Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

AIP Advances

Machine-learning-based automated loading of strontium isotopes into magneto-optical trap

Korak Biswas, Kushal Patel, S. Sagar Maurya, Pranab Dutta, Umakant D. Rapol

Published Jul 1, 2023• 2 citations
Publisher

Abstract

We implemented optimization techniques of machine learning (ML) to obtain the mutually exclusive sets of experimental parameters that maximize the number of strontium atoms of different isotopes (88Sr, 86Sr, and 87Sr) in a magneto-optical trap (MOT). Machine learning optimization techniques are significantly faster than conventional manual optimization. While optimizing the parameters, these algorithms efficiently tackle the problem of being confined in one of the local maxima in the parametric space. Thus, ML can be implemented to automate the loading of different isotopes into MOT to perform multiple experiments in a single setup.

DOI
10.1063/5.0145844

Related papers

Maximized atom number for a grating magneto-optical trap via machine-learning assisted parameter optimization

Sangwon Seo, Jae Hoon Lee, Sang-Bum Lee +5 more

We present a parameter set for obtaining the maximum number of atoms in a grating magneto-optical trap (gMOT) by employing a machine learning algorithm. In the multi-dimensional parameter space, which imposes a challenge for global optimization, the atom number is efficiently modeled via Bayesian optimization with the evaluation of the trap performance given by a Monte-Carlo simulation. Modeling gMOTs for six representative atomic species - 7Li, 23Na, 87Rb, 88Sr, 133Cs, 174Yb - allows us to discover that the optimal grating reflectivity is consistently higher than a simple estimation based on balanced optical molasses. Our algorithm also yields the optimal diffraction angle which is independent of the beam waist. The validity of the optimal parameter set for the case of 87Rb is experimentally verified using a set of grating chips with different reflectivities and diffraction angles.

Optics Express•Oct 11, 2021•19 citations

Review and experimental benchmarking of machine learning algorithms for efficient optimization of cold atom experiments

Oliver Anton, Victoria Henderson, Elisa Da Ros +4 more

Abstract The generation of cold atom clouds is a complex process which involves the optimization of noisy data in high dimensional parameter spaces. Optimization can be challenging both in and especially outside of the lab due to lack of time, expertise, or access for lengthy manual optimization. In recent years, it was demonstrated that machine learning offers a solution since it can optimize high dimensional problems quickly, without knowledge of the experiment itself. In this paper we present results showing the benchmarking of nine different optimization techniques and implementations, alongside their ability to optimize a rubidium (Rb) cold atom experiment. The investigations are performed on a 3D 87Rb molasses with 10 and 18 adjustable parameters, respectively, where the atom number obtained by absorption imaging was chosen as the test problem. We further compare the best performing optimizers under different effective noise conditions by reducing the signal-to-noise ratio of the images via adapting the atomic vapor pressure in the 2D+ magneto-optical trap and the detection laser frequency stability.

arXiv:2312.13397•Machine Learning Science and Technology•Apr 9, 2024•6 citations

Enhanced magnetic trap loading for atomic strontium

Daniel S. Barker, Benjamin J. Reschovsky, Neal C. Pisenti +1 more

We report on a technique to improve the continuous loading of atomic strontium into a magnetic trap from a magneto-optical trap. This is achieved by adding a depumping laser tuned to the $^{3}P_{1}\ensuremath{\rightarrow}^{3}S_{1}$ (688-nm) transition. The depumping laser increases atom number in the magnetic trap and subsequent cooling stages by up to 65% for the bosonic isotopes and up to 30% for the fermionic isotope of strontium. We optimize this trap loading strategy with respect to the 688-nm laser detuning, intensity, and beam size. To understand the results, we develop a one-dimensional rate equation model of the system, which is in good agreement with the data. We discuss the use of other transitions in strontium for accelerated trap loading and the application of the technique to other alkaline-earth-like atoms.

arXiv:1508.05405•Physical Review A•Oct 26, 2015•9 citations

Optimizing loading of cold cesium atoms into a hollow-core fiber using machine learning

