Extending the Capabilities of Data-Driven Reduced-Order Models to Make Predictions for Unseen Scenarios: Applied to Flow Around Buildings

Extending the Capabilities of Data-Driven Reduced-Order Models to Make Predictions for Unseen Scenarios: Applied to Flow Around Buildings

We present a data-driven or non-intrusive reduced-order model (NIROM) which is capable of making predictions for a significantly larger domain than the one used to generate the snapshots or training data. This development relies on the combination of a novel way of sampling the training data (which...

Full description

Bibliographic Details
Main Authors: Claire E. Heaney, Xiangqi Liu, Hanna Go, Zef Wolffs, Pablo Salinas, Ionel M. Navon, Christopher C. Pain
Format: Article
Language:English
Published: Frontiers Media S.A. 2022-07-01
Series:Frontiers in Physics
Subjects:
data-driven reduced-order modelling
non-intrusive reduced-order modelling
adversarial neural network
autoencoder
urban flows
machine learning
Online Access:https://www.frontiersin.org/articles/10.3389/fphy.2022.910381/full

Internet

https://www.frontiersin.org/articles/10.3389/fphy.2022.910381/full

Similar Items