Thermometry of one-dimensional Bose gases with neural networks

Abstract

We design a neural network to extract and process features from absorption images taken of one-dimensional Bose gases in the quasi-condensate regime. Specifically, the network is trained to predict both the temperature of single realizations of the system and the uncertainty thereof. For multiple realizations, the individual predictions can be combined in an estimate of the mean temperature, improving precision. We benchmark our model on both simulated and experimentally measured data and compare it to the established method of density ripples thermometry. We find the predictions of the two methods compatible, although the neural network reaches similar precision needing much fewer realizations, thus highlighting the efficiency gain achievable when incorporating neural networks into analysis of data from cold gas experiments. Further, we study feature maps to reveal which local features of the condensate are extracted by the network and how said features correlate with properties of the system. A similar analysis could be employed to uncover physical relations in more complex systems.

18 pages, 9 figures

References in corpus (9)

• Many-Body Physics with Ultracold Gases
• Learning phase transitions by confusion
• Experimental Observation of a Generalized Gibbs Ensemble
• Extension of Bogoliubov theory to quasi-condensates
• Linear response theory for a pair of coupled one-dimensional condensates of interacting atoms
• Single-exposure absorption imaging of ultracold atoms using deep learning
• From observations to complexity of quantum states via unsupervised learning
• Density ripples in expanding low-dimensional gases as a probe of correlations
• Microscopic atom optics: from wires to an atom chip

Cited by in corpus (9)

• Emergent Pauli blocking in a weakly interacting Bose gas
• Correlation properties of a one-dimensional repulsive Bose gas at finite temperature
• The Whitham approach to Generalized Hydrodynamics
• Sample-efficient estimation of entanglement entropy through supervised learning
• Thermal fading of the $1/k^4$-tail of the momentum distribution induced by the hole anomaly
• Identifying diffusive length scales in one-dimensional Bose gases
• Measurement of total phase fluctuation in cold-atomic quantum simulators
• Systematic analysis of relative phase extraction in one-dimensional Bose gases interferometry
• Particle-hole origin of thermal beating in dipole-compression modes of a 1D Bose gas