Job Description

Development of multi-phase SPH tools and scientific machine learning approach for wind and wave load predictions at model-scale with preliminary outcomes. Application to practical problems involving M&O assets with final deliverable in terms of wind and wave load predictions, as well as fine-tuning of the developed scientific machine learning approach.

At NUS, the health and safety of our staff and students are one of our utmost priorities, and COVID-vaccination supports our commitment to ensure the safety of our community and to make NUS as safe and welcoming as possible. Many of our roles require a significant amount of physical interactions with students/staff/public members. Even for job roles that may be performed remotely, there will be instances where on-campus presences are required. 

In accordance with Singapore's legal requirements, unvaccinated workers will not be able to work on the NUS premises with effect from 15 January 2022. As such, job applicants will need to be fully COVID-19 vaccinated to secure successful employment with NUS.

Qualifications

• Candidate must have a strong interest and background in the creation of computational data from High Fidelity Computational Continuum Mechanics (CCM) Simulations i.e. CFD, CSD, 6-DOF Dynamics using open source solvers for multi-phase fluid dynamics of the air-sea interface to provide estimates of unsteady aerodynamic and wave loading on offshore superstructures,  creation of reduced order models from these high fidelity data to train physics informed deep learning networks for fast and reliable hydrodynamic and wave load predictions on marine offshore superstructures.
• While the candidate is expected to have experience working with open source CCM tools such as OpenFOAM, Fluidity, SPH and FENICS, and as this is a project in progress, the interest in developing tools using DualSPHysics will be of prime interest for this position. The candidate must be familiar with Linux OS and parallel computing technologies and be adept at using High Performance Computing Platforms such as multi-core and GPU systems for all high fidelity computational simulations.
• Candidate should be interested in model order reduction techniques and able to use these data to construct reliable machine learning surrogates for prediction using Tensorflow / deep learning / python tools and be able to demonstrate this capability and is expected to build on the existing efforts in progress in this area for which training data is generated using DualSPHysics.

More Information

Location: Kent Ridge Campus
Organization: Engineering
Department: Mechanical Engineering
Employee Referral Eligible: No
Job requisition ID: 13166