PhD Scholarship in Machine Learning for Non-Stationary and Non-Static Nano-Tomography - DTU Compute

A fully funded three-year PhD project at DTU Compute developing learning-based methods for X-ray nano-tomography. As synchrotron imaging pushes to ever higher spatial resolution, small positioning errors, mechanical drift and sample deformation degrade reconstructions. The project combines neural representations, inverse problems, geometric modelling and computational imaging to reconstruct accurate 3D and 4D representations while accounting for positional uncertainty during acquisition and changes in sample shape over time. Expected start: 1 March 2027 or by agreement.

A two-year master’s degree (120 ECTS) or equivalent in computer science, applied mathematics, physics, engineering or a related discipline; applicants may apply before completing the degree.