Table 2 Summary of naming for each model.
From: Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning
Model name | Compression | Subspace dimension | Compression techniques |
|---|---|---|---|
POD 16 RB | Linear | 16 | Proper orthogonal decomposition |
POD 50 RB | Linear | 50 | Proper orthogonal decomposition |
POD 100 RB | Linear | 100 | Proper orthogonal decomposition |
POD 500 RB | Linear | 500 | Proper orthogonal decomposition |
AE 4 Q | Nonlinear | 4 | Autoencoder |
DC–AE 4 Q | Nonlinear | 4 | Deep convolutional autoencoder |
BT–AE 4 Q | Nonlinear | 4 | Barlow twins + autoencoder |
AE 16 Q | Nonlinear | 16 | Autoencoder |
DC–AE 16 Q | Nonlinear | 16 | Deep convolutional autoencoder |
BT–AE 16 Q | Nonlinear | 16 | Barlow twins + autoencoder |
AE 256 Q | Nonlinear | 256 | Autoencoder |
DC–AE 256 Q | Nonlinear | 256 | Deep convolutional autoencoder |
BT–AE 256 Q | Nonlinear | 256 | Barlow twins + autoencoder |
