DRL-EnVar: an adaptive hybrid ensemble–variational data assimilation method based on deep reinforcement learning

Lilan HUANG; Hongze LENG; Junqiang SONG; Dongzi WANG; Wuxin WANG; Ruisheng HU; Hang CAO

doi:10.1631/FITEE.2401063

Your Location：

Home >

Browse articles >

DRL-EnVar: an adaptive hybrid ensemble–variational data assimilation method based on deep reinforcement learning

Regular Papers | Updated：2026-01-12

- DRL-EnVar: an adaptive hybrid ensemble–variational data assimilation method based on deep reinforcement learning
  Enhanced Publication
- DRL-EnVar：基于深度强化学习的自适应混合集合-变分资料同化方法
- “In the field of numerical weather prediction, researchers have made significant progress. They established the DRL-EnVar system, which provides solutions to improve data assimilation performance and forecast accuracy.”
- Frontiers of Information Technology & Electronic Engineering Vol. 26, Issue 12, Pages: 2583-2603(2025)
- Affiliations：
  
  1.College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China
  2.College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China
- Author bio：
  
  E-mail: huanglilan18@nudt.edu.cn
  ‡ Corresponding authors
- Funds：
- DOI：10.1631/FITEE.2401063
  CLC： TP391
- Received：14 December 2024，
  
  Revised：2025-08-19，
  
  Published Online：26 November 2025，
  
  Published：2025-12
- Accepted：
Scan QR Code
Lilan HUANG, Hongze LENG, Junqiang SONG, et al. DRL-EnVar: an adaptive hybrid ensemble–variational data assimilation method based on deep reinforcement learning[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(12): 2583-2603.
DOI：

Lilan HUANG, Hongze LENG, Junqiang SONG, et al. DRL-EnVar: an adaptive hybrid ensemble–variational data assimilation method based on deep reinforcement learning[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(12): 2583-2603. DOI： 10.1631/FITEE.2401063.

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

SPID: a deep reinforcement learning-based solution framework for siting low-altitude takeoff and landing facilities^#

Black-box adversarial attacks on deep reinforcement learning-based proportional–integral–derivative controllers for load frequency control

Federated deep reinforcement learning based computation offloading in a low Earth orbit satellite edge computing system

Significance extraction based on data augmentation for reinforcement learning

Incentive-based task offloading for digital twins in 6G native artificial intelligence networks: a learning approach

Related Author

Minghua HU

Yupu LIU

Meilong LE

Xiaocheng LIU

Xuguo JIAO

Xin WANG

Zhenyong ZHANG

Wei WANG

Related Institution

College of Civil Aviation, Nanjing University of Aeronautics and Astronautics

State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University

School of Information and Control Engineering, Qingdao University of Technology

Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Qilu University of Technology (Shandong Academy of Sciences)

State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University

Intro

Map

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰

DRL-EnVar: an adaptive hybrid ensemble–variational data assimilation method based on deep reinforcement learning

DOI：10.1631/FITEE.2401063