Multiparameter optimisation of a magneto-optical trap using deep learning

Machine learning assisted vector atomic magnetometry

Multiparameter sensing such as vector magnetometry often involves complex setups due to various external fields needed in explicitly connecting one measured signal to one parameter. Here, we propose a paradigm of indirect encoding for vector atomic magnetometry based on machine learning. We encode the three-dimensional magnetic-field information in the set of four simultaneously acquired signals associated with the optical rotation of a laser beam traversing the atomic sample. The map between the recorded signals and the vectorial field information is established through a pre-trained deep neural network. We demonstrate experimentally a single-shot all optical vector atomic magnetometer, with a simple scalar-magnetometer design employing only one elliptically-polarized laser beam and no additional coils. Magnetic field amplitude sensitivities of about 100 [Formula: see text] and angular sensitivities of about [Formula: see text] (for a magnetic field of around 140 nT) are derived from the neural network. Our approach can reduce the complexity of the architecture of vector magnetometers, and may shed light on the general design of multiparameter sensing.

Photonic integrated beam delivery for a rubidium 3D magneto-optical trap

Cold atoms are important for precision atomic applications including timekeeping and sensing. The 3D magneto-optical trap (3D-MOT), used to produce cold atoms, will benefit from photonic integration to improve reliability and reduce size, weight, and cost. These traps require the delivery of multiple, large area, collimated laser beams to an atomic vacuum cell. Yet, to date, beam delivery using an integrated waveguide approach has remained elusive. Here we report the demonstration of a ⁸⁷Rb 3D-MOT using a fiber-coupled photonic integrated circuit to deliver all beams to cool and trap > 1 ×10⁶ atoms to near 200 μK. The silicon nitride photonic circuit transforms fiber-coupled 780 nm cooling and repump light via waveguides to three mm-width non-diverging free-space cooling and repump beams directly to the rubidium cell. This planar, CMOS foundry-compatible integrated beam delivery is compatible with other components, such as lasers and modulators, promising system-on-chip solutions for cold atom applications.

Automated Machine Learning Strategies for Multi-Parameter Optimisation of a Caesium-Based Portable Zero-Field Magnetometer

Machine learning (ML) is an effective tool to interrogate complex systems to find optimal parameters more efficiently than through manual methods. This efficiency is particularly important for systems with complex dynamics between multiple parameters and a subsequent high number of parameter configurations, where an exhaustive optimisation search would be impractical. Here we present a number of automated machine learning strategies utilised for optimisation of a single-beam caesium (Cs) spin exchange relaxation free (SERF) optically pumped magnetometer (OPM). The sensitivity of the OPM (T/Hz), is optimised through direct measurement of the noise floor, and indirectly through measurement of the on-resonance demodulated gradient (mV/nT) of the zero-field resonance. Both methods provide a viable strategy for the optimisation of sensitivity through effective control of the OPM's operational parameters. Ultimately, this machine learning approach increased the optimal sensitivity from 500 fT/Hz to <109fT/Hz. The flexibility and efficiency of the ML approaches can be utilised to benchmark SERF OPM sensor hardware improvements, such as cell geometry, alkali species and sensor topologies.

Transfer learning enhanced water-enabled electricity generation in highly oriented graphene oxide nanochannels

Harvesting energy from spontaneous water flow within artificial nanochannels is a promising route to meet sustainable power requirements of the fast-growing human society. However, large-scale nanochannel integration and the multi-parameter coupling restrictive influence on electric generation are still big challenges for macroscale applications. In this regard, long-range (1 to 20 cm) ordered graphene oxide assembled framework with integrated 2D nanochannels have been fabricated by a rotational freeze-casting method. The structure can promote spontaneous absorption and directional transmission of water inside the channels to generate considerable electric energy. A transfer learning strategy is implemented to address the complicated multi-parameters coupling problem under limited experimental data, which provides highly accurate performance optimization and efficiently guides the design of 2D water flow enabled generators. A generator unit can produce ~2.9 V voltage or ~16.8 μA current in a controllable manner. High electric output of ~12 V or ~83 μA is realized by connecting several devices in series or parallel. Different water enabled electricity generation systems have been developed to directly power commercial electronics like LED arrays and display screens, demonstrating the material’s potential for development of water enabled clean energy.

