He/Him

Home Research Software Publication Teaching Contact

Motivation and Challenge

This line of my research answers a fundamental question: “How can we effectively incorporate uncertain information and beliefs into the analysis and design of geosystems?” Due to the availability of computing tools, there is a pool of techniques ranging from analytical formulas to probabilistic numerical models that engineers can choose from to handle uncertainties. However, there also exists a multitude of issues related to the nature and complexity of uncertainties. Is there a unified technique that can handle the multitude of uncertainty issues?

Deep-learning-aided geotechnical reliability analysis & design

National University of Singapore & Center for Protective Technology

2019-Present

In my foundational paper (Wang et al., 2019), I pioneered the use of deep-learning algorithms to perform the task. I strategically showed the AI model how other techniques perform the task, from which the model gained the capability of interpreting uncertainties. I showed that the AI model is a much simpler system that handles uncertainties more effectively, offering engineers a handy tool to incorporate uncertainties into the reliability analysis of geosystems. Through several additional papers, I extended the AI system to analyse a range of realistic problems that engineers may encounter in practice. Through this collection of research articles, not only did I demonstrate the generalizability of the AI model in addressing multiple uncertainty issues, but I also sparked further research into the bridging of AI and geotechnical reliability analysis.

Peer-reviewed Journal Articles

Wang, Z. Z., Zhang, J. Z.*, & Huang, H. W. (2023). Interpreting Random Fields Through the U-Net Architecture for Failure Mechanism and Deformation Predictions of Geosystems. Geoscience Frontiers. (Accepted)
Jiang, S. H., Zhu, G. Y., Wang, Z. Z.*, Huang, Z. T., & Huang, J. (2023). “Data augmentation for CNN-based probabilistic slope stability analysis in spatially variable soils”. Computers and Geotechnics, 160, 105501. https://doi.org/10.1016/j.compgeo.2023.105501.[PDF]
Wang, Z. Z.*, Goh, S. H., & Zhang, W. (2022), “Reliability-based design in spatially variable soils using deep learning: an illustration using shallow foundation”. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards. https://doi.org/10.1080/17499518.2022.2083178. [PDF]
Wang, Z. Z.* (2022), “Deep-learning for geotechnical reliability analysis with multiple uncertainties”. Journal of Geotechnical and Geoenvironmental Engineering. https://doi.org/10.1061/(ASCE)GT.1943-5606.0002771.[PDF]
Wang, Z. Z.*, Goh, S. H. (2021). A maximum entropy method using fractional moments and deep learning for geotechnical reliability analysis. Acta Geotechnica. https://doi.org/10.1007/s11440-021-01326-2 [PDF]
Wang, Z. Z.*, Goh, S. H. (2021). Novel approach to efficient slope reliability analysis in spatially variable soils. Engineering Geology. https://doi.org/10.1016/j.enggeo.2020.105989. [PDF]
Wang, Z. Z.*, Xiao, C. L., Goh, S. H., & Deng, M. X. (2021). Meta-model based reliability analysis in spatially variable soils using Convolutional Neural Networks. Journal of Geotechnical and Geoenvironmental Engineering. https://doi.org/10.1061/(ASCE)GT.1943-5606.0002486.[PDF]

Peer-reviewed Conference Papers

Wang, Z. Z.*, Deng, M. X., & Goh, S. H. (2023). “Development of a stochastic finite-element package for use with Plaxis 2D”. In 10th European Conference on Numerical Methods in Geotechnical Engineering (NUMGE 2023). https://doi.org/10.53243/NUMGE2023-233. [PDF]
Wang, Z. Z.*, Zhang, J. Z., Goh, S. H., & Huang, H. W. (2022). “Application of image segmentation for predicting slope failure mechanism in spatially variable soils”. In 8th International Symposium on Geotechnical Safety and Risk. (Best Student Paper Award). https://doi.org/10.3850/978-981-18-5182-7_03-009-cd. [PDF]
Wang, Z. Z.*, Goh, S. H., & Zheng, X. (2022). Numerical modelling of cone penetration tests in spatially variable clays. In Cone Penetration Testing 2022 (pp. 753-759). CRC Press. [PDF]
Wang, Z. Z.*, Goh, S. H., & Pai, S.G.S (2022). Adaptive training of convolutional neural networks for slope reliability analysis in spatially variable soils . In 7th International Young Geotechnical Engineers Conference (7iYGEC). [PDF]