This repository includes Tensorflow-based implementations of several machine learning models for the reconstruction of unsteady two- and three-dimensional fluid flows around arbitrary objects using a Schwarz-Christoffel conformal mapping based dense field sampling strategy.
The mappings are computed using pydscpack, a set of Python bindings to a numerical Schwarz-Christoffel mapping computation package by Hu (1998).
For greater detail, please see our paper describing the methodology:
Ali Girayhan Özbay and Sylvain Laizet, "Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings", AIP Advances 12, 045126 (2022) https://doi.org/10.1063/5.0087488