We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-convolutional autoencoders (DC-AE) has been shown to capture nonlinear solution manifolds but fails to perform adequately when linear subspace approaches such as proper orthogonal decomposition (POD) would be optimal. Besides, most DL-ROM models rely on convolutional layers, which might limit its application to only a structured mesh. The proposed framework in this study relies on the combination of an autoencoder (AE) and Barlow Twins (BT) self-supervised learning, where BT maximizes the information content of the embedding with the latent space through a joint embedding architecture. Through a series of benchmark problems of natural convection in porous media, BT-AE performs better than the previous DL-ROM framework by providing comparable results to POD-based approaches for problems where the solution lies within a linear subspace as well as DL-ROM autoencoder-based techniques where the solution lies on a nonlinear manifold; consequently, bridges the gap between linear and nonlinear reduced manifolds. We illustrate that a proficient construction of the latent space is key to achieving these results, enabling us to map these latent spaces using regression models. The proposed framework achieves a relative error of 2% on average and 12% in the worst-case scenario (i.e., the training data is small, but the parameter space is large.). We also show that our framework provides a speed-up of [Formula: see text] times, in the best case, and [Formula: see text] times on average compared to a finite element solver. Furthermore, this BT-AE framework can operate on unstructured meshes, which provides flexibility in its application to standard numerical solvers, on-site measurements, experimental data, or a combination of these sources.

Kadeethum, T., Ballarin, F., O'Malley, D., Choi, Y., Bouklas, N., Yoon, H., Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning, <<SCIENTIFIC REPORTS>>, 2022; 12 (1): N/A-N/A. [doi:10.1038/s41598-022-24545-3] [https://hdl.handle.net/10807/220906]

Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning

Ballarin, Francesco;
2022

Abstract

We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-convolutional autoencoders (DC-AE) has been shown to capture nonlinear solution manifolds but fails to perform adequately when linear subspace approaches such as proper orthogonal decomposition (POD) would be optimal. Besides, most DL-ROM models rely on convolutional layers, which might limit its application to only a structured mesh. The proposed framework in this study relies on the combination of an autoencoder (AE) and Barlow Twins (BT) self-supervised learning, where BT maximizes the information content of the embedding with the latent space through a joint embedding architecture. Through a series of benchmark problems of natural convection in porous media, BT-AE performs better than the previous DL-ROM framework by providing comparable results to POD-based approaches for problems where the solution lies within a linear subspace as well as DL-ROM autoencoder-based techniques where the solution lies on a nonlinear manifold; consequently, bridges the gap between linear and nonlinear reduced manifolds. We illustrate that a proficient construction of the latent space is key to achieving these results, enabling us to map these latent spaces using regression models. The proposed framework achieves a relative error of 2% on average and 12% in the worst-case scenario (i.e., the training data is small, but the parameter space is large.). We also show that our framework provides a speed-up of [Formula: see text] times, in the best case, and [Formula: see text] times on average compared to a finite element solver. Furthermore, this BT-AE framework can operate on unstructured meshes, which provides flexibility in its application to standard numerical solvers, on-site measurements, experimental data, or a combination of these sources.
2022
Inglese
Kadeethum, T., Ballarin, F., O'Malley, D., Choi, Y., Bouklas, N., Yoon, H., Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning, <<SCIENTIFIC REPORTS>>, 2022; 12 (1): N/A-N/A. [doi:10.1038/s41598-022-24545-3] [https://hdl.handle.net/10807/220906]
File in questo prodotto:
File Dimensione Formato  
5c7c367a-8e86-4a77-9b0b-e86290239ea8.pdf

accesso aperto

Tipologia file ?: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 7.04 MB
Formato Adobe PDF
7.04 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/220906
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 4
social impact