© 2026 Aqora Quantum S.A.S.

Terms Privacy Legal Notice

International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC)

Online Optimization of Cold Atom Experiment Parameters Based on Artificial Neural Networks and Genetic Algorithms

Q. P. Wang, Changwen Liang, Xiaoxiao Ma, Lingxiao Zhu

Published Sep 19, 2025• 0 citations

Abstract

Cold atom experiments involve a large number of parameters, and there are even different degrees of coupling between these parameters. To achieve the optimal cooling effect, the optimization of experimental parameters is an indispensable step in the atomic cooling process. An online optimization scheme for atomic cooling experimental parameters based on artificial neural networks and genetic algorithms is proposed in this paper. First, the experimental setup and principle scheme used in the experiment are introduced, with emphasis on elaborating in detail on the laser system, cooling sequence, optimization steps, and algorithm flow. Then, the influence of different network structures on prediction performance is analyzed. Finally, the optimization scheme is verified on an actual atomic cooling experimental setup. Experimental results show that the optimization algorithm can accurately predict the optimal parameters of the experimental setup. Compared with manual optimization, the proposed scheme achieves a more significant cooling effect, with the temperature improved by approximately a factor of two in both horizontal and vertical directions.

DOI: 10.1109/aiahpc66801.2025.11290541

Related papers

Applying machine learning optimization methods to the production of a quantum gas

Adam Barker, Hillary Style, Kathrin Luksch +5 more

Abstract We apply three machine learning strategies to optimize the atomic cooling processes utilized in the production of a Bose–Einstein condensate (BEC). For the first time, we optimize both laser cooling and evaporative cooling mechanisms simultaneously. We present the results of an evolutionary optimization method (differential evolution), a method based on non-parametric inference (Gaussian process regression) and a gradient-based function approximator (artificial neural network). Online optimization is performed using no prior knowledge of the apparatus, and the learner succeeds in creating a BEC from completely randomized initial parameters. Optimizing these cooling processes results in a factor of four increase in BEC atom number compared to our manually-optimized parameters. This automated approach can maintain close-to-optimal performance in long-term operation. Furthermore, we show that machine learning techniques can be used to identify the main sources of instability within the apparatus.

arXiv:1908.08495•Machine Learning Science and Technology•Feb 25, 2020•37 citations

Stochastic optimization of a cold atom experiment using a genetic algorithm

Wolfgang Rohringer, Robert Bücker, Stephanie Manz +6 more

We employ an evolutionary algorithm to automatically optimize different stages of a cold atom experiment without human intervention. This approach closes the loop between computer based experimental control systems and automatic real time analysis and can be applied to a wide range of experimental situations. The genetic algorithm quickly and reliably converges to the most performing parameter set independent of the starting population. Especially in many-dimensional or connected parameter spaces, the automatic optimization outperforms a manual search.

arXiv:0810.4474•Applied Physics Letters•Dec 29, 2008•31 citations

Evolutionary optimization of an experimental apparatus

I. Geisel, K. Cordes, J. Mahnke +5 more

In recent decades, cold atom experiments have become increasingly complex. While computers control most parameters, optimization is mostly done manually. This is a time-consuming task for a high-dimensional parameter space with unknown correlations. Here we automate this process using a genetic algorithm based on differential evolution. We demonstrate that this algorithm optimizes 21 correlated parameters and that it is robust against local maxima and experimental noise. The algorithm is flexible and easy to implement. Thus, the presented scheme can be applied to a wide range of experimental optimization tasks.

arXiv:1305.4094•Applied Physics Letters•May 27, 2013•21 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

Accelerated Bayesian optimization in deep cooling atoms

Xiaoxiao Ma, Changwen Liang, Rong Sha +5 more

Abstract Laser cooling, which cools atomic and molecular gases to near absolute zero, is the crucial initial step for nearly all atomic gas experiments. However, fast achievement of numerous sub-μK cold atoms is challenging. To resolve the issue, we propose and experimentally validate an intelligent polarization gradient cooling approach enhanced by an optical lattice, utilizing maximum hypersphere compensation sampling Bayesian optimization (MHCS-BO). MHCS-BO demonstrates a twofold increase in optimization efficiency and superior prediction accuracy compared to conventional Bayesian optimization. Finally, approximately 10 8 cold atoms at a temperature of 0.4±0.2 μK can be achieved given the optimal parameters within 15 minutes. Our work provides an intelligent protocol, which can be generalized to other high-dimensional parameter optimization problems, and paves the way for the preparation of ultracold atoms in quantum experiments.

arXiv:2412.11793•Chinese Physics B•Nov 27, 2025•0 citations

Optimization and analysis of experimental parameters for polarization gradient cooling of cold cesium atoms

Zhonghua Ji, Jinpeng Yuan, Yanting Zhao +4 more

We systematically investigate the dependence of the temperature of cold cesium atoms of polarization gradient cooling (PGC) in optical molasses on experimental parameters, which contain changing modes of cooling laser, PGC interaction time, cooling laser frequency and its intensity. The SR mode of cooling laser, that means the cooling laser frequency is changed with step mode and cooling laser intensity is changed with ramp mode, is found to be the best for PGC comparing with other SS, RS, and RR modes. We introduce a statistical explanation and an exponential decay function to explain the variation of cold atomic temperature on time. The heating effect is observed when the cooling laser intensity is lower than the saturation intensity of cold atoms. After optimization, the lowest temperature of cold cesium atoms is observed to be about 4uK with the number of 2x10^9, a density of 1x10^11/cm^3 and the phase space density of 4.4x10^(-5). The optimization process and analysis of controllable experimental parameters are also meaningful for other cold atomic systems.

