MSc project: Hybrid physics-ML modeling with zero-th order optimization

23.08.2024, Abschlussarbeiten, Bachelor- und Masterarbeiten

In the context of numerical climate and weather modeling, we aim to replace the expensive function “run a high-resolution simulation and then coarse-grain” with a hybrid physics-ML model with an in-the-loop data-driven corrector, learned via a zero-th order optimization method.

See the full description of the project here: https://sirop.org/app/e91e3b38-c5c3-408c-aa7d-2815dfb7e63f?_k=Gu6ypb2JgGc27qe9

Kontakt: gideond@gmail.com

Mehr Information

https://sirop.org/app/e91e3b38-c5c3-408c-aa7d-2815dfb7e63f?_k=Gu6ypb2JgGc27qe9