Loading [MathJax]/jax/output/HTML-CSS/config.js
Volume 7, Issue 2
Two-Dimensional Convolutional Neural Networks for Predicting Non-Markovian Quantum Dissipative Dynamics

Zhiqian Huang, Cun Long, Qingdong Zhu, Jiaan Cao & Xiao Zheng

Commun. Comput. Chem., 7 (2025), pp. 134-144.

Published online: 2025-06

[An open-access article; the PDF is free to any online user.]

Export citation
  • Abstract

Simulating non-Markovian quantum dissipative dynamics remains a major challenge in theoretical and computational chemistry. While traditional numerical methods such as hierarchical equations of motion are numerically exact, they suffer from prohibitive computational costs when modeling systems with complex environmental couplings or strong non-Markovian effects. To address this limitation, we propose a deep learning framework based on two-dimensional convolutional neural networks (2D-CNN) for efficiently predicting long-time quantum dissipative dynamics using only short-time trajectory data. Our approach incorporates a 1D-to-2D feature reconstruction strategy, which transforms 1D time-series data into 2D images, and a multi-timescale fusion network to resolve complex dynamical features. We validate the framework on two paradigmatic cases — dissipative relaxation in a two-level system and Rabi oscillations in a dissipative spin system — achieving prediction mean absolute errors of $10^{-3}$ and $10^{-2},$ respectively. The results highlight the effectiveness of our 2D-CNN approach in capturing long-time temporal correlations, providing a computationally efficient pathway for simulating quantum dynamics in realistic open systems.

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{CiCC-7-134, author = {Huang , ZhiqianLong , CunZhu , QingdongCao , Jiaan and Zheng , Xiao}, title = {Two-Dimensional Convolutional Neural Networks for Predicting Non-Markovian Quantum Dissipative Dynamics}, journal = {Communications in Computational Chemistry}, year = {2025}, volume = {7}, number = {2}, pages = {134--144}, abstract = {

Simulating non-Markovian quantum dissipative dynamics remains a major challenge in theoretical and computational chemistry. While traditional numerical methods such as hierarchical equations of motion are numerically exact, they suffer from prohibitive computational costs when modeling systems with complex environmental couplings or strong non-Markovian effects. To address this limitation, we propose a deep learning framework based on two-dimensional convolutional neural networks (2D-CNN) for efficiently predicting long-time quantum dissipative dynamics using only short-time trajectory data. Our approach incorporates a 1D-to-2D feature reconstruction strategy, which transforms 1D time-series data into 2D images, and a multi-timescale fusion network to resolve complex dynamical features. We validate the framework on two paradigmatic cases — dissipative relaxation in a two-level system and Rabi oscillations in a dissipative spin system — achieving prediction mean absolute errors of $10^{-3}$ and $10^{-2},$ respectively. The results highlight the effectiveness of our 2D-CNN approach in capturing long-time temporal correlations, providing a computationally efficient pathway for simulating quantum dynamics in realistic open systems.

}, issn = {2617-8575}, doi = {https://doi.org/10.4208/cicc.2025.90.01}, url = {http://global-sci.org/intro/article_detail/cicc/24183.html} }
TY - JOUR T1 - Two-Dimensional Convolutional Neural Networks for Predicting Non-Markovian Quantum Dissipative Dynamics AU - Huang , Zhiqian AU - Long , Cun AU - Zhu , Qingdong AU - Cao , Jiaan AU - Zheng , Xiao JO - Communications in Computational Chemistry VL - 2 SP - 134 EP - 144 PY - 2025 DA - 2025/06 SN - 7 DO - http://doi.org/10.4208/cicc.2025.90.01 UR - https://global-sci.org/intro/article_detail/cicc/24183.html KW - deep learning, quantum dissipative dynamics, convolutional neural network. AB -

Simulating non-Markovian quantum dissipative dynamics remains a major challenge in theoretical and computational chemistry. While traditional numerical methods such as hierarchical equations of motion are numerically exact, they suffer from prohibitive computational costs when modeling systems with complex environmental couplings or strong non-Markovian effects. To address this limitation, we propose a deep learning framework based on two-dimensional convolutional neural networks (2D-CNN) for efficiently predicting long-time quantum dissipative dynamics using only short-time trajectory data. Our approach incorporates a 1D-to-2D feature reconstruction strategy, which transforms 1D time-series data into 2D images, and a multi-timescale fusion network to resolve complex dynamical features. We validate the framework on two paradigmatic cases — dissipative relaxation in a two-level system and Rabi oscillations in a dissipative spin system — achieving prediction mean absolute errors of $10^{-3}$ and $10^{-2},$ respectively. The results highlight the effectiveness of our 2D-CNN approach in capturing long-time temporal correlations, providing a computationally efficient pathway for simulating quantum dynamics in realistic open systems.

Huang , ZhiqianLong , CunZhu , QingdongCao , Jiaan and Zheng , Xiao. (2025). Two-Dimensional Convolutional Neural Networks for Predicting Non-Markovian Quantum Dissipative Dynamics. Communications in Computational Chemistry. 7 (2). 134-144. doi:10.4208/cicc.2025.90.01
Copy to clipboard
The citation has been copied to your clipboard