Kolloquium SoSe 2021

Speaker

Dr. David Greenberg

Helmholtz Centre Hereon

When: Mo, 10.05.2021, at 17:15

Online-Zoom-Meeting

You will receive the registration data via an email invitation. Please register for this at https://mailhost.informatik.uni-hamburg.de/mailman/listinfo/kolloquium.

Topic

Guiding Scientific Simulators with Machine Learning

Language: english

Abstract

Simulations are a powerful tool for combining and exploring scientific insights, and their predictions generalize better to new scenarios than non-physical data-driven aproaches. However, the problem of assimilating noisy and incomplete observations of the simulated system to constrain parameters or initial conditions is challenging, since for many important simulators the data likelihood is intractable. I will describe two recent machine learning-based approaches addresing this problem: Bayesian inference with normalizing flows and optimization with differentiable emulators. Both of these approaches use model simulations as training data, allowing the machine learning model to benefit from the scientfic insight used to design the simulator.

Bio

After a studying mathematics at Brown University, David Greenberg completed his PhD in computational neuroscience and computer vision at the Caesar research institute, Bonn. After completing a Postdoc on simulation-based inference at TUM, he joined Helmholtz Zentrum Hereon in Geesthacht in 2020 as a young investigator group leader, developing machine learning methods for Earth science. His work combines data-centric and physics-based approaches to forecasting, model tuning and uncertainty quantification.

Contact

Prof. Dr. Walid Maalej