Learning Quantum Drift-Diffusion Phenomenon by Physics-Constraint Machine Learning
Learning Quantum Drift-Diffusion Phenomenon by Physics-Constraint Machine Learning
复制标题
DOI：
10.1109/tnet.2022.3158987
复制
发表时间：
2022-04-07
影响因子：
3.7
通讯作者：
Wu, Boying
中科院分区：
文献类型：
--
作者：
Li, Chun;Yang, Yunyun;Wu, Boying
最近，深度学习（DL）被广泛用于检测物理现象，并取得了令人鼓舞的结果。一些工作表明，它可以学习量子现象。随后，量子机器学习（QML）受到学术界和工业界的广泛关注。量子漂移扩散（QDD）是一种常见的物理现象，是对半导体中电子和空穴的宏观描述。它们通常用于了解物理和工程中半导体器件的特性。我们的动机是从量子Navier Stokes Poisson系统到QDD方程的弛豫时间极限，并证明了QDD方程的有限能量弱解的存在性。因此，在这项工作中，量子漂移-扩散学习神经网络（QDDLNN）的建议，从有限的观察研究量子漂移现象。通过对量子限制输运方程--量子Navier-Stokes方程的模拟，得到了神经网络能够描述量子输运现象的数值证据。
Recently, deep learning (DL) is widely used to detect physical phenomena and has obtained encouraging results. Several works have shown that it can learn quantum phenomenon. Subsequently, quantum machine learning (QML) has been paid more attention by academia and industry. Quantum drift-diffusion (QDD) is a commonplace physical phenomenon, which is a macroscopic description of electrons and holes in a semiconductor. They are commonly used to attain an understanding of the property of semiconductor devices in physics and engineering. We are motivated by the relaxation-time limit from the quantum-Navier-Stokes-Poisson system (QNSP) to the QDD equation and the existence of finite energy weak solutions to the QDD equation has been proved. Therefore, in this work, the quantum drift-diffusion learning neural network (QDDLNN) is proposed to investigate the quantum drift phenomena from limited observations. Furthermore, a piece of numerical evidence is found that the NNs can describe quantum transport phenomena by simulating the quantum confinement transport equation-quantum Navier-Stokes equation.