Bokai Liu

Researcher in AI-driven multiscale modeling and sustainable materials. Principal Investigator of a VR starting Grant project at Umeå University.

0000-0002-7171-1219

Contact

bokai.liu@umu.se

X, Håken Gullessons väg 20, Teknikhuset, TEK.D.216 Umeå universitet, 901 87 Umeå

Works as

Postdoctoral fellow (on leave) at Department of Applied Physics and Electronics

Postdoctoral fellow at Department of Applied Physics and Electronics

I am a Researcher at Umeå University, Sweden, and a Research Professor at Korea University, School of Engineering, funded by STINT (SKERIC long-mobility project). In 2025, I was awarded the VR Starting Grant from the Swedish Research Council (11% success rate, 4.8M SEK), one of Sweden’s most prestigious early-career research grants. This milestone affirms my path as an independent principal investigator.

My research focuses on AI-driven multiscale modeling, computational mechanics, and sustainable materials, integrating materials informatics with energy-efficient engineering. I have led 8 funded projects (~7.5M SEK total) supported by funders such as VR, STINT, KSLA, SWECO, and others. With over 8 years of research experience and active international collaborations across Europe and Asia, I aim to bridge AI for Science with sustainable innovation and global academic–industry cooperation.

A prediction model for dyke-dam piping based on data augmentation and interpretable ensemble learning

Engineering Failure Analysis, Elsevier 2025, Vol. 182

Zhang, Xi; Xia, Yangyang; Zhang, Chao; et al.

An archimedes optimization algorithm based extreme gradient boosting model for predicting the bending strength of UV cured glass fiber reinforced polymer composites

Polymer Composites

Zhang, Xi; Xia, Yangyang; Zhang, Chao; et al.

Comparative analysis of heat transfer in polyurethane with phase change materials: advancing multi-scale modeling for energy efficiency

Healthy Buildings Europe 2025 Conference, Reykjavík, Iceland, June 8-11, 2025

Liu, Bokai; Liu, Pengju; Han, Ou; et al.

Explainable artificial intelligence (XAI) for material design and engineering applications: a quantitative computational framework

International Journal of Mechanical System Dynamics, John Wiley & Sons 2025, Vol. 5, (2) : 236-265

Liu, Bokai; Liu, Pengju; Lu, Weizhuo; et al.

Explainable machine learning for multiscale thermal conductivity modeling in polymer nanocomposites with uncertainty quantification

Composite structures, Elsevier 2025, Vol. 370

Liu, Bokai; Liu, Pengju; Wang, Yizheng; et al.

Stochastic multiscale modeling for thermal conductivity in polymeric graphene-enhanced composites: a study in interpretable machine learning

Computational and Experimental Simulations in Engineering: Proceedings of ICCES 2024 - Volume 4, Springer Nature 2025 : 208-219

Liu, Bokai; Liu, Pengju; Lu, Weizhuo; et al.

Enhancing thermal conductivity modeling of polyurethane with phase change materials via physics-informed neural networks at multiple scales

The 9th European Congress on Computational Methods in Applied Sciences and Engineering ECCOMAS Congress 2024

Liu, Bokai; Wang, Yizheng; Olofsson, Thomas; et al.

Interpretable machine learning for multiscale thermal conductivity modeling in polymer nanocomposites with uncertainty quantification

International Conference on Data-Driven Computing and Machine Learning in Engineering 2024 (DACOMA2024), Nanjing, Jiangsu Province, China, October 12-14, 2024

Liu, Bokai

Multi-scale and multi-tier energy efficient framework for sustainable buildings with PU-phase change materials in northern Sweden

2024 International Scientific Symposium for the Baltic University Programme (BUP) – “The Role of University and Research for Sustainable Regional Development”, Bialystok University of Technology, Białystok, Poland, April 21–23, 2024.

Liu, Bokai

Multi-scale modeling in thermal conductivity of polyurethane incorporated with phase change materials using physics-informed neural networks

Renewable energy, Elsevier 2024, Vol. 220

Liu, Bokai; Wang, Yizheng; Rabczuk, Timon; et al.

Stochastic interpretable machine learning based multiscale modeling in thermal conductivity of Polymeric graphene-enhanced composites

Composite structures, Elsevier 2024, Vol. 327

Liu, Bokai; Lu, Weizhuo; Olofsson, Thomas; et al.

Al-DeMat: A web-based expert system platform for computationally expensive models in materials design

Advances in Engineering Software, Elsevier 2023, Vol. 176

Liu, Bokai; Vu-Bac, Nam; Zhuang, Xiaoying; et al.

Data-driven quantitative analysis of an integrated open digital ecosystems platform for user-centric energy retrofits: A case study in northern Sweden

Technology in society, Elsevier 2023, Vol. 75