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 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.
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.
As ultracold atom experiments become highly controlled and scalable quantum simulators, they require sophisticated control over high-dimensional parameter spaces and generate increasingly complex measurement data that need to be analyzed and interpreted efficiently. Machine learning (ML) techniques have been established as versatile tools for addressing these challenges, offering strategies for data interpretation, experimental control, and theoretical modeling. In this review, we provide a perspective on how machine learning is being applied across various aspects of quantum simulation, with a focus on cold atomic systems. Emphasis is placed on practical use cases -- from classifying many-body phases to optimizing experimental protocols and representing quantum states -- highlighting the specific contexts in which different ML approaches prove effective. Rather than presenting algorithmic details, we focus on the physical insights enabled by ML and the kinds of problems in quantum simulation where these methods offer tangible benefits.
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.
The noise in absorption imaging of cold atoms significantly impacts measurement accuracy across a range of applications with ultracold atoms. It is crucial to adopt an approach that offers effective denoising capabilities without compromising the unique structure of atom clouds. Here, we introduce, to our knowledge, a novel image enhancement algorithm for cold atomic absorption imaging. The algorithm successfully suppresses background noise, enhancing image contrast significantly. Experimental results showcase that this approach can improve the image's signal-to-noise ratio by about 10 dB and enhance the uncertainty of cold atom number measurements by approximately tenfold, preserving the spatial distribution of the atom clouds. Moreover, the method exhibits exceptional performance and robustness when confronted with fringe noise and multi-component imaging scenarios, offering high stability. Importantly, this method can perform denoising based on a single image (without the need to establish a reference library), and the optimization process is entirely automated, eliminating the need for manual parameter selection. The method is both compatible and practical, making it applicable to various cold atom absorption imaging fields.
The ability to detect atoms in high spatiotemporal resolution provides a powerful tool for us to investigate the quantum properties of ultracold quantum gases. Plenty of useful imaging methods, including absorption imaging, phase contrast imaging and fluorescence imaging, have been implemented in detecting atoms. Among them, absorption imaging is the most widely used method in cold atoms laboratory. However, the traditional absorption imaging method is affected by perturbations such as interference between optical elements, fluctuation of laser power, frequency, and spatial position, resulting in residual spatially structured noise and degradation of imaging quality. Especially for regions with lower density or for longer time-of-flight, a large number of repetitions are often required to obtain better signal-to-noise ratio, which would increase the time cost and induce other noise. One must reduce the time between two imaging pulses to suppress the spatial noise. A better charge coupled device (CCD) with higher frame transfer rate or other method like fast-kinetic mode will be used to improve the imaging quality. In this paper, a single-shot cold atom imaging method based on machine learning is proposed, in which only one absorption imaging of cold atoms is required, and the corresponding background image can be generated through the neural network of an autoencoder. This effectively reduces the spatial striped noise in imaging, significantly improves the imaging quality, and makes it possible for cold atoms to be imaged multiple times in a single cycle.
Cold atom traps are at the heart of many quantum applications in science and technology. The preparation and control of atomic clouds involves complex optimization processes, that could be supported and accelerated by machine learning. In this work, we introduce reinforcement learning to cold atom experiments and demonstrate a flexible and adaptive approach to control a magneto-optical trap. Instead of following a set of predetermined rules to accomplish a specific task, the objectives are defined by a reward function. This approach not only optimizes the cooling of atoms just as an experimentalist would do, but also enables new operational modes such as the preparation of pre-defined numbers of atoms in a cloud. The machine control is trained to be robust against external perturbations and able to react to situations not seen during the training. Finally, we show that the time consuming training can be performed in-silico using a generic simulation and demonstrate successful transfer to the real world experiment.