PhD Candidate in Machine Learning for Temporal and Spatiotemporal Data

Four-year PhD position in machine learning at the Department of Computer Science (IDI), NTNU, within STRIDE, an interdisciplinary NTNU project on the resilience of transport systems in which transport networks are the main testbed. Forecasting models trained under normal operating conditions degrade when a disruption (a closed link, a capacity limit or a sudden change in demand) pushes a network into a rare regime. The PhD will develop deep learning methods that forecast reliably under such distribution shift and that detect and locate disruptions from observed data.

Possible directions include time-series foundation models pretrained on synthetic data from simulated dynamical systems, spatiotemporal graph neural networks modelling how disruptions propagate, and anomaly detection and localisation in time series on graphs. Main supervisor: Associate Professor Massimiliano Ruocco. Gross salary is normally NOK 580,000 per year.

Master's degree in computer science, machine learning, statistics, applied mathematics, physics or equivalent, including a major independent project; admission to the PhD programme in Computer Science.