arXiv:2305.18822 · Chinese Physics B

Magnetic field regression using artificial neural networks for cold atom experiments

Ziting Chen, Kin To Wong, Bojeong Seo, Mingchen Huang, Mithilesh K. Parit, Yifei He, Haoting Zhen, Jensen Li, Gyu-Boong Jo

Published Nov 16, 2023• 3 citations

arXiv HTML PDF

Abstract

Accurately measuring magnetic fields is essential for magnetic-field sensitive experiments in areas like atomic, molecular, and optical physics, condensed matter experiments, and other areas. However, since many experiments are often conducted in an isolated environment that is inaccessible to experimentalists, it can be challenging to accurately determine the magnetic field at the target location. Here, we propose an efficient method for detecting magnetic fields with the assistance of an artificial neural network (NN). Instead of measuring the magnetic field directly at the desired location, we detect fields at several surrounding positions, and a trained NN can accurately predict the magnetic field at the target location. After training, we achieve a below 0.3% relative prediction error of magnetic field magnitude at the center of the vacuum chamber, and successfully apply this method to our erbium quantum gas apparatus for accurate calibration of magnetic field and long-term monitoring of environmental stray magnetic field. The demonstrated approach significantly simplifies the process of determining magnetic fields in isolated environments and can be applied to various research fields across a wide range of magnetic field magnitudes.

DOI: 10.1088/1674-1056/ad0cc8

Related papers

Neural-network-based parameter estimation for quantum detection

Yue Ban, Javier Echanobe, Yongcheng Ding +2 more

Abstract Artificial neural networks (NNs) bridge input data into output results by approximately encoding the function that relates them. This is achieved after training the network with a collection of known inputs and results leading to an adjustment of the neuron connections and biases. In the context of quantum detection schemes, NNs find a natural playground. In particular, in the presence of a target (e.g. an electromagnetic field), a quantum sensor delivers a response, i.e. the input data, which can be subsequently processed by a NN that outputs the target features. In this work we demonstrate that adequately trained NNs enable to characterize a target with (i) minimal knowledge of the underlying physical model (ii) in regimes where the quantum sensor presents complex responses and (iii) under a significant shot noise due to a reduced number of measurements. We exemplify the method with a development for 171 Yb + atomic sensors. However, our protocol is general, thus applicable to arbitrary quantum detection scenarios.

arXiv:2012.07677Quantum Science and TechnologyJul 22, 202114 citations

In situ magnetometry for experiments with atomic quantum gases

Ludwig Krinner, Michael Stewart, Arturo Pazmiño +1 more

Precise control of magnetic fields is a frequent challenge encountered in experiments with atomic quantum gases. Here we present a simple method for performing in situ monitoring of magnetic fields that can readily be implemented in any quantum-gas apparatus in which a dedicated field-stabilization approach is not feasible. The method, which works by sampling several Rabi resonances between magnetically field sensitive internal states that are not otherwise used in a given experiment, can be integrated with standard measurement sequences at arbitrary fields. For a condensate of 87Rb atoms, we demonstrate the reconstruction of Gauss-level bias fields with an accuracy of tens of microgauss and with millisecond time resolution. We test the performance of the method using measurements of slow resonant Rabi oscillations on a magnetic-field sensitive transition and give an example for its use in experiments with state-selective optical potentials.

arXiv:1709.00487Review of Scientific InstrumentsJan 1, 20185 citations

Probing magnetic fields near atom traps via commercially available sensor modules

Lucas Eisenhart

Sensors are constant companions in our everyday lives and find countless applications in science. In this work we try to find sensors that are able to record magnetic field changes affecting trapped ions in our experiments. For this we assume that the magnetic field changes inside the vacuum chamber containing the trap in our experiment are the same as those measured by the sensor in the vicinity of the trap. To characterize three different sensors, we generate magnetic field offsets with a current-carrying wire, permanent magnet or a pair of coils. By isolating the sensors from the surroundings with a μ metal shield, we create a test environment under similar conditions. We showed that the fluxgate sensor is about a factor of 27500 more sensitive than the Hall sensor and a factor of 10 less sensitive than the atom itself as a sensor. We recognize that the noise of the electronics of the data acquisition system limits the performance of the fluxgate and Hall sensor. The fluxgate sensor, in contrast to the Hall sensor, turns out to be a suitable choice for monitoring magnetic field changes during experiments with ions.

