PhD Studentship - Data-driven Approaches to Viscoelastic Flow Control
Core
Applying machine learning and computational fluid dynamics to understand viscoelastic turbulence and design flow control strategies for porous media.
Role type
PhD researcher in applied mathematics and fluid dynamics
Builds
ML models for flow prediction and optimized porous media geometries
Domain
Fluid dynamics, applied mathematics, porous media engineering
Deliverable
production ML models
Required skills
computational science, mathematics, programming, machine learning, numerical simulations, high-performance computing, reduced order modelling, deep reinforcement learning
Preferred skills
knowledge of viscoelastic flows, porous media applications
Technologies
deep learning, reinforcement learning, high-performance computing
Responsibilities
Apply explainable deep learning to identify coherent structures in viscoelastic turbulence, develop ML models to predict complex flows in porous media, design optimized porous media geometries for enhanced mixing efficiency
Seniority
PhD candidate