Bayesian Analysis of Engineering Models with Spatially Variable Properties

We invite applications for a PhD position within the project BAYES (Bayesian Analysis of Engineering Models with Spatially Variable Properties) funded by the International Graduate School of Science and Engineering (IGSSE) of TUM.

You will develop methods for learning engineering models with spatially variable properties using Bayesian analysis. With advances in monitoring technologies, accurate predictions of monitored systems often require models that account for the random spatial variability of parameters. The Bayesian framework enables the combination of uncertain and incomplete information with sophisticated probabilistic models and it provides estimates of the accuracy of the resulting models. The two main goals of the project are: First, to carry out a systematic investigation of the effect of different model choices concerning spatially variable properties, and provide recommendations for engineering practice. Second, to identify and further enhance efficient computational methods for Bayesian analysis of engineering models with discretized random fields.

The suggested work is in the area of Computational Uncertainty Quantification and will be supervised by Prof. Elisabeth Ullmann (Professorship for Scientific Computing). The PhD student will collaborate closely with Prof. Daniel Straub, Dr. Iason Papaioannou and Wolfgang Betz at the Engineering Risk Analysis (ERA) group at TUM. The student will also spend three months at a partner university or scientific institution outside of Germany.

Candidates must have excellent analytical skills, a strong interest in PDE-based mathematical models, expertise in programming and numerical methods for PDEs, and strong communications skills. Proficiency in written and oral English is required for this position. Working knowledge of computational tools from uncertainty quantification (stochastic finite elements, Monte Carlo, Markov chains, Bayesian inference) is desirable. Applicants should ideally hold a master’s degree in Mathematics, Statistics or Computer Science, with strong background in numerical analysis, stochastic processes or computing, but other suitable candidates will also be considered.

If you are interested, please send your curriculum vitae and a short cover letter to: [Email Address Removed]

The search will be continued until the position is filled.