NTU-CEE Seminar Series: Assistant Professor Liang Gao

Organized By

CEE Seminar Committee

Host By

Assistant Professor Shi Chao

Topic

Assessing the Flood and Landslide Processes in Coastal Cities by integrating Numerical Models and Machine Learning Methods

About the Seminar

During storms or tropical cyclones, coastal cities are exposed to severe threats from flooding and landslides, and therefore accurate and timely prediction of the flood and landslide hazards in time–space domain is essential.

In this study, a hybrid model is proposed for real-time flooding prediction by considering the compound effects of storm tides, rainfall, and drainage outflows based on numerical modelling of historical storm and typhoon events in Macau. The model examines the dynamic interactions driving compound flooding, including intense rainfall, river discharges, overtopping flows, and sewer backflows, while also reconstructing landslide and debris flow initiation and propagation. Taking this a step further, we propose an advanced framework for spatiotemporal landslide prediction by coupling a slope stability model with machine learning.

Trained on 24 years of rainstorm and landslide data from Hong Kong and validated against the June 2008 storm event, this framework outperforms conventional physics-based and standalone machine-learning models. Both approaches achieve high computational efficiency, supporting improved flood risk management and emergency response planning.

About the Speaker

Dr. Liang Gao is currently an Assistant Professor at the State Key Laboratory of Internet of Things for Smart City and the Faculty of Science and Technology, University of Macau. Her research focuses on quantifying multi-hazard risks in coastal mountainous cities, including storm surges, flooding, landslides.

She has published over 80 SCI journal papers (45 as a leading author). She serves as an editorial board member for journals such as Georisk, Underground Space, International Journal of Sediment Research, Geodata and AI, Atmospheric and Climate Sciences, and Journal of Intelligent Construction.

Registration

Click here for registration
(Registration closes on 29 July 2025, 4:00pm)