arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.03090quant-phcond-mat.othernucl-thphysics.atom-phphysics.comp-ph
收藏

求解 Dirac 方程的深度神经网络方法

A deep neural network approach to solve the Dirac equation

Chuanxin Wang, Tomoya Naito, Jian Li, Haozhao Liang

AI总结:

本文扩展了已有方法,利用深度神经网络和无监督机器学习技术求解 Dirac 方程的基态及低激发态,通过引入逆 Hamiltonian 方法克服 Dirac 海导致的变分法失效问题,并经 Coulomb 和 Woods-Saxon 势验证了方法有效性。

摘要:

我们将 [Naito, Naito, and Hashimoto, Phys. Rev. Research 5, 033189 (2023)] 的方法进行扩展,利用深度神经网络和无监督机器学习技术求解 Dirac 方程,不仅适用于基态,也适用于低激发态。由于 Dirac 海的存在,变分法会失效,这可以通过引入逆 Hamiltonian 方法来避免。针对低激发态,我们提出了两种方法,它们具有不同的性能和优势。通过使用 Coulomb 和 Woods-Saxon 势的计算验证了该方法的有效性。

英文摘要:

We extend the method from [Naito, Naito, and Hashimoto, Phys. Rev. Research 5, 033189 (2023)] to solve the Dirac equation not only for the ground state but also for low-lying excited states using a deep neural network and the unsupervised machine learning technique. The variational method fails because of the Dirac sea, which is avoided by introducing the inverse Hamiltonian method. For low-lying excited states, two methods are proposed, which have different performances and advantages. The validity of this method is verified by the calculations with the Coulomb and Woods-Saxon potentials.

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。

↑