Jan 1, 20220 citations

A neural network assisted 171Yb+ quantum magnetometer

Yan Chen, Yue Ban, Ran He +5 more

Abstract A versatile magnetometer must deliver a readable response when exposed to target fields in a wide range of parameters. In this work, we experimentally demonstrate that the combination of 171 Yb + atomic sensors with adequately trained neural networks enables us to investigate target fields in distinct challenging scenarios. In particular, we characterize radio frequency (RF) fields in the presence of large shot noise, including the limit case of continuous data acquisition via single-shot measurements. Furthermore, by incorporating neural networks we significantly extend the working regime of atomic magnetometers into scenarios in which the RF driving induces responses beyond their standard harmonic behavior. Our results indicate the benefits to integrate neural networks at the data processing stage of general quantum sensing tasks to decipher the information contained in the sensor responses.

arXiv:2203.05849npj Quantum InformationDec 29, 202212 citations

Quantum network tomography of small Rydberg arrays by machine learning

K. Mukherjee, Johannes Schachenmayer, S. Whitlock +1 more

Configurable arrays of optically trapped Rydberg atoms are a versatile platform for quantum computation and quantum simulation, also allowing controllable decoherence. We demonstrate theoretically that they also enable proof-of-principle demonstrations for a technique to build models for open quantum dynamics using machine learning with artificial neural networks, recently proposed by Mukherjee et al. [Quantum Sci. Technol. 10, 02LT01 (2025)]. Using the outcome of quantum transport through a network of sites that correspond to excited Rydberg atoms, the multistage neural-network algorithm successfully identifies the number of atoms (or nodes in the network) and, subsequently, their location. It further extracts an effective interaction Hamiltonian and decoherence operators induced by the environment. To probe the Rydberg array, one initiates dynamics repeatedly from the same initial state and then measures the transport probability to an output atom. Large datasets are generated by varying the position of the latter. Measurements are required in only one single basis, making the approach complementary to, e.g., quantum process tomography. Due to steeply increasing requirements for training data size, the present implementation appears best suited for networks of just a few sites. The cold-atom platform discussed in this article can be used to explore the performance of the proposed protocol when training the neural network with simulation data but then applying it to construct models based on experimental data.

arXiv:2412.05742Physical Review AApr 22, 20254 citations

Multi-parameter deep learning for robust fiber eavesdropping detection and temporal localization

Yingbo Fan, yuang Li, Yuyuan Liang +5 more

As the backbone of global communication infrastructure, optical fibers carry vast amounts of sensitive data, making them prime targets for eavesdropping attacks that can compromise data confidentiality and national security. However, optical fibers are highly vulnerable to eavesdropping attacks-such as fiber bending or evanescent coupling-which can eavesdrop on data without interrupting the service. Accurate detection of eavesdropping remains a critical challenge, particularly under complex environmental disturbances. Environmental factors such as fluctuation and disturbances can induce signal distortions and polarization variations that mask or mimic eavesdropping characteristics, thereby posing a significant challenge to the training and generalization of machine learning-based classifiers. In this Letter, we propose a sensing framework based on a hybrid gated recurrent unit-convolutional neural network model that jointly analyzes polarization parameters and error vector magnitude. The proposed method enables accurate and robust eavesdropping detection and temporal localization under complex physical environments. Experiments conducted across seven practical scenarios demonstrate that the proposed scheme achieves a detection accuracy of 97.2%. Furthermore, we developed real-time and offline optical fiber monitoring platforms integrating mainstream detection techniques to facilitate comprehensive evaluation and deployment.

Optics LettersMar 12, 20260 citations