, and Professor Ding Dongsheng and Professor Shi Baosen are co-corresponding authors. The above research has been funded by the Ministry of Science and Technology, the Foundation Committee, the Chinese Academy of Sciences, the Anhui Provincial Major Science and Technology Project and the University of Science and Technology of China.