A Deep‐Learning Approach to the Dynamics of Landau–Zenner Transitions. Issue 7 (7th May 2021)

• Record Type: Journal Article
• Authors: Gao, Linliang; Sun, Kewei; Zheng, Huiru; Zhao, Yang
• Is Part Of: Advanced theory and simulations. Volume 4:Issue 7(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-05-07
• Subjects: back propagation neural networks -- convolutional neural networks -- generative adversarial networks -- Landau–Zener transitions; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.202100083
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: Traditional approaches to the dynamics of the open quantum systems with high precision are often resource intensive. How to improve computation accuracy and efficiency for target systems is an extremely difficult challenge. In this work, combining unsupervised and supervised learning algorithms, a deep‐learning approach is introduced to simulate and predict Landau–Zenner dynamics. Data obtained from multiple Davydov D 2 Ansatz with a low multiplicity of four are used for training, while the data from the trial state with a high multiplicity of ten are adopted as target data to assess the accuracy of prediction. After proper training, our method can successfully predict and simulate Landau–Zenner dynamics using only random noise and two adjustable model parameters. Compared to the high‐precision dynamics data from multiple Davydov D 2 Ansatz with a multiplicity of ten, the error rate falls below 0.6%. Abstract : A deep‐learning approach, combining GAN, CNN, and BPNN, is developed to predict many‐body Landau–Zener dynamics using only random noise and two adjustable model parameters. Compared to high‐precision dynamics data generated by the state‐of‐the‐art multiple Davydov D2 Ansatz with a multiplicity of 10, it is found that the error rate falls below 0.6%.