Anderson, Paul, Sreesh Venuturumilli, Michal Bajcsy

Experimental multi-parameter optimization can enhance the interfacing of cold atoms with waveguides and cavities. Recent implementations of machine learning (ML) algorithms demonstrate the optimization of complex cold atom ex perimental sequences in a multi-dimensional parameter space. Here, we report on the use of ML to optimize loading of cold atoms into a hollow-core fiber. We use Gaussian process machine learning in M-LOOP, an open-source online machine learning interface, to perform this optimization. This is implemented by iteratively adjusting experimental parameters based on feedback from an atom-counting measurement of optical "bleaching". We test the effectiveness of ML, alongside a manual scan, to converge to optimal loading conditions. We survey multiple ML runs to auto matically access appreciable atom-loading conditions. In conjunction with experimental design choices, ML-assisted optimization holds promise in the implementation and maintenance of complex cold atom experiments.

arXiv:2507.11519•Jul 15, 2025•0 citations

Magneto-optical-trap loading in a large optical-access experiment

Marius Gaudesius, J. M. Lee, Luke A. Kraft +2 more

We present an experimental, numerical, and analytical study of strontium magneto-optical trap (MOT) loading from a cold atomic beam in a configuration optimized for high numerical aperture optical tweezers. Our approach orients the beam flow along the MOT symmetry axis to reduce the experimental complexity and maximize the overall optical access into the scientific region of study. We use a moving molasses technique to enable this configuration and show that its performance depends critically on metastable-state shelving (to 5s5p 3P2) during the atom transfer to the three-dimensional (3D) MOT. Furthermore, we find that the parameters for optimal transfer efficiency are bounded by dark-state loss (to 5s5p 3P0) in the trap region where repumping is present. These observations are verified to great degree of accuracy using both our developed analytical and numerical models. The corresponding 3D simulation tool is used to perform a comprehensive study of the trap loading dynamics, beginning at the oven exit and ending at the 3D MOT, demonstrating its effectiveness in optimizing an effusive oven experiment.

arXiv:2505.03008•Physical Review A•Dec 23, 2025•0 citations

Cooling and trapping of atomic strontium

Xinye Xu, Thomas H. Loftus, J. L. Hall +2 more

We present a detailed investigation of strontium magneto-optical trap (MOT) dynamics. Relevant physical quantities in the trap, such as temperature, atom number and density, and loss channels and lifetime, are explored with respect to various trap parameters. By studying the oscillatory response of a two-level 1S0–1P1 88Sr MOT, we firmly establish the laser cooling dynamics predicted by Doppler theory. Measurements of the MOT temperature, however, deviate severely from Doppler theory predictions, implying significant additional heating mechanisms. To explore the feasibility of attaining quantum degenerate alkaline-earth samples via evaporative cooling, we also present the first experimental demonstration of magnetically trapped metastable 88Sr. Furthermore, motivated by the goal of establishing the fermionic isotope 87Sr as one of the highest-quality, neutral-atom-based optical frequency standards, we present a preliminary study of sub-Doppler cooling in a 87Sr MOT. A dual-isotope (87Sr and 88Sr) MOT is also demonstrated.

