Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows

作者：

Highlights：

• Learning a minimal and near-orthogonal set of non-linear modes from turbulent flows.

• Based on variational autoencoders (VAEs) and convolutional neural networks (CNNs).

• Ranking VAE-based modes with respect to their contribution to the reconstruction.

• Leading to the extraction of interpretable non-linear modes.

摘要

•Learning a minimal and near-orthogonal set of non-linear modes from turbulent flows.•Based on variational autoencoders (VAEs) and convolutional neural networks (CNNs).•Ranking VAE-based modes with respect to their contribution to the reconstruction.•Leading to the extraction of interpretable non-linear modes.

论文关键词：Non-linear mode decomposition,Turbulent flows,Variational autoencoders,Convolutional neural networks,Machine learning

论文评审过程：Received 31 October 2021, Revised 18 February 2022, Accepted 27 March 2022, Available online 9 April 2022, Version of Record 4 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117038