PhD Studentship: Cracks and Code: From High-Fidelity Simulations to Fast Scientific Machine Learning Models
Core
Investigate crack initiation and growth in metals under extreme high-rate conditions (shock waves, impacts) using large-scale atomistic and continuum simulations, then develop scientific machine-learning models to reproduce these processes efficiently.
Role type
PhD researcher in computational mechanics and scientific machine learning
Builds
Scientific ML models for predicting material failure under extreme conditions
Domain
Materials science, computational mechanics, high-performance computing
Deliverable
production ML models
Required skills
large-scale atomistic and continuum simulations, scientific machine learning, understanding of material failure mechanisms, high-rate deformation analysis
Preferred skills
industry partnership experience, advanced computational skills
Technologies
atomistic simulation, continuum simulation, machine learning frameworks
Responsibilities
study damage formation and localization in metals, develop efficient ML models to reproduce simulation processes, collaborate with industry partner AWE-NST
Seniority
PhD candidate (early career researcher)