Key Responsibilities:
- Contribute to the development of a digital twin-enabled Infrastructure Health Monitoring framework combining multi-sensor data, numerical models, and AI for marine structures.
- Apply model updating and data assimilation techniques to estimate key parameters and improve prediction accuracy.
- Build probabilistic prediction systems to assess structural health or settlement of marine structures, accounting for uncertainty in decision-making.
- Design and train machine learning / deep learning / physics-informed models to predict structural responses (e.g. dynamic responses for offshore structures, settlement behaviors for coastal protection infrastructures) using data from multiple sources, considering external factors / coastal processes, e.g. waves, wind, current, and tides.
- Validate the system through field deployment at a Proof-of-Concept site and benchmark performance.
- Collaborate closely with interdisciplinary teams to deliver impactful technical outcomes and peer-reviewed publications.
- PhD or Master?s degree in Coastal Engineering, Ocean Engineering, Civil Engineering, Applied Mathematics, or a related discipline.
- Strong foundation in coastal or ocean engineering, with knowledge of wave-structure interaction, tidal influences, and soil-water-structure response in nearshore / offshore environments.
- Proficiency in data assimilation techniques, including Bayesian inference, Kalman filtering and its variants, and model updating, with demonstrated application to engineering systems.
- Experience in developing data-driven models (machine learning, deep learning) and/or physics-informed models for structural or geospatial monitoring problems.
- Familiarity with coastal and offshore infrastructure systems, such as seawalls, breakwaters, quay walls, floating platforms, or station-keeping systems is an advantage.
- Proficiency in scientific programming using Python and/or MATLAB for data analysis, model development, and AI workflows.
- Proven ability to work both independently and collaboratively in interdisciplinary teams.
Type of Employment : Full-Time
Minimum Experience : 1 Year
Work Location : NUS
Report job