•Apr 26, 2013•0 citations

Cold atom experiments involve a large number of parameters, and there are even different degrees of coupling between these parameters. To achieve the optimal cooling effect, the optimization of experimental parameters is an indispensable step in the atomic cooling process. An online optimization scheme for atomic cooling experimental parameters based on artificial neural networks and genetic algorithms is proposed in this paper. First, the experimental setup and principle scheme used in the experiment are introduced, with emphasis on elaborating in detail on the laser system, cooling sequence, optimization steps, and algorithm flow. Then, the influence of different network structures on prediction performance is analyzed. Finally, the optimization scheme is verified on an actual atomic cooling experimental setup. Experimental results show that the optimization algorithm can accurately predict the optimal parameters of the experimental setup. Compared with manual optimization, the proposed scheme achieves a more significant cooling effect, with the temperature improved by approximately a factor of two in both horizontal and vertical directions.

Abstract We apply three machine learning strategies to optimize the atomic cooling processes utilized in the production of a Bose–Einstein condensate (BEC). For the first time, we optimize both laser cooling and evaporative cooling mechanisms simultaneously. We present the results of an evolutionary optimization method (differential evolution), a method based on non-parametric inference (Gaussian process regression) and a gradient-based function approximator (artificial neural network). Online optimization is performed using no prior knowledge of the apparatus, and the learner succeeds in creating a BEC from completely randomized initial parameters. Optimizing these cooling processes results in a factor of four increase in BEC atom number compared to our manually-optimized parameters. This automated approach can maintain close-to-optimal performance in long-term operation. Furthermore, we show that machine learning techniques can be used to identify the main sources of instability within the apparatus.

We employ an evolutionary algorithm to automatically optimize different stages of a cold atom experiment without human intervention. This approach closes the loop between computer based experimental control systems and automatic real time analysis and can be applied to a wide range of experimental situations. The genetic algorithm quickly and reliably converges to the most performing parameter set independent of the starting population. Especially in many-dimensional or connected parameter spaces, the automatic optimization outperforms a manual search.

In recent decades, cold atom experiments have become increasingly complex. While computers control most parameters, optimization is mostly done manually. This is a time-consuming task for a high-dimensional parameter space with unknown correlations. Here we automate this process using a genetic algorithm based on differential evolution. We demonstrate that this algorithm optimizes 21 correlated parameters and that it is robust against local maxima and experimental noise. The algorithm is flexible and easy to implement. Thus, the presented scheme can be applied to a wide range of experimental optimization tasks.

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.

Abstract Laser cooling, which cools atomic and molecular gases to near absolute zero, is the crucial initial step for nearly all atomic gas experiments. However, fast achievement of numerous sub-μK cold atoms is challenging. To resolve the issue, we propose and experimentally validate an intelligent polarization gradient cooling approach enhanced by an optical lattice, utilizing maximum hypersphere compensation sampling Bayesian optimization (MHCS-BO). MHCS-BO demonstrates a twofold increase in optimization efficiency and superior prediction accuracy compared to conventional Bayesian optimization. Finally, approximately 10 8 cold atoms at a temperature of 0.4±0.2 μK can be achieved given the optimal parameters within 15 minutes. Our work provides an intelligent protocol, which can be generalized to other high-dimensional parameter optimization problems, and paves the way for the preparation of ultracold atoms in quantum experiments.

We systematically investigate the dependence of the temperature of cold cesium atoms of polarization gradient cooling (PGC) in optical molasses on experimental parameters, which contain changing modes of cooling laser, PGC interaction time, cooling laser frequency and its intensity. The SR mode of cooling laser, that means the cooling laser frequency is changed with step mode and cooling laser intensity is changed with ramp mode, is found to be the best for PGC comparing with other SS, RS, and RR modes. We introduce a statistical explanation and an exponential decay function to explain the variation of cold atomic temperature on time. The heating effect is observed when the cooling laser intensity is lower than the saturation intensity of cold atoms. After optimization, the lowest temperature of cold cesium atoms is observed to be about 4uK with the number of 2x10^9, a density of 1x10^11/cm^3 and the phase space density of 4.4x10^(-5). The optimization process and analysis of controllable experimental parameters are also meaningful for other cold atomic systems.