Introducing a microstructure-embedded autoencoder approach for reconstructing high-resolution solution field from reduced parametric space

arXiv:2405.01975v1 Announce Type: cross
Abstract: In this study, we develop a novel multi-fidelity deep learning approach that transforms low-fidelity solution maps into high-fidelity ones by incorporating parametric space information into a standard autoencoder architecture. It is shown that, due to the integration of parametric space data, this method requires significantly less training data to achieve effective performance in predicting high-fidelity solution from the low-fidelity one. In this study, our focus is on a 2D steady-state heat transfer analysis in highly …

abstract architecture arxiv autoencoder cs.ce cs.lg data deep learning embedded fidelity information integration low maps novel ones parametric resolution solution space standard study type