arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04590cond-mat.quant-gasnlin.PS
收藏

基于物理信息的神经网络用于二元玻色-爱因斯坦凝聚体中的量子滴

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

Fuyang Normal University(阜阳师范大学);Key Laboratory of Functional Materials and Devices for Informatics of Anhui Educational Institutions, Fuyang Normal University(安徽省教育信息化功能材料与器件重点实验室,阜阳师范大学);Instituto de Alta Investigación, Universidad de Tarapacá(塔拉帕卡大学高等研究院);School of Mathematics and Statistics, Fuyang Normal University(阜阳师范大学数学与统计学院)

Dongshuai Liu, Boris A. Malomed, Wen Zhang

AI总结:

本文利用基于物理信息的神经网络研究二元玻色-爱因斯坦凝聚体中量子滴的形成与演化,展示了该方法在预测量子滴动态特性及鲁棒性方面的有效性。

摘要:

基于物理信息的神经网络(PINNs),将深度学习与物理先验知识相结合,已被证明是研究高维非线性系统动态的强大工具。本文利用PINNs分析二元玻色-爱因斯坦凝聚体(BEC)中量子滴(QDs)的存在和演化,揭示了该技术准确预测QDs结构特征、多峰轮廓和动态行为的能力。通过比较不同的网络架构,包括训练时间、损失值和L2误差,PINNs准确预测了QDs的特定动态特性。此外,通过将PINN应用于参数发现任务,考虑干净训练数据和受1%随机噪声污染的数据,评估了PINN的鲁棒性。结果突显了PINNs在建模复杂量子系统和在噪声条件下提取可靠参数方面的效率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