Physics-Informed Neural Networks for the Quantum Droplets in Binary Bose-Einstein Condensates

Abstract

Physics-Informed Neural Networks (PINNs), which integrate deep learning with physical prior knowledge, have proven to be a powerful tool for studying the dynamics of high-dimensional nonlinear systems. The present work utilizes PINNs to analyze the existence and evolution of quantum droplets (QDs) in a binary Bose-Einstein condensate (BEC), revealing the ability of this technique to accurately predict structural features of the QDs, their multipeak profiles, and dynamical behavior. The stable evolution of multipole QDs is thus demonstrated. Comparing different network architectures, including the training time, loss values, and ${\mathbb{L}}_2$ error, PINNs accurately predict specific dynamical characteristics of QDs. Furthermore, the PINN robustness is evaluated by the application of PINN to parameter-discovery tasks, considering both clean training data and data contaminated by $1\%$ random noise. The results highlight the efficiency of PINNs in modeling complex quantum systems and extracting reliable parameters under the noisy conditions.

11 pages, 9 figures,to be published in Chaos, Solitons & Fractals

References in corpus (23)

• Quantum Mechanical Stabilization of a Collapsing Bose-Bose Mixture
• Quantum liquid droplets in a mixture of Bose-Einstein condensates
• Self-bound quantum droplets in atomic mixtures
• Self-bound droplets of a dilute magnetic quantum liquid
• Ultradilute low-dimensional liquids
• Double species condensate with tunable interspecies interactions
• Dynamics of one-dimensional quantum droplets
• Two-dimensional vortex quantum droplets
• Collective Excitations of a One-Dimensional Quantum Droplet
• Universality of the three-body Efimov parameter at narrow Feshbach resonances
• The liquid state of one-dimensional Bose mixtures: a quantum Monte-Carlo study
• Metastability of quantum droplet clusters
• A double species ${}^{23}$Na and ${}^{87}$Rb Bose-Einstein condensate with tunable miscibility via an interspecies Feshbach resonance
• Universality in ultradilute liquid Bose-Bose mixtures
• Observation of a Lee-Huang-Yang Fluid
• Bloch Oscillations in Optical and Zeeman Lattices in the Presence of Spin-Orbit Coupling
• Thermal instability, evaporation and thermodynamics of one-dimensional liquids in weakly-interacting Bose-Bose mixtures
• Complex dynamics on the one-dimensional quantum droplets via time piecewise PINNs
• Spinning superfluid helium-4 nanodroplets
• Finite-range effects in ultradilute quantum drops
• Machine-learning assisted quantum control in random environment
• Enhanced mobility of quantum droplets in periodic lattices
• Multipole quantum droplets in quasi-one-dimensional asymmetric mixtures