Dr. Shuai ZHAO

E-mail : zhaosoi@126.com


Academic qualifications

  • Ph.D. in Civil Engineering, Tongji University, China, 2017 – 2022
  • Joint Ph.D. in geotechnical engineering, Nanyang Technological University, Singapore, 2019.12-2021.05
  • M.Sc. in Mining Engineering, Shandong University of Science and Technology, China, 2014 – 2016
  • B.Sc. in Mining Engineering, Shandong University of Science and Technology, China, 2010 – 2014

Professional experience (University)

  • Research Assistant, The Hong Kong Polytechnic University, Hong Kong, China, 08/2020 - present

Research interests

  • Deep Learning in tunnel engineering
  • Geotechnical and Tunnel Engineering Risk Assessment
  • Grouting Prevention for Defects of Shield Tunnel

Topic 1:Deep learning-based image instance segmentation

  • Contribution: 1) Established a integrated deep learning model for classification and instance segmentation of leakage and spalling images from shield tunnel linings, and refined crack segmentation with mitigated disjoint problem. 2) Further developed an A* algorithm to achieve refined crack quantification with improved accuracy. 3) Integrated the instance segmentation and quantification of cracks in one step with improved performance.
  • Significance: The proposed model can quickly select defect images from a large number of collected images, and automatically identify and quantify the defects in the defect images; the proposed model reduces the degree of discontinuity in identifying cracks, and improves crack segmentation accuracy and quantification accuracy of crack length and width.



  • Zhao S, Zhang DM, Huang HW. Deep learning–based image instance segmentation for moisture marks of shield tunnel lining, Tunnelling and Underground Space Technology, 2020, 95, 1-11.
  • Huang HW, Zhao S, Zhang DM, Chen JY. Deep learning-based instance segmentation of cracks from shield tunnel lining images, Structure and Infrastructure Engineering, 2020,1-14.
  • Zhao S, Shadabfar M, Zhang DM, Chen JY, Huang HW. Deep learning-based classification and instance segmentation of leakage-area and scaling images of shield tunnel linings, Structural Control and Health Monitoring, 2021, 28 (6), 1-22.
  • Zhao S, Zhang DM, Xue YD, Zhou ML, Huang HW. A deep learning-based approach for refined crack evaluation from shield tunnel lining images, Automation in Construction, 2021, 132,1-14.


Topic 2:Geotechnical and Tunnel Engineering Risk Assessment

  • Contribution: A multi-source heterogeneous fusion evaluation method based on Cloud-Copula-Evidence theory was proposed to evaluate the structural health status of shield tunnels in operation.
  • Significance: The fuzziness , randomness, and the correlation of the evaluation indicators can be considered, which can make the evaluation results more objective.




Topic 3:Grouting Prevention for Defects of Shield Tunnel

  • Contribution: 1) A laboratory apparatus for simulating microbial grouting behind the shield tunnel linings were developed. The application of microbial grouting method in the prevention of shield tunnel leakage was first discussed. 2) The method of applying pore pressure and expansion pressure to the soil element nodes in the microbial grouting area was used to investigate the variation law of pore pressure during the grouting process and the influence of grouting compaction on the deformation of the joint and the internal force of the segment.
  • Significance: An effective new path is provided for the prevention of leakage in shield tunnels.




  • Zhao S, Zhang DM, Huang HW, Chu J. Bio-grouting for seepage control for shield tunnels, 2022, Under Review .