FLOW article published in Nature Communications

Our FLOW colleagues Ricardo Vinuesa and Yuning Wang, together with collaborators from INTA, Universidad Carlos III de Madrid and IIT Chicago have recently published a paper in Nature Communications.

The authors use modern deep-learning techniques, namely b variational autoencoders and transformers, to develop very robust reduced-order models in fluid flows.

A. Solera-Rico, C. Sanmiguel Vila, M. Gómez-López, Y. Wang, A. Almashjary, S.T.M. Dawson, R. Vinuesa. β-Variational autoencoders and transformers for reduced-order modelling of fluid flows. Nat Commun 15, 1361 (2024). doi.org/10.1038/s41467-024-45578-4