Challenges and opportunities in quantum machine learning

At the intersection of machine learning and quantum computing, quantum machine learning has the potential of accelerating data analysis, especially for quantum data, with applications for quantum materials, biochemistry and high-energy physics. Nevertheless, challenges remain regarding the trainability of quantum machine learning models. Here we review current methods and applications for quantum machine learning. We highlight differences between quantum and classical machine learning, with a focus on quantum neural networks and quantum deep learning. Finally, we discuss opportunities for quantum advantage with quantum machine learning.

Dynamic compensation of stray electric fields in an ion trap using machine learning and adaptive algorithm

Surface ion traps are among the most promising technologies for scaling up quantum computing machines, but their complicated multi-electrode geometry can make some tasks, including compensation for stray electric fields, challenging both at the level of modeling and of practical implementation. Here we demonstrate the compensation of stray electric fields using a gradient descent algorithm and a machine learning technique, which trained a deep learning network. We show automated dynamical compensation tested against induced electric charging from UV laser light hitting the chip trap surface. The results show improvement in compensation using gradient descent and the machine learner over manual compensation. This improvement is inferred from an increase of the fluorescence rate of 78% and 96% respectively, for a trapped [Formula: see text]Yb[Formula: see text] ion driven by a laser tuned to [Formula: see text] MHz of the [Formula: see text]S[Formula: see text]P[Formula: see text] Doppler cooling transition at 369.5 nm.

Deep learning enhanced Rydberg multifrequency microwave recognition

Recognition of multifrequency microwave (MW) electric fields is challenging because of the complex interference of multifrequency fields in practical applications. Rydberg atom-based measurements for multifrequency MW electric fields is promising in MW radar and MW communications. However, Rydberg atoms are sensitive not only to the MW signal but also to noise from atomic collisions and the environment, meaning that solution of the governing Lindblad master equation of light-atom interactions is complicated by the inclusion of noise and high-order terms. Here, we solve these problems by combining Rydberg atoms with deep learning model, demonstrating that this model uses the sensitivity of the Rydberg atoms while also reducing the impact of noise without solving the master equation. As a proof-of-principle demonstration, the deep learning enhanced Rydberg receiver allows direct decoding of the frequency-division multiplexed signal. This type of sensing technology is expected to benefit Rydberg-based MW fields sensing and communication.

Quantum Reservoir Computing for Speckle Disorder Potentials

Quantum reservoir computing is a machine learning approach designed to exploit the dynamics of quantum systems with memory to process information. As an advantage, it presents the possibility to benefit from the quantum resources provided by the reservoir combined with a simple and fast training strategy. In this work, this technique is introduced with a quantum reservoir of spins and it is applied to find the ground state energy of an additional quantum system. The quantum reservoir computer is trained with a linear model to predict the lowest energy of a particle in the presence of different speckle disorder potentials. The performance of the task is analyzed with a focus on the observable quantities extracted from the reservoir and it is shown to be enhanced when two-qubit correlations are employed.

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

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.

Unsupervised machine learning of topological phase transitions from experimental data

Identifying phase transitions is one of the key challenges in quantum many-body physics. Recently, machine learning methods have been shown to be an alternative way of localising phase boundaries from noisy and imperfect data without the knowledge of the order parameter. Here, we apply different unsupervised machine learning techniques, including anomaly detection and influence functions, to experimental data from ultracold atoms. In this way, we obtain the topological phase diagram of the Haldane model in a completely unbiased fashion. We show that these methods can successfully be applied to experimental data at finite temperatures and to the data of Floquet systems when post-processing the data to a single micromotion phase. Our work provides a benchmark for the unsupervised detection of new exotic phases in complex many-body systems.

