Junle Liu 刘军乐

ABOUT ME

Hi, there. Dr.Junle LIU earned his Ph.D. degree from Hong Kong University of Science and Technology (HKUST) at the Wind Engineering and Building Aerodynamics (WEBA) group and his Bachelor’s degree from Harbin Institute of Technology Shenzhen, at Artificial Intelligence for Wind Engineering lab. His supervisors are Prof.Tim K.T. Tse and Prof.Gang Hu.

Dr Liu, from May 2025, joined KTH FLOW Center as a Research Fellow supervised by Stefan Wallin focusing on ERC ROSAS project, and his research topics are centered on DRL and wall modelling.

In his past research journey, he has been concentrating on AI-aided aerodynamics and data-driven techniques in experimental fluid mechanics and numerical simulation. As of now, Dr.Liu has published papers covering AI-enhanced fluid mechanics, experimental fluid mechanics, and reduced-order modelling techniques in aerodynamics.

Some recent research interests of Dr.Liu:

Wind Engineeirng: Experimental, Numerical, and Data-Driven perspectives;
Reinforcement Learning for flow control and UAV/drone optimization (low-attitude aerodynamics);
AI for Fluid Engineering: prediction, reconstruction, and control;
Atmosphere aerodynamics

Dr.Liu welcomes any kind of academic and industrial collaborations. If you are interested in integrating AI techniques with engineering practices, please feel free to drop an email or send an instant message.

Latest News

[2026 Sep] A General Program project funded by the National Natural Science Foundation of China (NSFC) has been awarded. I am a key participant in the project (ranked second).

**[2026 Aug] **New conference paper in BMVC 2026 accepted: Deep Multimodal Object Detection via Spatial Mask Interaction and Channel Competition

Topic: Computer vision, multimodal detection, RGB+IR

**[2026 July] **New collaboration paper in Physcis of Fludis out: Explainable machine learning-enhanced aerodynamic characteristic analysis of bluff bodies under interference effects

Topic: Investigate the two tandem building interference effects with XML methods;
Method: CFD, XML, SHAP, Uncertainity quantification;

**[2026 July] **New collaboration paper in Building And Environment out: POD-FNO for efficient and interpretable prediction of turbulent flow around bluff bodies

Topic: Develop and evaluate AI algorithms for turbulent flow prediction in interferrence zone;
Method: an interpretable POD-FNO method;
Findings: interpretable AI can predict turbulent features and understand physical information.

[2026 June] Nominated for the WAIC 2026 SAIL Award.

**[2026 May] **New Projects Awarded [SMARTRAIL: AI-based rail cable crack detection] supported by NAISS, collaborated with William Liu

Topic: Develop VLA tools for railway cable crack detection;
Method: Vision-based models, VLA models, physical interpretations;
Findings: Ongoing.

**[2026 Apr] **New Projects Awarded [PhyGeo-World: A Physics- and Geometry-Consistent World Model for Embodied AI] supported by NAISS

Topic: Develop GeoAI model for physical world;
Method: LLM, Diffusion;
Findings: Ongoing.

**[2026 Jan] **New collaboration paper in Energy out: Wind energy potential of a novel green building design: Three connected high-rise buildings with Y-plan layout

Topic: Estimate the wind energy potential in the urban city;
Method: Numerical-experiments cross-validation;
Findings: Installing wind turbines in urban city buildings can harvest a great amount of wind energy.

关于我

大家好！刘军乐博士于香港科技大学（HKUST）风工程与建筑空气动力学（WEBA）研究组获得博士学位，本科毕业于哈尔滨工业大学（深圳），曾在风工程人工智能实验室开展研究。他的导师为谢锦添教授（Prof. Tim K.T. Tse）和胡钢教授。

自 2025 年 5 月起，刘博士加入瑞典皇家理工学院（KTH）FLOW 中心担任研究员，在 Stefan Wallin 指导下参与 ERC ROSAS 项目，主要研究方向为深度强化学习与壁面建模。

在过往研究中，他一直专注于人工智能辅助空气动力学，以及实验流体力学和数值模拟中的数据驱动技术。目前，刘博士已发表多篇涉及人工智能增强流体力学、实验流体力学和空气动力学降阶建模的论文。

近期研究兴趣包括：

风工程：实验、数值与数据驱动方法；
面向流动控制及无人机优化的强化学习（低空空气动力学）；
流体工程人工智能：预测、重构与控制；
大气空气动力学。

刘博士欢迎各类学术与产业合作。如果你对人工智能技术与工程实践的融合感兴趣，欢迎通过电子邮件或即时消息与他联系。