Biography

ZongHao Xie is currently a PhD student at The Hong Kong Polytechnic University. He received his master's degree in Civil Infrastructural Engineering and Management from The Hong Kong University of Science and Technology in 2022 and his bachelor's degree in Safety Science and Engineering from Southwest Jiaotong University in 2021. His research focuses on hydrogen safety, gas release and dispersion modelling, computational fluid dynamics, and deep-learning-based probabilistic prediction.

​

​

Background of Education

• 2026 - Present, Ph.D., Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University.

• 2021 - 2022, M.Sc., Civil Infrastructural Engineering and Management, The Hong Kong University of Science and Technology .

• 2017 - 2021, B.Sc., Safety Science and Engineering, Southwest Jiaotong University.

​

Professional Experience

• 2023 - 2026, Research Assistant, The Hong Kong Polytechnic University; supervised by Dr. Jihao Shi. Research on real-time hydrogen release and dispersion modelling using deep-learning-based probabilistic approaches.

• 2022 - 2023, Research Assistant, The Hong Kong Polytechnic University; supervised by Dr. Xinyan Huang and Dr. Jihao Shi. Research on smart-city evacuation and hydrogen leakage and explosion simulation.

​

Research Areas

gas(hydrogen)release‑dispersion & explosion, CFD, probabilistic deep learning, graph neural networks

​

​

Prizes and Awards

• 2021 - 2022, Excellent Student Scholarship, The Hong Kong University of Science and Technology.

• 2018 - 2019, Fourth-class Scholarship, Southwest Jiaotong University.

• 2017 - 2018, Fourth-class Scholarship, Southwest Jiaotong University.

 

Research Experience

• 2022 - Present, Real-time hydrogen release and dispersion modelling using a deep-learning-based probabilistic approach. Used OpenFOAM and FLACS-CFD to simulate hydrogen leakage and explosion under different conditions and developed deep-learning models for rapid, accurate prediction.

• 2022, Application of AR/VR methods in smart-city evacuation. Conducted research on deep-learning applications for smart-city evacuation under the supervision of Dr. Xinyan Huang.

• 2021, Numerical study on the merging behaviours of two unequal fire sources in free space. Used PyroSim to simulate combustion and analyse interactions between the flames.

​

Publications

1. Li, J., Xie, Z., Shi, J., Usmani, A. S., Chang, Y., & Chen, G. (2025). Real-time hydrogen jet and diffusion modeling at urban scale using probabilistic graph neural network. Communications Engineering. (Under review).

2. Li, J., Xie, Z., Shi, J., Chang, Y., & Chen, G. (2025). Physics-assisted deep probability learning for natural gas leakage detection from infrared cameras without anomaly data. Engineering Applications of Artificial Intelligence. (Under review).

3. Li, J., Xie, Z., Shi, J., Chang, Y., & Chen, G. (2025). Real-time hydrogen explosion prediction of FCVs at urban scale using a physics-informed auto-regressive graph neural network. Renewable Energy. (Under review).

4. Li, J., Li, J., Xie, Z., Shi, J., Usmani, A. S., Chang, Y., & Chen, G. (2025). Graph neural network-based explosion prediction for offshore hydrogen production platforms with varying layouts. Applied Thermal Engineering. (Under review).

5. Li, J., Xie, Z., Shi, J., Huang, X., & Usmani, A. (2025). Uncertainty quantification of flammable gas dispersion numerical models driven by hybrid variational inference deep learning. Journal of Loss Prevention in the Process Industries, 105758.

6. Li, J., Xie, Z., Shi, J., Wang, K., Chang, Y., Chen, G., & Usmani, A. S. (2025). Domain adaptation based high-fidelity prediction for hydrogen-blended natural gas leakage and dispersion. Renewable Energy, 123461.

7. Shi, J., Li, J., Zhang, H., Xie, B., Xie, Z., Yu, Q., & Yan, J. (2025). Real-time gas explosion prediction at urban scale by GIS and graph neural network. Applied Energy, 377, 124614.

8. Li, J., Qian, X., Shi, J., Xie, Z., Chang, Y., & Chen, G. (2024). Natural gas leakage detection from offshore platform by OGI camera and unsupervised deep learning. Journal of Loss Prevention in the Process Industries, 92, 105449.

9. Li, J., Xie, Z., Liu, K., Shi, J., Wang, T., Chang, Y., & Chen, G. (2024). Real-time hydrogen plume spatiotemporal evolution forecasting by using deep probabilistic spatial-temporal neural network. International Journal of Hydrogen Energy, 72, 878-891.

10. Li, J., Xie, W., Li, H., Qian, X., Shi, J., Xie, Z., et al., & Chen, G. (2024). Real-time hydrogen release and dispersion modelling of hydrogen refuelling station by using deep learning probability approach.

​​

​

​​

（Last updated on 22/09/2026)

​​