Design of coaxial coils using hybrid machine learning

A coil system to generate a uniform field is urgently needed in quantum experiments. However, general coil configurations based on the analytical method have not considered practical restrictions, such as the region for coil placement due to holes in the center of the magnetic shield, which could not be directly applied in most of the quantum experiments. In this paper, we develop a coil design method for quantum experiments using hybrid machine learning. The algorithm part consists of a machine learner based on an artificial neural network and a differential evolution (DE) learner. The cooperation of both learners demonstrates its higher efficiency than a single DE learner and robustness in the coil optimization problem compared with analytical proposals. With the help of a DE learner, in numerical simulation, a machine learner can successfully design coaxial coil systems that generate fields whose relative inhomogeneity in a 25 mm-long central region is ∼10^-6 under constraints. In addition, for experiments, a coil system with 0.069% inhomogeneity of the field, designed by a machine learner, is constructed, which is mainly limited by machining the precision of the circuit board. Benefitting from machine learning's high-dimension optimization capabilities, our coil design method is convenient and has potential for various quantum experiments.

A Deep Ultraviolet Mode-locked Laser Based on a Neural Network

Deep ultraviolet lasers based on the phenomenon of mode-locking have been used widely in many areas in recent years, for example, in semiconductors, the environment and biomedicine. In the development of a mode-locked deep ultraviolet laser, one of the most important aspects is to optimize the multiple parameters of the complex system. Traditional optimization methods require experimenters with more optimization experience, which limits the wide application of the lasers. In this study, we optimize the deep ultraviolet mode-locked laser system using an online neural network to solve this problem. The neural network helps us control the position of the crystal, the length of the cavity, the position of the focusing lens and the temperature of the frequency doubling crystal. We generate a deep ultraviolet mode-locked laser with a power of 18 mW and a spectral center at 205 nm. This result is greatly improved compared to previous results with the same pump power. This technology provides a universal solution to multiparameter problems in the optimization of lasers.

Non-standard trajectories found by machine learning for evaporative cooling of 87Rb atoms

We present a machine-learning experiment involving evaporative cooling of gaseous ⁸⁷Rb atoms. The evaporation trajectory was optimized to maximize the number of atoms cooled down to a Bose-Einstein condensate using Bayesian optimization. After 300 trials within 3 hours, Bayesian optimization discovered trajectories that achieved atom numbers comparable with those of manual tuning by a human expert. Analysis of the machine-learned trajectories revealed minimum requirements for successful evaporative cooling. We found that the manually obtained curve and the machine-learned trajectories were quite similar in terms of evaporation efficiency, although the manual and machine-learned evaporation ramps were significantly different.

Approaching the adiabatic timescale with machine learning

The control and manipulation of quantum systems without excitation are challenging, due to the complexities in fully modeling such systems accurately and the difficulties in controlling these inherently fragile systems experimentally. For example, while protocols to decompress Bose-Einstein condensates (BECs) faster than the adiabatic timescale (without excitation or loss) have been well developed theoretically, experimental implementations of these protocols have yet to reach speeds faster than the adiabatic timescale. In this work, we experimentally demonstrate an alternative approach based on a machine-learning algorithm which makes progress toward this goal. The algorithm is given control of the coupled decompression and transport of a metastable helium condensate, with its performance determined after each experimental iteration by measuring the excitations of the resultant BEC. After each iteration the algorithm adjusts its internal model of the system to create an improved control output for the next iteration. Given sufficient control over the decompression, the algorithm converges to a solution that sets the current speed record in relation to the adiabatic timescale, beating out other experimental realizations based on theoretical approaches. This method presents a feasible approach for implementing fast-state preparations or transformations in other quantum systems, without requiring a solution to a theoretical model of the system. Implications for fundamental physics and cooling are discussed.