Journal of the Optical Society of America B•May 1, 2003•138 citations
We implemented optimization techniques of machine learning (ML) to obtain the mutually exclusive sets of experimental parameters that maximize the number of strontium atoms of different isotopes (88Sr, 86Sr, and 87Sr) in a magneto-optical trap (MOT). Machine learning optimization techniques are significantly faster than conventional manual optimization. While optimizing the parameters, these algorithms efficiently tackle the problem of being confined in one of the local maxima in the parametric space. Thus, ML can be implemented to automate the loading of different isotopes into MOT to perform multiple experiments in a single setup.
We present a parameter set for obtaining the maximum number of atoms in a grating magneto-optical trap (gMOT) by employing a machine learning algorithm. In the multi-dimensional parameter space, which imposes a challenge for global optimization, the atom number is efficiently modeled via Bayesian optimization with the evaluation of the trap performance given by a Monte-Carlo simulation. Modeling gMOTs for six representative atomic species - 7Li, 23Na, 87Rb, 88Sr, 133Cs, 174Yb - allows us to discover that the optimal grating reflectivity is consistently higher than a simple estimation based on balanced optical molasses. Our algorithm also yields the optimal diffraction angle which is independent of the beam waist. The validity of the optimal parameter set for the case of 87Rb is experimentally verified using a set of grating chips with different reflectivities and diffraction angles.
Abstract The generation of cold atom clouds is a complex process which involves the optimization of noisy data in high dimensional parameter spaces. Optimization can be challenging both in and especially outside of the lab due to lack of time, expertise, or access for lengthy manual optimization. In recent years, it was demonstrated that machine learning offers a solution since it can optimize high dimensional problems quickly, without knowledge of the experiment itself. In this paper we present results showing the benchmarking of nine different optimization techniques and implementations, alongside their ability to optimize a rubidium (Rb) cold atom experiment. The investigations are performed on a 3D 87Rb molasses with 10 and 18 adjustable parameters, respectively, where the atom number obtained by absorption imaging was chosen as the test problem. We further compare the best performing optimizers under different effective noise conditions by reducing the signal-to-noise ratio of the images via adapting the atomic vapor pressure in the 2D+ magneto-optical trap and the detection laser frequency stability.
We report on a technique to improve the continuous loading of atomic strontium into a magnetic trap from a magneto-optical trap. This is achieved by adding a depumping laser tuned to the $^{3}P_{1}\ensuremath{\rightarrow}^{3}S_{1}$ (688-nm) transition. The depumping laser increases atom number in the magnetic trap and subsequent cooling stages by up to 65% for the bosonic isotopes and up to 30% for the fermionic isotope of strontium. We optimize this trap loading strategy with respect to the 688-nm laser detuning, intensity, and beam size. To understand the results, we develop a one-dimensional rate equation model of the system, which is in good agreement with the data. We discuss the use of other transitions in strontium for accelerated trap loading and the application of the technique to other alkaline-earth-like atoms.
Experimental multi-parameter optimization can enhance the interfacing of cold atoms with waveguides and cavities. Recent implementations of machine learning (ML) algorithms demonstrate the optimization of complex cold atom ex perimental sequences in a multi-dimensional parameter space. Here, we report on the use of ML to optimize loading of cold atoms into a hollow-core fiber. We use Gaussian process machine learning in M-LOOP, an open-source online machine learning interface, to perform this optimization. This is implemented by iteratively adjusting experimental parameters based on feedback from an atom-counting measurement of optical "bleaching". We test the effectiveness of ML, alongside a manual scan, to converge to optimal loading conditions. We survey multiple ML runs to auto matically access appreciable atom-loading conditions. In conjunction with experimental design choices, ML-assisted optimization holds promise in the implementation and maintenance of complex cold atom experiments.
We present an experimental, numerical, and analytical study of strontium magneto-optical trap (MOT) loading from a cold atomic beam in a configuration optimized for high numerical aperture optical tweezers. Our approach orients the beam flow along the MOT symmetry axis to reduce the experimental complexity and maximize the overall optical access into the scientific region of study. We use a moving molasses technique to enable this configuration and show that its performance depends critically on metastable-state shelving (to 5s5p 3P2) during the atom transfer to the three-dimensional (3D) MOT. Furthermore, we find that the parameters for optimal transfer efficiency are bounded by dark-state loss (to 5s5p 3P0) in the trap region where repumping is present. These observations are verified to great degree of accuracy using both our developed analytical and numerical models. The corresponding 3D simulation tool is used to perform a comprehensive study of the trap loading dynamics, beginning at the oven exit and ending at the 3D MOT, demonstrating its effectiveness in optimizing an effusive oven experiment.
We present a detailed investigation of strontium magneto-optical trap (MOT) dynamics. Relevant physical quantities in the trap, such as temperature, atom number and density, and loss channels and lifetime, are explored with respect to various trap parameters. By studying the oscillatory response of a two-level 1S0–1P1 88Sr MOT, we firmly establish the laser cooling dynamics predicted by Doppler theory. Measurements of the MOT temperature, however, deviate severely from Doppler theory predictions, implying significant additional heating mechanisms. To explore the feasibility of attaining quantum degenerate alkaline-earth samples via evaporative cooling, we also present the first experimental demonstration of magnetically trapped metastable 88Sr. Furthermore, motivated by the goal of establishing the fermionic isotope 87Sr as one of the highest-quality, neutral-atom-based optical frequency standards, we present a preliminary study of sub-Doppler cooling in a 87Sr MOT. A dual-isotope (87Sr and 88Sr) MOT is also demonstrated.